A user behavior analysis system and method based on data analysis

Abstract

The present invention discloses a user behavior analysis system and method based on data analysis, which belongs to the field of information processing technology. The system includes a user management module, a push data storage module, a behavior data collection module, an intelligent analysis module and an intelligent push module; the user management module is used to provide a human-computer interaction interface, provide user login and identity authentication functions, and issue user operation instructions; the push data analysis module is used to store push data, classify push data, and analyze the browsing time required for push data; the behavior data collection module is used to collect user operation behavior data and send the collected behavior data to the intelligent analysis module; the intelligent analysis module is used to analyze the collected behavior data, determine the current user's browsing preference content, and select corresponding push data according to the user's browsing preference; the intelligent push module is used to send the selected push data to the user management module.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to a user behavior analysis system and method based on data analysis. Background Art

[0002] Data analysis refers to the process of analyzing large amounts of collected data through appropriate statistical analysis methods, extracting useful information, forming conclusions, and conducting detailed research and summarizing. Through the observation and analysis of data, it can help make more informed decisions, optimize business processes, identify trends and opportunities, and improve performance and efficiency.

[0003] User behavior analysis can deeply understand customer needs and provide personalized experience by analyzing user operation behaviors. Although user behavior analysis can be used to infer user hobbies and interests, the quality of user behavior data is uneven, and it is difficult to filter out truly useful information. By combining other data sources, such as user likes and comments, more comprehensive data analysis can be performed, but for some lurking users, a single behavior data analysis is often not accurate enough and it is difficult to dig out deeper data information. Summary of the invention

[0004] The purpose of the present invention is to provide a user behavior analysis system and method based on data analysis to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a user behavior analysis system based on data analysis, the system includes a user management module, a push data analysis module, a behavior data collection module, an intelligent analysis module and an intelligent push module;

[0006] The user management module is used to provide a human-computer interaction interface, provide user login and identity authentication functions, and issue user operation instructions; the push data analysis module is used to store push data, classify push data by tags, and analyze the browsing time required for push data; the behavior data collection module is used to collect user operation behavior data and send the collected behavior data to the intelligent analysis module; the intelligent analysis module is used to analyze the collected behavior data, determine the current user's browsing preference content, and select corresponding push data according to the user's browsing preference; the intelligent push module is used to send the selected push data to the user management module.

[0007] According to the above technical solution, the user management module includes an interface operation unit, an information verification unit and an interface management unit;

[0008] The interface operation unit is used for the user to operate the human-machine interface, and to issue operation instructions for entering the interface, exiting the interface, jumping to the interface, and pushing data refresh;

[0009] The information verification unit is used to provide a user login interface and verify the security of user information;

[0010] The interface management unit is used to present the pushed data on the interface.

[0011] According to the above technical solution, the push data analysis module includes a push data content analysis unit, a push data classification unit and a push data storage unit;

[0012] The push data content analysis unit is used to analyze the push data content and determine the required browsing time of the push data;

[0013] The push data classification unit is used to classify the push data by tags according to the push data content;

[0014] The push data storage unit is used to store push data.

[0015] According to the above technical solution, the intelligent analysis module includes a data analysis unit, an intelligent control unit and a historical database;

[0016] The data analysis unit is used to analyze user preference content according to user operation behavior data, and select corresponding push data according to user preference;

[0017] The intelligent control unit is used to send the selected push data to the user management module;

[0018] The historical database is used to store the user's historical browsing push data and historical operation behavior data.

[0019] A user behavior analysis method based on data analysis, the method comprising the following steps:

[0020] S10, the user logs in through the login interface for identity authentication, and pushes corresponding push data to the user based on the user's historical browsing push data;

[0021] S20, collecting user operation behavior data, and sending the collected data to the intelligent analysis module for analysis; the operation behavior data includes the user's activity log and click stream data; the intelligent analysis module is used to determine the current user's browsing preference content, and select corresponding push data according to the user's browsing preference;

[0022] S30, based on the collected user operation behavior data and push data content, analyzing the proportion of the effective browsing time of the user's push data in the total browsing time required for the push data, and judging the user's preferences; according to the user's push data browsing preferences, the intelligent analysis module provides the user with personalized push data recommendations;

[0023] S40, the user clicks on the interface to perform a push data refresh operation, the intelligent analysis module refreshes the push data in the interface, and sends the recommended push data to the user management module; the user management module is used to provide a human-computer interaction interface, provide user login and identity authentication functions, and issue user operation instructions;

[0024] Among them, user operation instructions include entering the interface, exiting the interface, interface jumping and pushing data refreshing; according to the user's push data browsing preferences, the push data is divided into interested push data and uninterested push data.

