A portal website user behavior prediction and optimization system based on big data

Abstract

The present invention discloses a portal website user behavior prediction and optimization system based on big data, which specifically relates to the field of big data, including a keyword division module, a user behavior data collection module, a user behavior data analysis module, a user behavior prediction module, a judgment module and an optimization module. The present invention divides a target portal website into sub-data areas and numbers them through the keyword division module, collects flow index parameters, content interaction parameters and conversion index parameters of each sub-data area through the user behavior data collection module, calculates the user activity, content interaction coefficient and conversion index coefficient of each sub-data area through the user behavior data analysis module, calculates the predicted user churn rate of each sub-data area through the user behavior prediction module, judges the predicted user churn rate through the judgment module, and optimizes the target portal website through the optimization module.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and more specifically, to a portal website user behavior prediction and optimization system based on big data. Background Art

[0002] Portal websites were originally meant to be front doors and entrances, but were later widely used in the Internet field and gradually evolved into integration platforms for various application systems. They integrate various application systems, data resources and Internet resources onto an information management platform, and provide it to users with a unified user interface, enabling enterprises to quickly establish information channels between business and customers, business and internal employees, and business and business, enabling enterprises to release various information stored inside and outside the enterprise.

[0003] The existing portal website user behavior prediction and optimization system mainly collects user behavior data on the portal website through the data collection system, including browsing history, search history, and dwell time, and then models and predicts the user behavior data through statistics, machine learning, and deep learning methods, and formulates corresponding optimization strategies based on the user behavior prediction results, including content recommendation, website structure, and layout optimization.

[0004] However, there are still some shortcomings in its actual use. For example, the existing systems cannot comprehensively and accurately collect and process user behavior data. For example, some systems may not be able to process unstructured data, or cannot accurately identify and process user privacy data. The existing systems use various advanced machine learning and deep learning algorithms to predict user behavior, but the accuracy of these models still needs to be improved. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a portal website user behavior prediction and optimization system based on big data, which solves the problems raised in the above-mentioned background technology through the following scheme.

[0006] To achieve the above-mentioned purpose, the present invention provides the following technical solution: a portal website user behavior prediction and optimization system based on big data, comprising:

[0007] Keyword division module: used to determine the user behavior data of the target portal website as the target data area, divide the target area into various sub-data areas by keyword division, and mark them as 1, 2...n in sequence.

[0008] User behavior data collection module: collects traffic index parameters, content interaction parameters and conversion index parameters of each sub-data area through big data technology, and transmits the collected parameters to the user behavior data analysis module.

[0009] User behavior data analysis module: includes traffic index analysis unit, content interaction analysis unit and conversion index analysis unit. Through the mathematical models established by each analysis unit, the transmission parameters of the user behavior data collection module are analyzed, and the user activity, content interaction coefficient and conversion index coefficient of each sub-data area are calculated and transmitted to the user behavior prediction module.

[0010] User behavior prediction module: used to establish a user behavior prediction model, import the user activity, content interaction coefficient and conversion index coefficient transmitted by the user behavior data analysis module into the user behavior prediction model to calculate the predicted user churn rate of the target portal website, and transmit it to the judgment module.

[0011] Judgment module: judges the predicted user churn rate transmitted by the user behavior prediction module through the preset user churn rate threshold, and transmits the judgment result to the optimization module.

[0012] Optimization module: used to receive the judgment results transmitted by the judgment module and optimize the target portal website.

[0013] Preferably, the traffic index parameters include user visits, number of independent IP addresses, number of return visits, number of messages left, and time period, which are marked as Ls i ,Le i ,Lx i , Lc i And Lv i , content interaction parameters include average page views, visit depth, click-through rate, and form submission rate, which are marked as Hr i , Hg i , Hb i And Hd i , the conversion indicator parameters include order conversion rate, purchase conversion rate, registration conversion rate and number of conversions, which are marked as Zj i , Zp i , Zo i and Zk i , where i=1, 2,...n, i represents the i-th sub-data area.

[0014] Preferably, the flow index analysis unit is used to establish a flow index analysis model, and import the flow index parameters into the flow index analysis model to obtain: L i Indicates the user activity of the ith sub-data area, Ls i Le represents the number of user visits to the ith sub-data area, i Indicates the number of independent IPs in the ith sub-data area, Lx i Indicates the number of revisits to the ith sub-data area, Lc iIndicates the number of messages in the ith sub-data area, Lv i represents the time period of the ith sub-data region, and μ1 represents other influencing factors of user activity.

