Information mining method, device, equipment, storage medium, and program product
By constructing an information heterogeneous graph and performing node sequence sampling to generate label features, the problems of difficulty in constructing label features and low coverage are solved, the effectiveness and coverage of label correlation mining are improved, and the intelligence of information mining is enhanced.
CN115982371BActive Publication Date: 2025-09-30TENCENT TECHNOLOGY (SHENZHEN) CO LTD
1 Cites 0 Cited by
Patent Information
- Application Number
- CN202111197802.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-10-14
- Publication Date
- 2025-09-30
- Estimated Expiration
- 2041-10-14
AI Technical Summary
Technical Problem
In the existing technology, the feature construction of labels is difficult, the effectiveness of label correlation mining is poor, and the coverage is low, resulting in a low level of intelligence in information mining.
Method used
By constructing an information heterogeneous graph, generating label features using node sequence sampling, and determining the correlation between label information based on clustering, information mining is achieved.
Benefits of technology
It reduces the difficulty of constructing label feature representation, improves the coverage and effectiveness of label correlation mining, and enhances the intelligence of information mining.
✦ Generated by Eureka AI based on patent content.
Abstract
The present application provides an information mining method, apparatus, device, storage medium, and program product. The embodiments of the present application can be applied to various scenarios such as cloud technology, artificial intelligence, smart transportation, and vehicle-mounted systems, and involve artificial intelligence technology and cloud computing. The method includes: obtaining multiple content information, multiple tag information, and multiple creation information; constructing an information heterogeneous graph based on the multiple content information, multiple tag information, and multiple creation information; wherein the information heterogeneous graph describes the associations between content information, tag information, and creation information, the associations within multiple content information, and the associations within multiple tag information; by sequentially sampling the nodes of the information heterogeneous graph, label features of each of the multiple tag information are generated; based on clustering the label features, the correlation between the multiple tag information is determined to achieve information mining. Through the present application, the intelligence level of information mining can be improved.
Need to check novelty before this filing date? Find Prior Art