[0025] The push data is divided into n types of tags; when the user passes the authentication login, the user's historical browsing push data is analyzed to obtain the historical effective browsing time A1, A2, ..., A of each type of tag push data. n ; Push data of each type of tag according to the historical effective browsing time of the push data in the form of A1: A2: ...: A n Proportional push;

[0026] Each piece of pushed data may correspond to one or more data type tags; n represents the number of pushed data type tags;

[0027] The push data is stored in a push data analysis module; the push data analysis module is used to store the push data, classify the push data by tags, and analyze the browsing time required for the push data;

[0028] Analyze the pushed data and determine the data tag type corresponding to each pushed data according to the content characteristics of the pushed data. The method steps are as follows:

[0029] S101, based on the pushed data, randomly select sample data from the pushed data, and mark the sample data label type;

[0030] S102: Based on the labeled sample data label type, a push data classification model is constructed, and the push data classification model is trained using the sample data; verification data is selected from the push data, and the push data classification model is re-optimized using the verification data;

[0031] S103: Input each piece of push data into the constructed push data classification model to obtain one or more data type labels corresponding to each piece of push data.

[0032] Analyze the proportion of effective browsing time of user push data to the total browsing time required for push data, and determine the user's preferences in the following steps:

[0033] S201, analyzing the user's historical browsing push data to obtain the behavior data when the user clicks to enter the push data browsing and performs the interface jump operation instruction; counting the time difference from the user entering the push data to the interface jump operation, analyzing the counted time difference, and obtaining the minimum threshold value T0 of the time interval from the start of browsing the push data to the interface jump when the user browses the push data;

[0034] S202, analyzing the user operation behavior data, adding time frames to the time points when the user enters the push data interface, exits the push data interface, and performs interface jump operations, and calculating the time interval between each time frame to obtain a set A; wherein A = {t1, t2, ..., t m}; t i represents the time interval between time frames in the corresponding i-th data; i = 1, 2, ..., m; m represents the number of data in set A;

[0035] S203, will t i Compare with T0; i The pushed data content corresponding to the time interval greater than T0 is regarded as the pushed data content segment of interest; i The push data corresponding to the time interval less than T0 is regarded as the push data content fragment of no interest;

[0036] S204: Determine the total browsing time T required for the push data corresponding to the push data content segment of interest 总 ; Push the data of interest in the time interval t i The time of the pushed data content segments greater than T0 is added together to obtain the effective total time t of the user browsing the pushed data of interest 总 ;

[0037] S205, calculating the proportion B of the effective browsing time corresponding to the pushed data in the total browsing time required for the pushed data; according to the formula:

[0038]

[0039] Since the total browsing time required for each push data is different, it is not rigorous to only analyze the total browsing time of users for push data of each tag type. By calculating the effective browsing time of users browsing the current push data and calculating the proportion of the effective browsing time in the total browsing time required for the push data, each push data is unitized, which can better analyze users' preferences for push data of different tag types.

[0040] In step S40, the intelligent analysis module provides personalized push data recommendation to the user in the following steps:

[0041] S301, analyzing the collected user operation behavior data, obtaining the number X of push data currently clicked and browsed by the user, and obtaining the browsing time T required for the corresponding x-th push data 总x ; Determine the effective browsing time t corresponding to the push data of Article x 总x ; Calculate the proportion of the effective browsing time corresponding to the xth push data in the total browsing time required for the push data B x ;

[0042] Wherein, x=1, 2, ..., X;

[0043] S302: classify the currently clicked push data into tags, determine the tag type corresponding to each push data, and determine the number of push data corresponding to each tag type. I ;

[0044] Where I = 1, 2, ..., n;

