点击率预估、页面展示方法、装置、设备及介质
By extracting common and individual preference vectors from the user's current spatiotemporal context, the problem of inaccurate click-through rate prediction is solved, resulting in more accurate recommendation performance.
CN116523553BActive Publication Date: 2026-07-17RAJAX NETWORK &TECHNOLOGY (SHANGHAI) CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- RAJAX NETWORK &TECHNOLOGY (SHANGHAI) CO LTD
- Filing Date
- 2023-04-28
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing technologies are ineffective at predicting click-through rates in location-based services, resulting in recommendations that do not match user preferences.
Method used
By acquiring the hot trend features and user behavior sequences of the user's current spatiotemporal scene, and using the click-through rate prediction model to extract the common and individual preference expression vectors of users, combined with the characteristics of the target object, the click-through rate of users is predicted.
Benefits of technology
It improves the accuracy of click-through rate prediction, makes the display and sorting of objects on the page more in line with user preferences, and enhances the user experience.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN116523553B_ABST
Abstract
本公开提供一种点击率预估、页面展示方法、装置、设备及介质，所述方法包括：确定待预估的目标对象；获取与用户当前所处的当前时空场景对应的热点趋势特征，所述热点趋势特征表示当前时空场景的历史热门对象的信息；获取所述用户的用户行为序列，所述用户行为序列包括用户历史点击过的对象信息；由点击率预估模型利用所述用户行为序列和所述热点趋势特征，提取所述用户在当前时空场景下对对象的共性偏好表达向量，以及利用所述用户行为序列提取所述用户在当前时空场景下对对象的个性偏好表达向量，至少根据所述共性偏好表达向量、所述个性偏好表达向量和所述目标对象的对象特征，预估所述用户对所述目标对象的点击率。
Need to check novelty before this filing date? Find Prior Art