信息推荐方法、装置、计算机设备、存储介质及程序产品
By determining the relevance and time factor of the information to be recommended, and calculating the recommendation probability, the problem of low information recommendation efficiency is solved, dynamic user preference matching is achieved, invalid recommendations are reduced, and recommendation efficiency is improved.
CN114329176BActive Publication Date: 2026-07-17TENCENT TECH WUHAN
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- TENCENT TECH WUHAN
- Filing Date
- 2021-11-08
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
The existing information recommendation process suffers from low recommendation efficiency, which can easily lead to user fatigue and ineffective recommendations.
Method used
By obtaining the associated information of the information to be recommended, the first recall probability is determined based on similarity and historical interaction data, and the second recall probability is determined by combining the recommendation time deviation and timeliness factor. The recommendation probability is then calculated and the information is recommended.
Benefits of technology
It enables dynamic recommendations based on changes in user preferences, reducing user fatigue and improving recommendation efficiency.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN114329176B_ABST
Abstract
本申请提供一种信息推荐方法、装置、计算机设备、存储介质及程序产品，涉及计算机网络、人工智能、智慧交通、辅助驾驶等技术领域。通过基于关联信息的历史交互数据、以及这两种信息之间的相似度，确定第一召回概率，从而结合历史交互情况及信息相似情况，准确量化目标对象在关联信息影响下对待推荐信息的偏好程度；并通过这两种信息的推荐时间偏差、时效因子确定第二召回概率，从时间效应衡量目标对象的偏好变化情况，以准确预测随时间推移对待推荐信息正反馈可能性，准确量化目标对象对待推荐信息的偏好可能性及偏好程度随时间的变化趋势；进一步实现基于不同变化趋势的推荐概率对信息推荐过程的动态控制，减少了无效推荐，进而提高推荐效率。
Need to check novelty before this filing date? Find Prior Art