User behavior visualization method, device, computer equipment and storage medium

Abstract

The present application discloses a user behavior visualization method, device, computer equipment and storage medium, including: collecting the behavior data of the target user in a preset logarithmic table, wherein the behavior data includes the target user's operation instructions for the user terminal; generating the first behavior flowchart of the target user according to the instruction timing of the operation instruction and the behavior data; reading the terminal log of the user terminal, and reading the error information in the terminal log and the error timestamp of generating the error information; according to the corresponding relationship between the error timestamp and the instruction timing, adapting the target process node corresponding to the error information in the first behavior flowchart, and displaying the target process node in a differentiated manner in the first behavior flowchart. The positioning accuracy and positioning operation difficulty of the error data are improved, so that the backstage personnel can easily locate the error information in the case of visual differences.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of data processing, and in particular to a method, apparatus, computer equipment and storage medium for visualizing user behavior. Background Art

[0002] User behavior analysis refers to the statistics and analysis of relevant data after obtaining basic data on the number of visits to websites or APPs and other platforms, thereby discovering the patterns of users' visits to websites or APPs and other platforms, and combining these patterns with online marketing strategies, etc., to discover possible problems in online marketing activities and provide a basis for further correction or reformulation of online marketing strategies.

[0003] The inventors of the present invention discovered during research that in the prior art, users' operating habits vary greatly, which may cause abnormal errors in different scenarios. However, users will not deliberately reserve the scene for technical personnel. Technical personnel need to retrieve massive online logs for analysis, making it difficult to locate production problems and making it more difficult for testers to reproduce the problems. Summary of the invention

[0004] The embodiments of the present invention provide a user behavior visualization method, device, computer equipment and storage medium capable of visually displaying error reporting data.

[0005] In order to solve the above technical problems, a technical solution adopted by an embodiment of the present invention is to provide a user behavior visualization method, including:

[0006] Collecting behavior data of the target user in a preset logarithmic table, wherein the behavior data includes operation instructions of the target user on the user terminal;

[0007] generating a first behavior flow chart of the target user according to the instruction timing of the operation instruction and the behavior data;

[0008] Reading a terminal log of the user terminal, and reading error information in the terminal log and an error timestamp for generating the error information;

[0009] According to the correspondence between the error timestamp and the instruction timing, a target process node corresponding to the error information is adapted in the first behavior flowchart, and the target process node is displayed in a differentiated manner in the first behavior flowchart.

[0010] Optionally, before collecting the behavior data of the target user in the preset logarithmic table, the method includes:

[0011] Reading the behavior data uploaded by the user terminal, and creating a blank logarithmic table based on the behavior data;

[0012] The behavior data is written into the logarithmic table, and the behavior data is arranged in ascending order in the logarithmic table according to the instruction timing.

[0013] Optionally, the adapting, in the first behavior flowchart, a target process node corresponding to the error message according to the correspondence between the error timestamp and the instruction timing, and displaying the target process node in a differentiated manner in the first behavior flowchart comprises:

[0014] Reading the target user instruction recorded in the target process node;

[0015] Reading a background image corresponding to the target user instruction stored in the user terminal according to the target user instruction;

[0016] A demonstration image corresponding to the error message is generated according to the target user instruction and the background image, and the demonstration image is associated with the target process node and stored.

[0017] Optionally, the generating a demonstration image corresponding to the error message according to the target user instruction and the background image, and associating and storing the demonstration image with the target process node, comprises:

[0018] Sending the demonstration image to the user terminal;

[0019] The user terminal obtains a first real-time operation instruction of the user, and captures a page image when the first real-time operation instruction is generated;

[0020] Performing image comparison processing on the page image and the demonstration image;

[0021] When the page image is identical to the demonstration image, the operation command corresponding to the first timely operation instruction is prohibited from being executed, and an error prompt message is displayed.

[0022] Optionally, the adapting, in the first behavior flowchart, a target process node corresponding to the error message according to the correspondence between the error timestamp and the instruction timing, and displaying the target process node in a differentiated manner in the first behavior flowchart comprises:

[0023] Reading the online request of the user terminal and approving the user terminal to go online after facial image recognition;

[0024] Collecting a second timely operation instruction generated based on the user's operation after the user terminal goes online, and generating a second behavior flow chart corresponding to the second timely operation instruction based on the instruction timing of the second timely operation instruction;

[0025] Determine whether the operating user is the target user according to the first behavior flowchart and the second behavior flowchart;

[0026] When the operating user is not the target user, the user terminal is cleared and the link connection with the user terminal is disconnected.

[0027] Optionally, determining whether the operating user is the target user according to the first behavior flowchart and the second behavior flowchart includes:

[0028] Inputting the first behavior flowchart and the second behavior flowchart into a preset image comparison model, wherein the image comparison model is a dual-channel recurrent neural network model pre-trained to a convergence state for image recognition comparison;

[0029] The classification result output by the image comparison model is read to determine whether the operating user is the target user.

