auto backup: 2026-05-13 08:10:01
This commit is contained in:
parent
e251630966
commit
f013d6f6ef
@ -61,6 +61,71 @@ C. [匹配项C内容/图片描述]
|
||||
【题目2】
|
||||
...（多套题重复上述结构）
|
||||
```
|
||||
## 图片描述规范（强制执行）
|
||||
阅读信息匹配题的每张图片必须对应一条**图片材料文本**，每条描述包含**标识/通知类型标签**和**图片上实际出现的文本内容**。
|
||||
|
||||
### 格式要求
|
||||
```
|
||||
图片材料文本：
|
||||
【Notice/Sign Type】
|
||||
Actual text content on the image.
|
||||
```
|
||||
|
||||
### 核心规则
|
||||
1. **类型标签必填**：每张图片必须标注 `【Type】`，描述该图片是什么类型的标识/通知（英文，不超过6词）
|
||||
2. **文本内容**：记录图片上实际出现的文字，保持原文（含大小写、标点），不翻译不改写
|
||||
3. **L2 B级及以上**：图片上文字需为1句完整陈述（3-5词+），不能只列单个词汇
|
||||
4. **图片必须是真实标识/通知**（如告示、海报、门牌、标签、通知等），不能是标签式词汇拼图
|
||||
|
||||
### 参考示例
|
||||
```
|
||||
图片材料文本：
|
||||
【Science Class Notice】
|
||||
Science lesson today! We live on EARTH. It goes round the sun.
|
||||
|
||||
图片材料文本：
|
||||
【School Notice】
|
||||
School HOLIDAY next Monday. Enjoy your time off with your family.
|
||||
|
||||
图片材料文本：
|
||||
【School Newsletter】
|
||||
New TERM starts on Monday. Please bring your pencil case and books.
|
||||
```
|
||||
|
||||
### 常用标识/通知类型标签参考
|
||||
| 类型标签 | 适用场景 |
|
||||
|----------|----------|
|
||||
| School Notice | 校园通知、公告 |
|
||||
| Library Notice / Sign | 图书馆通知/标识 |
|
||||
| Exam Notice | 考试相关通知 |
|
||||
| Door Sign | 门上标识 |
|
||||
| Warning Sign | 警示牌 |
|
||||
| Park Sign | 公园标识 |
|
||||
| Bus Sign | 公交标识 |
|
||||
| Shop Sign | 商店/维修店招牌 |
|
||||
| Market Sign | 市场标牌 |
|
||||
| Mall Sign | 商场标识 |
|
||||
| Hotel Notice | 酒店通知 |
|
||||
| Show Poster / Event Poster | 演出/活动海报 |
|
||||
| Party Banner / Invitation | 派对横幅/邀请函 |
|
||||
| Lost & Found | 失物招领 |
|
||||
| Award Certificate | 奖状 |
|
||||
| Greeting Card | 问候卡片 |
|
||||
| Family Note / Personal Note | 便条 |
|
||||
| Homework Reminder | 作业提醒 |
|
||||
| Recycling Sign | 回收标识 |
|
||||
| Room Sign / Lab Sign | 房间/实验室标识 |
|
||||
| Safety Poster | 安全海报 |
|
||||
| Information Desk | 咨询台标牌 |
|
||||
| Laundry Sign | 洗衣房标识 |
|
||||
| Art Club Notice / Art Room Sign | 美术相关通知/标识 |
|
||||
| Sports Notice | 体育通知 |
|
||||
| Science Fair Sign | 科学展标识 |
|
||||
| Wanted Notice | 通缉令 |
|
||||
| Toy Label | 玩具标签 |
|
||||
| Canteen Notice | 食堂通知 |
|
||||
| Building Sign | 大楼标识 |
|
||||
|
||||
## 校验规则
|
||||
自动校验不通过直接返回错误：
|
||||
1. 词汇校验：所有知识点必须在L1单词库中，禁止超纲
|
||||
|
||||
@ -5,3 +5,5 @@
|
||||
{"type":"memory.recall.recorded","timestamp":"2026-05-11T02:37:23.203Z","query":"writing_pic_qa 看图回答题 生产流程 bitable writing","resultCount":5,"results":[{"path":"memory/2026-05-07.md","startLine":215,"endLine":235,"score":1},{"path":"memory/2026-05-08.md","startLine":33,"endLine":55,"score":1},{"path":"memory/2026-05-07.md","startLine":199,"endLine":219,"score":1},{"path":"memory/2026-05-08.md","startLine":1,"endLine":23,"score":1},{"path":"memory/2026-05-07.md","startLine":1,"endLine":20,"score":1}]}
|
||||
{"type":"memory.recall.recorded","timestamp":"2026-05-11T02:37:23.204Z","query":"reading_pic_qa 看图回答题 口语看图回答题 speaking_pic_qa","resultCount":1,"results":[{"path":"memory/2026-05-07.md","startLine":1,"endLine":20,"score":1}]}
|
||||
{"type":"memory.recall.recorded","timestamp":"2026-05-11T02:51:47.112Z","query":"reading_pic_qa bitable table_id 单元挑战 阅读","resultCount":1,"results":[{"path":"memory/2026-05-07.md","startLine":1,"endLine":20,"score":1}]}
|
||||
{"type":"memory.recall.recorded","timestamp":"2026-05-12T01:33:44.968Z","query":"reading information matching 图片 阅读信息匹配题","resultCount":3,"results":[{"path":"memory/2026-05-07.md","startLine":1,"endLine":20,"score":1},{"path":"memory/2026-05-11.md","startLine":39,"endLine":55,"score":1},{"path":"memory/2026-05-11.md","startLine":20,"endLine":43,"score":1}]}
|
||||
{"type":"memory.recall.recorded","timestamp":"2026-05-12T01:41:17.155Z","query":"reading_matchInfo skill SKILL.md 阅读信息匹配题","resultCount":4,"results":[{"path":"memory/2026-05-07.md","startLine":1,"endLine":20,"score":1},{"path":"memory/2026-05-11.md","startLine":66,"endLine":83,"score":1},{"path":"memory/2026-05-11.md","startLine":51,"endLine":68,"score":1},{"path":"memory/2026-05-11.md","startLine":39,"endLine":55,"score":1}]}
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"version": 1,
|
||||
"updatedAt": "2026-05-11T02:51:47.112Z",
|
||||
"updatedAt": "2026-05-12T01:41:17.155Z",
|
||||
"entries": {
|
||||
"memory:memory/2026-05-07.md:57:74": {
|
||||
"key": "memory:memory/2026-05-07.md:57:74",
|
||||
@ -106,24 +106,27 @@
|
||||
"endLine": 20,
|
||||
"source": "memory",
|
||||
"snippet": "# 2026-05-07 工作日志 ## 会话记录 ### 刘彦江 (ou_5af74c1fb96042e33cc0f16b5ca02cf4) — 单元挑战新增3个题型 - **时间：** 11:19 ~ 11:28 - **需求：** 单元挑战新增3个题型：阅读看图回答题（reading_pic_qa）、阅读看图判断题（reading_pic_judge）、写作看图回答题（writing_pic_qa） - **状态：** ✅ 已完成题型规范落地 - **交付内容：** 1. 创建3个题型SKILL.md： - `reading/common/reading_pic_qa/SKILL.md` — 阅读看图回答题（共享大图+多题Yes/No判断） - `reading/common/reading_pic_judge/SKILL.md` — 阅读看图判断题（每题独立配图+Yes/No判断） - `writing/common/writing_pic_qa/SKILL.md` — 写作看图回答题（看图+提示答案开头+填空） 2. 更新 `MEMORY.md` 全题型阶段归属规则 3. 明确题型JSON结构、难度等级（A/B/C/D四级）、能力标签、校验规则 - **关键决策：** 3个题型均为 L1&L2 共用，通过难度参数区分阶段；reading_pic_qa 共享大图，reading_pic_judge 每题独立配图 ### 李应瑛 (ou_1bd7317ae2ccfeb57e1132028847279e) — 单词表对比请求",
|
||||
"recallCount": 5,
|
||||
"recallCount": 7,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 5,
|
||||
"totalScore": 7,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-08T01:18:18.412Z",
|
||||
"lastRecalledAt": "2026-05-11T02:51:47.112Z",
|
||||
"lastRecalledAt": "2026-05-12T01:41:17.155Z",
|
||||
"queryHashes": [
|
||||
"390d35f8d143",
|
||||
"fd4c9b7de37b",
|
||||
"be437071312f",
|
||||
"0e27779653c1",
|
||||
"5c08c6f8788a"
|
||||
"5c08c6f8788a",
|
||||
"4ab75020b1ab",
|
||||
"7ca0207f1308"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-08",
|
||||
"2026-05-09",
|
||||
"2026-05-11"
|
||||
"2026-05-11",
|
||||
"2026-05-12"
|
||||
],
|
||||
"conceptTags": [
|
||||
"reading-pic-qa",
|
||||
@ -229,6 +232,131 @@
|
||||
"going",
|
||||
"ready"
|
||||
]
|
||||
},
|
||||
"memory:memory/2026-05-11.md:39:55": {
|
||||
"key": "memory:memory/2026-05-11.md:39:55",
|
||||
"path": "memory/2026-05-11.md",
|
||||
"startLine": 39,
|
||||
"endLine": 55,
|
||||
"source": "memory",
|
||||
"snippet": "- `基础信息表达｜个人信息问答` — 姓名/年龄/家庭/外貌类 - `表达喜好与理由` — 偏好/观点/意愿类 - `过去经历描述｜Past Activities` — 过去事件类 - `互动应答｜问答交流` — 社交场景类 - `信息交换｜双向问答` — 物品归属/需求类 - 未使用标签（属看图/发音题型专用）：图片描述类(3个)、图片对比、故事讲述、发音与语调 - **分类逻辑**：基于关键词匹配（what do you say → 互动应答; what did you/last → 过去经历; favorite/like/want → 喜好; name/age/from/family → 个人信息; whose/need → 信息交换） ### 刘彦江 — reading_matchInfo 阅读信息匹配题（4套: 010901/011001/011101/011201，18:55 ~ 19:15） - **需求：** 4套 reading_matchInfo，L2 A级，能力标签 标识与通知理解｜标识 & 通知 - 每套 first=5q + second=5q，每题含 questionImage/question/options/answer/ability/explanation - **表：** 阅读-P1-信息匹配题（tblCgfYDnnqwLfgH） - **自动化问题：** 该表存在异步自动化，创建后会将 jsonData 改写为模板壳（减少题量+覆盖 ability） - **解决方案：** 两阶段延迟写入（先创建空记录→等35s让",
|
||||
"recallCount": 2,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 2,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-12T01:33:44.968Z",
|
||||
"lastRecalledAt": "2026-05-12T01:41:17.155Z",
|
||||
"queryHashes": [
|
||||
"4ab75020b1ab",
|
||||
"7ca0207f1308"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-12"
|
||||
],
|
||||
"conceptTags": [
|
||||
"姓名/年龄/家庭/外貌类",
|
||||
"偏好/观点/意愿类",
|
||||
"物品归属/需求类",
|
||||
"属看图/发音题型专用",
|
||||
"you/last",
|
||||
"favorite/like/want",
|
||||
"name/age/from/family",
|
||||
"whose/need"
|
||||
]
|
||||
},
|
||||
"memory:memory/2026-05-11.md:20:43": {
|
||||
"key": "memory:memory/2026-05-11.md:20:43",
|
||||
"path": "memory/2026-05-11.md",
|
||||
"startLine": 20,
|
||||
"endLine": 43,
|
||||
"source": "memory",
|
||||
"snippet": "- **需求：** 2套 reading_pic_qa，L2 A级，能力标签 图文判断｜句图一致性 - 每套5+5道 Y/N 判断，3Y2N平衡，4-7词陈述句 - **状态：** ✅ 已完成，2套全部入库 + 图片描述回填验证通过 - **脚本：** `scripts/batch_reading_pic_qa_2.py` | ID | 题组1 | 题组2 | record_id | |----|-------|-------|-----------| | 010701 | notebook/star/folder/diary/contact | friendly/crazy/brilliant/kind/afraid | recvjiQuGtsVp8 | | 010801 | uncle/aunt/grandma/neighbour/pet | expensive/entrance/upstairs/downstairs/toast | recvjiQvc8EsB8 | - 表：阅读-P7-看图回答题（tblweY65jGBiwSdt） - 当前该表累计：11条记录（000001~010801，含reading_pic_judge类型 4 条及其他） ### 刘彦江 — 口语-P1-日常回答 ability 标签填充（18:15 ~ 18:25） - **需求：** 从能力标签名称图片中，选择与已生成题目契合的标签填入 jsonData - 表：口语-P1-日常回答（tblRGv7k4WH58Jgq），26条有效记录，185道题 - **状态：** ✅ 全部完成 - *",
|
||||
"recallCount": 1,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 1,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-12T01:33:44.968Z",
|
||||
"lastRecalledAt": "2026-05-12T01:33:44.968Z",
|
||||
"queryHashes": [
|
||||
"4ab75020b1ab"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-12"
|
||||
],
|
||||
"conceptTags": [
|
||||
"reading-pic-qa",
|
||||
"y/n",
|
||||
"4-7词陈述句",
|
||||
"record-id",
|
||||
"uncle/aunt/grandma/neighbour/pet",
|
||||
"阅读-p7-看图回答题",
|
||||
"含reading-pic-judge类型",
|
||||
"口语-p1-日常回答"
|
||||
]
|
||||
},
|
||||
"memory:memory/2026-05-11.md:66:83": {
|
||||
"key": "memory:memory/2026-05-11.md:66:83",
|
||||
"path": "memory/2026-05-11.md",
|
||||
"startLine": 66,
|
||||
"endLine": 83,
|
||||
"source": "memory",
|
||||
"snippet": "1. 图片应是**真实标识/通知**（非标签式），如零售楼层导览那种 2. 图片上的文字**至少为一句话**，L2 A级难度，不能只有一个词 - **处理：** 4 套 reading_matchInfo 全部重新设计（题目+图片描述），两阶段延迟写入 - **新record_ids:** recvjj2Nuw9MJd / recvjj2NZz75zb / recvjj2Ov8Stks / recvjj2OX0Dmo5 - **改进要点：** - 每张图改为真实通知/标识，如 \"TRAINS to the NORTH. Go to Platform 3.\" - 图片文字至少 1 句完整陈述，含足够信息供阅读提取 - 题目围绕通知/标识内容提问，考察学生从标识中抓取关键信息的能力 ### 刘彦江 — reading_matchInfo 阅读信息匹配题（6套L2 B级: 021301-021801，19:30 ~ 19:45） - **需求：** 6套 reading_matchInfo，L2 B级，能力标签 标识与通知理解｜标识 & 通知 - **B级规范：** 文本3-5词短句，图片为同类差异，简单对应；每张图是真实的标识/通知（非标签式） - **状态：** ✅ 全部完成（两阶段延迟写入策略，避免自动化覆盖） - **脚本：** `scripts/batch_reading_matchInfo.py` | ID | 题组1 | 题组2 | record_id | |----|-------|-------|-----------| | 021301 |",
|
||||
"recallCount": 1,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 1,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-12T01:41:17.155Z",
|
||||
"lastRecalledAt": "2026-05-12T01:41:17.155Z",
|
||||
"queryHashes": [
|
||||
"7ca0207f1308"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-12"
|
||||
],
|
||||
"conceptTags": [
|
||||
"真实标识/通知",
|
||||
"reading-matchinfo",
|
||||
"新record-ids",
|
||||
"每张图改为真实通知/标识",
|
||||
"题目围绕通知/标识内容提问",
|
||||
"021301-021801",
|
||||
"文本3-5词短句",
|
||||
"每张图是真实的标识/通知"
|
||||
]
|
||||
},
|
||||
"memory:memory/2026-05-11.md:51:68": {
|
||||
"key": "memory:memory/2026-05-11.md:51:68",
|
||||
"path": "memory/2026-05-11.md",
|
||||
"startLine": 51,
|
||||
"endLine": 68,
|
||||
"source": "memory",
|
||||
"snippet": "- **自动化问题：** 该表存在异步自动化，创建后会将 jsonData 改写为模板壳（减少题量+覆盖 ability） - **解决方案：** 两阶段延迟写入（先创建空记录→等35s让自动化完成→PUT jsonData），010901/011201 修复后验证通过 | ID | 题组1 | 题组2 | record_id | |----|-------|-------|-----------| | 010901 | north/east/south/west/exit（方向标识） | businessman/job/letter/call/guard（职场） | recvjiYAHtp05c | | 011001 | beat/dancer/drum/player/work（音乐体育） | aged/good-looking/mistake/weakness/be good at（人物描述） | recvjiXLdt5itq | | 011101 | dangerous/badly/worst/steal/run away（危险） | minute/close/kilometre/second/away（时间距离） | recvjiXLOOWMsq | | 011201 | summer/winter/Earth/holiday/term（季节） | examination/plus/minus/biology/study（学校） | recvjiYBd8Mejs | - **脚本：** `scripts/batch_reading_matchInfo.py` - *",
|
||||
"recallCount": 1,
|
||||
"dailyCount": 0,
|
||||
"groundedCount": 0,
|
||||
"totalScore": 1,
|
||||
"maxScore": 1,
|
||||
"firstRecalledAt": "2026-05-12T01:41:17.155Z",
|
||||
"lastRecalledAt": "2026-05-12T01:41:17.155Z",
|
||||
"queryHashes": [
|
||||
