An information retrieval method, medium and device
By using a material relationship knowledge graph for multi-dimensional drug information retrieval, integrating multiple types of nodes and combining them with visual output, the problem of inaccurate and inefficient drug information retrieval in existing technologies is solved, and comprehensive, accurate and efficient retrieval of multi-dimensional information is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- YUYANG ZHISHU (BEIJING) TECHNOLOGY CO LTD
- Filing Date
- 2026-01-28
- Publication Date
- 2026-07-24
AI Technical Summary
Existing drug information retrieval methods cannot meet the needs of multi-dimensional cross-search, lack visualization of drugs, genes, pathways, diseases and treatment plans, and do not fully integrate clinical diagnosis and treatment guidelines, resulting in inaccurate search results and low efficiency.
It employs a material relationship knowledge graph for multi-dimensional keyword retrieval, integrating preset material nodes, target nodes, gene nodes, pathway nodes, disease nodes, and treatment plan nodes. Through association expansion, it generates associated sub-graphs, and combines them with structured material information tables and visual output, integrating authoritative evidence such as clinical diagnosis and treatment guidelines.
It enables comprehensive retrieval of multi-dimensional information, improves the accuracy and reliability of retrieval results, enhances information acquisition efficiency and user experience, and meets the needs of multiple scenarios in clinical diagnosis and treatment and scientific research.
Smart Images

Figure CN121979929B_ABST