[0030] Optionally, determining whether the operating user is the target user according to the first behavior flowchart and the second behavior flowchart includes:

[0031] Calculate the first hash value and the second hash value of the first behavior flowchart and the second behavior flowchart respectively according to a preset hash operation formula;

[0032] Calculating a deviation value between the first Hash value and the second Hash value;

[0033] When the deviation value is less than or equal to a preset deviation threshold, it is determined that the operating user is the target user; otherwise, it is confirmed that the operating user is not the target user.

[0034] In order to solve the above technical problems, an embodiment of the present invention further provides a user behavior visualization device, comprising:

[0035] A collection module, used to collect the behavior data of the target user in a preset logarithmic table, wherein the behavior data includes the operation instructions of the target user on the user terminal;

[0036] A generating module, configured to generate a first behavior flow chart of the target user according to the instruction timing of the operation instruction and the behavior data;

[0037] A processing module, configured to read a terminal log of the user terminal, read error information in the terminal log, and generate an error timestamp of the error information;

[0038] An execution module is used to adapt a target process node corresponding to the error information in the first behavior flowchart according to the corresponding relationship between the error timestamp and the instruction timing, and to display the target process node in a differentiated manner in the first behavior flowchart.

[0039] Optionally, the user behavior visualization device further includes:

[0040] A first reading submodule, configured to read the behavior data uploaded by the user terminal and create a blank logarithmic table based on the behavior data;

[0041] The first sorting submodule is used to write the behavior data into the logarithmic table, and arrange the behavior data in ascending order in the logarithmic table according to the instruction timing.

[0042] Optionally, the user behavior visualization device further includes:

[0043] A second reading submodule, used to read the target user instruction recorded in the target process node;

[0044] A first processing submodule, configured to read a background image corresponding to the target user instruction and stored in the user terminal according to the target user instruction;

[0045] The first execution submodule is used to generate a demonstration image corresponding to the error message according to the target user instruction and the background image, and store the demonstration image in association with the target process node.

[0046] Optionally, the user behavior visualization device further includes:

[0047] A first sending submodule, used for sending the demonstration image to the user terminal;

[0048] A first interception submodule, configured for the user terminal to obtain a first timely operation instruction of the user, and to intercept a page image when the first timely operation instruction is generated;

[0049] A second processing submodule is used to perform image comparison processing between the page image and the demonstration image;

[0050] The second execution submodule is used to prohibit the execution of the operation command corresponding to the first timely operation instruction and display an error prompt message when the page image is the same as the demonstration image.

[0051] Optionally, the user behavior visualization device further includes:

[0052] A third reading submodule is used to read the online request of the user terminal and approve the user terminal to go online after facial image recognition;

[0053] A first collection submodule, configured to collect a second timely operation instruction generated based on a user operation after the user terminal goes online, and generate a second behavior flow chart corresponding to the second timely operation instruction based on an instruction sequence of the second timely operation instruction;

[0054] A third processing submodule, configured to determine whether the operating user is the target user according to the first behavior flowchart and the second behavior flowchart;

[0055] The third execution submodule is used to clear the user terminal and disconnect the link connection with the user terminal when the operating user is not the target user.

[0056] Optionally, the user behavior visualization device further includes:

[0057] a fourth processing submodule, configured to input the first behavior flowchart and the second behavior flowchart into a preset image comparison model, wherein the image comparison model is a dual-channel recurrent neural network model pre-trained to a convergence state for image recognition comparison;

[0058] The fourth execution submodule is used to read the classification result output by the image comparison model and determine whether the operating user is the target user.

[0059] Optionally, the user behavior visualization device further includes:

[0060] A fifth processing submodule, configured to calculate a first hash value and a second hash value of the first behavior flowchart and the second behavior flowchart respectively according to a preset hash operation formula;

[0061] A first calculation submodule, configured to calculate a deviation value between the first Hash value and the second Hash value;

[0062] The fifth execution submodule is used to determine that the operating user is the target user when the deviation value is less than or equal to a preset deviation threshold; otherwise, confirm that the operating user is not the target user.

[0063] To solve the above technical problem, an embodiment of the present invention further provides a computer device, including a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the above-mentioned user behavior visualization method.

[0064] In order to solve the above technical problem, an embodiment of the present invention further provides a computer storage medium, and when the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the above-mentioned user behavior visualization method.

[0065] The beneficial effects of the embodiments of the present invention are: collecting user behavior data uploaded by the user terminal, storing the behavior data in a logarithmic table, sorting the user behavior data according to the instruction timing of the user operation instruction, and drawing the user behavior into a flow chart according to the sorted behavior data. When the backend user needs to review the user data, after reading the error message, according to the timestamp of the error message and the instruction timing of each node in the first behavior flow chart, match the target process node where the user behavior corresponding to the error message is located, and display the target process node in a differentiated manner, so that the backend user can quickly see the error data of the user terminal, improve the positioning accuracy of the error data and the difficulty of positioning operation, so that the backend personnel can easily locate the error message in the case of visual differences. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0067] Figure 1 A basic flow chart of a method for visualizing user behavior according to a specific embodiment of the present application;

[0068] Figure 2 A schematic diagram of the storage process of behavior data in a specific embodiment of the present application;

[0069] Figure 3 This is a schematic diagram of a process for restoring error information according to a specific embodiment of the present application;

[0070] Figure 4 This is a flowchart of a specific embodiment of the present application for prompting a user of an erroneous operation;

[0071] Figure 5 A flowchart of behavior verification according to a specific embodiment of the present application is shown;

[0072] Figure 6 A schematic diagram of a process of performing behavior recognition based on a model according to a specific embodiment of the present application;

[0073] Figure 7 A schematic diagram of a process of determining user behavior through a hash operation formula according to an embodiment of the present application;

[0074] Figure 8 A schematic diagram of the basic structure of a user behavior visualization device according to an embodiment of the present application;

[0075] Fig. 9 This is a basic structural block diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0076] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be interpreted as limiting the present application.

