Recommendation model training method and device based on large language model and recommendation method
By employing a recommendation model training method based on a large language model, and combining user interaction behavior data and text features, the accuracy problem of traditional recommendation systems in the case of new users or sparse data is solved, thereby improving the accuracy of the recommendation system and the user experience.
CN119598193BActive Publication Date: 2026-06-26SHANDONG LANGCHAO YUNTOU INFORMATION TECH CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHANDONG LANGCHAO YUNTOU INFORMATION TECH CO LTD
- Filing Date
- 2024-11-21
- Publication Date
- 2026-06-26
AI Technical Summary
Technical Problem
Traditional recommendation systems often fail to provide accurate recommendations when dealing with new users or sparse data, resulting in a poor user experience.
Method used
The recommendation model training method based on the large language model collects user interaction behavior data and text data, calculates the similarity between users and items, extracts text features using the large language model, and integrates user behavior features and text features into comprehensive features to train the recommendation model.
Benefits of technology
It improved the accuracy of recommendations, solved the cold start problem, and enhanced the user experience.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN119598193B_ABST
Abstract
The application discloses a recommendation model training method and device based on a large language model and a recommendation method, which comprises the following steps: collecting user interaction behavior data and text data in a target field; calculating the similarity between different users based on the user interaction behavior data to obtain a first similarity and the similarity between different items to obtain a second similarity; predicting the user behavior data corresponding to a target item based on the first similarity and the second similarity, and determining the user behavior features based on the user behavior data corresponding to the target item, wherein the target item is an item for which no corresponding user behavior exists for any user; extracting text features corresponding to the text data by using a target large language model; fusing the user behavior features and the text features into comprehensive features; and training a preset network model by using the comprehensive features as training samples to obtain a recommendation model. In this way, the accuracy of the recommendation can be improved, thereby improving the user experience.
Need to check novelty before this filing date? Find Prior Art