A user behavior analysis system and method based on AI intelligent recognition

Abstract

The present invention provides a user behavior analysis system based on AI intelligent recognition, including an action analysis module, a back-end processing module, a mobile phone data statistics module and a map data statistics module; the action analysis module is connected to the back-end processing module, and is used to process the results of the analysis through the back-end processing module; the mobile phone data statistics module and the map data statistics module are both connected to the action analysis module, and are used to provide data support for the action analysis module; the action analysis module includes a motion analysis unit and an operation analysis unit. The present invention can facilitate the identification of the user's motion trajectory, and can determine the user's active and home-staying phenomena in certain time periods, so as to solve the problem that the existing user behavior analysis is relatively single, and it is relatively simple to obtain the user's software habits but cannot well understand the user's other behaviors, and cannot determine the user's activeness in motion and the activeness and active time period at home.

Description

Technical Field

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

[0002] With the popularization of smart devices, operators need to analyze the behavior of each user in order to obtain more favorable data, so as to ensure that users are more comfortable in many subsequent experiences, make recommendations more accurate, and improve users' quality of life.

[0003] In the existing technology, the user behavior analysis is relatively simple. After simply obtaining the user's software habits, it is not possible to understand the user's other behaviors well, and it is not possible to judge the user's activity level and active time period at home, and thus it is impossible to make better recommendations and help to the user. Summary of the invention

[0004] In view of the shortcomings of the prior art, the purpose of the present invention is to provide a user behavior analysis system and method based on AI intelligent recognition, which can facilitate the identification of the user's movement trajectory and determine the user's active and home-based time periods, so as to solve the problem that the existing user behavior analysis is relatively single, and it is relatively simple to obtain the user's software habits but cannot fully understand the user's other behaviors, and cannot determine the user's active movement and home activity and active time period.

[0005] In order to achieve the above-mentioned purpose, the present invention is implemented through the following technical solutions: a user behavior analysis system based on AI intelligent recognition, including an action analysis module, a back-end processing module, a mobile phone data statistics module and a map data statistics module;

[0006] The action analysis module is connected to the back-end processing module and is used to process the analysis results through the back-end processing module;

[0007] The mobile phone data statistics module and the map data statistics module are both connected to the action analysis module to provide data support for the action analysis module;

[0008] The action analysis module includes a motion analysis unit and an operation analysis unit. The motion analysis unit is used to obtain the user's action trajectory and mileage, and analyze and classify the action trajectory and mileage. The operation analysis unit is used to obtain the software operation habit behavior of the home user, and analyze and classify the software operation habit behavior.

[0009] Further, the motion analysis unit is configured with an active motion analysis strategy, which is used to count and calculate the data of the user's daily moving position in the user's map data statistics module, and the active motion analysis strategy includes: counting the mileage moved every day in the map data statistics module, separating and counting the mileage of each time period, and then taking out the data of the mileage of each time period to perform statistical analysis of changes within a week, taking out the necessary mileage of the work place every day and multiplying it by the number of working days for statistics, and then adding and counting the actual mileage moved every day and subtracting the necessary mileage to obtain the active value;

[0010] The active exercise analysis strategy is configured with an exercise activity value algorithm, and the user's weekly exercise activity can be calculated through the exercise activity value algorithm.

[0011] Furthermore, the sports activity value algorithm is configured as Zh=(Z1+Z2+......+Z7)-(Gz×Gt), wherein Zh is the amount of sports activity, Z1 is the action mileage on Monday, Z2 is the action mileage on Tuesday, and similarly Z7 is the action mileage on Sunday, Gz is the necessary mileage for work, and Gt is the number of working days.

[0012] Furthermore, the motion analysis unit is also configured with an hourly segment motion analysis strategy, which includes: adding and counting the mileage data of active hours each day, then comparing the mileage data, counting the most active hours each day, and arranging the more active hours and inactive hours in turn.

