Self-service police service terminal user behavior analysis method and system based on artificial intelligence and medium

Abstract

The embodiment of the invention provides a self-service police service terminal user behavior analysis method and system based on artificial intelligence and a medium, and the method comprises the steps: capturing a user real-time operation image based on a visual recognition technology, extracting features of the user real-time operation image, and recognizing user operation behavior information; analyzing the user operation behavior information based on a deep learning algorithm to obtain a user behavior pattern; comparing the user behavior mode with a set behavior mode to obtain a comparison result; analyzing a user operation error behavior based on a comparison result to obtain user operation error information; establishing an expert database based on the user operation manual, and generating an operation prompt and an optimization suggestion for the user operation error information according to the expert database; the user operation behavior is analyzed in real time, and the user operation error information is modified and optimized, so that the user operation accuracy is improved, the operation error is reduced, and the convenience and safety of self-service are improved.

Description

Technical Field

[0001] The present application relates to the technical field of user behavior analysis, and more specifically, to a method, system and medium for analyzing user behavior of a self-service police terminal based on artificial intelligence. Background Art

[0002] Currently, the processing of certificates such as driver's license, vehicle registration, temporary license plate, and certificate of qualification requires the cooperation of the police and the public. If one party fails to respond in time, it will delay the processing time, which is greatly disadvantageous to both parties. Moreover, users who apply for certificates often have to wait for a long time to get the relevant certificates.

[0003] Although self-service data entry equipment has appeared on the market, which has accelerated the process to a certain extent, the existing police terminals are unable to accurately identify user behavior. It is also difficult to analyze erroneous behavior based on the identified behavior and modify and optimize it in real time, and user operation errors are frequent. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a method, system and medium for analyzing user behavior of a self-service police terminal based on artificial intelligence. By analyzing user operation behavior in real time and modifying and optimizing user operation error information, it helps to improve user operation accuracy, reduce operation errors, and enhance the convenience and safety of self-service.

[0005] The embodiment of the present application also provides a method for analyzing user behavior of a self-service police terminal based on artificial intelligence, including:

[0006] Capture the user's real-time operation images based on visual recognition technology, extract features from the user's real-time operation images, and identify the user's operation behavior information;

[0007] Analyze user operation behavior information based on deep learning algorithms to obtain user behavior patterns;

[0008] Compare the user behavior pattern with the set behavior pattern to obtain a comparison result;

[0009] Analyze the user's operation error behavior based on the comparison result to obtain the user's operation error information;

[0010] An expert database is established based on the user manual, and operation prompts and optimization suggestions are generated based on the expert database for user operation error information.

[0011] Optionally, in the method for analyzing user behavior of a self-service police terminal based on artificial intelligence described in the embodiment of the present application, capturing the real-time operation image of the user based on visual recognition technology, extracting features from the real-time operation image of the user, and identifying the user operation behavior information specifically include:

[0012] Establish a collection time window, and set a number of collection time nodes with equal time intervals within the collection time window;

[0013] The camera captures the user's real-time operation image corresponding to each acquisition time node;

[0014] Extract features from the user's real-time operation images captured at each acquisition time node;

[0015] Analyze the sequence of user operation behaviors based on the time sequence of the collected time nodes;

[0016] Analyze user operation behavior information based on the user operation behavior sequence.

[0017] Optionally, in the method for analyzing user behavior of a self-service police terminal based on artificial intelligence described in the embodiment of the present application, the user operation behavior information is analyzed based on a deep learning algorithm to obtain a user behavior pattern, which specifically includes:

[0018] Obtain historical user operation behavior data and establish a training set;

[0019] Select an initial learning model, train the initial learning model based on the training set, and obtain a training result;

[0020] Determining whether the training result converges;

[0021] If convergence occurs, a deep learning model is generated, and the user operation behavior information is analyzed based on the deep learning model to obtain the user behavior pattern;

[0022] If it does not converge, the training data in the training set is adjusted, and the initial model is trained again according to the adjusted training data until the training results converge.