"7ca0207f1308"
|
||||
],
|
||||
"recallDays": [
|
||||
"2026-05-12"
|
||||
],
|
||||
"conceptTags": [
|
||||
"010901/011201",
|
||||
"record-id",
|
||||
"north/east/south/west/exit",
|
||||
"beat/dancer/drum/player/work",
|
||||
"dangerous/badly/worst/steal/run",
|
||||
"summer/winter/earth/holiday/term",
|
||||
"自动",
|
||||
"问题"
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
280
memory/2026-05-12.md
Normal file
280
memory/2026-05-12.md
Normal file
@ -0,0 +1,280 @@
|
||||
# 2026-05-12 工作日志
|
||||
|
||||
## 会话记录
|
||||
|
||||
### 刘彦江 — 021301-021801 图片描述修正 + 技能更新（09:35 ~ 09:45）
|
||||
- **问题：** 021301-021801 信息匹配题的图片描述缺少 `【Notice Type】` 标签，格式不符合参考规范
|
||||
- **处理：**
|
||||
1. 查询 bitable 获取6条记录当前图片描述（tblCgfYDnnqwLfgH）
|
||||
2. 按每道题的上下文匹配对应的标识/通知类型标签（如 Show Poster、Wanted Notice、School Notice 等）
|
||||
3. 批量更新6条记录的图片描述字段，全部10个 `【Type】` 标签验证通过
|
||||
4. 脚本：`scripts/fix_matchInfo_0213_0218_desc.py`
|
||||
- **技能更新：** 将图片描述规范（格式要求、核心规则、参考示例、常用类型标签参考表）更新到 `business_production/单元挑战/skills/unit_challenge/questions/reading/reading_info_match/SKILL.md`
|
||||
- **规范要点：**
|
||||
- 每张图片 → `图片材料文本：\n【Type】\nActual text`
|
||||
- 图片必须是真实标识/通知（非标签式）
|
||||
- L2 B级及以上图片文字需为完整陈述句（3-5词+）
|
||||
|
||||
### 刘彦江 — L1 配置表审校 + 技能沉淀（11:50 ~ 12:10）
|
||||
- **数据源：** 飞书多维表格「互动知识点 - 句子」→「Level 1 配置表」(`Nq3Zb258aae7SRs2QfXcqsQYnxJ` / `tblTxGpf6GQ5c7DZ`)
|
||||
- **ID 编码规则：** 7位 = 前2位(Season) + 中2位(Unit) + 后3位(序列号)
|
||||
- 例: 1214001 = L1S2(12) + U14(14) + 001
|
||||
- **审校记录 1214001 (You need to...) 发现：**
|
||||
1. ❌ classificationInfo 值互换: cambridgeLevel=A1 vs cefrLevel=YLE（与列字段反了）
|
||||
2. ❌ sentenceStructureSort 题2: 单词库有need无needs，三单主语Otis语法错误
|
||||
3. ⚠️ sentenceStructureClozeWordMcq: "put your toys" 省略 away 不够自然
|
||||
- **技能沉淀：**
|
||||
- 脚本: `scripts/audit_l1_config.py` — 7项自动检查
|
||||
- SKILL.md: `skills/audit_l1_config/SKILL.md` — 含完整审校流程 + 4项人工审核清单
|
||||
# 2026-05-12 工作日志
|
||||
|
||||
## 会话记录
|
||||
|
||||
### 刘彦江 — 021301-021801 图片描述修正 + 技能更新（09:35 ~ 09:45）
|
||||
- **问题：** 021301-021801 信息匹配题的图片描述缺少 `【Notice Type】` 标签，格式不符合参考规范
|
||||
- **处理：**
|
||||
1. 查询 bitable 获取6条记录当前图片描述（tblCgfYDnnqwLfgH）
|
||||
2. 按每道题的上下文匹配对应的标识/通知类型标签（如 Show Poster、Wanted Notice、School Notice 等）
|
||||
3. 批量更新6条记录的图片描述字段，全部10个 `【Type】` 标签验证通过
|
||||
4. 脚本：`scripts/fix_matchInfo_0213_0218_desc.py`
|
||||
- **技能更新：** 将图片描述规范（格式要求、核心规则、参考示例、常用类型标签参考表）更新到 `business_production/单元挑战/skills/unit_challenge/questions/reading/reading_info_match/SKILL.md`
|
||||
- **规范要点：**
|
||||
- 每张图片 → `图片材料文本：\n【Type】\nActual text`
|
||||
- 图片必须是真实标识/通知（非标签式）
|
||||
- L2 B级及以上图片文字需为完整陈述句（3-5词+）
|
||||
|
||||
### 刘彦江 — L1 配置表审校 + 技能沉淀（11:50 ~ 12:10）
|
||||
- **数据源：** 飞书多维表格「互动知识点 - 句子」→「Level 1 配置表」(`Nq3Zb258aae7SRs2QfXcqsQYnxJ` / `tblTxGpf6GQ5c7DZ`)
|
||||
- **ID 编码规则：** 7位 = 前2位(Season) + 中2位(Unit) + 后3位(序列号)
|
||||
- 例: 1214001 = L1S2(12) + U14(14) + 001
|
||||
- **审校记录 1214001 (You need to...) 发现：**
|
||||
1. ❌ classificationInfo 值互换: cambridgeLevel=A1 vs cefrLevel=YLE（与列字段反了）
|
||||
2. ❌ sentenceStructureSort 题2: 单词库有need无needs，三单主语Otis语法错误
|
||||
3. ⚠️ sentenceStructureClozeWordMcq: "put your toys" 省略 away 不够自然
|
||||
- **技能沉淀：**
|
||||
- 脚本: `scripts/audit_l1_config.py` — 7项自动检查
|
||||
- SKILL.md: `skills/audit_l1_config/SKILL.md` — 含完整审校流程 + 4项人工审核清单
|
||||
|
||||
### 刘彦江 — 1213001-1216010 批量审校 40 条（12:10 ~ 14:00）
|
||||
- **范围：** L1S2 Units 13-16，每单元 10 条，共 40 条
|
||||
- **方法：** `scripts/audit_l1_config.py` 自动化扫描 → 误报排除 → 分类汇总 → 逐条审校回填
|
||||
- **脚本修复（过程中）：**
|
||||
1. sentenceStructureSort 单词对比大小写误报 → 添加 normalize（首字母大写 + 去标点）
|
||||
2. ID 末尾空格敏感 → strip 比较
|
||||
3. 句子朗读/跟读题误报 options/answer 缺失 → 跳过这两种题型
|
||||
|
||||
#### 审校结果汇总
|
||||
- **🔴 系统性问题（40/40，100%）：** classificationInfo JSON 内 cambridgeLevel="A1" 与 cefrLevel="YLE" 值互换，列字段正确但 JSON 存储写反，疑似模板/formula 级别 bug
|
||||
- **🟡 具体错误（17/40）：**
|
||||
- sentenceMeaningMeaning JSON 解析失败 × 10：1213004, 1213006, 1213010, 1214008, 1215005, 1216001, 1216004, 1216007, 1216008, 1216010（后8题含中文引号冲突）
|
||||
- ID 字段末尾空格 × 3：1213001, 1215001, 1216001
|
||||
- 看图选择题有CN无JSON × 3：1213008, 1215010, 1216005
|
||||
- sentenceStructureSort 语法/格式错误 × 3：1213004(缺逗号clean Otis→clean, Otis), 1213005(bird?连写应拆为bird+?), 1214001(need→needs三单)
|
||||
- 缺少 pointId 字段 × 1：1213001(sort 题2)
|
||||
- **🟢 仅有系统性问题的 23 条：** 其余 23 条仅 classificationInfo 互换问题，其他题型均通过自动化检查
|
||||
- **回填：** 全部 40 条审校结果已写入 bitable「审校结果」列，逐条验证通过
|
||||
- **脚本回填脚本：** `scripts/audit_batch_1213001_1216010.py`
|
||||
# 2026-05-12 工作日志
|
||||
|
||||
## 会话记录
|
||||
|
||||
### 刘彦江 — 021301-021801 图片描述修正 + 技能更新（09:35 ~ 09:45）
|
||||
- **问题：** 021301-021801 信息匹配题的图片描述缺少 `【Notice Type】` 标签，格式不符合参考规范
|
||||
- **处理：**
|
||||
1. 查询 bitable 获取6条记录当前图片描述（tblCgfYDnnqwLfgH）
|
||||
2. 按每道题的上下文匹配对应的标识/通知类型标签（如 Show Poster、Wanted Notice、School Notice 等）
|
||||
3. 批量更新6条记录的图片描述字段，全部10个 `【Type】` 标签验证通过
|
||||
4. 脚本：`scripts/fix_matchInfo_0213_0218_desc.py`
|
||||
- **技能更新：** 将图片描述规范（格式要求、核心规则、参考示例、常用类型标签参考表）更新到 `business_production/单元挑战/skills/unit_challenge/questions/reading/reading_info_match/SKILL.md`
|
||||
- **规范要点：**
|
||||
- 每张图片 → `图片材料文本：\n【Type】\nActual text`
|
||||
- 图片必须是真实标识/通知（非标签式）
|
||||
- L2 B级及以上图片文字需为完整陈述句（3-5词+）
|
||||
|
||||
### 刘彦江 — L1 配置表审校 + 技能沉淀（11:50 ~ 12:10）
|
||||
- **数据源：** 飞书多维表格「互动知识点 - 句子」→「Level 1 配置表」(`Nq3Zb258aae7SRs2QfXcqsQYnxJ` / `tblTxGpf6GQ5c7DZ`)
|
||||
- **ID 编码规则：** 7位 = 前2位(Season) + 中2位(Unit) + 后3位(序列号)
|
||||
- 例: 1214001 = L1S2(12) + U14(14) + 001
|
||||
- **审校记录 1214001 (You need to...) 发现：**
|
||||
1. ❌ classificationInfo 值互换: cambridgeLevel=A1 vs cefrLevel=YLE（与列字段反了）
|
||||
2. ❌ sentenceStructureSort 题2: 单词库有need无needs，三单主语Otis语法错误
|
||||
3. ⚠️ sentenceStructureClozeWordMcq: "put your toys" 省略 away 不够自然
|
||||
- **技能沉淀：**
|
||||
- 脚本: `scripts/audit_l1_config.py` — 7项自动检查
|
||||
- SKILL.md: `skills/audit_l1_config/SKILL.md` — 含完整审校流程 + 4项人工审核清单
|
||||
|
||||
### 刘彦江 — 1213001-1216010 批量审校 40 条（12:10 ~ 14:00）
|
||||
- **范围：** L1S2 Units 13-16，每单元 10 条，共 40 条
|
||||
- **方法：** `scripts/audit_l1_config.py` 自动化扫描 → 误报排除 → 分类汇总 → 逐条审校回填
|
||||
- **脚本修复（过程中）：**
|
||||
1. sentenceStructureSort 单词对比大小写误报 → 添加 normalize（首字母大写 + 去标点）
|
||||
2. ID 末尾空格敏感 → strip 比较
|
||||
3. 句子朗读/跟读题误报 options/answer 缺失 → 跳过这两种题型
|
||||
|
||||
#### 审校结果汇总（初版）
|
||||
- **🔴 系统性问题（40/40，100%）：** classificationInfo JSON 内 cambridgeLevel="A1" 与 cefrLevel="YLE" 值互换
|
||||
- **🟡 具体错误（17/40）：**
|
||||
- sentenceMeaningMeaning JSON 解析失败 × 10：1213004, 1213006, 1213010, 1214008, 1215005, 1216001, 1216004, 1216007, 1216008, 1216010
|
||||
- ID 字段末尾空格 × 3：1213001, 1215001, 1216001
|
||||
- 看图选择题有CN无JSON × 3：1213008, 1215010, 1216005
|
||||
- sentenceStructureSort 语法/格式错误 × 3：1213004(缺逗号clean Otis→clean, Otis), 1213005(bird?连写应拆为bird+?), 1214001(need→needs三单)
|
||||
- 缺少 pointId 字段 × 1：1213001(sort 题2)
|
||||
- **🟢 仅有系统性问题的 23 条**
|
||||
- **回填：** 全部 40 条审校结果已写入 bitable「审校结果」列，逐条验证通过
|
||||
- **脚本回填脚本：** `scripts/audit_batch_1213001_1216010.py`
|
||||
|
||||
### 刘彦江 — 审校结果修正 + 解析一致检查 + JSON 修复（14:00 ~ 15:38）
|
||||
- **YLE↔A1 误报排除：** 刘彦江确认 YLE 与 A1 等级可互通，classificationInfo 值互换不视为错误
|
||||
- 全部 40 条审校结果已更新，移除 classificationInfo 互换相关告警
|
||||
- 23 条变为 `✅ 通过`（无其他问题），17 条保留具体错误
|
||||
|
||||
- **解析与题目/答案对应性检查（人工审核项）：**
|
||||
- 检查题型：句意选择题 ×30、句子补全题、听句作答题、场景选择题、看图选择题
|
||||
- 验证方法：提取 explanation 中的英文引句 vs question 中的英文句子、正则提取"空处应填X" vs options[answer]
|
||||
- 结果：✅ **0 条实质性不对应**
|
||||
|
||||
- **10 条 sentenceMeaningMeaning JSON 修复：**
|
||||
- **根因：** explanation 文本中的 ASCII `"` (U+0022) 被当作中文双引号使用，JSON 解析器将其视为字符串终止符
|
||||
- **修复策略：** 从「句意选择题」中文列提取英文原句和选项 → json.dumps 重建标准 JSON（只修格式，不修内容）
|
||||
- **1216007 特殊处理：** 原始 JSON 损坏严重，需从中文列完全重建
|
||||
- **二次修复（Q2 丢失问题）：** 首次不完全修复导致 9 条记录的 Q2 被覆盖丢失，且 Q1 被 JSON 垃圾污染 → 从中文列全面重建 Q1+Q2
|
||||
- **最终结果：10/10 条记录 sentenceMeaningMeaning 均可 json.loads 正确解析，每条含 2 题，无残留垃圾数据**
|
||||
- **受影响记录：** 1213004, 1213006, 1213010, 1214008, 1215005, 1216001, 1216004, 1216007, 1216008, 1216010
|
||||
- **审校结果同步更新：** 移除所有 10 条的 `❌ JSON 解析失败` 标记
|
||||
- **注意：** Q1 explanation 在重建时词表述可能微调（内容含义一致），如需精确原始 wording 可从中文列恢复后人工微调
|
||||
|
||||
## 经验教训
|
||||
|
||||
### bitable 写入需严格流程管控（2026-05-12）
|
||||
- 批量更新 JSON 字段时必须：写入前完整提取原始数据 → 写入后逐字段 diff 验证 → 发现异常立即回滚
|
||||
- 本次 JSON 修复中首次写入不完整导致 Q2 丢失，原因：修复脚本未正确处理多题 JSON 结构
|
||||
- **教训：** 任何涉及 JSON 重建/修复的批量操作，先单条试运行验证通过后再批量执行，不可并行甩出多条
|
||||
|
||||
### sentenceMeaningMeaning 的 explanation 引号规范（2026-05-12）
|
||||
- explanation 字段中的中文双引号极易被误用为 ASCII `"` (U+0022)
|
||||
- 建议生产侧统一使用中文引号 `"` (U+201C) 和 `"` (U+201D)，或在 explanation 写入前做引号归一化预处理
|
||||
- 此类问题在常规 JSON 校验中不会被发现（JSON 仍有概率合法，取决于引号出现位置），一旦出现在 JSON 字符串边界附近即导致全段解析失败
|
||||
|
||||
### 刘彦江 — 核心互动全题型 JSON 配置标准沉淀（17:05 ~ 17:50）
|
||||
- **目标：** 从互动内容库遍历全部核心互动题型，提取 JSON 配置结构，沉淀为统一 Skill
|
||||
- **方式：** 先写 `bitable-reader` 通用读取 Skill → 遍历 15 个 bitable → 归纳通用字段 → 分类录入各题型
|
||||
|
||||
#### 架构决策
|
||||
- **统一入口，通用在上：** 一个 `core-content-json-standard` Skill 覆盖全部题型，不拆分为题型独立 Skill
|
||||
- **五大分类：** 📖阅读(2) / 🎧听力(3) / 🗣口语(4) / ✏️写作(5) / 未完成(1)
|
||||
- **通用字段提取：** ID/dataStatus/kpStatus/kpInfo/taskData 是所有题型共用的基础结构
|
||||
|
||||
#### 覆盖率
|
||||
- 14 种题型已录入 ✅（1 种无数据：口语探讨）
|
||||
- 4 个一级板块：通用结构 / 题型专区 / 审校规则 / 扩展指南
|
||||
- 每个题型：cType + bitable 定位 + JSON 字段表 + 结构特点 + 与同类题型的差异说明
|
||||
|
||||
#### 发现
|
||||
- 写作互动和邮件组句 cType 相同（`core_writing_questionMakeSentence`），通过 textInfo 区分素材
|
||||
- 口语快答/妙问 JSON 结构几乎相同，差异在 prompt 配置和对话样例内容
|
||||
- 合作阅读和合作听力的核心差异：`textData.text[]` ↔ `textData.audio[]`
|
||||
- meaning 标签（合作阅读）为开放型自由文本，非受控词表
|
||||
|
||||
#### 产出文件
|
||||
- `skills/bitable-reader/SKILL.md` — 通用 bitable 读取技能（164行）
|
||||
- `skills/core-content-json-standard/SKILL.md` — 全题型 JSON 标准 v2.0（393行）
|
||||
- `scripts/audit_core_reading_S0.py` — 合作阅读 S0 审校脚本（含审校发现）
|
||||
# 2026-05-12 工作日志
|
||||
|
||||
## 会话记录
|
||||
|
||||
### 刘彦江 — 021301-021801 图片描述修正 + 技能更新（09:35 ~ 09:45）
|
||||
- **问题：** 021301-021801 信息匹配题的图片描述缺少 `【Notice Type】` 标签
|
||||
- **处理：** 批量更新6条记录的图片描述字段，全部10个标签验证通过
|
||||
- **脚本：** `scripts/fix_matchInfo_0213_0218_desc.py`
|
||||
- **技能更新：** 图片描述规范写入 `business_production/单元挑战/skills/unit_challenge/questions/reading/reading_info_match/SKILL.md`
|
||||
|
||||
### 刘彦江 — L1 配置表审校 + 技能沉淀（11:50 ~ 12:10）
|
||||
- **数据源：** `Nq3Zb258aae7SRs2QfXcqsQYnxJ` / `tblTxGpf6GQ5c7DZ`
|
||||
- **ID 编码：** 7位 = S(2位) + U(2位) + 序列号(3位)
|
||||
- **技能沉淀：** `scripts/audit_l1_config.py` + `skills/audit_l1_config/SKILL.md`
|
||||
|
||||
### 刘彦江 — 1213001-1216010 批量审校 40 条（12:10 ~ 14:00）
|
||||
- **范围：** L1S2 Units 13-16
|
||||
- **脚本修复（过程中）：** sort 大小写误报 / ID 末尾空格 / 朗读跟读题误报
|
||||
- **结果：** 系统性 classificationInfo 互换(已标记不视为错误) + 17条具体错误 + 23条通过
|
||||
- **脚本：** `scripts/audit_l1_config.py` + `scripts/audit_batch_1213001_1216010.py`
|
||||
|
||||
### 刘彦江 — 审校结果修正 + JSON 修复（14:00 ~ 15:38）
|
||||
- **YLE↔A1 误报排除：** 确认等级互通，40条审校结果已更新
|
||||
- **解析与题目一致性检查：** ✅ 0条不对应
|
||||
- **10 条 sentenceMeaningMeaning JSON 修复：**
|
||||
- 根因：explanation 中 ASCII `"` 被用作中文引号
|
||||
- 修复策略演变：状态机拆分失败 → 正则重建 → 发现Q2丢失 → 从中文列完整重建
|
||||
- 最终：10/10 可正确解析，审校结果同步更新
|
||||
- 受影响：1213004/1213006/1213010/1214008/1215005/1216001/1216004/1216007/1216008/1216010
|
||||
|
||||
### 刘彦江 — 核心互动全题型 JSON 配置标准沉淀（17:05 ~ 17:50）
|
||||
- **产出 Skill 1：** `skills/bitable-reader/SKILL.md` — 通用 bitable 读取（任何 bitable 通用）
|
||||
- **产出 Skill 2：** `skills/core-content-json-standard/SKILL.md` v2.0 — 全题型 JSON 标准（393行）
|
||||
- **架构：** 通用字段在前（ID/kpInfo/taskData）+ 5大题型分类（📖阅读2 🎧听力3 🗣口语4 ✏️写作5）+ 审校规则 + 扩展指南
|
||||
- **覆盖率：** 14/15 种题型（口语探讨 S0 无数据）
|
||||
- **产出脚本：** `scripts/audit_core_reading_S0.py` — 合作阅读 S0 审校
|
||||
|
||||
## 经验教训
|
||||
|
||||
