数据对象分类方法、装置、存储介质及电子装置
By acquiring and utilizing representation vectors for data object classification, the problems of low classification efficiency and poor accuracy in existing technologies are solved, achieving efficient and accurate data object classification.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NETEASE (HANGZHOU) NETWORK CO LTD
- Filing Date
- 2023-09-04
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies suffer from low efficiency and poor accuracy in classifying data objects, and cannot guarantee strong correlation between data objects in the classification results.
By acquiring multiple representation vectors of the data objects to be classified and classifying them based on preset classification conditions, the classification of data objects is carried out using similarity thresholds and the similarity between representation vectors, including creating and updating classification storage areas to store data objects with high similarity.
It achieves efficient classification of data objects, improves the accuracy and efficiency of classification, and ensures that there is a strong correlation between data objects in the classification results.
Smart Images
Figure CN117251761B_ABST