User continuous characteristic behavior test method, electronic equipment and storage medium

Abstract

The invention relates to the technical field of software testing, and provides a user continuous characteristic behavior testing method, electronic equipment and a storage medium, and the method comprises the steps: collecting user track and click event data, and preprocessing the user track and click event data into user continuous behavior data according to a time sequence; converting historical user continuous behavior data into reference sample data; constructing and training an LSTM model through the reference sample data; collecting continuous behavior data of the user in real time, and judging whether the continuous behavior data is abnormal or not through an LSTM model; and giving an alarm according to the abnormity. According to the scheme, the data sample and the model data can be updated everyday to adapt to internet business characteristics with fast rhythm change; through the model, the abnormal behavior of a single user can be judged, and the system abnormality in the regional time can be detected; and an abnormal early warning module is provided, and the behavior template can be automatically maintained.

Description

Technical Field

[0001] The present application relates to the field of software testing technology, and in particular to a method for testing user continuous characteristic behavior, an electronic device, and a storage medium. Background Art

[0002] Software products rely on the UI (User Interface) for human-computer interaction. The user interface is directly related to the user experience of the software product, and the quality of the UI is crucial to the overall usability of the software product. However, UI testing is labor-intensive and costly. For certain complex UI testing techniques, the testing workflow is unclear, the test framework maintenance costs are high, and test case pass rate statistics are inaccurate. No matter how complex or important the technical architecture, users ultimately interact with the front-end UI. Modern software products incorporate a wealth of front-end business logic and specifications in addition to back-end logic. Relying solely on back-end interfaces and simple unit tests cannot effectively demonstrate user-side product usability. Furthermore, automated testing techniques rely on the current test environment and cannot be run independently. This not only generates a large amount of invalid business data and consumes system memory, but also results in redundant code in the automated testing framework, resulting in low software product quality. However, existing solutions suffer from several drawbacks: They rigidly define sample and calculation model data, making them unsuitable for the volatile nature of internet products or businesses; they only calculate scores based on single-user behaviors, lacking overall anomaly risk monitoring; and they lack anomaly warning modules, let alone warnings for specific abnormal behaviors or business anomaly modules. Summary of the Invention

[0003] In order to help improve the problem of lack of overall abnormal risk monitoring in the existing technology, the present application provides a user continuous characteristic behavior testing method, electronic device and storage medium.

[0004] In a first aspect, the present application provides a method for testing a user's continuous characteristic behavior, the method comprising the steps of:

[0005] Collect user trajectory and click event data, and pre-process them into user continuous behavior data in chronological order;

[0006] Convert historical user continuous behavior data into benchmark sample data;

[0007] Build and train the LSTM model using benchmark sample data;

[0008] Collect users' continuous behavior data in real time and use the LSTM model to determine whether it is abnormal;

[0009] Issue alerts based on exceptions.

[0010] By adopting the above technical solutions, the efficiency of UI testing and overall abnormal risk monitoring can be greatly improved.

[0011] In a second aspect, the present application provides an electronic device, which adopts the following technical solution:

[0012] An electronic device, comprising:

[0013] at least one processor;

[0014] Memory;

[0015] At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the user continuous characteristic behavior testing method as described above.

[0016] In a third aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0017] A computer-readable storage medium stores a computer program thereon, which, when executed in a computer, causes the computer to execute any one of the user continuous characteristic behavior testing methods provided in the first aspect.

[0018] To sum up, the present application includes at least one of the following beneficial technical effects: data samples and model data can be updated daily to adapt to the fast-changing characteristics of Internet business; the model can not only judge the abnormal behavior of individual users, but also detect system anomalies within regional time; there is an abnormal warning module, and the behavior template will be automatically maintained. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a flow chart of a method for testing user continuous characteristic behavior provided by an embodiment of the present application;

[0020] Figure 2 This is a flowchart of a method for testing user continuous characteristic behavior provided by another embodiment of the present application;

[0021] Figure 3 This is a schematic diagram of the module principle of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of this application more clear, the following Figure 1-3 It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application.

[0023] An embodiment of the present application provides a method for testing user continuous characteristic behavior, which is used in a testing system.

[0024] This embodiment uses the UI test system as an application example to specifically illustrate the above method. In actual implementation, the above method can also be used in other test systems, which is not limited in this embodiment.

[0025] Specific reference Figure 1 The technical solution of the embodiment of the present invention proposes a method for testing user continuous characteristic behavior, which includes the following steps:

[0026] S10: Collect user trajectory and click event data, and pre-process them into user continuous behavior data in chronological order; when collecting user trajectory and click event data: collect multiple continuous trajectory and click event data of the user through multiple embedding points.

[0027] S20: Convert historical user continuous behavior data into benchmark sample data;

[0028] S30: Build and train an LSTM model using benchmark sample data;

[0029] S40: Collects user continuous behavior data in real time and uses the LSTM model to determine whether it is abnormal;

[0030] When determining whether an abnormality is detected through the LSTM model: the LSTM model generates a user behavior template and sets a normal value range for the data; the user's continuous behavior data for a preset time period is input into the behavior template and judged as normal / abnormal / mismatched behavior.

[0031] S50: Issue an alarm based on the abnormality.

[0032] After the LSTM model training is completed, new user continuous behavior data is added in real time to train and correct the LSTM model.