[0023] Optionally, in the method for analyzing user behavior of a self-service police terminal based on artificial intelligence described in the embodiment of the present application, the user behavior pattern is compared with a set behavior pattern to obtain a comparison result, which specifically includes:

[0024] Obtain user behavior patterns, compare the user behavior patterns with the set behavior patterns, and obtain behavior difference information;

[0025] Compare the behavior difference information with the set difference information to obtain the difference deviation rate;

[0026] If the difference deviation rate is greater than the first difference deviation rate and less than the second difference deviation rate, a first difference result is generated, and a first comparison result is generated based on the first difference result;

[0027] If the difference deviation rate is greater than or equal to the second difference deviation rate, a second comparison result is generated.

[0028] Optionally, in the method for analyzing user behavior of a self-service police terminal based on artificial intelligence described in the embodiment of the present application, analyzing the user operation error behavior based on the comparison result to obtain the user operation error information specifically includes:

[0029] Obtain the operation tasks of the self-service police terminal and set standard behavior information based on the operation tasks;

[0030] Obtain the comparison results, analyze the user's operation behavior and compare it with the standard behavior information based on the comparison results, and obtain the behavior deviation rate;

[0031] Determining whether the behavior deviation rate is greater than or equal to a set behavior deviation rate threshold;

[0032] If it is greater than or equal to, a user operation error behavior is generated and user operation error information is obtained;

[0033] If it is less than, the real-time user operation behavior is monitored in real time.

[0034] Optionally, in the method for analyzing user behavior of a self-service police terminal based on artificial intelligence described in the embodiment of the present application, an expert database is established based on the user operation manual, and operation prompts and optimization suggestions are generated for user operation error information according to the expert database, specifically including:

[0035] Obtain the user operation manual, and obtain the user's standard operation behavior according to the user operation manual;

[0036] Establish an expert database based on user standard behavior;

[0037] Obtain user operation behavior information, analyze the user operation behavior information with data in the expert database, and obtain user operation error information;

[0038] Provide correct operation prompts and optimization suggestions based on user operation error information.

[0039] In a second aspect, an embodiment of the present application provides a user behavior analysis system for a self-service police terminal based on artificial intelligence, the system comprising: a memory and a processor, the memory comprising a program of a user behavior analysis method for a self-service police terminal based on artificial intelligence, the program of the user behavior analysis method for a self-service police terminal based on artificial intelligence when executed by the processor implements the following steps: capturing a real-time operation image of a user based on visual recognition technology, extracting features from the real-time operation image of the user, and identifying user operation behavior information;

[0040] Analyze user operation behavior information based on deep learning algorithms to obtain user behavior patterns;

[0041] Compare the user behavior pattern with the set behavior pattern to obtain a comparison result;

[0042] Analyze the user's operation error behavior based on the comparison result to obtain the user's operation error information;

[0043] An expert database is established based on the user manual, and operation prompts and optimization suggestions are generated based on the expert database for user operation error information.

[0044] Optionally, in the user behavior analysis system of the self-service police terminal based on artificial intelligence described in the embodiment of the present application, capturing the real-time operation image of the user based on visual recognition technology, extracting features from the real-time operation image of the user, and identifying the user operation behavior information specifically include:

[0045] Establish a collection time window, and set a number of collection time nodes with equal time intervals within the collection time window;

[0046] The camera captures the user's real-time operation image corresponding to each acquisition time node;

[0047] Extract features from the user's real-time operation images captured at each acquisition time node;

[0048] Analyze the sequence of user operation behaviors based on the time sequence of the collected time nodes;

[0049] Analyze user operation behavior information based on the user operation behavior sequence.

[0050] Optionally, in the user behavior analysis system of the self-service police terminal based on artificial intelligence described in the embodiment of the present application, the user operation behavior information is analyzed based on a deep learning algorithm to obtain a user behavior pattern, which specifically includes:

[0051] Obtain historical user operation behavior data and establish a training set;

[0052] Select an initial learning model, train the initial learning model based on the training set, and obtain a training result;

[0053] Determining whether the training result converges;

[0054] If convergence occurs, a deep learning model is generated, and the user operation behavior information is analyzed based on the deep learning model to obtain the user behavior pattern;

[0055] If it does not converge, the training data in the training set is adjusted, and the initial model is trained again according to the adjusted training data until the training results converge.