### bitable 写入需严格流程管控（2026-05-12）
|
||||
- 批量更新 JSON：写入前完整提取 → 写入后逐字段 diff → 异常立即回滚
|
||||
- 首次修复多题 JSON 导致 Q2 丢失 → 先单条试跑验证再批量
|
||||
|
||||
### sentenceMeaningMeaning 引号规范（2026-05-12）
|
||||
- explanation 中 ASCII `"` 与中文引号混用导致 JSON 解析失败
|
||||
- 建议：生产侧统一用中文引号 `""`（U+201C/D），或写入前做引号归一化
|
||||
|
||||
### 写作互动 / 邮件组句 cType 相同（2026-05-12）
|
||||
- 两者 cType 均为 `core_writing_questionMakeSentence`，通过 textInfo.textList[].type 区分素材
|
||||
|
||||
### 刘彦江 — 中互动全题型录入（18:00 ~ 18:25）
|
||||
|
||||
#### 发现
|
||||
- **中互动结构高度统一：** 全部 27 类都用 `jsonData`（主配置）+ `kpInfo`（知识点绑定），没有核心互动那种多字段分散结构
|
||||
- **6 大分类：** 🗨对话(7) / 📋信息(6) / 📦词汇(2) / 🖼图片选择(4) / 📝语法(3) / 🔧其他(5)
|
||||
- **对话类公共字段：** cType, cId, title, resourceMapping, preDialog, imgShowTimingList
|
||||
- 写作互动和邮件组句 cType 相同（`core_writing_questionMakeSentence`）
|
||||
|
||||
#### 产出文件
|
||||
- `skills/interactive-component-json/references/json_structure_guide.md` — 27 种中互动 jsonData 字段结构（8736 bytes）
|
||||
- `skills/interactive-component-json/references/component_registry.md` — 核心互动部分从🔲更新为完整注册表（含 cType+bitable_token）
|
||||
- 与 `skills/core-content-json-standard/SKILL.md` 双向关联
|
||||
|
||||
#### 覆盖率
|
||||
- 核心互动：15/15 ✅（口语探讨 S0 无数据已标注）
|
||||
- 中互动：27/27 ✅
|
||||
- 关联文件：3 个（core-content-json-standard + component_registry + json_structure_guide）
|
||||
## 刘彦江 — 中互动+核心互动 回填任务（18:37 待继续）
|
||||
|
||||
### 上下文
|
||||
- 用户提供剧本文档: `https://makee-interactive.feishu.cn/wiki/YqzzwpjwjihK9YkyRhXccaqLnzu`
|
||||
- 要求：识别文档中的 3 个中互动 + 1 个核心互动，回填到对应位置
|
||||
- 上次已读取文档，找到 1 个核心互动标记（第4幕 听力拖拽），但 3 个中互动标记不明显
|
||||
- 用户让我"Continue"继续处理
|
||||
|
||||
### 当前状态
|
||||
- 需要重新拉取文档，仔细识别所有互动标记
|
||||
- 文档位于 space_id=7487521512283799556
|
||||
- 上次发现的场景：太空故事 / 太空船起飞 / 小行星带 / 发光的星球 + 尾声
|
||||
## 中互动+核心互动 回填任务 — 继续（18:37）
|
||||
|
||||
### 本轮 Session — 实际写入 bitable
|
||||
|
||||
上一轮已确认：文档中 4 个场景对应 4 个互动类型（3中+1核），标签已写入文档。但用户说的"回填到对应为止"指的是**写入 bitable 多维表格记录**，而非仅文档标签。
|
||||
|
||||
### 需要写入的 4 条记录
|
||||
|
||||
| 场景 | 互动类型 | cType | bitable_token |
|
||||
|------|---------|-------|---------------|
|
||||
| 第1幕 太空故事 | 对话朗读互动 | `mid_dialog_repeat` | `MuwubKXoSaJe55sO4k9c63VSnmh` |
|
||||
| 第2幕 太空船起飞 | 对话互动 | `mid_sentence_dialogue` | `GH0hbBT0ZavkCesaVQ7c40Zfnub` |
|
||||
| 第3幕 小行星带 | 指令互动 | `mid_vocab_instruction` | `UorxbVCNYaqpx3sOUdTcF6bUnAh` |
|
||||
| 第4幕 发光的星球 | 听力拖拽 | `core_listening_drag` | `Uey8bhdLBa66TIsGrFBcIQKRnsg` |
|
||||
|
||||
### 下一步
|
||||
1. 读取 4 个 bitable 的表结构（字段名）
|
||||
2. 基于剧本内容和 JSON 结构标准，构造 jsonData/kpInfo 等字段
|
||||
3. 调用 Bot API create_record 写入
|
||||
4. 写后回读验证
|
||||
BIN
scripts/__pycache__/audit_l1_config.cpython-312.pyc
Normal file
BIN
scripts/__pycache__/audit_l1_config.cpython-312.pyc
Normal file
Binary file not shown.
276
scripts/audit_core_reading_S0.py
Normal file
276
scripts/audit_core_reading_S0.py
Normal file
@ -0,0 +1,276 @@
|
||||
#!/usr/bin/env python3
|
||||
"""合作阅读 S0 表审校脚本 — 纯规则检查，不调用大模型"""
|
||||
import json, sys, requests, re
|
||||
|
||||
TOKEN = None
|
||||
APP_TOKEN = 'HIuLbJ6E8aNw2lsdT1YcvNOmnog'
|
||||
TABLE_ID = 'tblAZT1KNUuNY3cN'
|
||||
|
||||
def get_token():
|
||||
global TOKEN
|
||||
if TOKEN:
|
||||
return TOKEN
|
||||
r = requests.post('https://open.feishu.cn/open-apis/auth/v3/tenant_access_token/internal',
|
||||
json={'app_id':'cli_a931175d41799cc7','app_secret':'Iw2vEfbjT6GtV0GhbxbZqfQ4nAPtbR14'})
|
||||
TOKEN = r.json()['tenant_access_token']
|
||||
return TOKEN
|
||||
|
||||
def fetch_all(token):
|
||||
records = []
|
||||
page_token = ''
|
||||
while True:
|
||||
r = requests.get(
|
||||
f'https://open.feishu.cn/open-apis/bitable/v1/apps/{APP_TOKEN}/tables/{TABLE_ID}/records?page_size=100',
|
||||
headers={'Authorization': f'Bearer {token}'},
|
||||
params={'page_token': page_token})
|
||||
d = r.json()
|
||||
items = d.get('data',{}).get('items',[])
|
||||
records.extend(items)
|
||||
if not d.get('data',{}).get('has_more'):
|
||||
break
|
||||
page_token = d.get('data',{}).get('page_token','')
|
||||
return records
|
||||
|
||||
def safe_json(fields, key):
|
||||
v = fields.get(key, '')
|
||||
if not v:
|
||||
return None, 'EMPTY'
|
||||
try:
|
||||
return json.loads(v), 'OK'
|
||||
except Exception as e:
|
||||
return None, f'PARSE_ERROR: {e}'
|
||||
|
||||
def audit(record):
|
||||
fields = record['fields']
|
||||
fid = (fields.get('ID') or '').strip()
|
||||
rid = record['record_id']
|
||||
issues = []
|
||||
warnings = []
|
||||
|
||||
# ===== 1. ID 基础检查 =====
|
||||
if not fid:
|
||||
issues.append('❌ ID字段为空')
|
||||
elif fid == 'None' or fid == 'null':
|
||||
issues.append('❌ ID字段异常值(None/null)')
|
||||
elif not fid.isdigit():
|
||||
issues.append(f'❌ ID字段非纯数字: "{fid}"')
|
||||
|
||||
# ===== 2. JSON 字段解析检查 =====
|
||||
json_fields = {
|
||||
'taskData': fields.get('taskData',''),
|
||||
'sequenceData': fields.get('sequenceData',''),
|
||||
'textData': fields.get('textData',''),
|
||||
'learningData': fields.get('learningData',''),
|
||||
'kpInfo': fields.get('kpInfo',''),
|
||||
}
|
||||
parsed = {}
|
||||
for key, raw in json_fields.items():
|
||||
obj, status = safe_json(fields, key)
|
||||
parsed[key] = obj
|
||||
if status != 'OK' and raw: # 有内容但解析失败
|
||||
issues.append(f'❌ {key} JSON解析失败: {status}')
|
||||
elif status == 'EMPTY':
|
||||
warnings.append(f'⚠️ {key} 为空')
|
||||
|
||||
# ===== 3. ID 一致性检查 =====
|
||||
td = parsed.get('taskData')
|
||||
kp = parsed.get('kpInfo')
|
||||
if td and kp:
|
||||
if td.get('cId','') != fid:
|
||||
issues.append(f'❌ taskData.cId="{td.get("cId")}" ≠ ID="{fid}"')
|
||||
if kp.get('cId','') != fid:
|
||||
issues.append(f'❌ kpInfo.cId="{kp.get("cId")}" ≠ ID="{fid}"')
|
||||
if td.get('cId','') != kp.get('cId',''):
|
||||
issues.append(f'❌ taskData.cId≠kpInfo.cId ({td.get("cId")} vs {kp.get("cId")})')
|
||||
|
||||
# ===== 4. textData 检查 =====
|
||||
td_obj = parsed.get('textData')
|
||||
if td_obj:
|
||||
texts = td_obj.get('text', [])
|
||||
questions = td_obj.get('question', [])
|
||||
|
||||
for qi, q in enumerate(questions):
|
||||
# 4a. meaning 不为空
|
||||
meaning = q.get('meaning','')
|
||||
if not meaning:
|
||||
issues.append(f'❌ textData.question[{qi}] meaning 为空')
|
||||
|
||||
# 4b. answer 在范围内
|
||||
answer = q.get('answer', [])
|
||||
opts = q.get('optionList', [])
|
||||
if isinstance(answer, list) and len(answer) > 0:
|
||||
aidx = answer[0]
|
||||
if aidx >= len(opts):
|
||||
issues.append(f'❌ textData.question[{qi}] answer={aidx} 超出optionList范围({len(opts)})')
|
||||
elif not answer:
|
||||
issues.append(f'❌ textData.question[{qi}] answer 为空')
|
||||
|
||||
# 4c. optionList 每项有 feedback
|
||||
for oi, opt in enumerate(opts):
|
||||
fb = opt.get('feedback', {})
|
||||
if not fb.get('content', ''):
|
||||
issues.append(f'❌ textData.question[{qi}].option[{oi}] feedback 为空')
|
||||
|
||||
# 4d. npcName 非空
|
||||
if not q.get('npcName',''):
|
||||
issues.append(f'❌ textData.question[{qi}] npcName 为空')
|
||||
|
||||
# 4e. text 内容非空
|
||||
for ti, t in enumerate(texts):
|
||||
if not t.get('textBody',''):
|
||||
issues.append(f'❌ textData.text[{ti}] textBody 为空')
|
||||
if not t.get('textTitle',''):
|
||||
issues.append(f'⚠️ textData.text[{ti}] textTitle 为空')
|
||||
|
||||
# ===== 5. learningData 检查 =====
|
||||
ld = parsed.get('learningData')
|
||||
if ld:
|
||||
parts = ld.get('learningPart', [])
|
||||
for pi, part in enumerate(parts):
|
||||
learnings = part.get('learning', [])
|
||||
for li, lq in enumerate(learnings):
|
||||
# 5a. meaning 不为空
|
||||
if not lq.get('meaning',''):
|
||||
issues.append(f'❌ learningData.learningPart[{pi}].learning[{li}] meaning 为空')
|
||||
|
||||
# 5b. answer 在范围内
|
||||
answer = lq.get('answer', [])
|
||||
opts = lq.get('optionList', [])
|
||||
if isinstance(answer, list) and len(answer) > 0:
|
||||
aidx = answer[0]
|
||||
if aidx >= len(opts):
|
||||
issues.append(f'❌ learningPart[{pi}].learning[{li}] answer={aidx} 超出optionList({len(opts)})')
|
||||
|
||||
# 5c. optionList 每项有 feedback
|
||||
for oi, opt in enumerate(opts):
|
||||
fb = opt.get('feedback', {})
|
||||
if not fb.get('content', ''):
|
||||
issues.append(f'❌ learningPart[{pi}].learning[{li}].option[{oi}] feedback 为空')
|
||||
|
||||
# 5d. leadIn 检查
|
||||
lid = part.get('leadIn', {})
|
||||
if lid and not lid.get('desc',''):
|
||||
issues.append(f'❌ learningPart[{pi}].leadIn.desc 为空')
|
||||
|
||||
# ===== 6. sequenceData 索引越界检查 =====
|
||||
sd = parsed.get('sequenceData')
|
||||
if sd and td_obj:
|
||||
seq = sd.get('sequence', [])
|
||||
texts = td_obj.get('text', [])
|
||||
questions = td_obj.get('question', [])
|
||||
for si, step in enumerate(seq):
|
||||
if 'text' in step:
|
||||
idx = step['text'][0] if step['text'] else -1
|
||||
if idx >= len(texts):
|
||||
issues.append(f'❌ sequence[{si}].text[{idx}] 越界 (text共{len(texts)}段)')
|
||||
if 'question' in step:
|
||||
idx = step['question'][0] if step['question'] else -1
|
||||
if idx >= len(questions):
|
||||
issues.append(f'❌ sequence[{si}].question[{idx}] 越界 (question共{len(questions)}题)')
|
||||
|
||||
# ===== 7. NPC 一致性 =====
|
||||
npc_config = fields.get('角色配置', '')
|
||||
npc_names_from_config = set()
|
||||
if npc_config and npc_config != 'None':
|
||||
# 格式: "Skylar：308" 或 "Brainy" 等
|
||||
for m in re.findall(r'([A-Za-z#\d]+)', npc_config):
|
||||
npc_names_from_config.add(m)
|
||||
|
||||
# 收集所有实际使用的 npcName
|
||||
used_npc = set()
|
||||
if td_obj:
|
||||
for q in td_obj.get('question', []):
|
||||
nm = q.get('npcName','')
|
||||
if nm:
|
||||
used_npc.add(nm.split('#')[0]) # 去掉 #编号
|
||||
|
||||
if ld:
|
||||
for part in ld.get('learningPart', []):
|
||||
nm = part.get('npcName','')
|
||||
if nm:
|
||||
used_npc.add(nm.split('#')[0])
|
||||
closing = ld.get('closing', {})
|
||||
if closing.get('npcName'):
|
||||
used_npc.add(closing['npcName'].split('#')[0])
|
||||
|
||||
# 不在配置中的 NPC
|
||||
for nm in used_npc:
|
||||
if nm not in npc_names_from_config and npc_names_from_config:
|
||||
warnings.append(f'⚠️ NPC "{nm}" 出现在数据中但未在角色配置中声明')
|
||||
|
||||
# ===== 8. kpInfo 与 taskData.key 对应性 =====
|
||||
if td and kp:
|
||||
keys = set()
|
||||
for group in td.get('key', []):
|
||||
for item in group.get('keyList', []):
|
||||
keys.add(item.get('content',''))
|
||||
|
||||
kp_words = set()
|
||||
for info in kp.get('kpInfo', []):
|
||||
kp_words.add(info.get('kpTitle',''))
|
||||
|
||||
only_in_key = keys - kp_words
|
||||
only_in_kp = kp_words - keys
|
||||
if only_in_key:
|
||||
warnings.append(f'⚠️ taskData.key 有但 kpInfo 无: {only_in_key}')
|
||||
if only_in_kp:
|
||||
warnings.append(f'⚠️ kpInfo 有但 taskData.key 无: {only_in_kp}')
|
||||
|
||||
# ===== 9. 能力维度覆盖检查 =====
|
||||
if td_obj:
|
||||
meanings = set()
|
||||
for q in td_obj.get('question', []):
|
||||
m = q.get('meaning','')
|
||||
if m:
|
||||
meanings.add(m)
|
||||
known = {'理解文章中的细节信息','理解文章的主旨大意','推断文章的隐含意义','理解文章中的指代关系'}
|
||||
unknown = meanings - known
|
||||
if unknown:
|
||||
warnings.append(f'⚠️ textData.question 发现未知meaning标签: {unknown}')
|
||||
# 检查是否覆盖了至少 Detail + Main idea
|
||||
if '理解文章中的细节信息' not in meanings:
|
||||
warnings.append('⚠️ 缺少「理解文章中的细节信息」维度')
|
||||
if '理解文章的主旨大意' not in meanings:
|
||||
warnings.append('⚠️ 缺少「理解文章的主旨大意」维度')
|
||||
|
||||
return {
|
||||
'id': fid,
|
||||
'record_id': rid,
|
||||
'title': td.get('title','?') if td else '?',
|
||||
'issues': issues,
|
||||
'warnings': warnings,
|
||||
'total_severity': len(issues),
|
||||
'total_warnings': len(warnings)
|
||||
}
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
token = get_token()
|
||||
records = fetch_all(token)
|
||||
results = [audit(r) for r in records]
|
||||
|
||||
# 输出
|
||||