[0015] Preferably, the content interaction analysis unit is used to establish a content interaction analysis model, and import the content interaction parameters into the content interaction analysis model to obtain: H i Represents the content interaction coefficient of the ith sub-data area, Hr i Hg represents the average number of page views per capita in the ith sub-data area. i Indicates the access depth of the ith sub-data area, Hb i Indicates the click rate of the ith sub-data area, Hd i represents the form submission rate of the i-th sub-data area, and μ2 represents other influencing factors of the content interaction coefficient.

[0016] Preferably, the conversion index analysis unit is used to establish a conversion index analysis model, and import the conversion index parameters into the conversion index analysis model to obtain: Z i Represents the conversion index coefficient of the ith sub-data area, Zj i represents the order conversion rate of the ith sub-data area, Zp i represents the purchase conversion rate of the ith sub-data area, Zo i represents the registration conversion rate of the ith sub-data area, Zk i represents the number of conversions of the ith sub-data area, and μ3 represents other influencing factors of the conversion index coefficient.

[0017] Preferably, the user behavior prediction model is: η represents the predicted user churn rate of the target portal website, L i represents the user activity of the ith sub-data area, H i represents the content interaction coefficient of the ith sub-data area, Z i represents the conversion index coefficient of the i-th sub-data area, β1 represents the weight factor of user activity, β2 represents the weight factor of content interaction coefficient, β3 represents the weight factor of conversion index coefficient, and λ represents other influencing factors for predicting user turnover rate.

[0018] Preferably, the preset user churn rate is η0. When η0>η, it means that the preset user churn rate is greater than the predicted user churn rate, indicating that the target portal website does not need to be optimized, and the user behavior data analysis of the target portal website is maintained. When η0≤η, it means that the preset user churn rate is less than or equal to the predicted user churn rate of the target portal website, indicating that the predicted user churn rate of the target portal website needs to be optimized, and the judgment result is transmitted to the optimization module.

[0019] Preferably, the optimization module optimizes the target portal website through data-driven decision-making and A / B testing, collects user feedback by sending emails and questionnaires, and stores and records user feedback in the user behavior data collection module.

[0020] Technical effects and advantages of the present invention:

[0021] By analyzing and predicting user behavior, the present invention can understand user needs and preferences, provide users with more personalized content and services, make users feel more comfortable and satisfied, and enhance user experience. By predicting and optimizing user behavior, it can help the target portal website to better guide users and improve user experience. By analyzing user traffic, interaction, and conversion behavior data, it can discover problems in the structure and layout of the target portal website, and then optimize the target portal website to make it easier to use and navigate, thereby improving the usability of the target portal website. Through the user behavior prediction and optimization system based on big data, it is possible to have a deeper understanding of user needs and market dynamics, and then formulate more accurate and effective marketing strategies and product strategies, so that the target portal website can maintain a leading position in the fierce market competition and enhance the competitiveness of the website. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a schematic diagram of the overall structure of the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] As attached Figure 1 The user behavior prediction and optimization system of a portal website based on big data shown in the figure includes a keyword classification module, a user behavior data collection module, a user behavior data analysis module, a user behavior prediction module, a judgment module and an optimization module.

[0025] The keyword division module is used to determine the user behavior data of the target portal website as the target data area, divide the target area into various sub-data areas by keyword division, and mark them as 1, 2...n in sequence.

[0026] The user behavior data collection module collects traffic index parameters, content interaction parameters and conversion index parameters of each sub-data area through big data technology, and transmits the collected parameters to the user behavior data analysis module.

[0027] The traffic index parameters include user visits, number of independent IPs, number of return visits, number of messages, and time period, which are marked as Ls i ,Le i ,Lx i , Lc i And Lv i , content interaction parameters include average page views, visit depth, click-through rate, and form submission rate, which are marked as Hr i , Hg i , Hb i And Hd i , the conversion indicator parameters include order conversion rate, purchase conversion rate, registration conversion rate and number of conversions, which are marked as Zj i , Zp i , Zo i and Zk i , where i=1, 2,...n, i represents the i-th sub-data area.

[0028] The user behavior data analysis module includes a traffic index analysis unit, a content interaction analysis unit and a conversion index analysis unit. The mathematical models established by each analysis unit are used to analyze the transmission parameters of the user behavior data acquisition module, calculate the user activity, content interaction coefficient and conversion index coefficient of each sub-data area, and transmit them to the user behavior prediction module.

