User shopping behavior identification method based on big data, storage equipment, and mobile terminal

Abstract

The invention discloses a user shopping behavior identification method based on big data, which is applicable to computer equipment. The method includes the following steps: basic data preparation; user behavior acquisition: acquiring browse, click, collection, forwarding and purchase behavior data of users when users open web pages through an acquisition module; user behavior quantification: classifying and summarizing the acquired behavior data, and establishing the functional relationship of users, commodity labels and the behavioral attention of a user on a certain commodity label; establishing a user preference matrix: establishing a user preference function according to the functional relationship of users, commodity labels and the behavioral attention of a user on a certain commodity label; establishing user similarity; and displaying commodities. In the invention, user behaviors are quantified, and user preference and similarity functions are established. The logic theory is simple and highly operable. The purchase scenario and user participation are considered, and the analysis result is more accurate.

Description

technical field [0001] The invention relates to the field of big data analysis, in particular to a method for identifying user shopping behavior based on big data. Background technique [0002] With the rapid development of the mobile Internet and the massive popularization of online shopping, commodity information has grown explosively, and the problems brought about by the massive information are as follows: [0003] The utilization rate of information is low. Faced with a large number of products, users do not have enough patience and time to browse the products in the back; the timeliness is poor, and when the information is updated in real time, users cannot obtain the products they are interested in immediately; the operation is difficult Large, need to find the products you are interested in, often go through a lot of condition setting and sorting, require users to have considerable technical knowledge; how do users choose? For merchants, how to provide users with pr...

AI Technical Summary

Problems solved by technology

[0003] The utilization rate of information is low. Faced with a large number of products, users do not have enough patience and time to browse the products in the back; the timeliness is poor, and when the information is updated in real time, users cannot obtain the products they are interested in immediately; the operation is difficult Large, need to find the products you are interested in, often go through a lot of condition setting and sorting, require users to have considerable technical knowledge; how do users choose? For merchants, how to provide users with products they are interested in?

[0004] In view of the above problems, it is urgent to identify the user's shopping behavior, analyze the user's bias and preferences, and recommend products according to the user's bias and preferences. There are already some recommendation algorithms in the prior art to recommend products according to the user's bias and preferences. However, these technologies have some shortcomings: strong theory, based on user scoring mechanism, lack of quantification of shopping behavior and shopping scenarios; poor real-time performance, unable to respond quickly after a large number of calculations and analysis; lack of consideration of the impact of time on user preferences

Images