[0077] Those skilled in the art will appreciate that, unless otherwise stated, the singular forms "a", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0078] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art to which this application belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with those in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as here.

[0079] It will be understood by those skilled in the art that the term "terminal" as used herein includes both devices with wireless signal receivers, which are devices with only wireless signal receivers without transmission capabilities, and devices with receiving and transmitting hardware, which are devices with receiving and transmitting hardware capable of performing two-way communications over a two-way communication link. Such devices may include: cellular or other communication devices, which have a single-line display or a multi-line display or a cellular or other communication device without a multi-line display; PCS (Personal Communications Service), which may combine voice, data processing, fax and / or data communication capabilities; PDA (Personal Digital Assistant), which may include a radio frequency receiver, a pager, Internet / intranet access, a web browser, a notepad, a calendar and / or a GPS (Global Positioning System) receiver; conventional laptop and / or palmtop computers or other devices, which have and / or include a conventional laptop and / or palmtop computer or other device with and / or including a radio frequency receiver. The "terminal" used here can be portable, transportable, installed in a vehicle (air, sea and / or land), or suitable for and / or configured to run locally, and / or in a distributed form, running at any other location on the earth and / or in space. The "terminal" used here can also be a communication terminal, an Internet terminal, a music / video playing terminal, for example, a PDA, a MID (Mobile Internet Device) and / or a mobile phone with a music / video playing function, or a smart TV, a set-top box and other devices.

[0080] Figure 1 FIG. 1 is a basic flow chart of the user behavior visualization method of this embodiment. Figure 1 As shown, a user behavior visualization method includes:

[0081] S110, collecting behavior data of a target user in a preset logarithmic table, wherein the behavior data includes operation instructions of the target user on a user terminal;

[0082] A logarithmic table is set in the background server in this embodiment. For each operation instruction performed by the target user on the user terminal, corresponding behavior data will be generated and written into the logarithmic table. The behavior data includes fields (not limited to): user unique identifier userId, interface information: class name.Method name, request input parameter req_content and output parameter res_content, interface response code res_code and response message res_msg, request unique serial number traceId, and request time.

[0083] Since the user's operation is not single but composed of a series of user operation instructions, each set of user behavior data includes the timestamp of the generation of the operation instruction, that is, the instruction timing.

[0084] S120, generating a first behavior flow chart of the target user according to the instruction timing of the operation instruction and the behavior data;

[0085] A first behavior flow chart is generated according to the instruction timing of the operation instruction and the behavior data. Since each behavior data includes an instruction timing corresponding to a corresponding operation instruction, the behavior data is arranged in ascending order according to the instruction timing in the behavior data, that is, the behavior data with a later generation time is arranged after the behavior data with an earlier generation time, and the data chain composed of the behavior data is generated after arranging them in sequence.

[0086] Visualize the data chain: take each set of behavior data in the data chain as a process node, generate a block diagram for representing a set of behavior data according to the order of the behavior data in the data chain, arrange the block diagrams corresponding to each behavior data according to the position of the behavior data in the data chain, and connect adjacent block diagrams to generate the first behavior flow chart.

[0087] After the first behavior flow chart is generated, each frame diagram must be associated and stored with the behavior data it represents, and a trigger script must be set on each frame diagram. When the user clicks on any frame diagram, the behavior data details corresponding to the frame diagram must be displayed in an expanded display, including fields (not limited to): user unique identifier userId, interface information: class name. Method name, request input parameter req_content and output parameter res_content, interface response code res_code and response message res_msg, request unique serial number traceId, request time and other fields.

[0088] S130, reading the terminal log of the user terminal, and reading the error information in the terminal log and the error timestamp for generating the error information;

[0089] When a fault occurs in a user terminal, the fault will be recorded in the user terminal log in the form of an error message, and each error message will generate an error timestamp and be saved in the terminal log. Therefore, when you need to view the error message of the user terminal, you must first call the terminal log in the user terminal, and then retrieve the error message field in the terminal log to obtain the content of the error message and the corresponding error timestamp.

[0090] S140. Adapt a target process node corresponding to the error information in the first behavior flowchart according to the correspondence between the error timestamp and the instruction timing, and display the target process node in a differentiated manner in the first behavior flowchart.

