一种对象信息推送方法、装置、电子设备、存储介质及程序产品
By utilizing cross-domain feature transfer technology to predict consumption characteristics based on user interaction data and push object information in the case of new user cold start, the problem of low push accuracy under the case of new user cold start is solved, and accurate object information recommendation is achieved.
CN122420380APending Publication Date: 2026-07-17BEIJING WODONG TIANJUN INFORMATION TECH CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BEIJING WODONG TIANJUN INFORMATION TECH CO LTD
- Filing Date
- 2026-04-24
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
The accuracy of push notifications is not high when new users are cold-starting, and existing technologies cannot accurately recommend food delivery stores.
Method used
By acquiring user interaction data of target users in the first consumption scenario, predicting their consumption characteristics in the second consumption scenario, and using cross-domain feature transfer technology to push object information, including adversarial training and consumption level consistency constraints, domain-invariant user interaction features are generated.
Benefits of technology
It significantly improves the accuracy and conversion rate of push notifications for new users during cold starts, ensuring personalized recommendations of target information.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN122420380A_ABST
Abstract
本发明实施例公开了一种对象信息推送方法、装置、电子设备、存储介质及程序产品。该方法包括：获取目标用户在第一消费场景下的用户交互数据；根据用户交互数据预测目标用户在第二消费场景下的消费特征；根据消费特征进行对象信息推送，其中，所推送的对象信息用于描述第二消费场景下的对象。本发明实施例的技术方案，可提升在新用户冷启动情况下的推送精度。
Need to check novelty before this filing date? Find Prior Art