Vehicle recommendation method and device, equipment and storage medium

Abstract

The embodiment of the invention discloses a vehicle recommendation method and device, equipment and a storage medium. The method comprises the steps of obtaining a user feature vector of a current user and determining a vehicle feature vector of a to-be-recommended vehicle; determining a long-term behavior vector of the current user in the first time period and a short-term behavior vector of thecurrent user in the second time period according to the historical interaction information of the current user for the historical recommended vehicle; inputting the user feature vector, the vehicle feature vector, the long-term behavior vector and the short-term behavior vector into a DeepFM model to obtain a behavior prediction score of the interaction behavior of the current user on the to-be-recommended vehicle; and recommending the vehicle to the current user according to the behavior prediction score. According to the technical scheme provided by the embodiment of the invention, the long-term and short-term behavior preferences of the user can be tracked in the use process of the DeepFM model, so that the personalized requirements of the user are met during vehicle recommendation, thematching degree between the vehicle recommendation result and the user is improved, and the user experience is improved.

Description

technical field [0001] The embodiments of the present invention relate to the field of computer technology, and in particular to a vehicle recommendation method, device, equipment and storage medium. Background technique [0002] As a new economic form, the sharing economy temporarily transfers the idle resources of the supply side through the sharing platform, improves the utilization rate of assets, and creates value for the demand side. [0003] In the prior art, when car sharing platforms recommend vehicles to users, they are usually calculated directly based on statistical data such as popularity and user clicks, and the granularity is relatively coarse. At the same time, the recommendations are mainly based on public interest and general preference vehicles, and the recommendation results are easily affected by group popularity. The coverage rate is low, which makes the recommendation result poorly matched with the user and reduces the user experience. Contents of th...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, when car sharing platforms recommend vehicles to users, they are usually calculated directly based on statistical data such as popularity and user clicks, and the granularity is relatively coarse. At the same time, the recommendations are mainly based on public interest and general preference vehicles, and the recommendation results are easily affected by group popularity. The coverage is low, which makes the matching between the recommendation result and the user poor and reduces the user experience

Images