一种对象推荐方法、装置、设备、存储介质及程序产品
By utilizing historical evaluation data from the recommending recipients to predict evaluation data for the current period, the problems of low accuracy and efficiency in object recommendation are solved, achieving efficient and accurate object recommendation.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- TENCENT TECHNOLOGY (SHENZHEN) CO LTD
- Filing Date
- 2022-10-28
- Publication Date
- 2026-07-17
AI Technical Summary
In existing technologies, object recommendation suffers from low accuracy and low efficiency, mainly due to the lack of real-time rating data, which makes matrix factorization difficult, computationally intensive, and unable to effectively predict and recommend.
By acquiring historical evaluation data from the recipients over 2N historical periods, evaluation prediction parameters are determined. These parameters and historical evaluation data are then used to predict the evaluation data for the current period, thereby selecting target objects for recommendation.
It improves the accuracy and efficiency of object recommendation, uses historical data to predict real-time rating data for the current period, reduces computation time, and achieves fast and accurate recommendations.
Smart Images
Figure CN117033760B_ABST