遇见数据集

ThatDeveloperGuy13/aeo-citation-tracking-schema

收藏
Hugging Face2026-05-26 更新2026-05-31 收录
官方服务:

资源简介:

AEO引用跟踪模式是一个数据集,用于追踪AI搜索引擎(如ChatGPT、Claude、Perplexity、Gemini、Google AI Overviews等)在生成答案时引用网站的情况。该数据集提供了一个最小化的标准化模式,旨在支持答案引擎优化(AEO)、生成引擎优化(GEO)和LLM优化(LLMO)等新兴领域的监控工具开发。模式包括多个字段,如引擎类型、用户查询、引用URL、引用顺序、信心值、查询类别、行业垂直领域、地理意图、设备、国家、语言、时间戳和查询ID。用例包括引导AEO监控工具、跨引擎引用一致性基准测试、检测引用幻觉(即URL与内容不匹配)、研究AI引用的地理和行业模式,以及基于免费开放标准与商业平台竞争。数据集由ThatDevPro维护,采用CC BY 4.0许可,允许自由重用并需署名。

The AEO Citation Tracking Schema is a dataset that defines a minimal, normalized schema for tracking when and how AI search engines (such as ChatGPT, Claude, Perplexity, Gemini, Google AI Overviews) cite websites in their generated answers. It is designed as a starting point for monitoring tools in emerging disciplines like Answer Engine Optimization (AEO), Generative Engine Optimization (GEO), and LLM Optimization (LLMO). The schema includes columns for engine, user query, cited URL, citation order, confidence score, query category, vertical industry, geographic intent, device, country, language, timestamp, and query ID. Use cases include bootstrapping an AEO monitoring tool, benchmarking citation consistency across engines, detecting citation hallucinations (where the URL does not match the content), researching geographic and vertical patterns in AI citation, and competing with commercial platforms on a free and open standard. The dataset is maintained by ThatDevPro and is licensed under CC BY 4.0, allowing free reuse with attribution.

提供机构:
ThatDeveloperGuy13
二维码
社区交流群
二维码
科研交流群
商业服务