Effective behavior detection and personalized recommendation methods

Abstract

The embodiment of the invention provides effective behavior detection and personalized recommendation methods. The effective behavior detection method comprises the steps of obtaining user data of a user; determining behavior detection parameters of the user based on the user data; wherein the behavior detection parameters comprise an operation behavior moment, an equipment operation state and / ora reaction result for an effective behavior test; and selecting an effective behavior sample and / or an invalid behavior sample from the user data based on the behavior detection parameters. Accordingto the effective behavior detection and personalized recommendation methods, depending on user data, the behavior detection parameters of the user are determined according to the user data, and then the effective behavior sample and / or the invalid behavior sample are / is selected from the user data, so that accurate effective behavior detection is realized, the effective behavior obtained by effective behavior detection is applied to the user portrait, the accuracy of the user portrait is improved, and accurate and reliable personalized recommendation is realized.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to an effective behavior detection and personalized recommendation method. Background technique [0002] User portrait recall is one of the most important recall methods in personalized recommendation. Recall refers to the strategy of screening a recommendation candidate set from a large data set. In user portrait recall, the quality of user portrait will directly affect the accuracy of recall. [0003] Take song recommendation in the online song business scenario of a music APP (Application, mobile phone software) as an example. In the music APP, songs are mainly automatically played in batches in the form of playlists. In the existing technology, in order to complete the construction of the user portrait, the music APP first needs to determine the user's favorite songs, and the music APP provided by the existing technology often determines the user's preference for the song base...

AI Technical Summary

Problems solved by technology

[0004] However, in the solution provided by the above-mentioned prior art, the total duration of a single song is relatively short and can be played in a short time, so it is difficult to distinguish whether the user has performed an effective song listening behavior, for example: the user forgot to close the music APP when leaving, But the music app is still playing the music, or the user is playing the music but turned the volume to the lowest level instead of listening to the song

Due to the existence of the above situations, if we continue to use the existing technology to determine the user's favorite song based on whether the music APP plays a song completely, the accuracy of the created user portrait will be poor, which will affect the effect of recommendation based on the user portrait.

Images