[0091] Since user behavior data has an instruction timing when it is uploaded, and the error information also has an error timestamp, and the error timestamp and the instruction timing are generated at the same time, or occur within a preset time interval, therefore, when the user behavior and the error information are paired, as long as the error timestamp is matched among a large number of behavior data, and the instruction timing is the same as or the difference is within a preset time interval, the behavior data corresponding to the error information can be matched.

[0092] According to the behavior data corresponding to the error message, the process node corresponding to the error message in the first behavior flowchart is further determined, and the process node corresponding to the error message is defined as the target process node. The process node corresponding to the error message indicates that a fault has occurred at the process node, thus completing the process of confirming the fault node in the first behavior flowchart.

[0093] After determining the target process node, the target process node needs to be displayed in a differentiated manner in the first line of the flowchart. For example, when the first line of the flowchart is all black graphic boxes, the graphic box of the target process node is represented by red. However, the differentiated display of the target process node is not limited to this. According to different specific application scenarios, in some embodiments, the differentiated display of the target process node can be: differentiated display by graphic difference, color difference or logo difference.

[0094] In the above implementation, the user behavior data uploaded by the user terminal is collected, and the behavior data is stored in a logarithmic table, the user behavior data is sorted according to the instruction timing of the user operation instruction, and the user behavior is drawn into a flow chart according to the sorted behavior data. When the backend user needs to review the user data, after reading the error message, the target process node where the user behavior corresponding to the error message is located is matched according to the timestamp of the error message and the instruction timing of each node in the first behavior flow chart, and the target process node is displayed in a differentiated manner, so that the backend user can quickly see the error data of the user terminal, which improves the positioning accuracy of the error data and the difficulty of positioning operation, so that the backend personnel can easily locate the error information in the case of visual differences.

[0095] In some implementations, the behavior data uploaded by the user terminal is stored in a logarithmic table. Figure 2 , Figure 2 Schematic diagram of the storage process of behavior data in this embodiment.

[0096] like Figure 2 As shown, S110 previously included:

[0097] S101, reading the behavior data uploaded by the user terminal, and creating a blank logarithmic table based on the behavior data;

[0098] When the user performs an operation, the user terminal executes the user's operation instructions and generates corresponding behavior data. The behavior data includes (but is not limited to): the user's unique identifier userId, interface information: class name. method name, request input parameter req_content and output parameter res_content, interface response code res_code and response message res_msg, request unique serial number traceId, request time and other parameters.

[0099] After receiving the behavior data, the server creates a new logarithmic table. A logarithmic table is a table that is compiled by calculating the logarithms of integers starting from 1. The leading number is not listed in the logarithmic table, which is determined by the properties of common logarithms. The accuracy of the true number and the logarithmic mantissa depends on the number of digits in the logarithmic table. The higher the number of digits, the higher the accuracy.

[0100] S102, writing the behavior data into the logarithmic table, and arranging the behavior data in ascending order in the logarithmic table according to the instruction timing.

[0101] Since the user's operation is not a single action, but a series of user operation instructions, each set of user behavior data includes the timestamp of the operation instruction generation, that is, the instruction sequence. The behavior data is arranged in ascending order according to the instruction sequence in the behavior data, that is, the behavior data with a later generation time is arranged after the behavior data with an earlier generation time, and a data chain composed of the behavior data is generated after arranging them in sequence. The data chain is stored in a logarithmic table.

[0102] In some implementations, it is necessary to restore the error message visually. Figure 3 , Figure 3 The figure is a flow chart of restoring error information in this embodiment.

[0103] like Figure 3 As shown, after S140, including:

[0104] S151, reading the target user instruction recorded in the target process node;

[0105] In some implementations, the fault that generates the error message is caused by a user's erroneous operation. Therefore, the user's erroneous operation behavior needs to be corrected to reduce the above error message.

[0106] When there is a target process node in the first user behavior flow chart, the target user instruction in the target process node is read, and the target user instruction includes user instruction operation details and the position coordinates of the target user instruction on the page. The user instruction operation details refer to the operation content of the user single-clicking, double-clicking, sliding or using shortcut keys to operate the page.

[0107] S152, reading a background image corresponding to the target user instruction stored in the user terminal according to the target user instruction;

[0108] In this embodiment, each time the user terminal sends behavior data to the user, the display content of the user terminal when the behavior data is generated is captured as the background image of the behavior data.

[0109] Therefore, each target process node has a corresponding background image stored in association with it, and after the target user instruction recorded in the target process node is read, the background image associated with it can be read.

[0110] S153: Generate a demonstration image corresponding to the error message according to the target user instruction and the background image, and store the demonstration image in association with the target process node.

[0111] After obtaining the background image, based on the user operation details in the target user instructions and the location coordinates of the user operation, the task of issuing the operation instruction and the operation process at that location can be located on the background image. Then, the location where the target user instruction acts is marked in the background image, and the location is identified based on the user operation details to generate a demonstration image of the error information.

[0112] After the demonstration image is generated, it is associated and stored with its corresponding target process node. When the back-end personnel click the graphic box of the target process node, they can call up the demonstration image, allowing the personnel to more intuitively observe the restoration scene of the erroneous operation.

