# chizhu/KGQA_HLM

基于知识图谱的《红楼梦》人物关系可视化及问答系统

Repository: https://github.com/chizhu/KGQA_HLM
Canonical: https://ross.abutalabs.com/products/kgqa_hlm
Language: HTML
License Family: other
Topics: nlp, kgqa
Last push: 2019-04-23T13:24:43+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": 3042, "days_push": 2689, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1336, forks 317 (observed 2026-08-28T04:04:25.391613+00:00)

## What it is
A knowledge-graph-based question answering and visualization system for character relationships in the Chinese classic novel 'Dream of the Red Chamber'. It uses Neo4j as the graph database, pyltp for Chinese NLP (segmentation, POS tagging, NER), and a Flask web app for the frontend.

## Use cases
- visualize character relationships in Dream of the Red Chamber
- build a knowledge graph in Neo4j from extracted triples
- ask natural language questions about novel characters
- demo a Chinese KGQA pipeline with ltp NER
- learn how to combine web scraping, knowledge graphs, and QA

## When to choose
- you need a reference implementation of Chinese knowledge-graph question answering
- you want to visualize literary character relationship networks
- you are teaching or learning KGQA with Neo4j and pyltp

## When to avoid
- you need production-grade, maintained software with a license
- you need English-language QA or modern LLM-based QA
- you cannot set up Neo4j with JDK8 and older Python 3.6 dependencies

## Facets
- artifact type: application
- maturity: maintenance
- function: nlp, search-engine, data-visualization, web-scraping, chatbot
- domain: databases, web-development
- platform: python, self-hosted
- tags: knowledge-graph, kgqa, neo4j, question-answering, dream-of-the-red-chamber, chinese-nlp, ltp, character-relationships, natural-language-processing, search, web-server

## Member repositories
- chizhu/KGQA_HLM (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:25.391613+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 2026-08-30T04:44:07.107317+00:00, confidence not recorded.
  - readme: https://github.com/chizhu/KGQA_HLM (fetched 2026-08-28T04:04:25.391613+00:00, sha 69fc8943ec4b)
- Data as of 2026-08-30T08:39:29.467469+00:00.