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

Abstract

The invention relates to a user behavior playback method and device, computer equipment and a storage medium. The method comprises the steps that in response to a log obtaining request of a current application, corresponding log information is obtained from a pre-configured log warehouse according to user information in the log obtaining request, the log information comprises a user behavior burying point log and an interface burying point log, and in response to a user behavior playback request, the interface burying point log is played back. And determining an operation sequence of the user and request time corresponding to the operation sequence according to the log information, and performing user behavior playback according to the operation sequence of the user and the request time corresponding to the operation sequence. By adopting the method, the operation behavior of the user can be accurately reproduced, and developers are helped to position the cause of the problem.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a user behavior playback method, apparatus, computer device, and storage medium. Background Technology

[0002] With the development of internet algorithm technology, large-scale user behavior data monitoring technology has emerged. This technology can comprehensively capture and store user behavior data such as clicks, browsing, and transactions on the platform, which in turn leads to methods for identifying user behavior anomalies and locating problems that rely on manual analysis.

[0003] However, current manual analysis methods suffer from low processing efficiency when dealing with massive amounts of collected data and are prone to missing key abnormal behaviors, making it difficult for developers to accurately reproduce the operating environment and operation sequence at the time. Summary of the Invention

[0004] Therefore, it is necessary to provide a user behavior playback method, apparatus, computer equipment, and storage medium that can accurately reproduce user operation behavior in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a user behavior playback method, including: In response to the current application's log retrieval request, the corresponding log information is retrieved from the pre-configured log repository based on the user information in the log retrieval request. The log information includes user behavior event logs and interface event logs. In response to a request to replay user behavior, determine the user's operation sequence and the request time corresponding to the operation sequence based on log information; User behavior is replayed based on the user's sequence of actions and the corresponding request times.

[0006] In one embodiment, the user behavior replay method further includes: Retrieve the target interface pre-configured for the current application; In response to the current application's log retrieval request, retrieve the corresponding log information from a pre-configured log repository based on the user information in the log retrieval request, including: Log information is retrieved from the log repository based on the user information and time period carried in the target interface and log retrieval request.

[0007] In one embodiment, in response to a request for user behavior replay, determining the user's operation sequence and the request time corresponding to the operation sequence based on log information includes: The Long Short-Term Memory (LSTM) network model is used to process user behavior tracking logs in order to extract user action sequences. The request and response times of the operation sequence are determined based on user behavior tracking logs and API tracking logs, and the request duration is determined based on the request and response times.

[0008] In one embodiment, the user behavior replay method further includes: Generate at least one session record based on the log information and display the session record; In response to a trigger command from a target session record in the selected session records, submit a request to replay user behavior. User behavior replay is performed based on the user's action sequence and the corresponding request times, including: The user's actions are replayed from the target session record based on the user's sequence of actions and the corresponding request times.

[0009] In one embodiment, the user behavior replay method further includes: The isolated forest algorithm is used to detect abnormal user actions by analyzing user behavior logs. The abnormal user operations are clustered using a clustering algorithm to obtain the percentage of users with abnormal operations. User behavior analysis results are generated based on abnormal operations and the percentage of users who perform abnormal operations.

[0010] In one embodiment, the user behavior replay method further includes: The network status analysis results are determined based on the request time corresponding to the user's operation sequence and the pre-configured interface response time.

[0011] In one embodiment, in response to a log retrieval request from the current application, corresponding log information is retrieved from a pre-configured log repository based on the user information in the log retrieval request, including: In response to the current application's page loading request, identify interactive elements within the current page and extract key interactive elements to be tracked. Add listeners to key interactive elements; In response to interactive operations triggered by key interactive elements, user behavior tracking logs and interface tracking logs are collected in real time through listeners and stored in the log repository.

