Method and apparatus for recommending multimedia resources
By acquiring the similarity and recommendation frequency between multimedia resources and account information, and utilizing deep neural networks and recall models, the problem of low efficiency in multimedia resource recommendation was solved, and the utilization rate and delivery effect of cold start resources were improved.
CN115438203BActive Publication Date: 2026-06-12BEIJING DAJIA INTERNET INFORMATION TECH CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING DAJIA INTERNET INFORMATION TECH CO LTD
- Filing Date
- 2022-10-11
- Publication Date
- 2026-06-12
AI Technical Summary
⚠Technical Problem
In existing technologies, the recommendation process for multimedia resources is inefficient, resulting in low utilization rates.
⚗Method used
By obtaining the similarity between the target multimedia resource and the current account information and the number of times it has been recommended, a deep neural network model is used to train the similarity, and combined with the recall model and reward parameters, multimedia resources to be recommended are selected.
🎯Benefits of technology
It improves the recommendation efficiency and utilization rate of target multimedia resources, especially the push effect of cold start multimedia resources, and extends the delivery life cycle of multimedia resources.
✦ Generated by Eureka AI based on patent content.
Abstract
The present disclosure relates to a multimedia resource recommendation method and device. The multimedia resource recommendation method comprises: obtaining at least one target multimedia resource, wherein the number of times of recommendation of the at least one target multimedia resource within a predetermined time satisfies a first preset number of times condition; obtaining, from the at least one target multimedia resource, a target multimedia resource whose similarity to account information of a current account satisfies a preset condition; selecting a multimedia resource to be recommended from the target multimedia resource whose similarity to the account information of the current account satisfies the preset condition and a multimedia resource whose number of times of recommendation satisfies a second preset number of times condition, which is obtained in advance; and recommending the multimedia resource to be recommended to the current account.
Need to check novelty before this filing date? Find Prior Art