[0045] S303: Calculate the weight W corresponding to the first tag type I ; According to the formula:

[0046]

[0047] S304: according to the calculated weights corresponding to the tag types, when the user issues a push data refresh instruction, the push data corresponding to the tag types are updated in the order of W1: W2: ...: W n Push in proportion;

[0048] The effective browsing time of the pushed data of each tag type is unitized and accumulated to obtain the total effective browsing time of the pushed data of each tag type. By analyzing the proportion of the number of users' browsing of the pushed data of each tag type in the total number of pushed data browsing, the user's preference for the pushed data of each tag type is obtained. The preference for the pushed data of each tag type is multiplied by the total effective browsing time of the pushed data of each tag type to obtain the weight corresponding to each tag type. Data is pushed according to the ratio of the weights corresponding to each tag type, so that the pushed data content is more in line with the user.

[0049] When the user exits the user management interface, the collected user operation behavior data and browsing push data are stored as historical data in a history database; the history database is used to store the user's historical browsing push data and historical operation behavior data.

[0050] Compared with the prior art, the beneficial effects achieved by the present invention are: providing a user behavior analysis system and method based on data analysis, by analyzing the effective browsing time of users on pushed data, deleting the invalid time in the user's browsing push data, making the analysis of the user's preference for different pushed data more reliable; the mining of single data is more accurate, and comprehensive analysis of data from multiple angles is performed to improve the accuracy of data push. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0052] Figure 1 It is a structural schematic diagram of a user behavior analysis system based on data analysis of the present invention. DETAILED DESCRIPTION

[0053] 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.

[0054] See also Figure 1 , the present invention provides a technical solution: a user behavior analysis system based on data analysis, the system includes a user management module, a push data analysis module, a behavior data collection module, an intelligent analysis module and an intelligent push module;

[0055] The user management module is used to provide a human-computer interaction interface, provide user login and identity authentication functions, and issue user operation instructions; the push data analysis module is used to store push data, classify push data by tags, and analyze the browsing time required for push data; the behavior data collection module is used to collect user operation behavior data and send the collected behavior data to the intelligent analysis module; the intelligent analysis module is used to analyze the collected behavior data, determine the current user's browsing preference content, and select corresponding push data according to the user's browsing preference; the intelligent push module is used to send the selected push data to the user management module.

[0056] The user management module includes an interface operation unit, an information verification unit and an interface management unit;

[0057] The interface operation unit is used for the user to operate the human-machine interface, and to issue operation instructions for entering the interface, exiting the interface, jumping to the interface, and pushing data refresh;

[0058] The information verification unit is used to provide a user login interface and verify the security of user information;

[0059] The interface management unit is used to present the pushed data on the interface.

[0060] The push data analysis module includes a push data content analysis unit, a push data classification unit and a push data storage unit;

[0061] The push data content analysis unit is used to analyze the push data content and determine the required browsing time of the push data;

[0062] The push data classification unit is used to classify the push data by tags according to the push data content;

[0063] The push data storage unit is used to store push data.

[0064] The intelligent analysis module includes a data analysis unit, an intelligent control unit and a historical database;

[0065] The data analysis unit is used to analyze user preference content according to user operation behavior data, and select corresponding push data according to user preference;

[0066] The intelligent control unit is used to send the selected push data to the user management module;

[0067] The historical database is used to store the user's historical browsing push data and historical operation behavior data.

[0068] A user behavior analysis method based on data analysis, the method comprising the following steps:

[0069] S10, the user logs in through the login interface for identity authentication, and pushes corresponding push data to the user based on the user's historical browsing push data;

[0070] S20, collecting user operation behavior data, and sending the collected data to the intelligent analysis module for analysis; the operation behavior data includes the user's activity log and click stream data; the intelligent analysis module is used to determine the current user's browsing preference content, and select corresponding push data according to the user's browsing preference;

[0071] S30, based on the collected user operation behavior data and push data content, analyzing the proportion of the effective browsing time of the user's push data in the total browsing time required for the push data, and judging the user's preferences; according to the user's push data browsing preferences, the intelligent analysis module provides the user with personalized push data recommendations;

[0072] S40, the user clicks on the interface to perform a push data refresh operation, the intelligent analysis module refreshes the push data in the interface, and sends the recommended push data to the user management module; the user management module is used to provide a human-computer interaction interface, provide user login and identity authentication functions, and issue user operation instructions;

[0073] Among them, user operation instructions include entering the interface, exiting the interface, interface jumping and pushing data refreshing; according to the user's push data browsing preferences, the push data is divided into interested push data and uninterested push data.

