word-wzq · Word(.docx) 多模态教学知识库自动化构建
把 Word 讲义/教材文稿自动转化为可检索、可复用、可再加工的多模态教学知识库: 节级文本 + 公式 LaTeX + 图片集 + 图片 AI 理解 + 教材文案 + 图文绑定 JSON。 与 pptx-wzq 同构——指令、流程、产物协议完全一致。
核心方案:混合法
Word 是连续流文档、无物理页,故采用「标题层级逻辑分块 + 可选渲染定页」:
- 逻辑分块(默认):以 Heading1
9 / 标题19 样式切分「节」→ 节即伪「页」, 段落/表格/图片/公式归属最近一节;教材语义比物理页更贴切; - 渲染定页(
--render-pages增强):LibreOffice/Word 导出 PDF 后映射物理页码, 用于与「PPTX 转 PDF」对齐或人工核对。
安装
pip install word-wzq
pip install "word-wzq[render]" # 混合法增强:物理页码映射
快速开始
# 一条命令完整流水线(自动装依赖 / 引导 Key / 预估 Token / 确认执行)
word-paser 模拟电子技术讲义.docx -o 讲义输出
# 结果目录:images/ + <名>_captions.md + <名>_textbook.md + <名>_binding.json
# 分步执行
word-text 讲义.docx -o out
word-formula 讲义.docx -o out
word-img 讲义.docx -o out
word-caption out/images -o cap.md --texts out/texts.md --formulas out/formulas.md
word-author --texts out/texts.md --formulas out/formulas.md --captions cap.md -o textbook.md
word-bind out -o binding.json --textbook textbook.md --images-dir out/images
指令一览
| 命令 | 功能 | 模型 | Token |
|---|---|---|---|
word-text |
节级文本/表格提取(标题层级逻辑分块) | — | 0 |
word-formula |
三路径公式→LaTeX(OMML/EQ3/OCR) | — | 0 |
word-img |
节级图片提取+过滤+EMF/WMF 渲染 | — | 0 |
word-caption |
图片 AI 解读(文档上下文模式) | qwen3.7-plus | 有 |
word-author |
教材文案(学科推断+分批) | deepseek-v4-flash | 有 |
word-bind |
节级图文绑定 JSON | — | 0 |
word-paser |
整体编排(混合法) | — | — |
作者
吴振谦 · wuzhenqian@nbu.edu.cn · QQ:38328063
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
word_wzq-2.1.0.tar.gz
(65.9 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
word_wzq-2.1.0-py3-none-any.whl
(77.9 kB
view details)
File details
Details for the file word_wzq-2.1.0.tar.gz.
File metadata
- Download URL: word_wzq-2.1.0.tar.gz
- Upload date:
- Size: 65.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/7.0.0 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
9c7d5e43f756402bf93032d1b7e19daca2f51cb1fddd5977975bd7b4f639c4c6
|
|
| MD5 |
61222e74144eec753918c76a3ce5c956
|
|
| BLAKE2b-256 |
e4ca3fef6a72e1b5ee8a6fabfd10b31fe0e0ff8b81ef79e7035d4e4f58b90c67
|
File details
Details for the file word_wzq-2.1.0-py3-none-any.whl.
File metadata
- Download URL: word_wzq-2.1.0-py3-none-any.whl
- Upload date:
- Size: 77.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/7.0.0 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
1acadf45845115fd55b9bb666322c17242727af1e54fc5822092e8227f66d539
|
|
| MD5 |
30dd55e3db22577bb99f18e4f92ccb18
|
|
| BLAKE2b-256 |
60cd2d8ad668e85384a6168fc152f6b6d3b0d1097afc4df868d3dacf87269a3f
|