[0113] In some implementations, after the demonstration image is generated, in order to prevent the target user from continuing to make erroneous operations and generating the same error message, it is necessary to regulate the user's behavior. Figure 4 , Figure 4 This is a schematic diagram of the process of prompting the user of incorrect operations in this embodiment.

[0114] like Figure 4 As shown, after S153, including:

[0115] S154, sending the demonstration image to the user terminal;

[0116] After the server generates a demonstration image corresponding to the target process node, the demonstration image is sent to the user terminal to prompt the user's behavior.

[0117] S155, the user terminal obtains a first real-time operation instruction of the user, and captures a page image when the first real-time operation instruction is generated;

[0118] After receiving the demonstration image, the user terminal stores the demonstration image. When executing the operation instruction of the user row later, the user terminal records the operation instruction as the first timely operation instruction.

[0119] When the first timely operation instruction is recorded, the user terminal captures the page image when the first timely operation instruction is generated, and then marks the position and operation content of the first timely operation instruction in the page image to generate a page image with the same structure as the demonstration image.

[0120] S156, performing image comparison processing on the page image and the demonstration image;

[0121] The user terminal performs image comparison processing on the page image and the demonstration image. The image comparison processing is mainly performed through a neural network model that has been pre-trained to a convergence state. The neural network model can be (but not limited to): a convolutional neural network model, a deep convolutional neural network model, a recurrent neural network model, or a variant model of any one of the models.

[0122] S157: When the page image is identical to the demonstration image, the operation command corresponding to the first timely operation instruction is prohibited from being executed, and an error prompt message is displayed.

[0123] When the image comparison result shows that the page image and the demonstration image are the same, it means that the user is performing an operation that triggers an error message. At this time, it is necessary to prevent the user's operation from triggering adverse consequences. The user terminal is prohibited from executing the operation command corresponding to the first timely operation instruction, that is, the request information corresponding to the first timely operation instruction is not sent to the server. Then, the user's wrong operation information is displayed on the user terminal to prompt the user to adjust the behavior.

[0124] Through the above method, the user terminal can prompt the user of wrong behavior without going through the server, and blocking the execution of the operation command corresponding to the first timely operation instruction can prevent computer downtime caused by the fault and avoid wasting network data transmission resources.

[0125] In some implementations, the user behavior visualization method of this implementation can also prevent teenagers from playing games by swiping faces on behalf of others. Figure 5 , Figure 5Schematic diagram of the behavior verification process of this embodiment.

[0126] like Figure 5 As shown, after S140, including:

[0127] S161, reading the online request of the user terminal, and approving the user terminal to go online after facial image recognition;

[0128] In some application scenarios, some minors log in to other people's game accounts and use others to scan their faces to evade the inspection of the anti-addiction system and play games overtime.

[0129] When the user goes online, the face of the logged-in user is recognized through face recognition technology. After confirming that the user is the target user of the account, the user terminal's online request is approved, allowing the user to enter the corresponding game environment or other operating environment.

[0130] S162: collecting a second timely operation instruction generated based on the user's operation after the user terminal goes online, and generating a second behavior flow chart corresponding to the second timely operation instruction based on the instruction sequence of the second timely operation instruction;

[0131] After the user logs in, the user terminal continuously collects user operation instructions to generate a second timely operation instruction, and then sends the second timely operation instruction to the server. After receiving the second timely operation instruction, the server performs the same visualization processing on the first behavior flowchart according to the first behavior flowchart generation step to generate a second behavior flowchart.

[0132] S163, determining whether the operating user is the target user according to the first behavior flowchart and the second behavior flowchart;

[0133] After the second behavior flowchart is generated, since the first behavior flowchart and the second behavior flowchart both represent a user operation process, different users have different operation habits and cannot be exactly the same. Therefore, it is possible to determine whether the current operator is the target user based on the content represented by the first behavior flowchart and the second behavior flowchart.

[0134] Specifically, the judgment of user behavior differences is achieved by comparing the first behavior flowchart and the second behavior flowchart. In some embodiments, an image comparison model is pre-constructed, and the image comparison model is a dual-channel recurrent neural network model that is pre-trained to a convergence state and is used for image recognition comparison. The image comparison model is provided with two input channels, which can extract features of two images at the same time. The recurrent neural network model can input the content of the previous node into the next node, and can enable the image comparison model to learn the characteristics of the connection relationship between the previous and next process nodes in the flowchart, so that the comparison is more accurate. The image comparison model is trained to convergence through supervised training.

[0135] In some implementations, the first behavior flowchart and the second behavior flowchart can be compared by a hash operation formula, and the first behavior flowchart and the second behavior flowchart are calculated by the same hash operation formula. If the two diagrams are the same, the calculated hash values ​​are the same or have a slight error. Therefore, by calculating the difference between the corresponding hash values ​​of the first behavior flowchart and the second behavior flowchart, it can be determined whether the first behavior flowchart and the second behavior flowchart are the same.

[0136] S164: When the operating user is not the target user, clear the user terminal and disconnect the link connection with the user terminal.