total_issues = 0
|
||||
total_warnings = 0
|
||||
for r in results:
|
||||
sev = '🔴' if r['total_severity'] > 0 else ('🟡' if r['total_warnings'] > 0 else '🟢')
|
||||
print(f"\n{'='*60}")
|
||||
print(f"{sev} [{r['id']}] {r['title']}")
|
||||
print(f"{'='*60}")
|
||||
for i in r['issues']:
|
||||
print(f" {i}")
|
||||
total_issues += 1
|
||||
for w in r['warnings']:
|
||||
print(f" {w}")
|
||||
total_warnings += 1
|
||||
if not r['issues'] and not r['warnings']:
|
||||
print(f" ✅ 通过")
|
||||
|
||||
print(f"\n{'='*60}")
|
||||
print(f"汇总: {len(results)} 条记录 | 🔴 {total_issues} 个错误 | ⚠️ {total_warnings} 个警告")
|
||||
zero = sum(1 for r in results if r['total_severity']==0 and r['total_warnings']==0)
|
||||
print(f"全通过: {zero}/{len(results)}")
|
||||
|
||||
# 输出 JSON 供后续使用
|
||||
print('\n---RESULT_JSON---')
|
||||
print(json.dumps(results, ensure_ascii=False, indent=2))
|
||||
278
scripts/audit_l1_config.py
Normal file
278
scripts/audit_l1_config.py
Normal file
@ -0,0 +1,278 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Level 1 配置表 句子知识点审校 — 自动化检查脚本
|
||||
用法: python3 scripts/audit_l1_config.py <bitable_app_token> <table_id> [record_id]
|
||||
record_id 可选，不传则检查全表
|
||||
"""
|
||||
import json, requests, re, sys, os
|
||||
|
||||
CRED = "/root/.openclaw/credentials/xiaoyan/config.json"
|
||||
THIRD_SINGULAR_RULES = [
|
||||
(r"\bHe\b.*\bneed\b", "need→needs"), (r"\bShe\b.*\bneed\b", "need→needs"),
|
||||
(r"\bIt\b.*\bneed\b", "need→needs"), (r"\bOtis\b.*\bneed\b", "need→needs"),
|
||||
(r"\bTom\b.*\bneed\b", "need→needs"), (r"\bMum\b.*\bneed\b", "need→needs"),
|
||||
(r"\bDad\b.*\bneed\b", "need→needs"), (r"\bBen\b.*\bneed\b", "need→needs"),
|
||||
(r"\bhave\b", "三单检查"),
|
||||
]
|
||||
|
||||
REQUIRED_JSON_FIELDS = {
|
||||
"basicInfo": ["type", "id", "meaning", "desc", "structure", "valaLevel"],
|
||||
"classificationInfo": ["type", "id", "cambridgeLevel", "cefrLevel", "ncLevel"],
|
||||
"config": ["type", "id", "title"],
|
||||
"usageInfo": ["type", "id", "usage"],
|
||||
}
|
||||
QUESTION_FIELDS = {
|
||||
"sentenceMeaningChooseMcq": "场景选择题",
|
||||
"sentenceMeaningMatchMcq": "听句作答题",
|
||||
"sentenceMeaningMeaning": "句意选择题",
|
||||
"sentenceMeaningPic2SentMcq": "看图选择题",
|
||||
"sentencePronRead": "句子朗读",
|
||||
"sentencePronRepeatSentence": "句子跟读题",
|
||||
"sentenceStructureClozeWordMcq": "句子补全题",
|
||||
"sentenceStructureSort": "句型结构题",
|
||||
}
|
||||
Q_REQUIRED = ["category", "skill", "type", "pointId", "question", "options", "answer"]
|
||||
# 发音类题型不需要 options/answer
|
||||
PRONUNCIATION_TYPES = {"sentence_pron_read", "sentence_pron_repeat_sentence"}
|
||||
|
||||
def get_token():
|
||||
with open(CRED) as f:
|
||||
c = json.load(f)
|
||||
r = requests.post("https://open.feishu.cn/open-apis/auth/v3/tenant_access_token/internal",
|
||||
json={"app_id": c["apps"][0]["appId"], "app_secret": c["apps"][0]["appSecret"]})
|
||||
return r.json()["tenant_access_token"]
|
||||
|
||||
def check_classification_swap(record):
|
||||
"""检查 classificationInfo 中 cambridgeLevel/cefrLevel 是否与列字段互换"""
|
||||
issues = []
|
||||
try:
|
||||
ci = json.loads(record.get("classificationInfo", "{}"))
|
||||
except:
|
||||
return ["❌ classificationInfo JSON 解析失败"]
|
||||
col_cambridge = record.get("剑桥考试级别", "")
|
||||
col_cefr = record.get("欧标等级", "")
|
||||
if ci.get("cambridgeLevel") and col_cambridge and ci["cambridgeLevel"] != col_cambridge:
|
||||
if ci.get("cefrLevel") == col_cambridge:
|
||||
issues.append(f"❌ classificationInfo 值互换: cambridgeLevel={ci['cambridgeLevel']}(应为{col_cambridge}), cefrLevel={ci['cefrLevel']}(应为{col_cefr})")
|
||||
else:
|
||||
issues.append(f"⚠️ classificationInfo.cambridgeLevel={ci['cambridgeLevel']} ≠ 列字段剑桥考试级别={col_cambridge}")
|
||||
if ci.get("cefrLevel") and col_cefr and ci["cefrLevel"] != col_cefr:
|
||||
if ci.get("cambridgeLevel") != col_cefr:
|
||||
issues.append(f"⚠️ classificationInfo.cefrLevel={ci['cefrLevel']} ≠ 列字段欧标等级={col_cefr}")
|
||||
return issues
|
||||
|
||||
def check_json_integrity(record, field, required):
|
||||
"""检查 JSON 字段的必填字段完整性"""
|
||||
issues = []
|
||||
try:
|
||||
data = json.loads(record.get(field, "{}"))
|
||||
except:
|
||||
return [f"❌ {field} JSON 解析失败"]
|
||||
if not isinstance(data, dict):
|
||||
return []
|
||||
for key in required:
|
||||
if key not in data or data[key] is None or data[key] == "":
|
||||
issues.append(f"❌ {field} 缺少必填字段 {key}")
|
||||
# id consistency (strip trailing spaces from both sides)
|
||||
rid = (record.get("ID", "") or "").strip()
|
||||
if data.get("id") and rid and str(data["id"]).strip() != rid:
|
||||
issues.append(f"❌ {field}.id={data['id']} ≠ record ID={rid}")
|
||||
return issues
|
||||
|
||||
def check_question_item(q, qtype, rid):
|
||||
"""检查单个 question 对象的完整性"""
|
||||
issues = []
|
||||
qtype_name = q.get("type", "")
|
||||
# 发音类题型豁免 options/answer
|
||||
skip = {"options", "answer"} if qtype_name in PRONUNCIATION_TYPES else set()
|
||||
for key in Q_REQUIRED:
|
||||
if key in skip:
|
||||
continue
|
||||
if key not in q or q[key] is None or (isinstance(q[key], (list, str)) and len(q[key]) == 0):
|
||||
issues.append(f"⚠️ {qtype} 缺少字段 {key}")
|
||||
# pointId consistency (strip spaces)
|
||||
rid_stripped = rid.strip() if rid else ""
|
||||
if q.get("pointId") and rid_stripped and str(q["pointId"]).strip() != rid_stripped:
|
||||
issues.append(f"⚠️ {qtype}.pointId={q['pointId']} ≠ record ID={rid_stripped}")
|
||||
# answer index validity
|
||||
options = q.get("options", [])
|
||||
answers = q.get("answer", [])
|
||||
for a in answers:
|
||||
if isinstance(a, int) and (a < 0 or a >= len(options)):
|
||||
issues.append(f"❌ {qtype} answer 索引 {a} 超出 options 范围 0~{len(options)-1}")
|
||||
return issues
|
||||
|
||||
def check_sort_wordbank_answer(question, rid):
|
||||
"""检查句型结构题：单词库能否拼出答案，第三人称单数是否正确"""
|
||||
issues = []
|
||||
words = question.get("options", [])
|
||||
indices = question.get("answer", [])
|
||||
explanation = question.get("explanation", "")
|
||||
# 拼出句子
|
||||
try:
|
||||
assembled = " ".join(words[i] for i in indices)
|
||||
except:
|
||||
return [f"❌ sentenceStructureSort answer 索引超出单词库范围"]
|
||||
# 从 explanation 提取声明答案
|
||||
m = re.search(r'正确答案是 "(.+?)"', explanation)
|
||||
if m:
|
||||
declared = m.group(1)
|
||||
# 标准化后比较：去末尾标点 + 首字母大写归一
|
||||
def norm(s):
|
||||
s = s.rstrip(".!?")
|
||||
if s and s[0].islower():
|
||||
s = s[0].upper() + s[1:]
|
||||
return s
|
||||
if norm(assembled) != norm(declared):
|
||||
issues.append(f"❌ sentenceStructureSort 单词拼出 \"{assembled}\" ≠ 解释声明 \"{declared}\"")
|
||||
# 第三人称单数检查
|
||||
third_singular_subjects = ["He", "She", "It"] + re.findall(r'\b([A-Z][a-z]+)\b', " ".join(words[:1]))
|
||||
for subj in third_singular_subjects:
|
||||
if assembled.startswith(subj) and subj not in ["I", "You", "We", "They"]:
|
||||
if "need " in assembled and "needs" not in words:
|
||||
issues.append(f"❌ sentenceStructureSort {subj}三单主语，单词库有need无needs")
|
||||
break
|
||||
return issues
|
||||
|
||||
def check_question_set(record, rid):
|
||||
"""检查所有题型 JSON"""
|
||||
issues = []
|
||||
for field, cname in QUESTION_FIELDS.items():
|
||||
raw = record.get(field, "")
|
||||
if not raw:
|
||||
issues.append(f"⚠️ {field}({cname}) 为空")
|
||||
continue
|
||||
try:
|
||||
questions = json.loads(raw)
|
||||
except:
|
||||
issues.append(f"❌ {field}({cname}) JSON 解析失败")
|
||||
continue
|
||||
if not isinstance(questions, list):
|
||||
issues.append(f"❌ {field}({cname}) 应为数组")
|
||||
continue
|
||||
for i, q in enumerate(questions):
|
||||
q_issues = check_question_item(q, f"{cname}[{i}]", rid)
|
||||
issues.extend(q_issues)
|
||||
# 句型结构题专项检查
|
||||
if field == "sentenceStructureSort":
|
||||
issues.extend(check_sort_wordbank_answer(q, rid))
|
||||
return issues
|
||||
|
||||
def check_consistency_with_chinese_fields(record):
|
||||
"""中文描述列与 JSON 列内容一致性"""
|
||||
issues = []
|
||||
mapping = [
|
||||
("句意选择题", "sentenceMeaningMeaning"),
|
||||
("句型结构题", "sentenceStructureSort"),
|
||||
("句子朗读", "sentencePronRead"),
|
||||
("看图选择题", "sentenceMeaningPic2SentMcq"),
|
||||
("听句作答题", "sentenceMeaningMatchMcq"),
|
||||
("场景选择题", "sentenceMeaningChooseMcq"),
|
||||
("句子补全题", "sentenceStructureClozeWordMcq"),
|
||||
("句子跟读题", "sentencePronRepeatSentence"),
|
||||
]
|
||||
for col, json_field in mapping:
|
||||
cn = record.get(col, "")
|
||||
try:
|
||||
jd = json.loads(record.get(json_field, "[]"))
|
||||
except:
|
||||
continue
|
||||
if cn and not jd:
|
||||
issues.append(f"⚠️ {col} 有中文内容但 {json_field} 为空")
|
||||
if not cn and jd:
|
||||
issues.append(f"⚠️ {json_field} 有数据但 {col} 为空")
|
||||
return issues
|
||||
|
||||
def audit_record(record):
|
||||
"""对单条记录执行全量自动化审校"""
|
||||
rid = record.get("ID", record.get("record_id", "unknown"))
|
||||
all_issues = []
|
||||
|
||||
# 0. ID 字段检查（末尾空格）
|
||||
if isinstance(rid, str) and rid != rid.rstrip():
|
||||
all_issues.append(f"⚠️ ID 字段含末尾空格: [{rid}] len={len(rid)}")
|
||||
rid_clean = rid.strip() if isinstance(rid, str) else str(rid)
|
||||
|
||||
# 1. 基础信息完整性
|
||||
for field, required in REQUIRED_JSON_FIELDS.items():
|
||||
all_issues.extend(check_json_integrity(record, field, required))
|
||||
|
||||
# 2. classificationInfo 互换检测
|
||||
all_issues.extend(check_classification_swap(record))
|
||||
|
||||
# 3. 题型 JSON 检查
|
||||
all_issues.extend(check_question_set(record, rid_clean))
|
||||
|
||||
# 4. 中英文字段一致性
|
||||
all_issues.extend(check_consistency_with_chinese_fields(record))
|
||||
|
||||
return rid_clean, all_issues
|
||||
|
||||
def main():
|
||||
app_token = sys.argv[1] if len(sys.argv) > 1 else "Nq3Zb258aae7SRs2QfXcqsQYnxJ"
|
||||
table_id = sys.argv[2] if len(sys.argv) > 2 else "tblTxGpf6GQ5c7DZ"
|
||||
target_id = sys.argv[3] if len(sys.argv) > 3 else None
|
||||
|
||||
print(f"🔍 Level 1 配置表审校 | {app_token}/{table_id}")
|
||||
if target_id:
|
||||
print(f" 目标: {target_id}")
|
||||
print()
|
||||
|
||||
token = get_token()
|
||||
|
||||
if target_id:
|
||||
# 搜索特定记录
|
||||
page_token = ""
|
||||
record = None
|
||||
while True:
|
||||
r = requests.get(
|
||||
f"https://open.feishu.cn/open-apis/bitable/v1/apps/{app_token}/tables/{table_id}/records",
|
||||
headers={"Authorization": f"Bearer {token}"},
|
||||
params={"page_size": 50, "page_token": page_token})
|
||||
d = r.json().get("data", {})
|
||||
for item in (d.get("items") or []):
|
||||
if item["fields"].get("ID") == target_id:
|
||||
record = item["fields"]
|
||||
record["record_id"] = item["record_id"]
|
||||
break
|
||||
if record:
|
||||
break
|
||||
if not d.get("has_more"):
|
||||
break
|
||||
page_token = d.get("page_token", "")
|
||||
|
||||
if not record:
|
||||
print(f"❌ 未找到 {target_id}")
|
||||
return
|
||||
rid, issues = audit_record(record)
|
||||
print(f"=== {rid} === 共 {len(issues)} 个问题")
|
||||
for i in issues:
|
||||
print(f" {i}")
|
||||
if not issues:
|
||||
print(" ✅ 自动化审校通过")
|
||||
else:
|
||||
# 全表扫描
|
||||
page_token = ""
|
||||
total_issues = 0
|
||||
total_records = 0
|
||||
while True:
|
||||
r = requests.get(
|
||||
f"https://open.feishu.cn/open-apis/bitable/v1/apps/{app_token}/tables/{table_id}/records",
|
||||
headers={"Authorization": f"Bearer {token}"},
|
||||
params={"page_size": 50, "page_token": page_token})
|
||||
d = r.json().get("data", {})
|
||||
for item in (d.get("items") or []):
|
||||
rec = item["fields"]
|
||||
rec["record_id"] = item["record_id"]
|
||||
rid, issues = audit_record(rec)
|
||||
if issues:
|
||||
total_issues += len(issues)
|
||||
total_records += 1
|
||||
print(f" {rid}: {len(issues)} issues | {issues[0][:80]}...")
