Electric power material commodity recommendation method and device based on improved deep interest network

By adopting an improved deep interest network in the power material recommendation system, combining semantics and channel attention mechanisms, as well as an adaptive Cauchy loss function, problems such as cold start, long-tail product recommendation and data sparseness in the power material recommendation system are solved, and more accurate, robust and real-time recommendation effects are achieved.

CN119671660APending Publication Date: 2025-03-21XUCHANG POWER SUPPLY COMPANY OF STATE GRID HENAN ELECTRIC POWER
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411451237.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-17
Publication Date
2025-03-21

AI Technical Summary

Technical Problem

The power supply recommendation system faces problems such as cold start of new items, difficulty in recommending long-tail items, dependence on professional knowledge, data sparseness and real-time requirements.

Method used

The recommended method based on an improved deep interest network is adopted, by adding a semantic level and channel level attention mechanism, the correlation between different products is captured, and the smoothness of the training process is dynamically adjusted using the adaptive Cauchy loss function to enhance the representation ability and robustness of the model.

Benefits of technology

It improves the accuracy of recommendations for new items and long-tail products, enhances the robustness and characterization capabilities of the model, and can quickly respond to changes in the power material market and meet real-time needs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119671660A_ABST
    Figure CN119671660A_ABST
Patent Text Reader

Abstract

The invention discloses an electric power material commodity recommendation method and device based on an improved deep interest network. According to the method, the problem of inaccurate commodity recommendation caused by lack of sufficient interaction data of new articles or a long tail effect in an electric power material recommendation system is solved. By introducing an instance attention mechanism and a channel attention mechanism, feature expression is enhanced, so that a recommendation system can make accurate commodity recommendation under the condition of a small number of samples, and the method is particularly suitable for commodity recommendation scenes with professional characteristics such as electric power materials; and the smoothness of the training process is dynamically adjusted by using the Cauchy loss, so that the ability of the model to capture the deep characteristics of the high-dimensional incomplete data is enhanced, and the model is further endowed with stronger representation ability and robustness.
Need to check novelty before this filing date? Find Prior Art