[0029] The flow index analysis unit is used to establish a flow index analysis model, and import the flow index parameters into the flow index analysis model to obtain: L i Indicates the user activity of the ith sub-data area, Ls i Le represents the number of user visits to the ith sub-data area, i Indicates the number of independent IPs in the ith sub-data area, Lx i Indicates the number of revisits to the ith sub-data area, Lc i Indicates the number of messages in the ith sub-data area, Lv i represents the time period of the ith sub-data region, and μ1 represents other influencing factors of user activity.

[0030] The content interaction analysis unit is used to establish a content interaction analysis model, and import the content interaction parameters into the content interaction analysis model to obtain: H i Represents the content interaction coefficient of the ith sub-data area, Hri Hg represents the average number of page views per capita in the ith sub-data area. i Indicates the access depth of the ith sub-data area, Hb i Indicates the click rate of the ith sub-data area, Hd i represents the form submission rate of the i-th sub-data area, and μ2 represents other influencing factors of the content interaction coefficient.

[0031] The conversion index analysis unit is used to establish a conversion index analysis model, and import the conversion index parameters into the conversion index analysis model to obtain: Z i Represents the conversion index coefficient of the ith sub-data area, Zj i represents the order conversion rate of the ith sub-data area, Zp i represents the purchase conversion rate of the ith sub-data area, Zo i represents the registration conversion rate of the ith sub-data area, Zk i represents the number of conversions of the ith sub-data area, and μ3 represents other influencing factors of the conversion index coefficient.

[0032] The user behavior prediction module is used to establish a user behavior prediction model, import the user activity, content interaction coefficient and conversion index coefficient transmitted by the user behavior data analysis module into the user behavior prediction model to calculate the predicted user churn rate of the target portal website, and transmit it to the judgment module.

[0033] The user behavior prediction model is: η represents the predicted user churn rate of the target portal website, L i represents the user activity of the ith sub-data area, H i represents the content interaction coefficient of the ith sub-data area, Z i represents the conversion index coefficient of the i-th sub-data area, β1 represents the weight factor of user activity, β2 represents the weight factor of content interaction coefficient, β3 represents the weight factor of conversion index coefficient, and λ represents other influencing factors for predicting user turnover rate.

[0034] The judgment module judges the predicted user churn rate transmitted by the user behavior prediction module by using a preset user churn rate threshold, and transmits the judgment result to the optimization module.

[0035] The preset user churn rate is η0. When η0>η, it means that the preset user churn rate is greater than the predicted user churn rate, indicating that the target portal website does not need to be optimized, and the user behavior data analysis of the target portal website is maintained. When η0≤η, it means that the preset user churn rate is less than or equal to the predicted user churn rate of the target portal website, indicating that the predicted user churn rate of the target portal website needs to be optimized, and the judgment result is transmitted to the optimization module.

[0036] The optimization module is used to receive the judgment result transmitted by the judgment module and optimize the target portal website.

[0037] The optimization module specifically optimizes the target portal website through data-driven decision-making and A / B testing, and collects user feedback by sending emails and questionnaires, and stores and records user feedback in the user behavior data collection module.

[0038] The present invention divides a target portal website into sub-data areas and numbers them through a keyword division module, collects traffic index parameters, content interaction parameters and conversion index parameters of each sub-data area through a user behavior data collection module, calculates the user activity, content interaction coefficient and conversion index coefficient of each sub-data area through a user behavior data analysis module, calculates the predicted user churn rate of each sub-data area through a user behavior prediction module, judges the predicted user churn rate through a judgment module, and optimizes the target portal website through an optimization module.

[0039] By analyzing and predicting user behavior, the present invention can understand user needs and preferences, provide users with more personalized content and services, make users feel more comfortable and satisfied, and enhance user experience. By predicting and optimizing user behavior, it can help the target portal website to better guide users and improve user experience. By analyzing user traffic, interaction and conversion behavior data, it can discover problems in the structure and layout of the target portal website, and then optimize the target portal website to make the target portal website easier to use and navigate, thereby improving the usability of the target portal website. Through the user behavior prediction and optimization system based on big data, it is possible to have a deeper understanding of user needs and market dynamics, and then formulate more accurate and effective marketing strategies and product strategies, so that the target portal website can maintain a leading position in the fierce market competition and enhance the competitiveness of the website.