[0137] When the current operating user is determined not to be the target user through image comparison, it is proved that the current operating user has engaged in face scanning on behalf of others and cannot continue to play games or other operations. The server can then clear the user's logged-in account and put the user terminal offline. At the same time, the server actively disconnects the network link with the user terminal, forcing the user terminal to stop running the system that requires server support. This prevents teenagers from circumventing the anti-addiction system to surf the Internet.

[0138] In some embodiments, a neural network is used to identify whether the first behavior flowchart and the second behavior flowchart are the same. Figure 6 , Figure 6 The figure is a flow chart of behavior recognition based on the model in this embodiment.

[0139] like Figure 6 As shown, S163 includes:

[0140] S171, inputting the first behavior flowchart and the second behavior flowchart into a preset image comparison model, wherein the image comparison model is a dual-channel recurrent neural network model pre-trained to a convergence state for image recognition comparison;

[0141] The judgment of user behavior differences is achieved by comparing the first behavior flowchart and the second behavior flowchart. In some embodiments, an image comparison model is pre-constructed, and the image comparison model is a dual-channel recurrent neural network model that is pre-trained to a convergence state and is used for image recognition comparison. The image comparison model is provided with two input channels, which can extract features of two images at the same time. The recurrent neural network model can input the content of the previous node into the next node, and can enable the image comparison model to learn the characteristics of the connection relationship between the previous and next process nodes in the flowchart, so that the comparison is more accurate. The image comparison model is trained to convergence through supervised training.

[0142] S172: Read the classification result output by the image comparison model to determine whether the operating user is the target user.

[0143] The classification result output by the image comparison model is a binary classification result, that is, the same or different. When the output classification result is the same, it means that the user behaviors represented by the first behavior flowchart and the second behavior flowchart are the same; when the output result is different, it means that the user behaviors represented by the first behavior flowchart and the second behavior flowchart are different.

[0144] In some implementations, a hash operation is used to determine whether the first behavior flow chart and the second behavior flow chart are the same. Figure 7 , Figure 7 The figure is a flow chart of determining user behavior through a hash operation in this embodiment.

[0145] like Figure 7 As shown, S163 includes:

[0146] S181, respectively calculating a first hash value and a second hash value of the first behavior flowchart and the second behavior flowchart according to a preset hash operation formula;

[0147] The first behavior flowchart and the second behavior flowchart are calculated using the same hash operation formula, and the hash value obtained by calculating the first behavior flowchart is a first hash value, and the hash value obtained by calculating the second behavior flowchart is a second hash value.

[0148] S182. Calculate a deviation value between the first Hash value and the second Hash value;

[0149] Subtract the first hash value from the second hash value. When the deviation value of the subtraction operation is 0, or the deviation value is less than or equal to the preset deviation threshold, it is determined that the user behaviors represented by the first behavior flowchart and the second behavior flowchart are the same, that is, the current user and the target user are the same person. When the deviation value is greater than the preset deviation threshold, it is determined that the user behaviors represented by the first behavior flowchart and the second behavior flowchart are different, that is, the current user and the target user are not the same person.

[0150] The deviation threshold in this implementation can be customized according to actual environment requirements.

[0151] S183. When the deviation value is less than or equal to a preset deviation threshold, it is determined that the operating user is the target user; otherwise, it is confirmed that the operating user is not the target user.

[0152] If the two graphs are the same, the calculated hash values ​​are the same or the error is less than or equal to the deviation threshold. Therefore, by calculating the difference between the hash values ​​corresponding to the first behavior flowchart and the second behavior flowchart, it is possible to determine whether the first behavior flowchart and the second behavior flowchart are the same.

[0153] To solve the above technical problems, the present invention also provides a user behavior visualization device. Figure 8 , Figure 8 Schematic diagram of the basic structure of the user behavior visualization device of this embodiment.

[0154] like Figure 8 As shown, a user behavior visualization device includes: a collection module 110, a generation module 120, a processing module 130 and an execution module 140. The collection module 110 is used to collect the behavior data of the target user in the preset logarithmic table, wherein the behavior data includes the operation instructions of the target user on the user terminal; the generation module 120 is used to generate the first behavior flow chart of the target user according to the instruction timing of the operation instruction and the behavior data; the processing module 130 is used to read the terminal log of the user terminal, and read the error information in the terminal log and generate the error timestamp of the error information; the execution module 140 is used to adapt the target process node corresponding to the error information in the first behavior flow chart according to the corresponding relationship between the error timestamp and the instruction timing, and display the target process node in the first behavior flow chart in a differentiated manner.

[0155] The user behavior visualization device collects user behavior data uploaded by the user terminal, stores the behavior data in a logarithmic table, sorts the user behavior data according to the instruction timing of the user operation instruction, and draws the user behavior into a flow chart according to the sorted behavior data. When the back-end user needs to review the user data, after reading the error message, the target process node where the user behavior corresponding to the error message is located is matched according to the timestamp of the error message and the instruction timing of each node in the first behavior flow chart, and the target process node is displayed in a differentiated manner, so that the back-end user can quickly see the error data of the user terminal, improve the positioning accuracy of the error data and the difficulty of positioning operation, and enable the back-end personnel to easily locate the error information in the presence of visual differences.

