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.

翻译：ORACLE 平台将每日新闻转化为周度、可用于决策的洞察，服务于芬兰一所应用科学大学。该平台爬取并版本化新闻数据，应用大学特定的相关性过滤，对内容进行嵌入表示，将条目分类至 PESTEL 维度，并构建一个简洁的时间依赖递归摘要图（TRSG）：该图包含两个由大语言模型（LLM）总结的聚类层，并每周重新计算。一个轻量级变化检测器突出显示新增、移除或变更的内容，随后将差异分组为主题，以支持基于 PESTEL 维度的分析。本文详细阐述了该处理流程，讨论了使系统在生产环境中保持稳定的具体设计选择，并介绍了一个课程智能用例及其评估方案。