[0012] Secondly, this application provides a user behavior playback device, comprising: The acquisition module is used to respond to the log acquisition request of the current application and retrieve the corresponding log information from the pre-configured log repository based on the user information in the log acquisition request. The log information includes user behavior tracking logs and interface tracking logs. The determination module is used to respond to user behavior replay requests by determining the user's operation sequence and the corresponding request time based on log information. The replay module is used to replay user behavior based on the user's operation sequence and the corresponding request time.

[0013] In a third aspect, this application provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the user behavior playback method provided in any embodiment of the first aspect of this application.

[0014] In a fourth aspect, this application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the user behavior playback method provided in any embodiment of the first aspect of this application.

[0015] The aforementioned user behavior playback method, device, computer equipment, and storage medium obtain corresponding user behavior tracking logs and interface tracking logs from a pre-configured log repository, integrate the user behavior tracking logs and interface tracking logs, and further replay the user operation process in video form based on the user behavior tracking logs and interface tracking logs. This achieves a complete restoration of the user's operation behavior, making it easier for developers to analyze user behavior and helping them locate the cause of problems. It solves the problem in traditional technologies where developers find it difficult to accurately restore the user's operating environment and operation sequence when encountering bugs or abnormal situations. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating the user behavior replay method in some embodiments; Figure 2 This is a schematic diagram of the configuration interface in some embodiments; Figure 3 This is a schematic diagram of the session recording display interface in some embodiments; Figure 4 This is a structural block diagram of the user behavior playback device in some embodiments; Figure 5 This is a diagram showing the internal structure of a computer device in some embodiments. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0018] In a first aspect, this application provides a method for replaying user behavior, such as Figure 1 As shown, taking the application of this method to a terminal as an example, the steps include: Step S11: In response to the current application's log retrieval request, retrieve the corresponding log information from the pre-configured log repository based on the user information in the log retrieval request. The log information includes user behavior tracking logs and interface tracking logs.

[0019] Here, "current application" refers to the application to which the user behavior to be replayed belongs. For example, if we need to replay user behavior in WeChat, then WeChat is the current application. This application requires pre-binding the current application, specifically by entering the domain name address of the current application. Log information from the current application will be retrieved subsequently based on this domain name address.

[0020] A log retrieval request is an instruction initiated by an application or operator to retrieve log data from a specified user. It typically includes parameters such as a request identifier and the target user range.

[0021] User information refers to characteristic data used to uniquely identify users, such as user ID and device number.

[0022] A log repository is a database or storage medium used to centrally store user behavior tracking logs and interface tracking logs.

[0023] Log information refers to the collection of all log data retrieved from the log repository that matches the target user, and serves as the data source for subsequent behavior replay.

[0024] User behavior event logs are records of user interactions with the application collected by event listeners, such as timestamps, element attributes, and page states for actions like clicking the "Buy Now" button, entering search keywords, and scrolling through a page.

[0025] Interface logging records are the records of interface calls between the application and the backend server during user interaction, such as interface request parameters, response results, and call time.

[0026] Specifically, this application can monitor log retrieval requests sent by the current application and parse the user information carried in the requests. Based on the address of a pre-configured log repository, it retrieves the corresponding log information from the log repository.

[0027] Please refer to Figure 2 , Figure 2 This is a schematic diagram of the configuration interface in one embodiment. Figure 2 In the application, users can bind the current application by entering its domain name address through an address input control. The configuration area allows users to configure the log repository address, log data format, and other log-related settings. The preview webpage on the left displays a video replay of user behavior.

[0028] Step S12: In response to the user's request to replay the behavior, determine the user's operation sequence and the request time corresponding to the operation sequence based on the log information.

[0029] Among them, the request for user behavior replay is an instruction initiated by the application or operator to restore the target user's historical interaction process.

[0030] A user's action sequence is an ordered set of continuous user interactions, sorted by timestamps in the log information, such as entering a product details page, clicking on a product image, selecting product specifications, and clicking "add to cart."

[0031] The request time corresponding to the operation sequence refers to the time spent on the interface call associated with each action in the operation sequence, or the time interval between two adjacent operations, which is used to accurately reproduce the rhythm of user operations.