|
||||
if not d.get("has_more"):
|
||||
break
|
||||
page_token = d.get("page_token", "")
|
||||
print(f"\n全表扫描完成: {total_records} 条记录有 {total_issues} 个问题")
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
343
scripts/fix_matchInfo_0213_0218_desc.py
Normal file
343
scripts/fix_matchInfo_0213_0218_desc.py
Normal file
@ -0,0 +1,343 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Fix 图片描述 for 021301-021801: add 【Notice Type】 labels per reference format"""
|
||||
import json, requests, time, sys
|
||||
|
||||
CRED = "/root/.openclaw/credentials/xiaoyan/config.json"
|
||||
TOKEN_APP = "CMHSbUUjka3TrUsaxxEc297ongf"
|
||||
TBL = "tblCgfYDnnqwLfgH"
|
||||
|
||||
with open(CRED) as f:
|
||||
cred = json.load(f)
|
||||
aid = cred["apps"][0]["appId"]
|
||||
asecret = cred["apps"][0]["appSecret"]
|
||||
|
||||
def get_token():
|
||||
r = requests.post("https://open.feishu.cn/open-apis/auth/v3/tenant_access_token/internal",
|
||||
json={"app_id": aid, "app_secret": asecret})
|
||||
return r.json()["tenant_access_token"]
|
||||
|
||||
# New descriptions with 【Type】 labels
|
||||
# Format: 图片材料文本：\n【Type】\nText content
|
||||
NEW_DESC = {
|
||||
"021301": """1.
|
||||
图片材料文本：
|
||||
【Show Poster】
|
||||
The ACTOR is on stage.
|
||||
|
||||
图片材料文本：
|
||||
【Wanted Notice】
|
||||
Man with black BEARD wanted.
|
||||
|
||||
图片材料文本：
|
||||
【Art Label】
|
||||
These pictures are DIFFERENT.
|
||||
|
||||
图片材料文本：
|
||||
【Award Certificate】
|
||||
Lily was very BRAVE today.
|
||||
|
||||
图片材料文本：
|
||||
【Greeting Card】
|
||||
A new NEIGHBOUR moved in.
|
||||
|
||||
2.
|
||||
图片材料文本：
|
||||
【Family Note】
|
||||
DINNER at six tonight.
|
||||
|
||||
图片材料文本：
|
||||
【Door Sign】
|
||||
Mum is COOKING right now.
|
||||
|
||||
图片材料文本：
|
||||
【Fire Exit Sign】
|
||||
FIRE exit this way →
|
||||
|
||||
图片材料文本：
|
||||
【Event Poster】
|
||||
Family ALBUM on show Friday.
|
||||
|
||||
图片材料文本：
|
||||
【Personal Note】
|
||||
Do not read my DIARY.""",
|
||||
|
||||
"021401": """1.
|
||||
图片材料文本：
|
||||
【Planning Note】
|
||||
PLAN your weekend now.
|
||||
|
||||
图片材料文本：
|
||||
【Shop Sign】
|
||||
Bike REPAIR in one hour.
|
||||
|
||||
图片材料文本：
|
||||
【Library Sign】
|
||||
Today's NEWSPAPER on the desk.
|
||||
|
||||
图片材料文本：
|
||||
【Lost & Found】
|
||||
Lost: Blue BACKPACK in Room 3.
|
||||
|
||||
图片材料文本：
|
||||
【Bus Sign】
|
||||
Give your SEAT to old people.
|
||||
|
||||
2.
|
||||
图片材料文本：
|
||||
【School Notice】
|
||||
School GARDEN open after class.
|
||||
|
||||
图片材料文本：
|
||||
【Market Sign】
|
||||
Sweet MELON for sale today.
|
||||
|
||||
图片材料文本：
|
||||
【Warning Sign】
|
||||
Do not drink lake WATER.
|
||||
|
||||
图片材料文本：
|
||||
【School Notice】
|
||||
PLANT a tree on Friday.
|
||||
|
||||
图片材料文本：
|
||||
【School Notice】
|
||||
SUMMER camp starts next week.""",
|
||||
|
||||
"021501": """1.
|
||||
图片材料文本：
|
||||
【School Sign】
|
||||
VISITORs sign in at the office.
|
||||
|
||||
图片材料文本：
|
||||
【Party Banner】
|
||||
WELCOME to the birthday party!
|
||||
|
||||
图片材料文本：
|
||||
【Party Invitation】
|
||||
You are INVITEd to Tom's party.
|
||||
|
||||
图片材料文本：
|
||||
【Event Poster】
|
||||
Come and LAUGH with us!
|
||||
|
||||
图片材料文本：
|
||||
【Hotel Notice】
|
||||
GUESTs: breakfast 7 to 9 a.m.
|
||||
|
||||
2.
|
||||
图片材料文本：
|
||||
【Homework Reminder】
|
||||
Check for MISTAKEs first.
|
||||
|
||||
图片材料文本：
|
||||
【Exam Notice】
|
||||
Read the INSTRUCTION carefully.
|
||||
|
||||
图片材料文本：
|
||||
【Office Notice】
|
||||
Give a REASON if late.
|
||||
|
||||
图片材料文本：
|
||||
【Room Sign】
|
||||
No drinks near TECHNOLOGY room.
|
||||
|
||||
图片材料文本：
|
||||
【Art Room Sign】
|
||||
Wash your paint BRUSH here.""",
|
||||
|
||||
"021601": """1.
|
||||
图片材料文本：
|
||||
【Sports Notice】
|
||||
New school RECORD in jump!
|
||||
|
||||
图片材料文本：
|
||||
【School Notice】
|
||||
Sports day — a big EVENT.
|
||||
|
||||
图片材料文本：
|
||||
【Door Sign】
|
||||
Do not ENTER without teacher.
|
||||
|
||||
图片材料文本：
|
||||
【Library Notice】
|
||||
RETURN books by this Friday.
|
||||
|
||||
图片材料文本：
|
||||
【Recycling Sign】
|
||||
Please SORT paper and glass.
|
||||
|
||||
2.
|
||||
图片材料文本：
|
||||
【Lost & Found】
|
||||
Lost: red HANDBAG near playground.
|
||||
|
||||
图片材料文本：
|
||||
【No Photo Sign】
|
||||
No CAMERA in this room.
|
||||
|
||||
图片材料文本：
|
||||
【Park Sign】
|
||||
Park GATE closes at eight.
|
||||
|
||||
图片材料文本：
|
||||
【Shop Sign】
|
||||
Fix your WHEEL in 30 minutes.
|
||||
|
||||
图片材料文本：
|
||||
【Building Sign】
|
||||
Main ENTRANCE on north side.""",
|
||||
|
||||
"021701": """1.
|
||||
图片材料文本：
|
||||
【Bus Sign】
|
||||
Do not talk to the DRIVER.
|
||||
|
||||
图片材料文本：
|
||||
【Safety Poster】
|
||||
Look both ways on the STREET.
|
||||
|
||||
图片材料文本：
|
||||
【Market Sign】
|
||||
Farmers' MARKET every Saturday.
|
||||
|
||||
图片材料文本：
|
||||
【Information Desk】
|
||||
Free GUIDEBOOK at this desk.
|
||||
|
||||
图片材料文本：
|
||||
【Mall Sign】
|
||||
SHOPPING hours: 10 a.m. to 8 p.m.
|
||||
|
||||
2.
|
||||
图片材料文本：
|
||||
【Laundry Sign】
|
||||
Washing MACHINE on first floor.
|
||||
|
||||
图片材料文本：
|
||||
【Art Club Notice】
|
||||
DRAW your family for the show.
|
||||
|
||||
图片材料文本：
|
||||
【Sports Notice】
|
||||
BASKETBALL practice at four today.
|
||||
|
||||
图片材料文本：
|
||||
【Library Sign】
|
||||
Put books on the BOOKCASE.
|
||||
|
||||
图片材料文本：
|
||||
【Science Fair Sign】
|
||||
Show your INVENTION on Monday.""",
|
||||
|
||||
"021801": """1.
|
||||
图片材料文本：
|
||||
【Library Notice】
|
||||
LIBRARY open 8 a.m. to 4 p.m.
|
||||
|
||||
图片材料文本：
|
||||
【Reading Room Sign】
|
||||
New MAGAZINEs — read here only.
|
||||
|
||||
图片材料文本：
|
||||
【TV Room Sign】
|
||||
CARTOON at three this afternoon.
|
||||
|
||||
图片材料文本：
|
||||
【Exam Notice】
|
||||
English TEST on Friday morning.
|
||||
|
||||
图片材料文本：
|
||||
【Lab Sign】
|
||||
Read CAREFULLY before you start.
|
||||
|
||||
2.
|
||||
图片材料文本：
|
||||
【Toy Label】
|
||||
This toy needs a new BATTERY.
|
||||
|
||||
图片材料文本：
|
||||
【Library Sign】
|
||||
Reading CORNER on the left side.
|
||||
|
||||
图片材料文本：
|
||||
【School Notice】
|
||||
Play at the THEATRE this Saturday.
|
||||
|
||||
图片材料文本：
|
||||
【Park Sign】
|
||||
Do not CLIMB the park trees.
|
||||
|
||||
图片材料文本：
|
||||
【Canteen Notice】
|
||||
Lunch is at MIDDAY today.""",
|
||||
}
|
||||
|
||||
# Step 1: Get current records & record_ids
|
||||
token = get_token()
|
||||
r = requests.get(
|
||||
f"https://open.feishu.cn/open-apis/bitable/v1/apps/{TOKEN_APP}/tables/{TBL}/records",
|
||||
headers={"Authorization": f"Bearer {token}"},
|
||||
params={"page_size": 50})
|
||||
|
||||
records = {}
|
||||
for item in r.json().get("data", {}).get("items", []):
|
||||
fid = item["fields"].get("题目集合 ID", "")
|
||||
if fid in NEW_DESC:
|
||||
records[fid] = item["record_id"]
|
||||
|
||||
print(f"Found {len(records)} records to update")
|
||||
|
||||
# Step 2: Update 图片描述
|
||||
print("=== Updating 图片描述 ===")
|
||||
for qid in sorted(NEW_DESC):
|
||||
if qid not in records:
|
||||
print(f" ❌ {qid}: record not found")
|
||||
continue
|
||||
rid = records[qid]
|
||||
desc = NEW_DESC[qid]
|
||||
r = requests.put(
|
||||
f"https://open.feishu.cn/open-apis/bitable/v1/apps/{TOKEN_APP}/tables/{TBL}/records/{rid}",
|
||||
headers={"Authorization": f"Bearer {token}", "Content-Type": "application/json"},
|
||||
json={"fields": {"图片描述": desc}})
|
||||
code = r.json().get("code")
|
||||
print(f" {qid} ({rid}): code={code} len={len(desc)}chars")
|
||||
time.sleep(0.5)
|
||||
|
||||
# Step 3: Wait then verify
|
||||
print("\n=== Step 3: Wait 5s + Verify ===")
|
||||
time.sleep(5)
|
||||
token = get_token()
|
||||
|
||||
all_ok = True
|
||||
for qid in sorted(NEW_DESC):
|
||||
rid = records.get(qid)
|
||||
if not rid:
|
||||
continue
|
||||
r = requests.get(
|
||||
f"https://open.feishu.cn/open-apis/bitable/v1/apps/{TOKEN_APP}/tables/{TBL}/records/{rid}",
|
||||
headers={"Authorization": f"Bearer {token}"})
|
||||
fields = r.json()["data"]["record"]["fields"]
|
||||
desc = fields.get("图片描述", "") or ""
|
||||
|
||||
# Check: contains 【 and has expected structure
|
||||
has_labels = "【" in desc
|
||||
has_text = "图片材料文本" in desc
|
||||
ok = has_labels and has_text and len(desc) > 200
|
||||
|
||||
# Count 【 occurrences - should be 10 (one per image)
|
||||
bracket_count = desc.count("【")
|
||||
desc_ok = bracket_count == 10
|
||||
|
||||
status = "✅" if (ok and desc_ok) else "❌"
|
||||
if not ok or not desc_ok:
|
||||
all_ok = False
|
||||
print(f" {status} {qid}: labels={bracket_count}/10 char={len(desc)}")
|
||||
|
||||
# Show first 2 entries as sample
|
||||
if has_labels:
|
||||
lines = desc.strip().split("\n")
|
||||
for i, line in enumerate(lines):
|
||||
if "【" in line:
|
||||
print(f" {line}")
|
||||
|
||||
print(f"\n{'✅ All OK' if all_ok else '❌ Some checks failed'}")
|
||||
124
skills/audit_l1_config/SKILL.md
Normal file
124
skills/audit_l1_config/SKILL.md
Normal file
@ -0,0 +1,124 @@
|
||||
---
|
||||
name: audit_l1_config
|
||||
description: Level 1 配置表（句子知识点）自动化审校技能。覆盖基础信息完整性、分类字段互换检测、题型JSON结构、单词库-答案一致性、第三人称单数语法等7项自动检查 + 4项人工审核清单。触发关键词：L1配置表审校、句子知识点审校、巩固题审校、audit l1 config
|
||||
---
|
||||
|
||||
# L1 配置表审校 — 句子知识点
|
||||
|
||||
## 目标数据源
|
||||
|
||||
- **多维表格**: 「互动知识点 - 句子」→「Level 1 配置表」
|
||||
- **App Token**: `Nq3Zb258aae7SRs2QfXcqsQYnxJ`
|
||||
- **Table ID**: `tblTxGpf6GQ5c7DZ`
|
||||
- **字段结构**: ID(7位数字化) / 基础信息(basicInfo/classificationInfo/config/usageInfo) / 8种题型JSON / 中文字段描述 / 审校结果
|
||||
|
||||
## ID 编码规则
|
||||
|
||||
| 位 | 含义 | 示例 |
|
||||
|----|------|------|
|
||||
| 1-2 | Level + Season | 10=L1S0, 11=L1S1, 12=L1S2 |
|
||||
| 3-4 | Unit | 00=U1, 01=U2, ... 14=U14 |
|
||||
| 5-7 | 序列号 | 001-010 |
|
||||
|
||||
例: 1214001 = L1 Season2, Unit14, 序列001
|
||||
|
||||
## 审校流程
|
||||
|
||||
```
|
||||
Step 1: 运行自动审校脚本 → python3 scripts/audit_l1_config.py [app_token] [table_id] [record_id]
|
||||
Step 2: 对自动检查发现的问题，确认真实性（排除误报）
|
||||
Step 3: 按人工审核清单逐项检查
|
||||
Step 4: 汇总结果写入 bitable「审校结果」列
|
||||
```
|
||||
|
||||
## 自动化检查项（7项）
|
||||
|
||||
### 1. basicInfo/config/usageInfo 字段完整性
|
||||
- 检查 JSON 是否包含必填字段：type, id, meaning, desc, structure, valaLevel
|
||||
- 检查 id 与 record ID 是否一致
|
||||
|
||||
### 2. classificationInfo 值互换检测 ⚠️ 高频问题
|
||||
- 检查 `cambridgeLevel` 是否与列字段「剑桥考试级别」一致（应为 YLE/PET/KET 等）
|
||||
- 检查 `cefrLevel` 是否与列字段「欧标等级」一致（应为 A1/A2/B1 等）
|
||||
- **常见问题**: 两个字段值互换，如 cambridgeLevel="A1" 而 cefrLevel="YLE"
|
||||
|
||||
### 3. 题型 JSON 结构完整性
|
||||
- 8种题型 JSON 是否存在，内容是否为空数组
|
||||
- 每道题必含: category, skill, type, pointId, question, options, answer
|
||||
- pointId 与 record ID 一致性
|
||||
- answer 索引不超出 options 范围
|
||||
- 发音类题型（句子朗读/跟读）豁免 options/answer 检查
|
||||
|
||||
### 4. sentenceStructureSort 单词库-答案一致性
|
||||
- 按 answer 索引从单词库拼出句子
|
||||
- 与 explanation 中「正确答案是 "..."」对比（去标点后）
|
||||
- **常见问题**: 单词库给 "need" 但正确形式应为 "needs"（三单）
|
||||
|
||||
### 5. sentenceStructureSort 第三人称单数语法
|
||||
- 主语为 He/She/It/人名 时，检查动词是否有三单变形
|
||||
- 特殊检查: 单词库有 "need" 但无 "needs"，且主语为三单 → 报错
|
||||
|
||||
### 6. 题型覆盖率
|
||||
- 确认所有8种题型字段非空且 JSON 可解析
|
||||
- 缺失题型标记为 ⚠️
|
||||
|
||||
### 7. 中文字段 × JSON 字段一致性
|
||||
- 中文描述列（句意选择题/句型结构题等）与对应 JSON 字段双向校验
|
||||
- 一边有数据另一边为空 → 标记 ⚠️
|
||||
|
||||
## 人工审核清单（4项）
|
||||
|
||||
### A. 填空题选项自然度
|
||||
- 如 sentenceStructureClozeWordMcq 中 "put your toys" 省略 "away" 是否可接受
|
||||
- 需结合 L1 级别和教学目标判断省略形式的合理性
|
||||
|
||||
### B. 解释文本质量
|
||||
- 解释是否准确、完整、易于理解
|
||||
- 语法术语是否符合目标年龄段
|
||||
|
||||
### C. 选项干扰项合理性
|
||||
- 干扰项是否与正确答案有足够的区分度（不能太明显）
|
||||
- 干扰项是否过于混淆（不能太接近）
|
||||
|
||||
### D. 图片描述与题型匹配
|
||||
- sentenceMeaningPic2SentMcq 的图片描述是否符合场景
|
||||
- 图片是否清晰传达目标知识点
|
||||
|
||||
## 使用示例
|
||||
|
||||
### 单条记录审校
|
||||
```bash
|
||||
python3 scripts/audit_l1_config.py Nq3Zb258aae7SRs2QfXcqsQYnxJ tblTxGpf6GQ5c7DZ 1214001
|
||||
```
|
||||
|
||||
### 全表扫描
|
||||
```bash
|
||||
python3 scripts/audit_l1_config.py
|
||||
```
|
||||
|
||||
### 输出示例
|
||||
```
|
||||
🔍 Level 1 配置表审校 | Nq3Zb258aae7SRs2QfXcqsQYnxJ/tblTxGpf6GQ5c7DZ
|
||||
目标: 1214001
|
||||
|
||||
=== 1214001 === 共 3 个问题
|
||||
❌ classificationInfo 值互换: cambridgeLevel=A1(应为YLE), cefrLevel=YLE(应为A1)
|
||||
❌ sentenceStructureSort 单词拼出 "Otis need to pack his schoolbag" ≠ 解释声明 "Otis needs to pack his schoolbag."
