Big data platform based user behavior analysis system

Abstract

The invention proposes a big data platform based user behavior analysis system. The system comprises a user behavior information acquisition interface, a basic data layer module, a user behavior information analysis module, a user behavior information relevance determination module, a user behavior information organization module, a relevant data group representation module, a user feature analysis module, an aggregation module and an application module. According to the system, a relevant data group between user behavior information (between user behaviors and/or between the content of behavior objects) is established by utilizing interrelations of the user behaviors and the behavior objects, the data group describes effective information contained in the relation of the user behaviors, starting points and ending points of a series of the interrelated user behaviors can be accurately positioned, quantizable user behavior information can be accurately metered based on the relevant data group, and a series of the interrelated user behaviors can be subjected to comprehensive statistical analysis.

Description

technical field [0001] The invention relates to the field of Internet data analysis and processing, in particular to a user behavior analysis system based on a big data platform. Background technique [0002] In the field of Internet applications, user behavior analysis refers to the statistics and analysis of real-time and historical user behaviors generated during the whole process of users accessing network services (including accessing and browsing web pages, performing interactive operations, using APP, etc.) information. A large amount of valuable information is contained in the behavior process of users accessing network services. According to estimates, a user pays attention to 3-4 items on average, visits 5-7 websites, and browses more than 40 pages during an online shopping process. User behavior information includes but is not limited to the following: the number of visits to network services, visit frequency, visit stay time, active operation time, user input k...

AI Technical Summary

Problems solved by technology

[0008] Secondly, it is impossible to locate the starting point and end point of a series of user behaviors, and it is also impossible to distinguish between one-time behaviors and continuous behaviors of users. I have been receiving advertisements about hammers of various styles and brands from the shopping website since then, but in fact, for durable goods such as hammers, the user will no longer have the need to continue buying for many years in the future, so the The user behavior of buying a hammer is actually an occasional one-time behavior, and the purchase itself has put an end to this behavior process; but the shopping website obviously uses the same calculation method as the continuous behavior, and has not correctly judged the user behavior. On the contrary, since the user points to a hammer in multiple continuous user behaviors such as inputting keywords, browsing, adding to a shopping cart, and paying, the hammer is also identified as a feature associated with the user, resulting in Users passively obtain a lot of hammer-related content

[0009] Third, the quantitative calculation of user behavior information is over-represented and prone to deviation

If the above user behavior information is viewed in terms of isolated data points, the user’s visit time to the web pages of models B, C, D, and E is not much different from that of model A, and may even be longer than that of model A. However, in fact, the user’s behavior for several other mobile phones is to compare the price and performance of the A mobile phone based on the purchase goal, and the duration of visits to other several mobile phones can also be credited to the A mobile phone In this way, mobile phone A should be extracted and utilized as the most prominent feature in the above-mentioned series of user behaviors, such as giving priority to pushing advertisements and preferential information of mobile phone A, but the existing technology cannot achieve the above effects, often It is to push the advertisements and discounts of other mobile phones indiscriminately from the mobile phone A

[0010] Fourth, due to cutting off or even splitting the relationship between various user behaviors, services based on big data can only focus on one or a few parts of user behavior

However, the existing big data system cannot realize the above-mentioned correlation analysis. Although it is possible to find that the user has followed the band and browsed the news about the band through the same behavior object, it can only be used as the band. Push tickets, albums, posters and other related information based on the characteristics associated with users, but cannot effectively connect the behavior of searching for tickets with the band

Regarding the impact of this lack of connection, for example, the big data system can also push the user to find hotel discounts in Shanghai based on the user’s behavior of searching for air tickets, but it cannot give priority to pushing hotels around the concert venue Related Information

[0011] It can be seen that the classification, analysis and application of user behavior information cannot be realized from the perspective of the relevance of user behavior and its behavior objects, which brings the above limitations to the existing user behavior information big data platform

Images