[0032] Specifically, this application can receive requests for user behavior replay and retrieve the log information obtained in step S11. The user behavior event logs in the log information are sorted in ascending order by timestamp to identify the user's continuous interactive actions and generate a user operation sequence. The interface event logs corresponding to each action in the operation sequence are associated, the interface call time is extracted, and the request time corresponding to the operation sequence is calculated. The operation sequence and the corresponding request time are then associated and stored.

[0033] Step S13: Replay user behavior based on the user's operation sequence and the request time corresponding to the operation sequence.

[0034] User behavior replay refers to the technical action of accurately reconstructing the historical interaction process of a target user in the current application based on the operation sequence and request time. It can intuitively reproduce the user's operation steps, rhythm and corresponding interface response status.

[0035] Specifically, this application can read the user's operation sequence and the corresponding request time. Following the chronological order of the operation sequence, it simulates each user interaction behavior in the current application, such as locating the corresponding page element and simulating clicks, input, scrolling, etc. The execution rhythm of each operation is controlled based on the request time, such as setting operation intervals according to the API call duration, thus recreating the speed of the user's actual operations. During the replay process, the corresponding API logging information is simultaneously displayed, achieving a fully visualized reconstruction of the user's behavior.

[0036] In one embodiment, the user behavior replay method may further include: obtaining a target interface pre-configured for the current application, responding to a log retrieval request from the current application, and retrieving corresponding log information from a pre-configured log repository based on the user information in the log retrieval request, including: retrieving log information from the log repository based on the target interface and the user information and time period carried in the log retrieval request.

[0037] The target interface refers to the pre-configured response interface related to the user behavior to be replayed.

[0038] Specifically, this application pre-configures the target interface for the current application. This interface is the business response interface associated with the user behavior to be replayed, such as the product information query interface, the order submission interface, etc., and completes the parameter mapping between the interface and the log repository.

[0039] In response to the current application's log retrieval request, first extract the user information and time period carried in the request, such as the start and end timestamps of the behavior and the identifier of the target interface corresponding to the behavior to be replayed. Use the user information, time period, and target interface identifier as a joint filtering condition to query log information from the log repository, and extract the user behavior event logs and interface event logs generated by the user calling the target interface within the specified time period, such as interface response time and parameters.

[0040] The beneficial effect of this embodiment is that by adding a target interface as a filtering dimension, and combining user information and time period, the log data corresponding to the behavior to be replayed can be directly located, avoiding the retrieval of a large number of irrelevant logs.

[0041] In one embodiment, in response to a request for user behavior replay, the user's operation sequence and the request time corresponding to the operation sequence are determined based on log information, including: processing the user behavior tracking logs using a Long Short-Term Memory network model to extract the user's operation sequence, determining the request time and response time of the operation sequence based on the user behavior tracking logs and interface tracking logs, and determining the request duration based on the request time and response time.

[0042] Among them, the Long Short-Term Memory (LSTM) network model is an improved recurrent neural network used to process time-dependent data. It can effectively capture the sequential relationship of user behavior tracking logs and is suitable for extracting ordered user operation sequences from disordered or scattered log data.

[0043] Request time refers to the timestamp when a user triggers a certain interactive operation, and the corresponding business interface sends a data request to the backend server.

[0044] Response time refers to the timestamp after the backend server receives the interface request, completes the data processing, and returns the response result to the current application. It is also recorded by the interface instrumentation log and is a key basis for judging the server processing time.

[0045] Specifically, this application can retrieve user behavior tracking logs, extract temporal feature data such as operation actions, operation timestamps, and page element identifiers from the logs, and input them into a Long Short-Term Memory (LSTM) network model after preliminary sorting by time dimension. The LSM network model learns the temporal dependencies between operation actions through a gating mechanism, filters out invalid or interfering operations, and outputs a continuous user operation sequence that conforms to the user's actual interaction logic. For each operation action in the extracted operation sequence, the corresponding interface tracking logs are associated, and the request time and response time of the interface triggered by that operation are extracted. For each operation action, the interface call time of a single operation is calculated using the formula Request Duration = Request Time - Response Time. Then, the request durations of all operations are associated with the operation sequence and stored to form complete replay base data.

