Mobile terminal APP usage prediction method combining with time-context based on sequence mode

Abstract

The invention discloses a mobile terminal APP usage prediction method combining with time-context based on a sequence mode, comprising steps of using a sequence mode to extract the private app usage relevance of the user from a user history app usage sequence, which is the user application usage mode, combining with the fact whether the user is in the mobile phone usage active period, and comprehensively consider the recent behavior mode of the user during the prediction and the time-context information that the user currently use so as to enable the predicted application usage to accord with the real-time demand and preference of the user.

Description

technical field [0001] The invention belongs to the technical field of data mining and recommendation, and in particular relates to a mobile terminal APP usage prediction method based on a sequence pattern combined with a time context. Background technique [0002] In recent years, in order to achieve better user experience, increase user viscosity, and promote targeted marketing, major platform manufacturers hope to use big data technology to segment users, mine user attributes, and draw user portraits. Facing the rise of the mobile Internet, along with the emergence of mobile big data, mobile big data has high commercial value. According to the usage of mobile objects APP, it can objectively reflect the user's hobbies and behavior habits. Coupled with the rich physical location information of moving objects, the user's data is more abundant, which also attracts the attention of the academic and engineering circles to the data mining of moving objects. Behavior Model (Beha...

AI Technical Summary

Problems solved by technology

However, there is little research on predicting the user's next use of APP in the existing research.

In the traditional statistical forecasting algorithm, only the application with the highest user frequency is used as the forecast. The forecast value of this mode has certain blindness and fixedness, and cannot perceive the user's behavioral intention.

Yen-SsuChou and others built a four-layer structure diagram by collecting the quadruple data (user, geographic location, time, service) of most users, and used the MJMF (MatchJoinsUsingMaxFlows) algorithm to predict the APP service that the target user will use in the next location. However, this algorithm obviously neglects to treat all user behavior patterns in a unified manner, lacks the isolation between mobile user data, and ignores the personal usage habits of individual mobile users, etc.

Images