Association recommendation method and device, equipment and readable storage medium
By identifying the user-selected 3D model in an augmented reality device and combining gaze behavior and zoom operations to calculate the size information of the 3D model, the problem of content bias in existing technologies is solved, and more accurate related recommendations are achieved.
CN116881561BActive Publication Date: 2026-05-29MIGU COMIC CO LTD +2
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- MIGU COMIC CO LTD
- Filing Date
- 2023-07-17
- Publication Date
- 2026-05-29
AI Technical Summary
Technical Problem
Existing object association recommendation methods rely solely on users' past behavior for recommendations, failing to accurately predict users' current needs, resulting in biased or irrelevant content being recommended.
Method used
By determining the 3D model selected by the user in the current scene, and combining the user's gaze behavior and zoom operation, the size information of the 3D model is calculated. Based on this information and the user's basic information, the target search library is retrieved to obtain related recommendation results.
Benefits of technology
This improves the accuracy of recommendation results, making them more relevant to the user's current context and needs, and reduces the probability of irrelevant content appearing in search results.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN116881561B_ABST
Abstract
The application provides a correlation recommendation method and device, equipment and a readable storage medium, wherein the method comprises the following steps: determining a three-dimensional model of a first object selected by a user in a current scene; performing scaling processing on the three-dimensional model according to a user gaze behavior and a zoom operation of the user on the three-dimensional model to obtain size information of a scaled 3D model; and searching a target search library based on the size information of the scaled 3D model and user basic information to obtain a correlation recommendation result of the first object. According to the scheme, context correlation information is added on the basis of reference to user basic information, the current state of the user is obtained and the demand is speculated, so that more accurate object correlation recommendation can be made.
Need to check novelty before this filing date? Find Prior Art