[0046] The data processing steps for the Long Short-Term Memory (LSTM) network model include: The data in user behavior tracking logs is structured, and features such as action types (clicks, inputs, navigation, timestamps, and associated page elements) are extracted. These features are then arranged chronologically into a time-series input sequence and fed into an LSTM model. The LSTM model filters out invalid operations from the logs using a forget gate; it selects and retains valid operation features related to core interaction logic using an input gate, such as consecutive actions like clicking on product details pages, selecting specifications, and adding items to the cart; and it extracts the time-series correlation features of the filtered valid operations using an output gate.

[0047] Furthermore, based on the filtered valid operation sequences, the logical relationships between adjacent operations are learned, and a temporal dependency model of user interaction behavior is constructed to correct the timestamp errors in the logs caused by network latency and operation lag. Based on the constructed temporal dependency model, a user operation sequence ordered according to the actual interaction logic is output.

[0048] The beneficial effect of this embodiment is that the Long Short-Term Memory Network model can accurately capture the temporal correlation of user behavior. Compared with the traditional timestamp sorting method, it can effectively filter out invalid operations, generate operation sequences that are more in line with the user's real interaction process, and reduce replay deviation.

[0049] In one embodiment, the user behavior replay method may further include: generating at least one session record based on log information and displaying the session record; responding to a trigger instruction of a target session record in the selected session record; submitting a request for user behavior replay; and performing user behavior replay based on the user's operation sequence and the request time corresponding to the operation sequence, including: performing user behavior replay on the target session record based on the user's operation sequence and the request time corresponding to the operation sequence.

[0050] Session records refer to structured records generated by integrating user behavior tracking logs and interface tracking logs according to the cycle of a single user session. They contain core data such as operation actions, interface call information, and timestamp sequences within the session. Multiple independent interactions of a user correspond to multiple session records.

[0051] The target session record refers to the specific session record that the user selects from multiple session records for which the action replay operation needs to be performed.

[0052] Specifically, this application can retrieve acquired user log information and divide a single user session into cycles based on session segmentation rules (e.g., from when a user opens the application to when they place an order). It then integrates and correlates data such as actions, API call timestamps, and timestamps within each cycle to generate at least one structured session record. Key information from all session records, such as session start and end times and core operation summaries, is displayed on the front-end interface. Responding to user selections on the front-end interface, it captures trigger commands for a specific session record. Using this target session record as a parameter, it automatically submits a user behavior replay request. It retrieves the associated user operation sequence and corresponding request timestamps from the target session record. Following the temporal logic of the operation sequence, it simulates and executes each interactive action, controlling the operation rhythm based on the request timestamps to fully recreate the user's actual interaction process within the session.

[0053] Please refer to Figure 3 , Figure 3 This is a schematic diagram illustrating the page display of session records in one embodiment. Figure 3 In the dialog box, users can enter a user ID and a time range. The dialog box will then display all dialog records that match the user ID and time range. Users can select one or more dialog records and click the "Confirm" button to trigger a request to replay the user behavior. The user behavior will then be replayed on the preview webpage.

[0054] The beneficial effects of this embodiment are: dividing user behavior according to session cycle, avoiding the mixing of log data from different interaction scenarios, allowing users to accurately select the target session that needs to be replayed, and greatly reducing the processing cost of invalid data.

[0055] In one embodiment, the user behavior replay method may further include: detecting abnormal user actions using the isolated forest algorithm from user behavior tracking logs; and clustering the abnormal user actions using a clustering algorithm to obtain the percentage of users with abnormal actions. User behavior analysis results are generated based on abnormal operations and the percentage of users who perform abnormal operations.

