# charlesXu86/Chatbot_CN

基于金融-司法领域(兼有闲聊性质)的聊天机器人，其中的主要模块有信息抽取、NLU、NLG、知识图谱等，并且利用Django整合了前端展示,目前已经封装了nlp和kg的restful接口

Repository: https://github.com/charlesXu86/Chatbot_CN
Canonical: https://ross.abutalabs.com/products/chatbot_cn
License: Apache-2.0
License Family: permissive
Topics: deep-learning, chatbot-cn, tenserflow-serving, intent-detection, django-restful, reinforcement-learning, knowledge-graph, slot-filling, dialogue-systems, ir, oriented-dialogs, sentiment-analysis, tensorflow, ner, nlu, nlg, attention-mechanism, text-correct, text-classification, recommendation
Last push: 2021-06-13T10:00:09+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2954, "days_push": 1907, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1289, forks 424 (observed 2026-08-28T04:04:15.322131+00:00)

## What it is
Chatbot_CN is a Chinese multi-turn, task-oriented chatbot platform targeting the finance and legal domains (with chitchat support), combining rule systems, deep learning, reinforcement learning, and knowledge graphs. It bundles NLU, NLG, information extraction, dialogue management, and NLP/KG modules, exposing them through Django-based RESTful interfaces with a web frontend.

## Use cases
- build a Chinese task-oriented chatbot for finance or legal question answering
- add intent detection and slot filling to a dialogue system
- answer user questions over a knowledge graph with a bot
- serve NLP models like NER, sentiment analysis, and text correction behind REST APIs
- deploy a customer service bot on WeChat, DingTalk, or a web page
- implement multi-turn dialogue management with reinforcement learning policies
- turn a Raspberry Pi or microcontroller into a smart voice assistant

## When to choose
- You need a Chinese-language, domain-specific (finance/legal) task-oriented dialogue system with NLU, knowledge graph, and NLG components
- You want a full-stack reference implementation covering data collection, model training, dialogue engine, and Django REST serving
- You are studying end-to-end dialogue-system engineering: intent detection, NER, slot filling, dialogue policy, and RL-based strategy optimization in one codebase

## When to avoid
- You need an actively maintained or production-hardened framework - the latest release dates to mid-2021 and development has stalled
- You want English or multilingual dialogue support out of the box; the project is Chinese-focused
- You want modern LLM-based conversational AI; this is a pre-LLM TensorFlow-era stack of specialized models
- You need a lightweight library - this is a sprawling suite of roughly 13 sub-projects spanning data, algorithms, engines, and integrations

## Facets
- artifact type: application
- maturity: maintenance
- function: chatbot, nlp, machine-learning, deep-learning, reinforcement-learning
- domain: artificial-intelligence, chatbots, machine-learning, deep-learning, fintech, legal
- platform: python, self-hosted, embedded
- tags: knowledge-graph, dialogue-system, task-oriented-dialogue, multi-turn-dialogue, intent-detection, slot-filling, named-entity-recognition, sentiment-analysis, text-classification, information-extraction, tensorflow, tensorflow-serving, django-rest, chinese-nlp, finance-domain, legal-domain, voice-assistant, natural-language-processing, web-server

## Member repositories
- charlesXu86/Chatbot_CN (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:15.322131+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:55:43.579635+00:00, confidence not recorded.
  - readme: https://github.com/charlesXu86/Chatbot_CN (fetched 2026-08-28T04:04:15.322131+00:00, sha efb0c373eb6b)
- Data as of 2026-08-30T08:39:29.467469+00:00.