[0056] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium includes a self-service police terminal user behavior analysis method program based on artificial intelligence. When the self-service police terminal user behavior analysis method program based on artificial intelligence is executed by a processor, the steps of the self-service police terminal user behavior analysis method based on artificial intelligence as described in any one of the above items are implemented.

[0057] As can be seen from the above, the embodiment of the present application provides a method, system and medium for analyzing user behavior of a self-service police terminal based on artificial intelligence. By capturing real-time operation images of users based on visual recognition technology, features are extracted from real-time operation images of users, and user operation behavior information is identified; user operation behavior information is analyzed based on a deep learning algorithm to obtain user behavior patterns; the user behavior patterns are compared with set behavior patterns to obtain comparison results; user operation error behaviors are analyzed based on the comparison results to obtain user operation error information; an expert database is established based on the user operation manual, and operation prompts and optimization suggestions are generated for user operation error information according to the expert database; by analyzing user operation behaviors in real time and modifying and optimizing user operation error information, it helps to improve user operation accuracy, reduce operation errors, and enhance the convenience and safety of self-service. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0059] Figure 1 A flowchart of a method for analyzing user behavior of a self-service police terminal based on artificial intelligence provided in an embodiment of the present application;

[0060] Figure 2 A flow chart of a method for identifying user operation behavior information of a user behavior analysis method for a self-service police terminal based on artificial intelligence provided in an embodiment of the present application;

[0061] Figure 3 A flow chart of a deep learning model training method for an artificial intelligence-based self-service police terminal user behavior analysis method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0062] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0063] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0064] Please refer to Figure 1 , Figure 1 The flowchart of a method for analyzing user behavior of a self-service police terminal based on artificial intelligence in some embodiments of the present application is shown in FIG. The method for analyzing user behavior of a self-service police terminal based on artificial intelligence is used in a terminal device, and the method for analyzing user behavior of a self-service police terminal based on artificial intelligence includes the following steps:

[0065] S101, capturing a user's real-time operation image based on visual recognition technology, extracting features from the user's real-time operation image, and identifying user operation behavior information;

[0066] S102, analyzing the user operation behavior information based on a deep learning algorithm to obtain a user behavior pattern;

[0067] S103, comparing the user behavior pattern with the set behavior pattern to obtain a comparison result;

[0068] S104, analyzing the user's operation error behavior based on the comparison result to obtain user operation error information;

[0069] S105, establishing an expert database based on the user operation manual, and generating operation prompts and optimization suggestions for user operation error information according to the expert database.

[0070] It should be noted that visual recognition technology (camera) is used to capture real-time images of users' real-time operations in front of police terminals, and the images are analyzed, processed and compared to analyze whether the user has made any operational errors, so as to provide timely operational prompts and optimization suggestions for erroneous operations and improve the intelligence of police terminals.

[0071] Please refer to Figure 2 , Figure 2 This is a flowchart of a method for identifying user operation behavior information of a self-service police terminal user behavior analysis method based on artificial intelligence in some embodiments of the present application. According to an embodiment of the present invention, based on visual recognition technology, real-time user operation images are captured, features are extracted from real-time user operation images, and user operation behavior information is identified, specifically including:

[0072] S201, establishing a collection time window, and setting a number of collection time nodes with equal time intervals within the collection time window;

[0073] S202, capturing a real-time user operation image corresponding to each acquisition time node by a camera;

[0074] S203, extracting features from the user's real-time operation image captured at each acquisition time node;

[0075] S204, analyzing the user operation behavior sequence according to the time sequence of the collection time nodes;

[0076] S205: Analyze the user operation behavior information based on the user operation behavior sequence.

[0077] It should be noted that by analyzing the real-time operation images of users at adjacent time nodes and extracting features, the user's dynamic operation behavior can be obtained in the order of the acquisition time nodes, thereby accurately analyzing the user behavior.