[0056] Among them, the Isolation Forest algorithm is an anomaly detection algorithm based on unsupervised learning. By constructing multiple isolated trees, it recursively divides the data samples in the user behavior tracking logs and judges behaviors with short partitioning paths and easy isolation as abnormal operations. It is suitable for anomaly detection of time-series behavior data that does not require labeled samples.

[0057] Clustering algorithms are unsupervised learning algorithms that group similar data samples into the same category and different samples into different categories. Here, they are used to classify and aggregate abnormal operations detected by the Isolation Forest algorithm according to their operation features.

[0058] Abnormal user actions refer to records of actions that deviate from the user's normal interaction logic and do not conform to the application's preset behavior patterns. For example, if a user spends an unusually long time on a product details page and clicks on product images multiple times without making a purchase, this is identified as abnormal behavior. Cluster analysis revealed that 47% of users exhibited similar abnormal behavior on this page.

[0059] Generating user behavior analysis results refers to integrating data such as the type of abnormal operation, distribution characteristics, and corresponding user proportion to form a structured analysis report. For example, clustering algorithm analysis may reveal that 47% of users exhibited similar abnormal dwell behavior on the page.

[0060] Specifically, this application can extract operation feature data from user behavior tracking logs and input it into an isolated forest algorithm model. The isolated forest algorithm model recursively divides the feature data by constructing an isolated tree group, calculates the isolation degree of each operation sample, and filters out operations with an isolation degree higher than a preset threshold, marking them as abnormal user operations.

[0061] Furthermore, all detected abnormal operation samples are input into a clustering algorithm (such as K-Means) and classified and aggregated according to the similarity of operation features to obtain several abnormal operation categories; the number of users corresponding to abnormal operations under each category is counted, and the user proportion of each type of abnormal operation is calculated.

[0062] Furthermore, it integrates information on the categories, specific manifestations, triggering scenarios, and user percentages of abnormal operations, and conducts comparative analysis with benchmarks of normal user behavior; it generates structured user behavior analysis results according to preset templates, which may include visual charts, such as pie charts of abnormal type distribution, bar charts of user percentages, and text descriptions.

[0063] The beneficial effects of this embodiment are as follows: the isolated forest algorithm does not rely on labeled samples, can efficiently process high-dimensional user behavior time-series data, accurately capture hidden abnormal operations, and the clustering algorithm can classify scattered abnormal operations according to features, clarify the types and patterns of high-incidence anomalies. The generated user behavior analysis results can directly provide decision-making basis for application function iteration, interaction design optimization, and fault diagnosis.

[0064] In one embodiment, the user behavior replay method may further include: determining the analysis results of the network status based on the request time corresponding to the user's operation sequence and the pre-configured interface response time.

[0065] Among them, the interface response time refers to the pre-configured baseline time threshold for the target interface to process a single request and return a result, which is usually set based on the ideal or standard value of the interface performance test.

[0066] The network status analysis results refer to the network status obtained by comparing the actual time taken for the corresponding request in the user operation sequence with the interface response time, such as network smoothness, network latency, network lag, etc.

[0067] Specifically, this application can collect the actual request time for each step in a user's operation sequence, i.e., the total time from sending the request to receiving the response. It retrieves the response time of the corresponding interface pre-configured in the system. Pre-defined comparison rules are established, for example: if the actual request time is less than or equal to the interface response time, the network is considered unobstructed; if the interface response time is less than or equal to twice the actual request time, it is considered slightly delayed; if the actual request time is greater than twice the interface response time, it is considered severely laggy. Based on these rules, the network status conclusions for each step are generated and then integrated into a complete network status analysis result.

[0068] The beneficial effect of this embodiment is that when replaying user behavior, it is possible to distinguish whether the operation lag is caused by an interface performance problem or a network problem, thus avoiding confusion in attribution.

