Big-data-based method and system for establishing and analyzing e-commerce user portrait of mobile terminal

Abstract

The invention discloses a big-data-based method and system for establishing and analyzing an e-commerce user portrait of a mobile terminal. The method comprises: offline data of a user are obtained; according to an identification code, data of different data sources are integrated into an offline knowledge base; pretreatment including normalization, discretization and attribute reduction is carried on the offline data; feature extraction is carried out on the offline data based on a customized tag rule and a basic tag of the user is constructed; weight and time attenuation factor processing iscarried out on the tag data and a user portrait offline prediction model based on a QPS cluster algorithm is established; data clustering mining is carried out on the offline knowledge base by usingthe prediction model to obtain an e-commerce user portrait of a mobile terminal; and distributed processing is carried out on online behavior data and then the processed data are integrated with the offline model. Therefore, massive data of the e-commerce transaction of the mobile terminal are analyzed in a big data environment; the real-time user behavior can be analyzed quickly and real-time image fusion is realized; and a multi-dimensional user portrait is built, so that the e-commerce user is analyzed comprehensively.

Description

technical field [0001] The invention relates to the technical field of data processing and analysis, in particular to a method for establishing and analyzing mobile terminal e-commerce user portraits based on big data. Background technique [0002] User portrait, also known as user role (Persona), is the labeling of user information. It is an effective way to outline target users, contact user demands and design directions. Its goal is to establish descriptive label attributes for users in many dimensions . It collects and analyzes the data of users' basic attributes, social attributes, living habits, consumption behaviors and other information, abstracts a complete picture of users to mine user needs and analyze user preferences, and supports personalized recommendation, automated marketing and other big data applications. Way. For example, during product development, user portraits can be analyzed to position and plan products; during product promotion, user portraits ca...

AI Technical Summary

Problems solved by technology

The problem with this method is that the data obtained is relatively one-sided. There is only user data on the site, and nothing is known about the user’s access behavior on other websites; on the other hand, when the user data reaches a sufficient density, the user Although the descriptive label attribute of , shows high stability, the above methods also have the problem of insufficient adaptability to flexible changes, especially in the case of step mutations in user data.

In terms of constructing user portrait algorithms, some cluster-based automatic construction methods of user portraits have been proposed by many scholars. Many existing studies have adopted the traditional K-Means algorithm, which has some problems in the clustering process. Fatal problem: On the one hand, the similarity quality index QPS in the grouped clusters cannot be guaranteed; on the other hand, the number of clusters and initial centroids need to be artificially selected, which has a certain degree of randomness, and usually the number of clusters in the portrait cannot be higher than before Precognition, making the whole process unpredictable and unstable

Although some research work has been carried out on the construction of user portraits in recent years, the existing research still has certain limitations, such as data fragmentation, data closure, and low algorithm efficiency, which cause the user portraits to be inaccurate.

The efficiency of offline training is low, and there is no perfect mechanism to cooperate with real-time user feedback, so there are problems such as low conversion rate of e-commerce transactions

Images