|
||||
❌ sentenceStructureSort Otis三单主语，单词库有need无needs
|
||||
```
|
||||
|
||||
## 审校结果写入规范
|
||||
|
||||
写入 bitable「审校结果」列时遵循：
|
||||
1. ❌ 标记真实错误（带具体定位和修正方案）
|
||||
2. ⚠️ 标记需确认项（带评估建议）
|
||||
3. ✅ 全量通过时写 `✅`
|
||||
4. 自动检查命中的问题需人工二次确认后再写入（排除误报）
|
||||
|
||||
## 常见误报场景（脚本使用者须知）
|
||||
|
||||
| 误报类型 | 原因 | 处理 |
|
||||
|---------|------|------|
|
||||
| 发音类题型报缺少 options/answer | sentencePronRead/sentencePronRepeatSentence 无选项 | 脚本已豁免 |
|
||||
| 单词拼出句子 ≠ 解释声明（仅标点差异） | 末尾句号差异 | 脚本已去标点后比较 |
|
||||
| 句子朗读 pointId ≠ record ID | 可能是跨知识点复用 | 人工判断是否为合理复用 |
|
||||
164
skills/bitable-reader/SKILL.md
Normal file
164
skills/bitable-reader/SKILL.md
Normal file
@ -0,0 +1,164 @@
|
||||
---
|
||||
name: bitable-reader
|
||||
version: 1.0.0
|
||||
description: "通用飞书多维表格结构读取技能。读取任意多维表格的表结构、字段定义、记录数据，自动处理分页和JSON字段解析。适用于内容发现、配置提取、数据分析等场景。"
|
||||
metadata:
|
||||
requires:
|
||||
permissions: ["bitable:app:readonly", "wiki:node:retrieve"]
|
||||
triggers:
|
||||
- "用户提供多维表格链接（wiki/bitable）要求查看内容"
|
||||
- "需要从多维表格提取配置数据做分析"
|
||||
- "需要了解某个多维表格的字3段结构和数据格式"
|
||||
---
|
||||
|
||||
# bitable-reader — 多维表格通用读取技能
|
||||
|
||||
## 身份规则
|
||||
- 所有读取操作**永远使用 Bot 身份**（`--as bot` / Bot tenant_access_token）
|
||||
- 禁止触发用户授权弹窗
|
||||
- 只读操作，绝不写入或删除
|
||||
|
||||
## 执行链路
|
||||
|
||||
### 步骤 0：获取 Bot 凭据
|
||||
|
||||
```bash
|
||||
TOKEN=$(curl -s -X POST "https://open.feishu.cn/open-apis/auth/v3/tenant_access_token/internal" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"app_id":"cli_a931175d41799cc7","app_secret":"Iw2vEfbjT6GtV0GhbxbZqfQ4nAPtbR14"}' \
|
||||
| python3 -c "import sys,json; print(json.load(sys.stdin)['tenant_access_token'])")
|
||||
```
|
||||
|
||||
Token 有效期 2 小时，同一会话复用即可。
|
||||
|
||||
### 步骤 1：定位多维表格
|
||||
|
||||
#### 1a. 从 wiki 链接进入
|
||||
```
|
||||
链接：https://xxx.feishu.cn/wiki/XXXXXX
|
||||
↓
|
||||
提取 wiki_token = "XXXXXX"
|
||||
↓
|
||||
lark-cli wiki spaces get_node --params '{"token":"XXXXXX"}' --as bot
|
||||
```
|
||||
|
||||
若返回 `has_child: true` 且非 bitable，遍历子节点（步骤 1b）。
|
||||
|
||||
#### 1b. 遍历 wiki 子目录
|
||||
```bash
|
||||
curl -s -X GET \
|
||||
"https://open.feishu.cn/open-apis/wiki/v2/spaces/<space_id>/nodes?parent_node_token=<node_token>" \
|
||||
-H "Authorization: Bearer $TOKEN"
|
||||
```
|
||||
分页用 `page_token` 参数。
|
||||
|
||||
#### 1c. 确认目标为 bitable
|
||||
Node 的 `obj_type` 为 `"bitable"` 时，`obj_token` 即为 `app_token`。
|
||||
|
||||
#### 1d. 直接提供 app_token 时
|
||||
跳过上述步骤，直接进入步骤 2。
|
||||
|
||||
### 步骤 2：列出所有数据表
|
||||
|
||||
```bash
|
||||
curl -s -X GET \
|
||||
"https://open.feishu.cn/open-apis/bitable/v1/apps/<app_token>/tables" \
|
||||
-H "Authorization: Bearer $TOKEN"
|
||||
```
|
||||
|
||||
返回结构：
|
||||
```json
|
||||
{
|
||||
"data": {
|
||||
"has_more": false,
|
||||
"items": [
|
||||
{"name": "S0", "revision": 1445, "table_id": "tblXXXXXX"},
|
||||
{"name": "S1", "revision": 3150, "table_id": "tblYYYYYY"}
|
||||
],
|
||||
"page_token": "...",
|
||||
"total": 7
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### 步骤 3：获取表字段结构
|
||||
|
||||
```bash
|
||||
curl -s -X GET \
|
||||
"https://open.feishu.cn/open-apis/bitable/v1/apps/<app_token>/tables/<table_id>/fields" \
|
||||
-H "Authorization: Bearer $TOKEN"
|
||||
```
|
||||
|
||||
返回每个字段的 `field_name` 和 `type`（类型代码对照表见附录）。
|
||||
|
||||
### 步骤 4：读取记录数据
|
||||
|
||||
#### 4a. 全量分页读取
|
||||
```bash
|
||||
curl -s -X GET \
|
||||
"https://open.feishu.cn/open-apis/bitable/v1/apps/<app_token>/tables/<table_id>/records?page_size=100" \
|
||||
-H "Authorization: Bearer $TOKEN"
|
||||
```
|
||||
|
||||
用返回的 `has_more` + `page_token` 循环翻页。
|
||||
|
||||
#### 4b. 按 ID 精读单条
|
||||
```bash
|
||||
curl -s -X GET \
|
||||
"https://open.feishu.cn/open-apis/bitable/v1/apps/<app_token>/tables/<table_id>/records/<record_id>" \
|
||||
-H "Authorization: Bearer $TOKEN"
|
||||
```
|
||||
|
||||
### 步骤 5：解析输出
|
||||
|
||||
每条记录返回：
|
||||
```json
|
||||
{
|
||||
"record_id": "recXXXXXX",
|
||||
"fields": {
|
||||
"ID": "0000001",
|
||||
"taskData": "{...JSON string...}",
|
||||
"textData": "{...JSON string...}",
|
||||
...
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**重要：** 长文本/JSON 字段在多维表格中以 **字符串** 形式存储，需用 `json.loads()` 反序列化后再分析内部结构。
|
||||
|
||||
## 常见字段类型说明
|
||||
|
||||
| type | 含义 | 读取形式 |
|
||||
|------|------|---------|
|
||||
| 1 | 文本 | 字符串 |
|
||||
| 2 | 数字 | 数字 |
|
||||
| 3 | 单选 | 字符串 |
|
||||
| 4 | 多选 | 字符串数组 |
|
||||
| 5 | 日期 | Unix 毫秒时间戳 |
|
||||
| 7 | 复选框 | 布尔 |
|
||||
| 17 | 文本（长） | 字符串（含 JSON） |
|
||||
| 20 | URL | 对象 `{link, text}` |
|
||||
| 21 | 附件 | 对象数组 `[{file_token, name, ...}]` |
|
||||
|
||||
## 典型使用模式
|
||||
|
||||
### 模式 A：探索未知表结构
|
||||
1. 列出所有表 → 展示表名/revision
|
||||
2. 用户选择目标表 → 读取字段结构
|
||||
3. 采样 2–3 条记录 → 分析 JSON 字段结构
|
||||
4. 归纳输出字段含义和内容模式
|
||||
|
||||
### 模式 B：批量导出特定字段
|
||||
1. 已知 table_id 和目标字段名
|
||||
2. 全量分页读取
|
||||
3. 提取目标字段 → 解析 JSON → 汇总
|
||||
|
||||
### 模式 C：按条件检索
|
||||
1. 已知 ID 范围或关键词
|
||||
2. 全量读取后本地过滤（bitable API 筛选较受限）
|
||||
|
||||
## 注意事项
|
||||
- 含 JSON 的字段（如 `taskData`, `learningData`）读取后为普通字符串，需显式 `json.loads()`
|
||||
- 部分表格可能包含内嵌 Sheet（`<sheet token="..."/>`），需用 `feishu-embedded-sheet` 技能处理
|
||||
- 读取大表（revision > 5000）时注意 API 限流，建议逐页 `sleep 0.3s`
|
||||
- 若返回 `99991663` 错误，重新获取 token 后重试
|
||||
393
skills/core-content-json-standard/SKILL.md
Normal file
393
skills/core-content-json-standard/SKILL.md
Normal file
@ -0,0 +1,393 @@
|
||||
---
|
||||
name: core-content-json-standard
|
||||
version: 2.0.0
|
||||
description: "核心互动内容 JSON 配置标准。覆盖全部 14 种核心互动题型的完整 JSON 结构，含通用字段定义和各题型专属规范。用于内容生产、审校、自动化校验。"
|
||||
metadata:
|
||||
triggers:
|
||||
- "生产/审校核心互动内容"
|
||||
- "需要了解核心互动题型 JSON 配置格式"
|
||||
- "验证核心互动 JSON 配置完整性"
|
||||
requires:
|
||||
knowledge: ["互动内容库 wiki (7487521512283799556)"]
|
||||
skills: ["bitable-reader"]
|
||||
coverage: "14 种题型（口语探讨暂无数据）"
|
||||
---
|
||||
|
||||
# core-content-json-standard — 核心互动内容 JSON 配置标准
|
||||
|
||||
## 数据源
|
||||
|
||||
- Wiki: `https://makee-interactive.feishu.cn/wiki/TbbGwZLIVizXeGkMEKQc2hKRnCc`
|
||||
- Space ID: `7487521512283799556`
|
||||
- 通过 `bitable-reader` 技能按 node_token 定位具体 bitable
|
||||
|
||||
---
|
||||
|
||||
# 第一部分：通用结构（所有核心互动共用）
|
||||
|
||||
## 1. 通用字段
|
||||
|
||||
| 字段 | 类型 | 说明 | 出现率 |
|
||||
|------|------|------|:-----:|
|
||||
| `ID` | string | 记录唯一标识 | 15/15 |
|
||||
| `dataStatus` | string | 数据状态（`"0"`=正常） | 15/15 |
|
||||
| `kpStatus` | string | 知识点状态（`"0"`/`"1"`） | 15/15 |
|
||||
| `kpInfo` | JSON | 知识点绑定信息 | 15/15 |
|
||||
| `kpListSentence` | list | 关联句型ID列表 | 阅读/听力/口语有 |
|
||||
| `kpListVocab` | list | 关联单词ID列表 | 阅读/听力/口语有 |
|
||||
| `互动描述` | text | 中文剧情/内容产出描述 | 15/15 |
|
||||
| `关联知识点` | text | 知识点文本汇总 | 14/15 |
|
||||
| `专有名词` | list | 专有名词对照表 | 部分有 |
|
||||
|
||||
## 2. kpInfo — 知识点绑定（通用结构）
|
||||
|
||||
```json
|
||||
{
|
||||
"pushType": "relationKp",
|
||||
"cType": "<题型标识>",
|
||||
"cId": "<与ID字段一致>",
|
||||
"kpInfo": [
|
||||
{
|
||||
"kpId": "0000007",
|
||||
"kpType": "vocab", // vocab / pattern
|
||||
"kpTitle": "passport",
|
||||
"kpSkill": "vocab_meaning", // 知识点技能
|
||||
"kpSkillName": "词义"
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
**约束：**
|
||||
- `cType` 必须与本记录所属题型的 cType 一致
|
||||
- `cId` 必须与字段 `ID` 一致
|
||||
- `kpInfo[]` 每一项对应一个知识点
|
||||
|
||||
## 3. taskData / taskInfo — 任务元信息（通用结构）
|
||||
|
||||
```json
|
||||
{
|
||||
"cType": "core_xxx_xxx", // 题型唯一标识（见下表）
|
||||
"cId": "0000001", // 任务ID
|
||||
"title": "任务中文名",
|
||||
"taskDesc": "任务描述", // 或以 sceneDesc 命名
|
||||
"sceneDesc": "场景背景描述"
|
||||
}
|
||||
```
|
||||
|
||||
> ⚠️ 字段名有两种：`taskData`（阅读/听力/口语）和 `taskInfo`（写作/看图选词）。内容结构相同。
|
||||
|
||||
## 4. cType 对照表
|
||||
|
||||
| cType | 题型中文名 | 分类 |
|
||||
|-------|-----------|:--:|
|
||||
| `core_reading_order` | 合作阅读 | 📖 阅读 |
|
||||
| `core_reading_imageDrag` | 看图选词 | 📖 阅读 |
|
||||
| `core_listening_order` | 合作听力 | 🎧 听力 |
|
||||
| `core_listening_drag` | 听力拖拽 | 🎧 听力 |
|
||||
| `core_listening_choose` | 听力选择 | 🎧 听力 |
|
||||
| `core_speaking_reply` | 口语快答 | 🗣 口语 |
|
||||
| `core_speaking_monologue` | 口语独白 | 🗣 口语 |
|
||||
| `core_speaking_inquiry` | 口语妙问 | 🗣 口语 |
|
||||
| `core_speaking_image` | 看图说话 | 🗣 口语 |
|
||||
| `core_writing_questionMakeSentence` | 写作互动 / 邮件组句 | ✏️ 写作 |
|
||||
| `core_writing_imgMakeSentence` | 看图组句 | ✏️ 写作 |
|
||||
| `core_writing_imgWrite` | 看图撰写 | ✏️ 写作 |
|
||||
| `core_writing_questionWrite` | 邮件撰写 | ✏️ 写作 |
|
||||
|
||||
> 口语探讨 (`core_speaking_discuss`) — S0 表当前为空，待后续补充
|
||||
|
||||
---
|
||||
|
||||
# 第二部分：题型专区
|
||||
|
||||
---
|
||||
|
||||
## 📖 阅读类
|
||||
|
||||
### 合作阅读 `core_reading_order`
|
||||
|
||||
**Bitable:** `HIuLbJ6E8aNw2lsdT1YcvNOmnog` / S0–S3
|
||||
**核心 JSON 字段：**
|
||||
|
||||
| 字段 | 结构 | 说明 |
|
||||
|------|------|------|
|
||||
| `taskData` | `{cType, cId, title, sceneDesc, img, key, cDesc}` | key=核心词汇列表，cDesc=中英产出概括 |
|
||||
| `sequenceData` | `{sequence: [{text|[i]}/{question|[j]}/{dialog}]}` | 流程推进引擎 |
|
||||
| `textData` | `{text: [{textType, textTitle, textBody}], question: [{type,npcName,content,optionList,answer,meaning,explain}]}` | 阅读材料+理解题 |
|
||||
| `learningData` | `{closing, learningPart: [{leadIn, type, npcName, content, learning: [{answer, meaning, optionList, question}]}]}` | 词汇/句型学习流程 |
|
||||
|
||||
**流程编排两种模式：**
|
||||
- **交替型：** text[i] → question[i] → text[i+1] → ...