[0013] Furthermore, the operation analysis unit includes an operation analysis strategy, which includes: calling out the user usage time data counted in the mobile phone data statistics module, obtaining the user's most frequently used mobile phone software based on the usage time, and obtaining the user's normal behavior.

[0014] Furthermore, the operation analysis strategy also includes an operation period detection strategy, and the operation period detection strategy includes: applying the commonly used mobile phone software obtained through analysis to count the usage time period from Monday to Sunday.

[0015] Furthermore, the map data statistics module is connected to the motion analysis unit, and is used to obtain statistics of the user's frequently visited areas, activity ranges, and bias types. The frequently visited areas can be used to obtain the scenic spots, shopping malls, and entertainment venues in the map data statistics module, and the number of times and time of going out in order can be obtained to obtain more accurate data. At the same time, the user's activity range and bias type can be determined through the frequently visited areas;

[0016] If the user is very active in physical exercise, we can judge based on the areas he or she frequently visits that the user is good at traveling or likes shopping. This way, we can get the user's accurate behavior and make recommendations to help him or her take action.

[0017] Furthermore, the back-end processing module takes out the data analyzed by the motion analysis unit. If the user's motion activity is large, the user's behavior is judged by the areas he frequently visits. If it is judged that the user frequently visits scenic spots in a certain period of time, data recommendations can be made to the user during the period when the user frequently visits scenic spots. If it is judged that the user frequently visits shopping malls in a certain period of time, the user can recommend the necessary items and activities to the shopping mall during the period when the user goes to the shopping mall. If it is judged that the user frequently visits entertainment venues in a certain period of time, the necessary items can be recommended to the user. If the activity is small, the operation analysis unit can be used to obtain the types of software frequently used by the user and the time period of use, so as to know what time period the user needs and likes to operate the app, and at the same time, auxiliary recommendations can be made or assistance can be provided.

[0018] Furthermore, the method comprises the following steps:

[0019] S1, using the mobile phone data statistics module to count the user's software operation behavior and the map data statistics module to obtain the user's usual walking range;

[0020] S2, analyzing the user's software operation data and the user's usual walking range data through the action analysis module to obtain the user's active exercise time period, active exercise range and commonly used mobile phone software;

[0021] S3, the acquired active time period, active exercise range and frequently used mobile phone software data are classified into the user's behavior trend through the back-end processing module.

[0022] Beneficial effects of the present invention: The present invention obtains the user's usual walking range by counting the user's software operation behavior through a mobile phone data statistics module and the user's usual walking range through a map data statistics module, and analyzes the user's software operation data and the user's usual walking range data through an action analysis module to obtain the user's active exercise time period, active exercise range and commonly used mobile phone software. The obtained active time period, active exercise range and commonly used mobile phone software data are classified into the user's behavior trend through a back-end processing module, thereby improving the accuracy of behavior analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0024] Figure 1 It is a system principle block diagram of the present invention;

[0025] Figure 2 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0026] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.

[0027] See also Figure 1 , Figure 1 It is a system principle block diagram of the present invention.

[0028] A user behavior analysis system and method based on AI intelligent recognition, including an action analysis module, a back-end processing module, a mobile phone data statistics module and a map data statistics module. The action analysis module is connected to the back-end processing module and is used to process the analysis results through the back-end processing module. The mobile phone data statistics module and the map data statistics module are both connected to the action analysis module to provide data support for the action analysis module. The action analysis module includes a motion analysis unit and an operation analysis unit. The motion analysis unit is used to obtain the user's action trajectory and mileage, and analyze and classify the action trajectory and mileage. The operation analysis unit is used to obtain the software operation habit behavior of the home user, and analyze and classify the software operation habit behavior.

[0029] See also Figure 2 , Figure 2 The figure is a flow chart of the method of the present invention.