[0078] Please refer to Figure 3 , Figure 3 This is a flow chart of a deep learning model training method for a self-service police terminal user behavior analysis method based on artificial intelligence in some embodiments of the present application. According to an embodiment of the present invention, the user operation behavior information is analyzed based on a deep learning algorithm to obtain a user behavior pattern, which specifically includes:

[0079] S301, obtaining historical user operation behavior data and establishing a training set;

[0080] S302, selecting an initial learning model, and training the initial learning model based on a training set to obtain a training result;

[0081] S303, determining whether the training result has converged;

[0082] S304: if converged, generate a deep learning model, analyze the user operation behavior information based on the deep learning model, and obtain the user behavior pattern;

[0083] S305: If it does not converge, the training data in the training set is adjusted, and the initial model is trained again according to the adjusted training data until the training result converges.

[0084] It should be noted that by constructing a training set to continuously train the model, the output accuracy of the deep learning model can be improved, making the deep learning model more and more accurate in analyzing user operation behavior and preventing analysis errors.

[0085] According to an embodiment of the present invention, the user behavior pattern is compared with the set behavior pattern to obtain a comparison result, which specifically includes:

[0086] Obtain user behavior patterns, compare the user behavior patterns with the set behavior patterns, and obtain behavior difference information;

[0087] Compare the behavior difference information with the set difference information to obtain the difference deviation rate;

[0088] If the difference deviation rate is greater than the first difference deviation rate and less than the second difference deviation rate, a first difference result is generated, and a first comparison result is generated based on the first difference result;

[0089] If the difference deviation rate is greater than or equal to the second difference deviation rate, a second comparison result is generated.

[0090] It should be noted that by analyzing user behavior patterns, different behavior difference information obtains different difference results, thereby accurately comparing and analyzing user behavior patterns and improving analysis accuracy.

[0091] According to an embodiment of the present invention, the user operation error behavior is analyzed based on the comparison result to obtain the user operation error information, which specifically includes:

[0092] Obtain the operation tasks of the self-service police terminal and set standard behavior information based on the operation tasks;

[0093] Obtain the comparison results, analyze the user's operation behavior and compare it with the standard behavior information based on the comparison results, and obtain the behavior deviation rate;

[0094] Determine whether the behavior deviation rate is greater than or equal to a set behavior deviation rate threshold;

[0095] If it is greater than or equal to, a user operation error behavior is generated and user operation error information is obtained;

[0096] If it is less than, the real-time user operation behavior is monitored in real time.

[0097] It should be noted that by comparing the differences between user operation behaviors and standard behaviors in real time, user operation error information can be screened out, user error operation behaviors can be accurately obtained, and the analysis effect can be improved.

[0098] According to an embodiment of the present invention, an expert database is established based on the user operation manual, and operation prompts and optimization suggestions are generated for user operation error information according to the expert database, specifically including:

[0099] Obtain the user operation manual, and obtain the user's standard operation behavior according to the user operation manual;

[0100] Establish an expert database based on user standard behavior;

[0101] Obtain user operation behavior information, analyze the user operation behavior information with data in the expert database, and obtain user operation error information;

[0102] Provide correct operation prompts and optimization suggestions based on user operation error information.

[0103] It should be noted that standardized user standard operating behaviors are formed according to the user operation manual, so that optimization suggestions can be accurately and efficiently put forward according to user error information, thereby improving the accuracy of user operations.

[0104] According to an embodiment of the present invention, the method further includes: collecting user avatar information, and analyzing user historical operation information based on the user avatar information;

[0105] Analyze the frequency and number of errors in user historical operations based on user historical operation information;

[0106] Establish matching operation prompts and optimization suggestions based on the frequency and number of occurrences of historical user operation errors.

[0107] It should be noted that the best optimization suggestions should be formulated based on different user historical operation situations to improve the accuracy of user operations.