[0156] In some embodiments, the user behavior visualization device further includes: a first reading submodule and a first sorting submodule. The first reading submodule is used to read the behavior data uploaded by the user terminal and create a blank logarithmic table based on the behavior data; the first sorting submodule is used to write the behavior data into the logarithmic table and arrange the behavior data in ascending order in the logarithmic table according to the instruction sequence.

[0157] In some embodiments, the user behavior visualization device further includes: a second reading submodule, a first processing submodule, and a first execution submodule. The second reading submodule is used to read the target user instruction recorded in the target process node; the first processing submodule is used to read the background image corresponding to the target user instruction stored in the user terminal according to the target user instruction; the first execution submodule is used to generate a demonstration image corresponding to the error message according to the target user instruction and the background image, and store the demonstration image in association with the target process node.

[0158] In some embodiments, the user behavior visualization device further includes: a first sending submodule, a first intercepting submodule, a second processing submodule, and a second execution submodule. The first sending submodule is used to send the demonstration image to the user terminal; the first intercepting submodule is used for the user terminal to obtain the user's first timely operation instruction and intercept the page image when the first timely operation instruction is generated; the second processing submodule is used to perform image comparison processing on the page image and the demonstration image; the second execution submodule is used to prohibit the execution of the operation command corresponding to the first timely operation instruction when the page image is the same as the demonstration image, and display an error prompt message.

[0159] In some embodiments, the user behavior visualization device further includes: a third reading submodule, a first acquisition submodule, a third processing submodule, and a third execution submodule. The third reading submodule is used to read the online request of the user terminal and agree to the online of the user terminal after facial image recognition; the first acquisition submodule is used to acquire the second timely operation instruction generated based on the user's operation after the user terminal goes online, and based on the instruction timing of the second timely operation instruction, generate a second behavior flow chart corresponding to the second timely operation instruction; the third processing submodule is used to determine whether the operating user is the target user according to the first behavior flow chart and the second behavior flow chart; the third execution submodule is used to clear the user terminal and disconnect the link connection with the user terminal when the operating user is not the target user.

[0160] In some embodiments, the user behavior visualization device further includes: a fourth processing submodule and a fourth execution submodule. The fourth processing submodule is used to input the first behavior flowchart and the second behavior flowchart into a preset image comparison model, wherein the image comparison model is a dual-channel recurrent neural network model pre-trained to a convergence state for image recognition comparison; the fourth execution submodule is used to read the classification result output by the image comparison model to determine whether the operating user is the target user.

[0161] In some embodiments, the user behavior visualization device further includes: a fifth processing submodule, a first calculation submodule, and a fifth execution submodule. The fifth processing submodule is used to calculate the first hash value and the second hash value of the first behavior flow chart and the second behavior flow chart respectively according to a preset hash operation formula; the first calculation submodule is used to calculate the deviation value between the first hash value and the second hash value; the fifth execution submodule is used to determine that the operating user is the target user when the deviation value is less than or equal to a preset deviation threshold; otherwise, confirm that the operating user is not the target user.

[0162] To solve the above technical problems, the embodiment of the present invention also provides a computer device. Fig. 9 , Fig. 9 This is a basic structural block diagram of the computer device in this embodiment.

[0163] like Fig. 9 As shown, a schematic diagram of the internal structure of a computer device. The computer device includes a processor, a non-volatile storage medium, a memory, and a network interface connected via a system bus. Among them, the non-volatile storage medium of the computer device stores an operating system, a database, and computer-readable instructions. The database may store a control information sequence. When the computer-readable instructions are executed by the processor, the processor can implement a user behavior visualization method. The processor of the computer device is used to provide computing and control capabilities to support the operation of the entire computer device. The memory of the computer device may store computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor can execute a user behavior visualization method. The network interface of the computer device is used to connect and communicate with a terminal. Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0164] In this embodiment, the processor is used to execute Figure 8The memory stores the program codes and various data required to execute the above modules. The network interface is used to transmit data between user terminals or servers. The memory in this embodiment stores the program codes and data required to execute all sub-modules in the user behavior visualization device, and the server can call the program codes and data of the server to execute the functions of all sub-modules.

[0165] The computer equipment collects the user behavior data uploaded by the user terminal, stores the behavior data in a logarithmic table, sorts the user behavior data according to the instruction timing of the user operation instruction, and draws the user behavior into a flow chart according to the sorted behavior data. When the back-end user needs to review the user data, after reading the error message, according to the timestamp of the error message and the instruction timing of each node in the first behavior flow chart, the target process node corresponding to the user behavior of the error message is matched, and the target process node is displayed in a differentiated manner, so that the back-end user can quickly see the error data of the user terminal, improve the positioning accuracy of the error data and the difficulty of positioning operation, so that the back-end personnel can easily locate the error information in the case of visual differences.

[0166] The present invention also provides a computer storage medium, and when the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the user behavior visualization method in any of the above embodiments.