|
||||
- **集中型：** text[0] → dialog → question[0] → dialog → question[1] → ...
|
||||
|
||||
**阅读题 meaning 标签（开放型）：**
|
||||
实际数据中的 meaning 为自由文本，常见分类：
|
||||
- 细节提取类：提取文章中的关键/具体/细节信息、识别文章中的形状细节
|
||||
- 概念理解类：理解文章中的关键概念、行为准则、求助对象、关键角色
|
||||
- 描述识别类：理解文章中的形容词/形状描述、动作指令、未知信息
|
||||
- 推理推测类：根据细节进行合理推测
|
||||
|
||||
**生产规范：**
|
||||
- 每篇至少覆盖「细节信息」+「主旨大意」两个维度
|
||||
- optionList 每项必须有 feedback
|
||||
- NPC 名称需与 角色配置 一致
|
||||
|
||||
**审校清单：**
|
||||
- [ ] JSON 可解析
|
||||
- [ ] taskData.cId = kpInfo.cId = ID
|
||||
- [ ] sequenceData 索引不越界
|
||||
- [ ] textData.question[].answer 在 optionList 范围内
|
||||
- [ ] optionList feedback 不为空
|
||||
- [ ] textData.question[].meaning 不为空
|
||||
- [ ] LearningData 的 answer 在范围内
|
||||
- [ ] 角色配置 NPC 一致性
|
||||
- [ ] taskData.key 与 kpInfo.kpInfo 对应
|
||||
|
||||
---
|
||||
|
||||
### 看图选词 `core_reading_imageDrag`
|
||||
|
||||
**Bitable:** `Qf0Ob6TyEaShufsORGBc8WTinFf` / L1
|
||||
**核心 JSON 字段：**
|
||||
|
||||
| 字段 | 结构 | 说明 |
|
||||
|------|------|------|
|
||||
| `taskInfo` | `{cId, cType, title, taskDesc, sceneDesc}` | 任务元信息 |
|
||||
| `questionGroup` | `[{...}]` list | 题目组（含图片+单词拖拽） |
|
||||
| `studyInfo` | `{learningPart: [...], closing}` | 学习流程 |
|
||||
| `学习流程配置` | text | Markdown 格式的学习流程 |
|
||||
|
||||
与 合作阅读 的区别：无 sequenceData/textData，聚焦于图片+单词的视觉匹配。
|
||||
|
||||
---
|
||||
|
||||
## 🎧 听力类
|
||||
|
||||
### 合作听力 `core_listening_order`
|
||||
|
||||
**Bitable:** `B8Z1b2TnYaKRa1sWSljcV4Q9nYf` / S1–S3, LV1
|
||||
**核心 JSON 字段：**
|
||||
|
||||
| 字段 | 结构 | 说明 |
|
||||
|------|------|------|
|
||||
| `taskData` | `{cType, cId, title, sceneDesc, img}` | 无 key/cDesc（词汇在 kpInfo） |
|
||||
| `sequenceData` | `{sequence: [...]}` | 同 合作阅读 |
|
||||
| `textData` | `{audio: [...], question: [...options+answer+meaning...]}` | ⚠️ 用 `audio` 替代 `text` |
|
||||
| `learningData` | `{closing, learningPart: [...]}` | 同 合作阅读 |
|
||||
|
||||
**与 合作阅读 的关键差异：**
|
||||
- `textData.audio[]` 替代 `textData.text[]`（音频材料 vs 文本材料）
|
||||
- sequence 中用 `{"audio": [i]}` 替代 `{"text": [i]}`
|
||||
- taskData 无 key/cDesc 字段
|
||||
|
||||
---
|
||||
|
||||
### 听力拖拽 `core_listening_drag`
|
||||
|
||||
**Bitable:** `Uey8bhdLBa66TIsGrFBcIQKRnsg` / S3, LV1
|
||||
**核心 JSON 字段：**
|
||||
|
||||
| 字段 | 结构 | 说明 |
|
||||
|------|------|------|
|
||||
| `taskData` | `{cType, cId, title, sceneDesc, key}` | 有 key 词汇表 |
|
||||
| `dialogList` | `[{...}]` list | 听力对话列表 |
|
||||
| `preDialog` | `[{...}]` list | 前置对话 |
|
||||
| `questionList` | `[{...}]` list | 拖拽题目列表 |
|
||||
| `learningData` | `{learningPart, closing}` | 学习流程 |
|
||||
| `听力材料` | text | 音频文本材料 |
|
||||
| `父记录` | list | 关联的父记录 |
|
||||
|
||||
---
|
||||
|
||||
### 听力选择 `core_listening_choose`
|
||||
|
||||
**Bitable:** `C7e9bzA1GaZ61FsTz87cEM8Ynoe` / S3, LV1
|
||||
**核心 JSON 字段：**
|
||||
|
||||
| 字段 | 结构 | 说明 |
|
||||
|------|------|------|
|
||||
| `taskData` | `{cType, cId, title, sceneDesc, key}` | 任务元信息 |
|
||||
| `questionGroup` | `[{...}]` list | 选择题组 |
|
||||
| `learningData` | `{learningPart, closing}` | 学习流程 |
|
||||
|
||||
---
|
||||
|
||||
## 🗣 口语类
|
||||
|
||||
### 口语快答 `core_speaking_reply`
|
||||
|
||||
**Bitable:** `D0Tpbs6D6aIRXdsKDLec0V0on3b` / S0–S3
|
||||
**核心 JSON 字段：**
|
||||
|
||||
| 字段 | 结构 | 说明 |
|
||||
|------|------|------|
|
||||
| `taskData` | `{cType, cId, title, taskDesc, sceneDesc}` | 任务元信息 |
|
||||
| `configData` | `{config: {...}}` | 对话配置（ASR/评分相关） |
|
||||
| `settingData` | `{setting: {...}}` | 场景设定 |
|
||||
| `exampleDialog` | `[{...}]` list | 对话样例 |
|
||||
| `learningData` | `{learningPart: [...]}` | 学习流程（无 closing） |
|
||||
| `promptInfo配置` | text | prompt 配置 |
|
||||
| `教研-任务规则与NPC设定` | text | 任务规则 |
|
||||
|
||||
**结构特点：** 侧重对话交互，有 configData/settingData 控制口语识别和评分。
|
||||
|
||||
---
|
||||
|
||||
### 口语妙问 `core_speaking_inquiry`
|
||||
|
||||
**Bitable:** `Ct4ebNgxUatyUssuVHycfhbgnXf` / S0–S3
|
||||
**核心 JSON 字段：**
|
||||
|
||||
| 字段 | 结构 | 说明 |
|
||||
|------|------|------|
|
||||
| `taskData` | `{cType, cId, title, taskDesc, sceneDesc}` | 同 口语快答 |
|
||||
| `configData` | `{config: {...}}` | 对话配置 |
|
||||
| `settingData` | `{setting: {...}}` | 场景设定 |
|
||||
| `exampleDialog` | `[{...}]` list | 对话样例 |
|
||||
| `learningData` | `{learningPart: [...]}` | 学习流程 |
|
||||
| `任务设定` | text | 任务规则 |
|
||||
|
||||
**与 口语快答 的区别：** 口语妙问侧重主动提问场景，口语快答侧重回答场景。JSON 结构基本相同，差异在内容配置中体现。
|
||||
|
||||
---
|
||||
|
||||
### 口语独白 `core_speaking_monologue`
|
||||
|
||||
**Bitable:** `JtsAbFoSbaWWvssLsxXcAgdEnkh` / L2
|
||||
**核心 JSON 字段：**
|
||||
|
||||
| 字段 | 结构 | 说明 |
|
||||
|------|------|------|
|
||||
| `taskData` | `{cId, cType, title, taskDesc, sceneDesc}` | 任务元信息 |
|
||||
| `configData` | `{sentenceMin, sentenceMax, monologueExample, passCondition, asrPrompt}` | ⚠️ 独白配置（句子数限制等） |
|
||||
| `npclistData` | `[{...}]` list | NPC 列表 |
|
||||
| `learningData` | `{learningPart, closing}` | 学习流程 |
|
||||
| `npc站位列表` | text | NPC 站位 |
|
||||
|
||||
**与 口语快答/妙问 的区别：** 独白型（无 exampleDialog），有句子数量约束（sentenceMin/Max）。
|
||||
|
||||
---
|
||||
|
||||
### 看图说话 `core_speaking_image`
|
||||
|
||||
**Bitable:** `DOVHbQamCaZPTCsuzJrclG1an6b` / S3, LV1
|
||||
**核心 JSON 字段：**
|
||||
|
||||
| 字段 | 结构 | 说明 |
|
||||
|------|------|------|
|
||||
| `taskData` | `{cType, cId, title, taskDesc, sceneDesc}` | 任务元信息 |
|
||||
| `configData` | `{config: {...}}` | 对话配置 |
|
||||
| `imageInfo` | `{questionImg: [...]}` | 图片素材信息 |
|
||||
| `questionList` | `[{...}]` list | 问题列表 |
|
||||
| `optionList` | `[{...}]` list | 选项列表 |
|
||||
| `learningData` | `{learningPart, closing}` | 学习流程 |
|
||||
|
||||
**结构特点：** 有 imageInfo 管理图片素材 + questionList/optionList 管理图文互动题。
|
||||
|
||||
---
|
||||
|
||||
## ✏️ 写作类
|
||||
|
||||
**5 种写作题型共享相同的 JSON 结构框架**，差异体现在 `textInfo` 和素材类型上：
|
||||
|
||||
| 题型 | cType | 素材来源 |
|
||||
|------|-------|---------|
|
||||
| 写作互动 | `core_writing_questionMakeSentence` | 文字问题 |
|
||||
| 邮件组句 | `core_writing_questionMakeSentence` | 邮件文本 |
|
||||
| 看图组句 | `core_writing_imgMakeSentence` | 图片 |
|
||||
| 看图撰写 | `core_writing_imgWrite` | 图片 |
|
||||
| 邮件撰写 | `core_writing_questionWrite` | 邮件文本 |
|
||||
|
||||
### 写作类通用 JSON 结构
|
||||
|
||||
| 字段 | 结构 | 说明 |
|
||||
|------|------|------|
|
||||
| `taskInfo` | `{cId, cType, title, taskDesc, sceneDesc}` | 任务元信息 |
|
||||
| `textInfo` | `{inputType, passCondition, textList: [...]}` | ⚠️ 写作素材+通过条件 |
|
||||
| `evalInfo` | `{title, taskDesc, sceneDesc, knowledge, passCondition}` | 评分/评价配置 |
|
||||
| `studyInfo` | `{learningPart: [...], closing}` | 学习流程 |
|
||||
| `kpInfo` | 通用结构 | 知识点绑定 |
|
||||
| `任务信息` | text | 中文任务描述 |
|
||||
| `写作材料` | text | 写作素材文本 |
|
||||
|
||||
**textInfo 字段详解：**
|
||||
```json
|
||||
{
|
||||
"inputType": "sentence_building", // 输入类型
|
||||
"passCondition": "...", // 通关条件描述
|
||||
"textList": [ // 素材列表
|
||||
{"type": "...", "content": "..."}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
**evalInfo 字段详解：**
|
||||
```json
|
||||
{
|
||||
"title": "任务中文名",
|
||||
"taskDesc": "任务描述",
|
||||
"sceneDesc": "场景背景",
|
||||
"knowledge": "...", // 所需知识点
|
||||
"passCondition": "..." // 通过条件
|
||||
}
|
||||
```
|
||||
|
||||
⚠️ 写作互动/邮件组句 cType 相同（`core_writing_questionMakeSentence`），通过 `textInfo.textList[].type` 区分素材是文本问题还是邮件格式。
|
||||
|
||||
---
|
||||
|
||||
# 第三部分：自动化审校规则
|
||||
|
||||
## 通用检查（所有题型）
|
||||
|
||||
```python
|
||||
# 规则列表（适用于所有 14 种题型）
|
||||
通用检查项 = [
|
||||
"JSON字段可解析性（json.loads 不抛异常）",
|
||||
"taskData/taskInfo.cId == kpInfo.cId == ID",
|
||||
"kpInfo.cType 正确",
|
||||
"dataStatus 不为空",
|
||||
"互动描述 不为空",
|
||||
]
|
||||
```
|
||||
|
||||
## 分题型检查
|
||||
|
||||
```python
|
||||
题型专属检查 = {
|
||||
"阅读类": [
|
||||
"sequenceData 索引不越界",
|
||||
"question[].answer 在 optionList 范围内",
|
||||
"optionList 每项有 feedback",
|
||||
"question[].meaning 不为空",
|
||||
],
|
||||
"听力类": [
|
||||
"textData.audio 不为空",
|
||||
"sequenceData 索引不越界",
|
||||
"听力材料 不为空",
|
||||
],
|
||||
"口语类": [
|
||||
"configData/settingData 可解析",
|
||||
"learningData 可解析",
|
||||
],
|
||||
"写作类": [
|
||||
"textInfo.textList 不为空",
|
||||
"evalInfo 可解析",
|
||||
"studyInfo 可解析",
|
||||
],
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
# 第四部分：扩展指南
|
||||
|
||||
新增题型时：
|
||||
1. 用 `bitable-reader` 获取 bitable → 列出表 → 读取第一个内容表
|
||||
2. 采样 1–2 条记录 → 提取 JSON 字段名和 cType
|
||||
3. 与已有结构对比 → 归类到阅读/听力/口语/写作
|
||||
4. 按本文件格式补充新章节
|
||||
5. 更新顶部 coverage 计数
|
||||
|
||||
**待补充:** 口语探讨 (`core_speaking_discuss`) — S0 表当前无数据
|
||||
@ -63,27 +63,27 @@
|
||||
5. 仍未匹配 → 报错：未知组件类型
|
||||
```
|
||||
|
||||
## 二、核心互动组件（待注册）
|
||||
## 二、核心互动组件
|
||||
|
||||
以下核心互动类型已从多维表格配置目录中发现，待后续注册：
|
||||
JSON 结构详见 `skills/core-content-json-standard/SKILL.md`。
|
||||
|
||||
| # | 多维表格名称 | wiki_token | 待注册 |
|
||||
|---|-------------|-----------|--------|
|
||||
| 1 | 核心互动 - 合作阅读 | `H6DJweNkpigCbak2Y5LcTZ8Vnfb` | 🔲 |
|
||||
| 2 | 核心互动 - 看图选词 | `MVo7wugWfimJPIkxhJCcqppFnyf` | 🔲 |
|
||||
| 3 | 核心互动 - 口语快答 | `TSwcw0nFmi21khkpUndchNMsn6f` | 🔲 |
|
||||
| 4 | 核心互动 - 口语独白 | `G20HwcF1uideNokLsHWcBs3znvg` | 🔲 |
|
||||
| 5 | 核心互动 - 口语妙问 | `GJUVwNSEkis3EXkrVj0ccbqdn8c` | 🔲 |
|
||||
| 6 | 核心互动 - 看图说话 | `KBOXwzVHfin6ORkKbA3c3eWEnoh` | 🔲 |
|
||||
| 7 | 核心互动 - 口语探讨 | `HoidwhEBWiWjaokQnz0cHbhTn6e` | 🔲 |
|
||||
| 8 | 核心互动 - 合作听力 | `FrxtwNRQDizqiikPkATcBzTCnYe` | 🔲 |
|
||||
| 9 | 核心互动 - 听力拖拽 | `K3QrwQnWqiPBm1krhnNcWDTqnhe` | 🔲 |
|
||||
| 10 | 核心互动 - 听力选择 | `Kwrcw6A4jip2sxkdLn4czd1knvf` | 🔲 |
|
||||
| 11 | 核心互动 - 写作互动 | `DVkcwVr2giswTckcgD0cpHwNnv2` | 🔲 |
|
||||
| 12 | 核心互动 - 看图组句 | `BkmtwUBwMiHd5Ak7VS6ccE9SnHd` | 🔲 |
|
||||
| 13 | 核心互动 - 看图撰写 | `KwPHwnaqdiWlvNkDm5fcFreDnQh` | 🔲 |
|
||||
| 14 | 核心互动 - 邮件组句 | `M5oTwUP6wiImC4kVJU8cRYnfnyf` | 🔲 |
|
||||
| 15 | 核心互动 - 邮件撰写 | `Brn0wldKYizsLZkBqK6clp1tnKd` | 🔲 |
|
||||
| # | 剧本类型名 | cType | 多维表格名称 | bitable_token |
|
||||
|---|-----------|-------|-------------|---------------|
|
||||
| 1 | 合作阅读 | `core_reading_order` | 核心互动 - 合作阅读 | `HIuLbJ6E8aNw2lsdT1YcvNOmnog` |
|
||||
| 2 | 看图选词 | `core_reading_imageDrag` | 核心互动 - 看图选词 | `Qf0Ob6TyEaShufsORGBc8WTinFf` |
|
||||
| 3 | 口语快答 | `core_speaking_reply` | 核心互动 - 口语快答 | `D0Tpbs6D6aIRXdsKDLec0V0on3b` |
|
||||
| 4 | 口语独白 | `core_speaking_monologue` | 核心互动 - 口语独白 | `JtsAbFoSbaWWvssLsxXcAgdEnkh` |
|
||||
| 5 | 口语妙问 | `core_speaking_inquiry` | 核心互动 - 口语妙问 | `Ct4ebNgxUatyUssuVHycfhbgnXf` |
|
||||
| 6 | 看图说话 | `core_speaking_image` | 核心互动 - 看图说话 | `DOVHbQamCaZPTCsuzJrclG1an6b` |
|
||||
| 7 | 口语探讨 | `core_speaking_discuss` | 核心互动 - 口语探讨 | `WYQobCGomaQ843sjB8Icp2SLnjb` ⚠️ S0无数据 |
|
||||
| 8 | 合作听力 | `core_listening_order` | 核心互动 - 合作听力 | `B8Z1b2TnYaKRa1sWSljcV4Q9nYf` |
|
||||
| 9 | 听力拖拽 | `core_listening_drag` | 核心互动 - 听力拖拽 | `Uey8bhdLBa66TIsGrFBcIQKRnsg` |
|
||||