[0108] In a second aspect, an embodiment of the present application provides a user behavior analysis system for a self-service police terminal based on artificial intelligence, the system comprising: a memory and a processor, the memory comprising a program of a user behavior analysis method for a self-service police terminal based on artificial intelligence, and the program of the user behavior analysis method for a self-service police terminal based on artificial intelligence when executed by the processor implements the following steps: capturing a real-time operation image of a user based on visual recognition technology, extracting features from the real-time operation image of the user, and identifying user operation behavior information;

[0109] Analyze user operation behavior information based on deep learning algorithms to obtain user behavior patterns;

[0110] Compare the user behavior pattern with the set behavior pattern to obtain a comparison result;

[0111] Analyze the user's operation error behavior based on the comparison result and obtain the user's operation error information;

[0112] An expert database is established based on the user manual, and operation prompts and optimization suggestions are generated based on the expert database for user operation error information.

[0113] It should be noted that visual recognition technology (camera) is used to capture real-time images of users' real-time operations in front of police terminals, and the images are analyzed, processed and compared to analyze whether the user has made any operational errors, so as to provide timely operational prompts and optimization suggestions for erroneous operations and improve the intelligence of police terminals.

[0114] According to an embodiment of the present invention, based on visual recognition technology, real-time user operation images are captured, features are extracted from the real-time user operation images, and user operation behavior information is identified, specifically including:

[0115] Establish a collection time window, and set a number of collection time nodes with equal time intervals within the collection time window;

[0116] The camera captures the user's real-time operation image corresponding to each acquisition time node;

[0117] Extract features from the user's real-time operation images captured at each acquisition time node;

[0118] Analyze the sequence of user operation behaviors based on the time sequence of the collected time nodes;

[0119] Analyze user operation behavior information based on the user operation behavior sequence.

[0120] It should be noted that by analyzing the real-time operation images of users at adjacent time nodes and extracting features, the user's dynamic operation behavior can be obtained in the order of the acquisition time nodes, thereby accurately analyzing the user behavior.

[0121] According to an embodiment of the present invention, the user operation behavior information is analyzed based on a deep learning algorithm to obtain a user behavior pattern, which specifically includes:

[0122] Obtain historical user operation behavior data and establish a training set;

[0123] Select an initial learning model, train the initial learning model based on the training set, and obtain a training result;

[0124] Determine whether the training results converge;

[0125] If convergence occurs, a deep learning model is generated, and the user operation behavior information is analyzed based on the deep learning model to obtain the user behavior pattern;

[0126] If it does not converge, the training data in the training set is adjusted, and the initial model is trained again according to the adjusted training data until the training results converge.

[0127] It should be noted that by constructing a training set to continuously train the model, the output accuracy of the deep learning model can be improved, making the deep learning model more and more accurate in analyzing user operation behavior and preventing analysis errors.

[0128] According to an embodiment of the present invention, the user behavior pattern is compared with the set behavior pattern to obtain a comparison result, which specifically includes:

[0129] Obtain user behavior patterns, compare the user behavior patterns with the set behavior patterns, and obtain behavior difference information;

[0130] Compare the behavior difference information with the set difference information to obtain the difference deviation rate;

[0131] If the difference deviation rate is greater than the first difference deviation rate and less than the second difference deviation rate, a first difference result is generated, and a first comparison result is generated based on the first difference result;

[0132] If the difference deviation rate is greater than or equal to the second difference deviation rate, a second comparison result is generated.

[0133] It should be noted that by analyzing user behavior patterns, different behavior difference information obtains different difference results, thereby accurately comparing and analyzing user behavior patterns and improving analysis accuracy.

[0134] According to an embodiment of the present invention, the user operation error behavior is analyzed based on the comparison result to obtain the user operation error information, which specifically includes:

[0135] Obtain the operation tasks of the self-service police terminal and set standard behavior information based on the operation tasks;

[0136] Obtain the comparison results, analyze the user's operation behavior and compare it with the standard behavior information based on the comparison results, and obtain the behavior deviation rate;

[0137] Determine whether the behavior deviation rate is greater than or equal to a set behavior deviation rate threshold;

[0138] If it is greater than or equal to, a user operation error behavior is generated and user operation error information is obtained;

[0139] If it is less than, the real-time user operation behavior is monitored in real time.

[0140] It should be noted that by comparing the differences between user operation behaviors and standard behaviors in real time, user operation error information can be screened out, user error operation behaviors can be accurately obtained, and the analysis effect can be improved.