[0033] The present invention is based on a method for monitoring abnormalities in user continuous behavior, and belongs to the field of big data. Model data training is performed based on user historical trajectories and click events. The main training method is user continuous behavior sample data. The sample data is used as the basic data of the LSTM model to perform abnormal judgment on user trajectories and continuous click behaviors in regional time and date. When the abnormal behavior reaches the warning threshold preset by the model, an abnormal detection warning will be triggered.

[0034] Based on the embodiment of the present invention, further determining whether the user's continuous behavior is abnormal includes:

[0035] Long-term user data is processed asynchronously to generate aggregated data of user continuous behavior and fluctuation trends in different time dimensions, and system anomalies are judged based on trend fluctuation thresholds.

[0036] Determining whether the user's continuous behavior is abnormal also includes:

[0037] The user data of a short time area is asynchronously modeled, and the system anomaly judgment is performed on the abnormal behavior of the user's continuous behavior based on the model anomaly judgment threshold.

[0038] Furthermore, determining whether the user's continuous behavior is abnormal also includes:

[0039] The real-time user data is processed by the model in real time, and abnormal judgments are made on the user's continuous behavior or multiple abnormal behaviors based on the model's abnormal judgment threshold.

[0040] This technical solution can adapt to the differences generated by different Internet businesses. It has different starting points, starting from the company's business and system, and is more inclined to ensure the stability of the system and user experience.

[0041] In another embodiment of the present invention, referring to Figure 2 As shown, the method includes: collecting and synchronizing user trajectory and click event tracking data, preprocessing the user data into user continuous behavior data in user time sequence; training a large amount of user historical behavior data into user common behavior sample data through a model; and using the sample data as the benchmark sample data of the LSTM model;

[0042] There are three main methods for detecting abnormal user behavior:

[0043] Process long-term user data through asynchronous models to generate aggregated data of user continuous behavior and fluctuation trends in different time dimensions. Detect system anomalies and issue early warnings based on trend fluctuation thresholds.

[0044] The user data of a short time period is asynchronously modeled, and the system abnormality judgment and warning are made for abnormal user continuous behavior based on the model abnormality judgment threshold;

[0045] The real-time user data is processed by the model in real time, and abnormal judgments and warnings are made for users' continuous or multiple abnormal behaviors based on the model's abnormal judgment threshold.

[0046] The present application also provides an electronic device, such as Figure 3 As shown, Figure 3 The electronic device 700 shown includes a processor 701 and a memory 703. The processor 701 and the memory 703 are connected, for example, via a bus 702. Optionally, the electronic device 700 may further include a transceiver 704. It should be noted that in actual applications, the number of transceivers 704 is not limited to one, and the structure of the electronic device 700 does not constitute a limitation on the embodiments of the present application.

[0047] Processor 701 can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 701 can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0048] The bus 702 may include a path for transmitting information between the above components. The bus 702 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 702 may be divided into an address bus, a data bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0049] The memory 703 can be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0050] The memory 703 is used to store application code for executing the solution of the present application, and the execution is controlled by the processor 701. The processor 701 is used to execute the application code stored in the memory 703 to implement the content shown in the above method embodiment.

[0051] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, notebook computers, PDAs (personal digital assistants), and PADs (tablet computers), and fixed terminals such as digital TVs and desktop computers, and may also be servers. Figure 3 The electronic device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0052] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed in a computer, the computer is caused to execute the user continuous characteristic behavior testing method provided in the above embodiment.

[0053] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps and they may be performed in other orders.

[0054] The above are only some of the implementation methods 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 method for testing user continuous characteristic behavior, characterized in that: The method comprises the steps of: Collect user trajectory and click event data, and pre-process them into user continuous behavior data in chronological order; Convert historical user continuous behavior data into benchmark sample data; Build and train the LSTM model using benchmark sample data; Collect users' continuous behavior data in real time and use the LSTM model to determine whether it is abnormal; Issue alerts based on exceptions.

2. The user continuous characteristic behavior testing method according to claim 1, characterized in that: Determining whether a user's continuous behavior is abnormal includes: Long-term user data is processed asynchronously to generate aggregated data of user continuous behavior and fluctuation trends in different time dimensions, and system anomalies are judged based on trend fluctuation thresholds.

3. The user continuous characteristic behavior testing method according to claim 1, characterized in that: Determining whether a user's continuous behavior is abnormal includes: The user data of a short time area is asynchronously modeled, and the system anomaly judgment is performed on the abnormal behavior of the user's continuous behavior based on the model anomaly judgment threshold.

4. The user continuous characteristic behavior testing method according to claim 1, characterized in that: Determining whether a user's continuous behavior is abnormal includes: The real-time user data is processed by the model in real time, and abnormal judgments are made on the user's continuous behavior or multiple abnormal behaviors based on the model's abnormal judgment threshold.

5. The user continuous characteristic behavior testing method according to claim 1, characterized in that: After the LSTM model training is completed, new user continuous behavior data is added in real time to train and correct the LSTM model.

6. The user continuous characteristic behavior testing method according to claim 1, characterized in that: When using the LSTM model to determine whether an anomaly exists: The LSTM model generates user behavior templates and sets the normal value range of the data; The user's continuous behavior data within a preset time period is input into the behavior template and judged as normal / abnormal / mismatching behavior.

7. The user continuous characteristic behavior testing method according to claim 1, characterized in that: When collecting user trajectory and click event data: collect multiple continuous user trajectory and click event data through multiple embedding points.

8. An electronic device, characterized in that: The electronic device includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the user continuous characteristic behavior testing method described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the user continuous characteristic behavior testing method according to any one of claims 1 to 7.

Images