[0074] The push data is divided into n types of tags; when the user passes the authentication login, the user's historical browsing push data is analyzed to obtain the historical effective browsing time A1, A2, ..., A of each type of tag push data. n ; Push data of each type of tag according to the historical effective browsing time of the push data in the form of A1: A2: ...: A n Proportional push;

[0075] Each piece of pushed data may correspond to one or more data type tags; n represents the number of pushed data type tags;

[0076] The push data is stored in a push data analysis module; the push data analysis module is used to store the push data, classify the push data by tags, and analyze the browsing time required for the push data;

[0077] Analyze the pushed data and determine the data tag type corresponding to each pushed data according to the content characteristics of the pushed data. The method steps are as follows:

[0078] S101, based on the pushed data, randomly select sample data from the pushed data, and mark the sample data label type;

[0079] S102: Based on the labeled sample data label type, a push data classification model is constructed, and the push data classification model is trained using the sample data; verification data is selected from the push data, and the push data classification model is re-optimized using the verification data;

[0080] S103: Input each piece of push data into the constructed push data classification model to obtain one or more data type labels corresponding to each piece of push data.

[0081] Analyze the proportion of effective browsing time of user push data to the total browsing time required for push data, and determine the user's preferences in the following steps:

[0082] S201, analyzing the user's historical browsing push data to obtain the behavior data when the user clicks to enter the push data browsing and performs the interface jump operation instruction; counting the time difference from the user entering the push data to the interface jump operation, analyzing the counted time difference, and obtaining the minimum threshold value T0 of the time interval from the start of browsing the push data to the interface jump when the user browses the push data;

[0083] S202, analyzing the user operation behavior data, adding time frames to the time points when the user enters the push data interface, exits the push data interface, and performs interface jump operations, and calculating the time interval between each time frame to obtain a set A; wherein A = {t1, t2, ..., t m}; t i represents the time interval between time frames in the corresponding i-th data; i = 1, 2, ..., m; m represents the number of data in set A;

[0084] S203, will t i Compare with T0; i The pushed data content corresponding to the time interval greater than T0 is regarded as the pushed data content segment of interest; i The push data corresponding to the time interval less than T0 is regarded as the push data content fragment of no interest;

[0085] S204: Determine the total browsing time T required for the push data corresponding to the push data content segment of interest 总 ; Push the data of interest in the time interval t i The time of the pushed data content segments greater than T0 is added together to obtain the effective total time t of the user browsing the pushed data of interest 总 ;

[0086] S205, calculating the proportion B of the effective browsing time corresponding to the pushed data in the total browsing time required for the pushed data; according to the formula:

[0087]

[0088] In step S40, the intelligent analysis module provides personalized push data recommendation to the user in the following steps:

[0089] S301, analyzing the collected user operation behavior data, obtaining the number X of push data currently clicked and browsed by the user, and obtaining the browsing time T required for the corresponding x-th push data 总x ; Determine the effective browsing time t corresponding to the push data of Article x 总x ; Calculate the proportion of the effective browsing time corresponding to the xth push data in the total browsing time required for the push data B x ;

[0090] Wherein, x=1, 2, ..., X;

[0091] S302: classify the currently clicked push data into tags, determine the tag type corresponding to each push data, and determine the number of push data corresponding to each tag type. I ;

[0092] Where I = 1, 2, ..., n;

[0093] S303: Calculate the weight W corresponding to the first tag type I ; According to the formula:

[0094]

[0095] S304: according to the calculated weights corresponding to the tag types, when the user issues a push data refresh instruction, the push data corresponding to the tag types are updated in the order of W1: W2: ...: W n push in proportion.

[0096] When the user exits the user management interface, the collected user operation behavior data and browsing push data are stored as historical data in a history database; the history database is used to store the user's historical browsing push data and historical operation behavior data.

