用LLM构建动态新闻图谱，帮高校预测未来趋势
ORACLE: Time-Dependent Recursive Summary Graphs for Foresight on News Data Using LLMs
- 每周更新的递归摘要图，分两层聚类并由LLM提炼
- 识别内容变化并按PESTEL维度归类，支持决策分析
- 专为高校设计，适合教育机构做趋势洞察与课程规划
ORACLE将每日新闻转化为周度可决策的洞察，服务于芬兰应用科学大学。系统爬取并版本化新闻，应用校内相关性过滤，嵌入内容，分类至PESTEL维度，并构建简洁的时变递归摘要图（TRSG）：两层聚类经由LLM总结并每周重算。轻量级变化检测器识别新增、删除或变更内容，将差异按主题分组，支持PESTEL感知分析。本文详述流程，讨论使系统在生产中稳定的实际设计选择，并提出课程智能应用场景及评估方案。
原文摘要 · Abstract (English)
ORACLE turns daily news into week-over-week, decision-ready insights for one of the Finnish University of Applied Sciences. The platform crawls and versions news, applies University-specific relevance filtering, embeds content, classifies items into PESTEL dimensions and builds a concise Time-Dependent Recursive Summary Graph (TRSG): two clustering layers summarized by an LLM and recomputed weekly. A lightweight change detector highlights what is new, removed or changed, then groups differences into themes for PESTEL-aware analysis. We detail the pipeline, discuss concrete design choices that make the system stable in production and present a curriculum-intelligence use case with an evaluation plan.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。