[0040] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0041] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A portal website user behavior prediction and optimization system based on big data, The invention comprises: Keyword division module: used to determine the user behavior data of the target portal website as the target data area, divide the target area into various sub-data areas by keyword division, and mark them as 1, 2...n in sequence; User behavior data collection module: collects traffic index parameters, content interaction parameters and conversion index parameters of each sub-data area through big data technology, and transmits the collected parameters to the user behavior data analysis module; The traffic index parameters include user visits, number of independent IPs, number of return visits, number of messages, and time period, which are marked as Ls i ,Le i ,Lx i , Lc i And Lv i , content interaction parameters include average page views, visit depth, click-through rate, and form submission rate, which are marked as Hr i , Hg i , Hb i And Hd i , the conversion indicator parameters include order conversion rate, purchase conversion rate, registration conversion rate and conversion times, which are marked as Zj i , Zp i , Zo i and Zk i , where i=1, 2, ..., n, i represents the i-th sub-data area; User behavior data analysis module: including traffic index analysis unit, content interaction analysis unit and conversion index analysis unit. Through the mathematical models established by each analysis unit, the transmission parameters of the user behavior data collection module are analyzed, and the user activity, content interaction coefficient and conversion index coefficient of each sub-data area are calculated and transmitted to the user behavior prediction module; The flow index analysis unit is used to establish a flow index analysis model, and import the flow index parameters into the flow index analysis model to obtain: L i Indicates the user activity of the ith sub-data area, Ls i Le represents the number of user visits to the ith sub-data area, i Indicates the number of independent IPs in the ith sub-data area, Lx i Indicates the number of revisits to the ith sub-data area, Lc i Indicates the number of messages in the ith sub-data area, Lv i represents the time period of the ith sub-data region, μ1 represents other influencing factors of user activity; The content interaction analysis unit is used to establish a content interaction analysis model, and import the content interaction parameters into the content interaction analysis model to obtain: H i Represents the content interaction coefficient of the ith sub-data area, Hr i Hg represents the average number of page views per capita in the ith sub-data area. i Indicates the access depth of the ith sub-data area, Hb i Indicates the click rate of the ith sub-data area, Hd i represents the form submission rate of the ith sub-data area, and μ2 represents other influencing factors of the content interaction coefficient; The conversion index analysis unit is used to establish a conversion index analysis model, and import the conversion index parameters into the conversion index analysis model to obtain: Z i Represents the conversion index coefficient of the ith sub-data area, Zj i represents the order conversion rate of the ith sub-data area, Zp i represents the purchase conversion rate of the ith sub-data area, Zo i represents the registration conversion rate of the ith sub-data area, Zk i represents the number of conversions of the ith sub-data area, and μ3 represents other influencing factors of the conversion index coefficient; User behavior prediction module: used to establish a user behavior prediction model, import the user activity, content interaction coefficient and conversion index coefficient transmitted by the user behavior data analysis module into the user behavior prediction model to calculate the predicted user churn rate of the target portal website, and transmit it to the judgment module; The user behavior prediction model is: η represents the predicted user churn rate of the target portal website, L i represents the user activity of the ith sub-data area, H i represents the content interaction coefficient of the ith sub-data area, Z i represents the conversion index coefficient of the ith sub-data area, β1 represents the weight factor of user activity, β2 represents the weight factor of content interaction coefficient, β3 represents the weight factor of conversion index coefficient, and λ represents other influencing factors for predicting user turnover rate; Judgment module: judges the predicted user churn rate transmitted by the user behavior prediction module by presetting the user churn rate threshold, and transmits the judgment result to the optimization module; Optimization module: used to receive the judgment results transmitted by the judgment module and optimize the target portal website.

2. The portal website user behavior prediction and optimization system based on big data according to claim 1, characterized in that: The preset user churn rate is η0. When η0>η, it means that the preset user churn rate is greater than the predicted user churn rate, indicating that the target portal website does not need to be optimized, and the user behavior data analysis of the target portal website is maintained. When η0≤η, it means that the preset user churn rate is less than or equal to the predicted user churn rate of the target portal website, indicating that the predicted user churn rate of the target portal website needs to be optimized, and the judgment result is transmitted to the optimization module.

3. The portal website user behavior prediction and optimization system based on big data according to claim 1, characterized in that: The optimization module specifically optimizes the target portal website through data-driven decision-making and A / B testing, and collects user feedback by sending emails and questionnaires, and stores and records user feedback in the user behavior data collection module.

Images