[0097] In this embodiment:

[0098] The system is specifically a video data information push system; in the system, the push data tag types are divided into five types: A1, A2, A3, A4 and A5, and the corresponding user historical effective browsing time ratio is 1:1:1:1:1; the minimum threshold T0 of the time interval from the user browsing the push data to the interface jump is 5s;

[0099] The user logs in through the login interface for identity authentication. After successful login, data is pushed based on the user's historical browsing history, and data of each tag type is pushed in a ratio of 1:1:1:1:1;

[0100] Collect user operation behavior data and analyze to find that the number of push data X currently clicked and browsed by the user is 5; the browsing time T required for each push data is 40s, 50s, 60s, 70s, and 80s respectively; the effective browsing time t corresponding to each push data is 20s, 25s, 30s, 35s, and 40s respectively;

[0101] Input each piece of push data into the constructed push data classification model to obtain the type label corresponding to each piece of push data; the number of push data corresponding to each label type is 1, 2, 3, 2, and 1 respectively;

[0102] Calculate the weight corresponding to each label type; according to the formula:

[0103]

[0104] The weight values ​​corresponding to each label type are calculated to be 1 / 18, 2 / 9, 1 / 2, 2 / 9, and 1 / 18 respectively;

[0105] When the user clicks on the interface to refresh the push data, the intelligent analysis module refreshes the push data in the interface and sends the recommended push data to the user management module in a ratio of 1:4:9:4:1 according to the push data tag type;

[0106] When the user exits the user management interface, the collected user operation behavior data and browsing push data are stored in the history database as historical data.

[0107] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0108] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A user behavior analysis method based on data analysis, characterized in that: The method comprises the following steps: S10, the user logs in through the login interface for identity authentication, and pushes corresponding push data to the user based on the user's historical browsing push data; S20, collecting user operation behavior data, and sending the collected data to the intelligent analysis module for analysis; the operation behavior data includes the user's activity log and click stream data; the intelligent analysis module is used to determine the current user's browsing preference content, and select corresponding push data according to the user's browsing preference; S30, based on the collected user operation behavior data and push data content, analyzing the proportion of the effective browsing time of the user's push data in the total browsing time required for the push data, and judging the user's preferences; according to the user's push data browsing preferences, the intelligent analysis module provides the user with personalized push data recommendations; S40, the user clicks on the interface to perform a push data refresh operation, the intelligent analysis module refreshes the push data in the interface, and sends the recommended push data to the user management module; the user management module is used to provide a human-computer interaction interface, provide user login and identity authentication functions, and issue user operation instructions; Among them, user operation instructions include entering the interface, exiting the interface, interface jump and push data refresh; push data is divided into interested push data and uninterested push data according to the user's push data browsing preferences; The push data is divided into n types of tags; when the user passes the authentication login, the user's historical browsing push data is analyzed to obtain the historical effective browsing time A1, A2, ..., A of each type of tag push data. n ; Push data of each type of tag according to the historical effective browsing time of the push data in the form of A1: A2: ...: A n Proportional push; Each piece of pushed data may correspond to one or more data type tags; n represents the number of pushed data type tags; The push data is stored in a push data analysis module; the push data analysis module is used to store the push data, classify the push data by tags, and analyze the browsing time required for the push data; Analyze the pushed data and determine the data tag type corresponding to each pushed data according to the content characteristics of the pushed data. The method steps are as follows: S101, based on the pushed data, randomly select sample data from the pushed data, and mark the sample data label type; S102: Based on the labeled sample data label type, a push data classification model is constructed, and the push data classification model is trained using the sample data; verification data is selected from the push data, and the push data classification model is re-optimized using the verification data; S103, inputting each piece of pushed data into the constructed push data classification model to obtain one or more data type labels corresponding to each piece of pushed data; Analyze the proportion of effective browsing time of user push data to the total browsing time required for push data, and determine the user's preferences in the following steps: S201, analyzing the user's historical browsing push data to obtain the behavior data when the user clicks to enter the push data browsing and performs the interface jump operation instruction; counting the time difference from the user entering the push data to the interface jump operation, analyzing the counted time difference, and obtaining the minimum threshold value T0 of the time interval from the start of browsing the push data to the interface jump when the user browses the push data; S202, analyzing the user operation behavior data, adding time frames to the time points when the user enters the push data interface, exits the push data interface, and performs interface jump operations, and calculating the time interval between each time frame to obtain a set A; wherein A = {t1, t2, ..., t m }; t i represents the time interval between time frames in the corresponding i-th data; i = 1, 2, ..., m; m represents the number of data in set A; S203, will t i Compare with T0; i The pushed data content corresponding to the time interval greater than T0 is regarded as the pushed data content segment of interest; i The push data corresponding to the time interval less than T0 is regarded as the push data content fragment of no interest; S204: Determine the total browsing time T required for the push data corresponding to the push data content segment of interest 总 ; Push the data of interest in the time interval t i The time of the pushed data content segments greater than T0 is added together to obtain the effective total time t of the user browsing the pushed data of interest 总 ; S205, calculating the proportion B of the effective browsing time corresponding to the pushed data in the total browsing time required for the pushed data; according to the formula: In step S40, the intelligent analysis module provides personalized push data recommendation to the user in the following steps: S301, analyzing the collected user operation behavior data, obtaining the number X of push data currently clicked and browsed by the user, and obtaining the browsing time T required for the corresponding x-th push data 总x ; Determine the effective browsing time t corresponding to the push data of Article x 总x ; Calculate the proportion of the effective browsing time corresponding to the xth push data in the total browsing time required for the push data B x ; Wherein, x=1, 2, ..., X; S302: classify the currently clicked push data into tags, determine the tag type corresponding to each push data, and determine the number of push data corresponding to each tag type. I ; Where I = 1, 2, ..., n; S303: Calculate the weight W corresponding to the first tag type I ; According to the formula: S304: according to the calculated weights corresponding to the tag types, when the user issues a push data refresh instruction, the push data corresponding to the tag types are updated in the order of W1: W2: ...: W n ratio for push.