[0141] According to an embodiment of the present invention, an expert database is established based on the user operation manual, and operation prompts and optimization suggestions are generated for user operation error information according to the expert database, specifically including:

[0142] Obtain the user operation manual, and obtain the user's standard operation behavior according to the user operation manual;

[0143] Establish an expert database based on user standard behavior;

[0144] Obtain user operation behavior information, analyze the user operation behavior information with data in the expert database, and obtain user operation error information;

[0145] Provide correct operation prompts and optimization suggestions based on user operation error information.

[0146] It should be noted that standardized user standard operating behaviors are formed according to the user operation manual, so that optimization suggestions can be accurately and efficiently put forward according to user error information, thereby improving the accuracy of user operations.

[0147] According to an embodiment of the present invention, the method further includes: collecting user avatar information, and analyzing user historical operation information based on the user avatar information;

[0148] Analyze the frequency and number of errors in user historical operations based on user historical operation information;

[0149] Establish matching operation prompts and optimization suggestions based on the frequency and number of occurrences of historical user operation errors.

[0150] It should be noted that the best optimization suggestions should be formulated based on different user historical operation situations to improve the accuracy of user operations.

[0151] The third aspect of the present invention provides a computer-readable storage medium, which includes a self-service police terminal user behavior analysis method program based on artificial intelligence. When the self-service police terminal user behavior analysis method program based on artificial intelligence is executed by a processor, the steps of the self-service police terminal user behavior analysis method based on artificial intelligence as described above are implemented.

[0152] The present invention discloses a method, system and medium for analyzing user behavior of a self-service police terminal based on artificial intelligence. The method captures real-time operation images of users based on visual recognition technology, extracts features from the real-time operation images of users, and identifies user operation behavior information; analyzes the user operation behavior information based on a deep learning algorithm to obtain a user behavior pattern; compares the user behavior pattern with a set behavior pattern to obtain a comparison result; analyzes user operation error behaviors based on the comparison result to obtain user operation error information; establishes an expert database based on a user operation manual, and generates operation prompts and optimization suggestions for the user operation error information according to the expert database; and helps to improve user operation accuracy, reduce operation errors, and enhance the convenience and safety of self-service by analyzing user operation behaviors in real time and modifying and optimizing user operation error information.

[0153] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0154] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0155] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0156] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, the aforementioned program can be stored in a readable storage medium, and when the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.

[0157] Or, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

Claims

1. A method for analyzing user behavior of a self-service police terminal based on artificial intelligence, characterized in that: include: Capture the user's real-time operation images based on visual recognition technology, extract features from the user's real-time operation images, and identify the user's operation behavior information; Analyze user operation behavior information based on deep learning algorithms to obtain user behavior patterns; Compare the user behavior pattern with the set behavior pattern to obtain a comparison result; Analyze the user's operation error behavior based on the comparison result to obtain the user's operation error information; An expert database is established based on the user manual, and operation prompts and optimization suggestions are generated based on the expert database for user operation error information.

2. The method for analyzing user behavior of a self-service police terminal based on artificial intelligence according to claim 1 is characterized in that: Based on visual recognition technology, the user's real-time operation images are captured, features are extracted from the user's real-time operation images, and user operation behavior information is identified, including: Establish a collection time window, and set a number of collection time nodes with equal time intervals within the collection time window; The camera captures the user's real-time operation image corresponding to each acquisition time node; Extract features from the user's real-time operation images captured at each acquisition time node; Analyze the sequence of user operation behaviors based on the time sequence of the collected time nodes; Analyze user operation behavior information based on the user operation behavior sequence.

3. The method for analyzing user behavior of a self-service police terminal based on artificial intelligence according to claim 2 is characterized in that: Analyze user operation behavior information based on deep learning algorithms to obtain user behavior patterns, including: Obtain historical user operation behavior data and establish a training set; Select an initial learning model, train the initial learning model based on the training set, and obtain a training result; Determining whether the training result converges; If convergence occurs, a deep learning model is generated, and the user operation behavior information is analyzed based on the deep learning model to obtain the user behavior pattern; If it does not converge, the training data in the training set is adjusted, and the initial model is trained again according to the adjusted training data until the training results converge.