[0069] In one embodiment, in response to a log retrieval request from the current application, corresponding log information is retrieved from a pre-configured log repository based on the user information in the log retrieval request. This includes: in response to a page loading request from the current application, identifying interactive elements within the current page, extracting key interactive elements to be tracked, and adding listeners to the key interactive elements. In response to interactive operations triggered by key interactive elements, user behavior tracking logs and interface tracking logs are collected in real time through listeners and stored in the log repository.

[0070] A page load request refers to a command request triggered by a user or application to obtain page resources from the server and render and display them on the client side, such as a page jump request initiated when a user clicks on a function entry point.

[0071] Interactive elements refer to user interface components on a page that support user operations, including elements such as buttons, input boxes, drop-down menus, and checkboxes that can trigger functional logic.

[0072] Key interactive elements refer to interactive elements that have core value for business process or user behavior analysis, such as payment buttons, form submission buttons, and core function entry buttons.

[0073] A listener is a pre-written event listener program that can be bound to a target element to capture specific operations of the element and trigger preset log collection logic.

[0074] Interactive actions refer to the active actions performed by users on interactive elements on a webpage, such as clicking buttons, entering text, selecting drop-down options, and swiping to switch pages.

[0075] Specifically, this application can listen for page loading requests of the current application. When a request is triggered, DOM (Document Object Model) parsing technology is used to identify all interactive elements. The interactivity of elements is determined based on characteristics such as element tag type, CSS (Cascading Style Sheets) styles, and event listeners. All interactive elements in the currently loading page are scanned and identified to form an element list. According to business rules, key interactive elements are selected from the list. Preset listeners are bound to the selected key interactive elements to listen for user clicks, inputs, scrolling, page jumps, and other operations. When the user performs an interactive operation on a key interactive element, the listener is triggered, and user behavior logs corresponding to the operation are collected in real time, such as operation type, operation time, user identifier, and interface logs, such as interface request parameters, response status, and time consumption. The collected log data is standardized and stored in a pre-configured log repository, completing one log collection process.

[0076] For example, when a user visits a product details page, the system automatically identifies key elements such as the "Buy Now" button, product images, and price information, and automatically adds event listeners to these elements. When the user clicks the "Buy Now" button, the system records information such as click coordinates, element attributes, page state, and timestamp.

[0077] The beneficial effect of this embodiment is that by triggering the collection through a listener, user operations and corresponding interface calls can be captured synchronously, realizing intelligent data collection and tracking.

[0078] In a second aspect, this application provides a user behavior playback device, such as Figure 4 As shown, the user behavior playback device includes: an acquisition module 41, a determination module 42, and a playback module 43, wherein: The acquisition module 41 is used to respond to the log acquisition request of the current application and obtain the corresponding log information from the pre-configured log repository based on the user information in the log acquisition request. The log information includes user behavior tracking logs and interface tracking logs. The determination module 42 is used to respond to the user behavior replay request and determine the user's operation sequence and the request time corresponding to the operation sequence based on the log information; The replay module 43 is used to replay user behavior based on the user's operation sequence and the request time corresponding to the operation sequence.

[0079] In some embodiments, the acquisition module 41 can also acquire a target interface pre-configured for the current application, and acquire log information from the log repository based on the target interface and the user information and time period carried in the log acquisition request.

[0080] In some embodiments, the determining module 42 can use a long short-term memory network model to process user behavior tracking logs to extract user operation sequences, determine the request time and response time of the operation sequence based on the user behavior tracking logs and interface tracking logs, and determine the request duration based on the request time and response time.

[0081] In some embodiments, the determining module 42 can also generate at least one session record based on log information and display the session record. In response to the triggering instruction of the target session record in the selected session record, it submits a request for user behavior playback. The playback module 43 can play back the user behavior of the target session record based on the user's operation sequence and the request time corresponding to the operation sequence.

[0082] In some embodiments, the determining module 42 can also detect user behavior logging points based on the isolated forest algorithm to obtain abnormal user operations, perform clustering processing on the abnormal user operations based on the clustering algorithm to obtain the user proportion of abnormal operations, and generate user behavior analysis results based on the abnormal operations and the user proportion of abnormal operations.