| 10 | 听力选择 | `core_listening_choose` | 核心互动 - 听力选择 | `C7e9bzA1GaZ61FsTz87cEM8Ynoe` |
|
||||
| 11 | 写作互动 | `core_writing_questionMakeSentence` | 核心互动 - 写作互动 | `HOhJb8xtMa02YjsHXMNc7MEpnfe` |
|
||||
| 12 | 看图组句 | `core_writing_imgMakeSentence` | 核心互动 - 看图组句 | `LNEcbo6meahQCosYN9Jc137rnde` |
|
||||
| 13 | 看图撰写 | `core_writing_imgWrite` | 核心互动 - 看图撰写 | `Be4rbTgoiaDMOvstB4Ucn8sjndh` |
|
||||
| 14 | 邮件组句 | `core_writing_questionMakeSentence` | 核心互动 - 邮件组句 | `F0e4bd2Z5aFDzpsIHndcxGhgnKd` |
|
||||
| 15 | 邮件撰写 | `core_writing_questionWrite` | 核心互动 - 邮件撰写 | `JcuybbTRParccasXKrUc7mD1neh` |
|
||||
|
||||
## 三、数据库目标表映射
|
||||
|
||||
|
||||
@ -0,0 +1,412 @@
|
||||
# 中互动组件 — jsonData 字段结构参考
|
||||
|
||||
> 本文档是中互动 27 种组件的 **jsonData 字段结构指南**，用于内容生产和审校。
|
||||
> cType 映射和 bitable_token 参见 `component_registry.md`。
|
||||
|
||||
## 通用规则
|
||||
|
||||
- 所有中互动组件结构统一：`jsonData`（主 JSON）+ `kpInfo`（知识点绑定）+ 辅助文本字段
|
||||
- `jsonData` 通过 `json.loads()` 可直接解析为 dict
|
||||
- 公共字段（所有组件都有）：`cType`, `cId`, `title`
|
||||
|
||||
## 分类汇总
|
||||
|
||||
| 分类 | 数量 | 组件列表 |
|
||||
|------|:---:|---------|
|
||||
| 🗨 对话类 | 7 | 对话互动、朗读、表达、选择、选读、挖空、组句 |
|
||||
| 📋 信息类 | 6 | 信息描写、拼词、组句、补词、填词、填句 |
|
||||
| 📦 词汇类 | 2 | 物品互动、图片互动 |
|
||||
| 🖼 图片选择类 | 4 | 图片单选、多选、有序、拖拽 |
|
||||
| 📝 语法类 | 3 | 材料互动、挖空互动、组句互动 |
|
||||
| 🔧 其他 | 5 | 指令互动、填词互动、语音互动、造句互动、发音互动 |
|
||||
|
||||
---
|
||||
|
||||
## 🗨 对话类（7 种）
|
||||
|
||||
**公共字段：** `cType`, `cId`, `title`, `resourceMapping`
|
||||
|
||||
### 对话互动 `mid_sentence_dialogue`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_sentence_dialogue"
|
||||
cId str 任务ID
|
||||
title str 中文标题
|
||||
asrPrompt str ASR语音识别提示
|
||||
preDialog list 前置对话 [{type,content}]
|
||||
question dict 问题配置 {mode, hint, desc}
|
||||
postDialog list 后置对话 [{type,content}]
|
||||
meaning str 能力维度标签
|
||||
resourceMapping list NPC角色映射 [name,...]
|
||||
```
|
||||
|
||||
### 对话朗读互动 `mid_dialog_repeat`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_dialog_repeat"
|
||||
cId str
|
||||
title str
|
||||
resourceMapping list NPC映射
|
||||
preDialog list 前置对话 [{type,content}]
|
||||
imgShowTimingList list 图片展示时机
|
||||
img dict 配图信息
|
||||
question dict 朗读问题 {sentence,...}
|
||||
postDialog list 后置对话
|
||||
```
|
||||
|
||||
### 对话表达互动 `mid_dialog_express`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_dialog_express"
|
||||
cId, title str
|
||||
asrPrompt str ASR提示（中文场景描述）
|
||||
resourceMapping list
|
||||
preDialog list 前置对话 [{type,content}]
|
||||
imgShowTimingList list 图片展示时机
|
||||
img dict 配图
|
||||
```
|
||||
|
||||
### 对话选择互动 `mid_dialog_choose`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_dialog_choose"
|
||||
cId, title str
|
||||
resourceMapping list
|
||||
preDialog list 前置对话
|
||||
imgShowTimingList list
|
||||
img dict
|
||||
optionList list 选项 [{option: "选项文本"},...]
|
||||
answer list 正确答案索引 [0]
|
||||
corFeedback dict 正确反馈 {type,npcName,content}
|
||||
errFeedback dict 错误反馈
|
||||
postDialog list 后置对话
|
||||
```
|
||||
|
||||
### 对话选读互动 `mid_dialog_select`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_dialog_select"
|
||||
cId, title str
|
||||
resourceMapping list
|
||||
preDialog list
|
||||
imgShowTimingList list
|
||||
optionList list 可选读句列表
|
||||
postDialog list
|
||||
```
|
||||
|
||||
### 对话挖空互动 `mid_dialog_fillin`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_dialog_fillin"
|
||||
cId, title str
|
||||
resourceMapping list
|
||||
preDialog list 前置对话（含挖空位置标记）
|
||||
imgShowTimingList list
|
||||
```
|
||||
|
||||
### 对话组句互动 `mid_dialog_sentence`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_dialog_sentence"
|
||||
cId, title str
|
||||
resourceMapping list
|
||||
preDialog list 前置对话（含组句片段）
|
||||
imgShowTimingList list
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 📋 信息类（6 种）
|
||||
|
||||
**公共字段：** `cType`, `cId`, `title`, `cDesc`, `question`
|
||||
|
||||
### 信息描写 `mid_message_trace`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_message_trace"
|
||||
cId, title str
|
||||
cDesc str 中文产出描述
|
||||
question dict 问题 {desc, ...}
|
||||
trace dict 描红/标注配置
|
||||
```
|
||||
|
||||
### 信息拼词 `mid_message_spell`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_message_spell"
|
||||
cId, title str
|
||||
cDesc str
|
||||
question dict 拼词问题 {desc, wordList, ...}
|
||||
tip str 提示文本
|
||||
```
|
||||
|
||||
### 信息组句 `mid_message_combine`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_message_combine"
|
||||
cId, title str
|
||||
cDesc str
|
||||
question dict 组句问题 {desc, wordList, ...}
|
||||
tip str
|
||||
```
|
||||
|
||||
### 信息补词 `mid_message_fillin`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_message_fillin"
|
||||
cId, title str
|
||||
cDesc str
|
||||
question dict 补词问题 {desc, stem, optionList, ...}
|
||||
tip str
|
||||
```
|
||||
|
||||
### 信息填词 `mid_message_word`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_message_word"
|
||||
cId, title str
|
||||
cDesc str
|
||||
question dict 填词问题 {desc, inputConfig, ...}
|
||||
tip str
|
||||
```
|
||||
|
||||
### 信息填句 `mid_message_sentence`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_message_sentence"
|
||||
cId, title str
|
||||
cDesc str
|
||||
question dict 填句问题 {desc, inputConfig, ...}
|
||||
tip str
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 📦 词汇类（2 种）
|
||||
|
||||
### 物品互动 `mid_vocab_item`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_vocab_item"
|
||||
cId, title str
|
||||
question dict 问题 {desc}
|
||||
optionList list 选项 [{option, note},...]
|
||||
answer list 正确答案 [0]
|
||||
cDesc str 产出描述
|
||||
meaning str 能力维度
|
||||
```
|
||||
|
||||
### 图片互动 `mid_vocab_image`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_vocab_image"
|
||||
cId, title str
|
||||
preDialog list 前置对话 [{type,content}]
|
||||
img dict 图片信息
|
||||
question dict 问题 {desc}
|
||||
answer list 答案
|
||||
tip str 提示
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 🖼 图片选择类（4 种）
|
||||
|
||||
**公共字段：** `cType`, `cId`, `title`, `meaning`, `resourceMapping`, `question`, `imageInfo`, `optionList`
|
||||
|
||||
### 图片单选 `mid_image_choose`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_image_choose"
|
||||
cId, title str
|
||||
meaning str 能力维度
|
||||
resourceMapping dict NPC映射
|
||||
question dict 问题 {desc, content}
|
||||
imageInfo dict 图片信息 {questionImg, answerImg}
|
||||
optionList list 选项 [{option},...]
|
||||
```
|
||||
|
||||
### 图片多选 `mid_image_multiple`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_image_multiple"
|
||||
...同图片单选（公共字段）
|
||||
optionList 选项更多（多选型）
|
||||
```
|
||||
|
||||
### 图片有序 `mid_image_sequence`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_image_sequence"
|
||||
...同图片单选（公共字段）
|
||||
optionList 选项需按序排列
|
||||
```
|
||||
|
||||
### 图片拖拽 `mid_image_drag`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_image_drag"
|
||||
...同图片单选（公共字段）
|
||||
optionList 拖拽目标区配置
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 📝 语法类（3 种）
|
||||
|
||||
**公共字段：** `cType`, `cId`, `title`, `preDialog`, `question`, `optionList`, `answer`
|
||||
|
||||
### 材料互动 `mid_sentence_material`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_sentence_material"
|
||||
cId, title str
|
||||
preDialog list 前置对话 [{type,content}]
|
||||
img dict 配图
|
||||
question dict 问题 {type, content}
|
||||
optionList list 选项 [{option, feedback},...]
|
||||
answer list 正确答案
|
||||
```
|
||||
|
||||
### 挖空互动 `mid_grammar_cloze`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_grammar_cloze"
|
||||
cId, title str
|
||||
preDialog list 前置对话
|
||||
question dict 问题 {type, desc, content}（含挖空标记）
|
||||
optionList list 选项 [{option, feedback},...]
|
||||
answer list 答案
|
||||
postDialog list 后置对话
|
||||
```
|
||||
|
||||
### 组句互动 `mid_grammar_sentence`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_grammar_sentence"
|
||||
cId, title str
|
||||
preDialog list 前置对话 [{type,npcName,content}]
|
||||
question dict 问题 {desc, content}
|
||||
optionList list 选项 [{option},...]
|
||||
answer list 答案
|
||||
tip str 提示
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 🔧 其他（5 种）
|
||||
|
||||
### 指令互动 `mid_vocab_instruction`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_vocab_instruction"
|
||||
cId, title str
|
||||
preDialog list 前置对话 [{type,npcName,content}]
|
||||
question dict 主问题 {type,npcName,content,mode}
|
||||
questionList list 子问题 [{desc,optionList,answer},...]
|
||||
corFeedback dict 正确反馈 {type,npcName,content}
|
||||
errFeedback dict 错误反馈
|
||||
```
|
||||
|
||||
### 填词互动 `mid_vocab_fillBlank`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_vocab_fillBlank"
|
||||
cId, title str
|
||||
itemName str 物品/词汇名称
|
||||
question dict 问题 {desc}
|
||||
inputConfig list 输入配置 [{stem,value},...]
|
||||
tip str 提示
|
||||
inputConfigExt list 扩展输入配置
|
||||
```
|
||||
|
||||
### 语音互动 `mid_sentence_voice`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_sentence_voice"
|
||||
cId, title str
|
||||
audioFile str 音频文件标识
|
||||
preDialog list 前置对话
|
||||
itemName str 物品名
|
||||
question dict 问题 {desc,type,npcName,content}
|
||||
optionList list 选项 [{option,feedback},...]
|
||||
```
|
||||
|
||||
### 造句互动 `mid_sentence_makeSentence`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_sentence_makeSentence"
|
||||
cId, title str
|
||||
preDialog list 前置对话 [{type,npcName,content}]
|
||||
itemName str 物品名
|
||||
question dict 问题 {desc,mode,hint}
|
||||
tip str 提示
|
||||
corFeedbackdict 正确反馈 {type,npcName,content}
|
||||
```
|
||||
|
||||
### 发音互动 `mid_pron_pron`
|
||||
|
||||
```
|
||||
jsonData:
|
||||
cType str "mid_pron_pron"
|
||||
cId, title str
|
||||
itemName str 单词名
|
||||
question dict 问题 {desc,mode,type,content}
|
||||
cDesc str 产出描述
|
||||
meaning str 能力维度
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 审校清单（中互动通用）
|
||||
|
||||
```
|
||||
- [ ] jsonData 可正确 json.loads 解析
|
||||
- [ ] jsonData.cType 正确（与组件注册表一致）
|
||||
- [ ] jsonData.cId 非空
|
||||
- [ ] kpInfo.cType == jsonData.cType
|
||||
- [ ] kpInfo.cId == jsonData.cId
|
||||
- [ ] optionList 有 option 时，answer 索引在范围内
|
||||
- [ ] preDialog/postDialog 每项的 type/content 非空
|
||||
- [ ] 对话类：resourceMapping 不为空
|
||||
- [ ] 图片选择类：imageInfo 非空
|
||||
- [ ] 语法类：optionList 每项有 feedback（如结构支持）
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 与核心互动的对比
|
||||
|
||||
| 维度 | 核心互动 | 中互动 |
|
||||
|------|---------|--------|
|
||||
| JSON 结构 | 多个独立 JSON 字段（taskData, textData, learningData,...） | 统一 `jsonData` + `kpInfo` |
|
||||
| 记录数 | 少（1-21 条/表） | 多（1-135 条/表） |
|
||||
| 使用场景 | 独立任务级 | 剧本内嵌组件 |
|
||||
| 知识库表 | S0-S3, LV1, Level 2 | S0-S3, LV1, L1-Demo, L2 |
|
||||
| 共字段 | ID, dataStatus, kpStatus, kpInfo | kpInfo |
|
||||
Loading…
Reference in New Issue
Block a user