Service recommendation method and system based on interaction between location and preference features

By combining the user and service identification, location information and historical call records, and using multi-head attention and deep residual neural networks for feature interaction, the problems of data sparsity and single features in existing recommendation methods are solved, and more accurate service quality prediction and recommendation are achieved.

CN114817735BActive Publication Date: 2025-10-03QILU UNIVERSITY OF TECHNOLOGY (SHANDONG ACADEMY OF SCIENCES)
2 Cites 0 Cited by

Patent Information

Application Number
CN202210515774.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-05-12
Publication Date
2025-10-03
Estimated Expiration
2042-05-12

AI Technical Summary

Technical Problem

In existing recommendation methods, the feature analysis of users and services is single, resulting in sparse data, poor generalization ability, low accuracy of recommendation results, and failure to fully integrate the potential information of users and services.

Method used

By obtaining the identification information, location information and historical call records of users and services, using the multi-head attention fusion network and interest feature extraction network to fuse the interest preferences of users and services, and inputting the deep residual neural network for feature interaction, the service quality can be accurately predicted.

Benefits of technology

It improves the accuracy of service recommendations, reduces data redundancy and inaccuracy, enhances the implicit relationship between users and services, and improves prediction accuracy.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present invention discloses a service recommendation method based on the interaction of location and preference features, comprising: obtaining identification information, location information, and historical call records of users and services; obtaining a service set corresponding to the user and a user set corresponding to the service based on the historical call information and location information of the user and service, respectively; fusing and extracting the interest preferences of the user and service using a multi-head attention fusion network and an interest feature extraction network; subjecting the interest preferences, location information, and identification information of the user and service to feature interaction, inputting the information into a deep residual neural network, and outputting a service quality prediction result; and selecting the service with the best service quality prediction result as the final recommended service. The present invention addresses the problems of data redundancy and imprecision by locating the interest preferences of users and services, integrating the location information and interest preferences of users and services into the prediction of service quality, and performing linear and nonlinear transformations on the features to improve the accuracy of predictions and recommendations.
Need to check novelty before this filing date? Find Prior Art