[0083] In some embodiments, the determining module 42 can also determine the analysis results of the network status based on the request time corresponding to the user's operation sequence and the pre-configured interface response time.

[0084] In some embodiments, the acquisition module 41 can respond to the current application's page loading request, identify interactive elements within the current page, and extract key interactive elements to be tracked. Add listeners to key interactive elements to respond to interactive operations triggered by key interactive elements. Collect user behavior tracking logs and interface tracking logs in real time through listeners and store them in the log repository.

[0085] In a third aspect, this application provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the user behavior playback method provided in any embodiment of the first aspect of this application.

[0086] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a user behavior playback method. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0087] In a fourth aspect, this application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the user behavior playback method provided in any embodiment of the first aspect of this application.

[0088] The computer-readable storage medium may be Figure 5 The computer-readable storage medium in the computer device shown.

[0089] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0090] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0091] The above embodiments merely illustrate several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for replaying user behavior, characterized in that, The method includes: In response to the current application's log retrieval request, the corresponding log information is retrieved from a pre-configured log repository based on the user information in the log retrieval request. The log information includes user behavior tracking logs and interface tracking logs. In response to a request to replay user behavior, the user's operation sequence and the request time corresponding to the operation sequence are determined based on the log information; User behavior is replayed based on the user's operation sequence and the request time corresponding to the operation sequence.

2. The method according to claim 1, characterized in that, The method further includes: Obtain the target interface pre-configured for the current application; The step of responding to a log retrieval request from the current application and retrieving corresponding log information from a pre-configured log repository based on the user information in the log retrieval request includes: The log information is retrieved from the log repository based on the target interface and the user information and time period carried in the log retrieval request.

3. The method according to claim 2, characterized in that, The step of responding to a user behavior replay request by determining the user's operation sequence and the request time corresponding to the operation sequence based on the log information includes: The user behavior tracking logs are processed using a long short-term memory network model to extract the user's operation sequence; The request time and response time of the operation sequence are determined based on the user behavior tracking logs and the interface tracking logs, and the request duration is determined based on the request time and response time.

4. The method according to claim 1, characterized in that, The method further includes: Generate at least one session record based on the log information, and display the session record; In response to a trigger command that selects a target session record in the selected session records, a request to replay the user behavior is submitted; The step of replaying user behavior based on the user's operation sequence and the request time corresponding to the operation sequence includes: The user's behavior is replayed in the target session record based on the user's operation sequence and the request time corresponding to the operation sequence.

5. The method according to claim 1, characterized in that, The method further includes: The user behavior logs are analyzed using the isolated forest algorithm to detect abnormal user actions. The abnormal operations of the users are clustered according to the clustering algorithm to obtain the proportion of users with abnormal operations. Based on the abnormal operations and the percentage of users who performed the abnormal operations, user behavior analysis results are generated.

6. The method according to claim 1, characterized in that, The method further includes: The network status analysis results are determined based on the request time corresponding to the user's operation sequence and the pre-configured interface response time.

7. The method according to claim 1, characterized in that, The step of responding to a log retrieval request from the current application and retrieving corresponding log information from a pre-configured log repository based on the user information in the log retrieval request includes: In response to the page loading request of the current application, identify the interactive elements in the current page and extract the key interactive elements to be tracked; Add listeners to the key interactive elements; In response to the interactive operation triggered by the key interactive element, the listener collects the user behavior tracking logs and the interface tracking logs in real time and stores them in the log repository.

8. A user behavior playback device, characterized in that, The device includes: The acquisition module is used to respond to the log acquisition request of the current application and acquire the corresponding log information from the pre-configured log repository according to the user information in the log acquisition request. The log information includes user behavior tracking logs and interface tracking logs. The determination module is used to respond to a user behavior replay request and determine the user's operation sequence and the request time corresponding to the operation sequence based on the log information; The replay module is used to replay user behavior based on the user's operation sequence and the request time corresponding to the operation sequence.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images