User behavior prediction method and device and electronic equipment

Abstract

The invention relates to a user behavior prediction method, which belongs to the field of computer technologies and solves a problem that the prediction result is inaccurate in the prior art. The userbehavior prediction method comprises the steps of constructing a t-moment behavior transfer probability matrix of a target user according to behavior data of a target user before the moment t; iteratively training a behavior prediction model of the target user based on the t-moment behavior transfer probability matrix and preset behavior influence factors; and predicting a next behavior of the target user based on the t-moment behavior transfer probability matrix, the preset behavior influence factors and a behavior prediction result of the target user at the previous moment according to thebehavior prediction model. According to the user behavior prediction method disclosed by the embodiment of the invention, behavior prediction is performed through combining related factors of user behaviors and a behavior transformation relation of the user, the behavior granularity of the user is refined, the user behaviors are comprehensively considered, model training is performed by combiningthe behavior transformation probability, and the prediction accuracy of the model is effectively improved.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a user behavior prediction method and device, and electronic equipment. Background technique [0002] User behavior prediction is to predict the user's next behavior based on the user's existing behavior. User behavior prediction is widely used in many fields such as online advertisement placement and recommendation system. Taking catering and gourmet food as an example in the O2O scenario, by predicting the user's next behavior, it is possible to push accurate coupons or merchant promotions for the user. Existing user behavior prediction methods generally collect and report user operation logs, clean and filter data based on user operation logs, and then record user behavior sequences according to coarse-grained divisions such as clicks, browses, and exposures. predict. However, different business scenarios focus on different user behaviors. Prediction based on th...

AI Technical Summary

Problems solved by technology

However, different business scenarios focus on different user behaviors. Prediction based on this coarse-grained user behavior cannot truly reflect specific business value, and it is difficult to achieve accurate prediction results

On the other hand, due to the limited individual behavior data and insufficient coverage of training samples, in the prior art, when the prediction model is trained based on the operation log to predict user behavior, the prediction will also be inaccurate.

Moreover, when forecasting is based on the user's existing preferences, there are limitations in the prediction of user behavior in O2O scenarios, and it is difficult to discover new behaviors of users in the prediction.

[0003] It can be seen that the user behavior prediction method in the prior art has at least the defect of inaccurate prediction results

Images