[0030] The motion analysis unit is configured with an active motion analysis strategy, which is used to count and calculate the data of the user's daily moving position in the user's map data statistics module. The active motion analysis strategy includes: counting the mileage moved every day in the map data statistics module, separating and counting the mileage of each time period, and then taking out the data of the mileage of each time period to perform statistical analysis of changes within a week, taking out the necessary mileage of the work place every day and multiplying it by the number of working days for statistics, and then adding and counting the actual mileage moved every day and subtracting the necessary mileage to obtain an active value;

[0031] The active exercise analysis strategy is configured with an exercise activity value algorithm, and the user's weekly exercise activity can be calculated through the exercise activity value algorithm.

[0032] The sports activity value algorithm is configured as Zh=(Z1+Z2+......+Z7)-(Gz×Gt), where Zh is the sports activity amount, Z1 is the action mileage on Monday, Z2 is the action mileage on Tuesday, and similarly Z7 is the action mileage on Sunday, Gz is the necessary mileage for work, and Gt is the number of working days.

[0033] The motion analysis unit is also configured with an hourly segment motion analysis strategy, which includes: adding and counting the mileage data of active hours every day, then comparing the mileage data, counting the most active hours every day, and arranging the more active hours and the inactive hours in turn.

[0034] The operation analysis unit includes an operation analysis strategy, which includes: calling out user usage time data counted in the mobile phone data statistics module, obtaining the user's most frequently used mobile phone software according to the usage time, and obtaining the user's normal behavior.

[0035] The operation analysis strategy also includes an operation period detection strategy, which includes: applying the commonly used mobile phone software obtained through analysis to count the usage time period from Monday to Sunday.

[0036] The map data statistics module is connected to the motion analysis unit and is used to obtain statistics on the user's frequently visited areas, activity ranges, and bias types. The frequently visited areas can be used to obtain the scenic spots, shopping malls, and entertainment venues in the map data statistics module. The number of times and time of going out in order can be obtained to obtain more accurate data. At the same time, the user's activity range and bias type can be determined through the frequently visited areas.

[0037] If the user is very active in physical exercise, we can judge based on the areas he or she frequently visits that the user is good at traveling or likes shopping. This way, we can get the user's accurate behavior and make recommendations to help him or her take action.

[0038] The back-end processing module takes out the data analyzed by the motion analysis unit. If the amount of motion activity is large, the user behavior is judged by the frequently visited areas. If it is judged that the user frequently visits scenic spots in a certain period of time, data recommendations can be made to the user during the time periods when the user frequently visits scenic spots. If it is judged that the user frequently visits shopping malls in a certain period of time, the items and activities that the user needs or is necessary to go to the shopping malls can be recommended to the user during the time periods when the user goes to the shopping malls. If it is judged that the user frequently visits entertainment venues in a certain period of time, the items that the user needs and is necessary can be recommended to the user. If the amount of activity is small, the types of software frequently used by the user and the time periods of use can be obtained through the operation analysis unit, so as to know what time periods the user needs and likes to operate apps, and auxiliary recommendations can be made or assistance can be provided.

[0039] S1, using the mobile phone data statistics module to count the user's software operation behavior and the map data statistics module to obtain the user's usual walking range;

[0040] S2, analyzing the user's software operation data and the user's usual walking range data through the motion analysis unit of the action analysis module to obtain the user's active exercise time period and active exercise range, and then analyzing the operation analysis unit to obtain the usage time period of commonly used mobile phone software;

[0041] S3, the acquired active time period, active exercise range and frequently used mobile phone software data are classified into the user's behavior trend through the back-end processing module.

[0042] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the attached claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved.