4. The method for analyzing user behavior of a self-service police terminal based on artificial intelligence according to claim 3 is characterized in that: Compare the user behavior pattern with the set behavior pattern to obtain the comparison results, including: Obtain user behavior patterns, compare the user behavior patterns with the set behavior patterns, and obtain behavior difference information; Compare the behavior difference information with the set difference information to obtain the difference deviation rate; If the difference deviation rate is greater than the first difference deviation rate and less than the second difference deviation rate, a first difference result is generated, and a first comparison result is generated based on the first difference result; If the difference deviation rate is greater than or equal to the second difference deviation rate, a second comparison result is generated.

5. The method for analyzing user behavior of a self-service police terminal based on artificial intelligence according to claim 4 is characterized in that: Analyze the user's operation error behavior based on the comparison results and obtain the user's operation error information, including: Obtain the operation tasks of the self-service police terminal and set standard behavior information based on the operation tasks; Obtain the comparison results, analyze the user's operation behavior and compare it with the standard behavior information based on the comparison results, and obtain the behavior deviation rate; Determining whether the behavior deviation rate is greater than or equal to a set behavior deviation rate threshold; If it is greater than or equal to, a user operation error behavior is generated and user operation error information is obtained; If it is less than, the real-time user operation behavior is monitored in real time.

6. The method for analyzing user behavior of a self-service police terminal based on artificial intelligence according to claim 5 is characterized in that: An expert database is established based on the user manual, and operation prompts and optimization suggestions are generated based on the expert database for user operation error information, including: Obtain the user operation manual, and obtain the user's standard operation behavior according to the user operation manual; Establish an expert database based on user standard behavior; Obtain user operation behavior information, analyze the user operation behavior information with data in the expert database, and obtain user operation error information; Provide correct operation prompts and optimization suggestions based on user operation error information.

7. An artificial intelligence-based self-service police terminal user behavior analysis system, characterized in that: The system includes: a memory and a processor, wherein the memory includes a program of a method for analyzing user behavior of a self-service police terminal based on artificial intelligence, and when the program of the method for analyzing user behavior of a self-service police terminal based on artificial intelligence is executed by the processor, the following steps are implemented: Capture the user's real-time operation images based on visual recognition technology, extract features from the user's real-time operation images, and identify the user's operation behavior information; Analyze user operation behavior information based on deep learning algorithms to obtain user behavior patterns; Compare the user behavior pattern with the set behavior pattern to obtain a comparison result; Analyze the user's operation error behavior based on the comparison result to obtain the user's operation error information; An expert database is established based on the user manual, and operation prompts and optimization suggestions are generated based on the expert database for user operation error information.

8. The artificial intelligence-based self-service police terminal user behavior analysis system according to claim 7 is characterized in that: Based on visual recognition technology, the user's real-time operation images are captured, features are extracted from the user's real-time operation images, and user operation behavior information is identified, including: Establish a collection time window, and set a number of collection time nodes with equal time intervals within the collection time window; The camera captures the user's real-time operation image corresponding to each acquisition time node; Extract features from the user's real-time operation images captured at each acquisition time node; Analyze the sequence of user operation behaviors based on the time sequence of the collected time nodes; Analyze user operation behavior information based on the user operation behavior sequence.

9. The artificial intelligence-based self-service police terminal user behavior analysis system according to claim 8 is characterized in that: Analyze user operation behavior information based on deep learning algorithms to obtain user behavior patterns, including: Obtain historical user operation behavior data and establish a training set; Select an initial learning model, train the initial learning model based on the training set, and obtain a training result; Determining whether the training result converges; If convergence occurs, a deep learning model is generated, and the user operation behavior information is analyzed based on the deep learning model to obtain the user behavior pattern; If it does not converge, the training data in the training set is adjusted, and the initial model is trained again according to the adjusted training data until the training results converge.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes an artificial intelligence-based self-service police terminal user behavior analysis method program. When the artificial intelligence-based self-service police terminal user behavior analysis method program is executed by a processor, the steps of the artificial intelligence-based self-service police terminal user behavior analysis method as described in any one of claims 1 to 6 are implemented.

Images