A method and system for recommending electric vehicle charging facilities based on federated learning

Abstract

The invention discloses a method and system for recommending electric vehicle charging facilities based on federated learning. The method includes: acquiring a pile feature data set and a car feature data set, and the pile feature data set is extracted from the pile operation data platform data and is related to charging. A collection of pile features related to pile operation. The car feature data set is a collection of car features related to car charging extracted from the data of the car enterprise data platform. The federated recommendation algorithm is used to carry out the pile feature data set and the car feature data set. Federated training to obtain the federated recommendation model; obtain the current pile feature data set and the current car feature data set corresponding to all the charging piles in the list of charging piles to be recommended; input the current pile feature data set and the current car feature data set into the federated recommendation model, and get Recommended results. By implementing the present invention, the integrated use of pile operation data platform data and car enterprise data platform data is realized, model features are expanded, and personalized recommendation for charging facilities is realized.

Description

technical field [0001] The invention relates to the technical field of the Internet of Things, in particular to a federated learning-based electric vehicle charging facility recommendation method and system. Background technique [0002] With the development of new energy technologies, the market share of electric vehicles is getting higher and higher, and the number of charging facilities continues to grow accordingly. However, according to statistics, the current utilization rate of charging service facilities of various operators is generally lower than 15%. Therefore, each charging facility operator has begun to build its own operation data platform, access pile-side data, and provide charging facility recommendation services for users. However, the current status analysis and recommendation of charging facilities mainly rely on pile-side data, without taking into account users’ needs. Individual needs. In addition, car companies with electric vehicle user-side data ha...

AI Technical Summary

Problems solved by technology

[0003] Therefore, the technical problem to be solved by the present invention is to overcome the defect that the charging facility recommendation method in the prior art is difficult to realize the user's personalized recommendation requirements for charging facilities, thereby providing a federated learning-based electric vehicle charging facility recommendation method and system

Images