[0043] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A user behavior analysis system based on AI intelligent recognition, including an action analysis module, a backend processing module, a mobile phone data statistics module and a map data statistics module; The action analysis module is connected to the back-end processing module and is used to process the analysis results through the back-end processing module; The mobile phone data statistics module and the map data statistics module are both connected to the action analysis module to provide data support for the action analysis module; The action analysis module includes a motion analysis unit and an operation analysis unit. The motion analysis unit is used to obtain the user's action trajectory and mileage, and analyze and classify the action trajectory and mileage. The operation analysis unit is used to obtain the software operation habit behavior of the home user, and analyze and classify the software operation habit behavior. The motion analysis unit is configured with an active motion analysis strategy, which is used to count and calculate the data of the user's daily moving position in the user's map data statistics module, and the active motion analysis strategy includes: Count the mileage of each day in the map data statistics module, separate the mileage of each time period, and then extract the mileage data of each time period for statistical analysis of changes within a week. Take out the necessary mileage of the work place every day and multiply it by the number of working days for statistics, and then add and subtract the necessary mileage to get the activity value; The active sports analysis strategy is configured with a sports activity value algorithm, and the user's weekly sports activity can be calculated by the sports activity value algorithm; The sports activity value algorithm is configured as Zh=(Z 1 +Z 2 +......+Z 7 )-(Gz×Gt), where Zh is the sports activity amount, Z1 is the action mileage on Monday, Z2 is the action mileage on Tuesday, and similarly Z7 is the action mileage on Sunday, Gz is the necessary mileage for work, and Gt is the number of working days; The motion analysis unit is also configured with an hourly segment motion analysis strategy, which includes: adding and counting the mileage data of active hours every day, then comparing the mileage data, counting the most active hours every day, and excluding the more active hours and the less active hours in turn; The operation analysis unit includes an operation analysis strategy, which includes: calling out the user usage time data counted in the mobile phone data statistics module, obtaining the user's most commonly used mobile phone software according to the usage time, and obtaining the user's normal behavior; The operation analysis strategy also includes an operation period detection strategy, which includes: applying the commonly used mobile phone software obtained through analysis to count the usage time period from Monday to Sunday; The back-end processing module takes out the data analyzed by the motion analysis unit. If the amount of motion activity is large, the user behavior is judged by the frequently visited areas. If it is judged that the user frequently visits scenic spots in a certain period of time, data recommendations can be made to the user during the time periods when the user frequently visits scenic spots. If it is judged that the user frequently visits shopping malls in a certain period of time, the items and activities that the user needs or is necessary to go to the shopping malls can be recommended to the user during the time periods when the user goes to the shopping malls. If it is judged that the user frequently visits entertainment venues in a certain period of time, the items that the user needs and is necessary can be recommended to the user. If the amount of activity is small, the types of software frequently used by the user and the time periods of use can be obtained through the operation analysis unit, so as to know what time periods the user needs and likes to operate apps, and auxiliary recommendations can be made or assistance can be provided.

2. The user behavior analysis system based on AI intelligent recognition according to claim 1 is characterized by: The map data statistics module is connected to the motion analysis unit and is used to obtain statistics on the user's frequently visited areas, activity ranges, and bias types. The frequently visited areas can be used to obtain the scenic spots, shopping malls, and entertainment venues in the map data statistics module. The number of times and time of going out in order can be obtained to obtain more accurate data. At the same time, the user's activity range and bias type can be determined through the frequently visited areas. If the user is very active in physical exercise, we can judge based on the areas he or she frequently visits that the user is good at traveling or likes shopping. This way, we can get the user's accurate behavior and make recommendations to help him or her take action.

3. A method for user behavior analysis system based on AI intelligent recognition according to claim 1 or 2, characterized in that: The method steps are as follows: S1, using the mobile phone data statistics module to count the user's software operation behavior and the map data statistics module to obtain the user's usual walking range; S2, analyzing the user's software operation data and the user's usual walking range data through the action analysis module to obtain the user's active exercise time period, active exercise range and commonly used mobile phone software; S3, the acquired active time period, active exercise range and commonly used mobile phone software data are classified into the user's behavior trend through the back-end processing module.

Images