[0167] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0168] Those skilled in the art will appreciate that the various operations, methods, steps, measures, and schemes in the processes discussed in this application may be alternated, altered, combined, or deleted. Further, other steps, measures, and schemes in the various operations, methods, and processes discussed in this application may also be alternated, altered, rearranged, decomposed, combined, or deleted. Further, the steps, measures, and schemes in the prior art that are similar to those disclosed in this application may also be alternated, altered, rearranged, decomposed, combined, or deleted.

[0169] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A user behavior visualization method, characterized in that: include: Collecting behavior data of the target user in a preset logarithmic table, wherein the behavior data includes operation instructions of the target user on the user terminal; generating a first behavior flow chart of the target user according to the instruction timing of the operation instruction and the behavior data; Reading a terminal log of the user terminal, and reading error information in the terminal log and an error timestamp for generating the error information; According to the correspondence between the error timestamp and the instruction timing, adapting the target process node corresponding to the error information in the first behavior flow chart, and displaying the target process node in a differentiated manner in the first behavior flow chart; The method of adapting a target process node corresponding to the error information in the first behavior flowchart according to the correspondence between the error timestamp and the instruction timing, and displaying the target process node in a differentiated manner in the first behavior flowchart, comprises: Reading the target user instruction recorded in the target process node; Reading a background image corresponding to the target user instruction stored in the user terminal according to the target user instruction; A demonstration image corresponding to the error message is generated according to the target user instruction and the background image, and the demonstration image is associated with the target process node and stored.

2. The user behavior visualization method according to claim 1, characterized in that: Before collecting the behavior data of the target user in the preset logarithmic table, the method includes: Reading the behavior data uploaded by the user terminal, and creating a blank logarithmic table based on the behavior data; The behavior data is written into the logarithmic table, and the behavior data is arranged in ascending order in the logarithmic table according to the instruction timing.

3. The user behavior visualization method according to claim 1, characterized in that: After generating a demonstration image corresponding to the error message according to the target user instruction and the background image, and associating and storing the demonstration image with the target process node, the method includes: Sending the demonstration image to the user terminal; The user terminal obtains a first real-time operation instruction of the user, and captures a page image when the first real-time operation instruction is generated; Performing image comparison processing on the page image and the demonstration image; When the page image is identical to the demonstration image, the operation command corresponding to the first timely operation instruction is prohibited from being executed, and an error prompt message is displayed.

4. The user behavior visualization method according to claim 1, characterized in that: According to the correspondence between the error timestamp and the instruction timing, adapting the target process node corresponding to the error information in the first behavior flow chart, and displaying the target process node in a differentiated manner in the first behavior flow chart, comprises: Reading the online request of the user terminal and approving the user terminal to go online after facial image recognition; Collecting a second timely operation instruction generated based on the user's operation after the user terminal goes online, and generating a second behavior flow chart corresponding to the second timely operation instruction based on the instruction timing of the second timely operation instruction; Determine whether the operating user is the target user according to the first behavior flowchart and the second behavior flowchart; When the operating user is not the target user, the user terminal is cleared and the link connection with the user terminal is disconnected.

5. The user behavior visualization method according to claim 4, characterized in that: The determining whether the operating user is the target user according to the first behavior flowchart and the second behavior flowchart includes: Inputting the first behavior flowchart and the second behavior flowchart into a preset image comparison model, wherein the image comparison model is a dual-channel recurrent neural network model pre-trained to a convergence state for image recognition comparison; The classification result output by the image comparison model is read to determine whether the operating user is the target user.

6. The user behavior visualization method according to claim 4, characterized in that: The determining whether the operating user is the target user according to the first behavior flowchart and the second behavior flowchart includes: Calculate the first hash value and the second hash value of the first behavior flowchart and the second behavior flowchart respectively according to a preset hash operation formula; Calculating a deviation value between the first Hash value and the second Hash value; When the deviation value is less than or equal to a preset deviation threshold, it is determined that the operating user is the target user; otherwise, it is confirmed that the operating user is not the target user.

7. A user behavior visualization device, characterized in that: include: A collection module, used to collect the behavior data of the target user in a preset logarithmic table, wherein the behavior data includes the operation instructions of the target user on the user terminal; A generating module, configured to generate a first behavior flow chart of the target user according to the instruction timing of the operation instruction and the behavior data; A processing module, configured to read a terminal log of the user terminal, read error information in the terminal log, and generate an error timestamp of the error information; An execution module, configured to adapt a target process node corresponding to the error message in the first behavior flow chart according to a corresponding relationship between the error timestamp and the instruction timing, and display the target process node in a differentiated manner in the first behavior flow chart; Wherein, the user behavior visualization device further includes: A second reading submodule, used for reading the target user instruction recorded in the target process node; A first processing submodule, configured to read a background image corresponding to the target user instruction and stored in the user terminal according to the target user instruction; The first execution submodule is used to generate a demonstration image corresponding to the error message according to the target user instruction and the background image, and store the demonstration image in association with the target process node.

8. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the user behavior visualization method according to any one of claims 1 to 6.

9. A computer storage medium, characterized in that: When the computer-readable instructions are executed by one or more processors, the one or more processors are caused to perform the steps of the user behavior visualization method according to any one of claims 1 to 6.

Images