2. The user behavior analysis method based on data analysis according to claim 1, characterized in that: When the user exits the user management interface, the collected user operation behavior data and browsing push data are stored as historical data in a history database; the history database is used to store the user's historical browsing push data and historical operation behavior data.

3. A user behavior analysis system based on data analysis, applying a user behavior analysis method based on data analysis as described in any one of claims 1-2, characterized in that: The system includes a user management module, a push data analysis module, a behavior data collection module, an intelligent analysis module and an intelligent push module; The user management module is used to provide a human-computer interaction interface, provide user login and identity authentication functions, and issue user operation instructions; the push data analysis module is used to store push data, classify push data by tags, and analyze the browsing time required for push data; The behavior data collection module is used to collect user operation behavior data and send the collected behavior data to the intelligent analysis module; the intelligent analysis module is used to analyze the collected behavior data, determine the current user's browsing preference content, and select corresponding push data based on the user's browsing preference; the intelligent push module is used to send the selected push data to the user management module.

4. The user behavior analysis system based on data analysis according to claim 3, characterized in that: The user management module includes an interface operation unit, an information verification unit and an interface management unit; The interface operation unit is used for the user to operate the human-machine interface, and to issue operation instructions for entering the interface, exiting the interface, jumping to the interface, and pushing data refresh; The information verification unit is used to provide a user login interface and verify the security of user information; The interface management unit is used to present the pushed data on the interface.

5. The user behavior analysis system based on data analysis according to claim 3, characterized in that: The push data analysis module includes a push data content analysis unit, a push data classification unit and a push data storage unit; The push data content analysis unit is used to analyze the push data content and determine the required browsing time of the push data; The push data classification unit is used to classify the push data by tags according to the push data content; The push data storage unit is used to store push data.

6. The user behavior analysis system based on data analysis according to claim 4, characterized in that: The intelligent analysis module includes a data analysis unit, an intelligent control unit and a historical database; The data analysis unit is used to analyze user preference content according to user operation behavior data, and select corresponding push data according to user preference; The intelligent control unit is used to send the selected push data to the user management module; The historical database is used to store the user's historical browsing push data and historical operation behavior data.

Images