Live broadcast test method and device, electronic equipment and medium

Abstract

The embodiment of the invention provides a live broadcast test method and device, electronic equipment and a medium, which are used for accurately and effectively realizing automatic test of live broadcast. According to the method, at least one browser instance is created, and each instance independently opens live broadcast content to be tested so as to simulate watching behaviors of different users. By integrating a large language model, feedback related to live broadcast content can be automatically obtained and generated, and the feedback is submitted as simulation comments. Meanwhile, the quality performance of the live broadcast is continuously monitored. According to the method, the simulation that multiple users watch the live broadcast concurrently is realized, and the user comment behavior is successfully simulated, so that the quality of the to-be-tested live broadcast is effectively monitored and evaluated.

Description

Technical Field

[0001] The present invention relates to the technical field of system testing, and in particular, to a live broadcast testing method, device, electronic device and medium. Background Art

[0002] With the rapid development of network technology, live broadcast has become a popular online interaction method, attracting a large number of users to participate. In order to improve the user experience, the live broadcast platform needs to be able to handle high-concurrency user requests while ensuring the quality of the live broadcast content and the fluency of the interaction.

[0003] To ensure the achievement of these goals, it is necessary to conduct a comprehensive test on the live broadcast system, including simulating the behaviors and feedback of real users. Compared with traditional testing methods, the automated live broadcast testing system has the advantages of being able to perform multi-concurrency user simulation testing, monitoring the live broadcast room for a long time, and having better cost-effectiveness. Therefore, it is particularly important to develop an automated testing method that can simulate various user behaviors and provide intelligent interaction functions. Summary of the Invention

[0004] Embodiments of the present invention provide a live broadcast testing method, device, electronic device and medium for accurately and effectively realizing the automated testing of live broadcasts.

[0005] In a first aspect, embodiments of the present invention provide a live broadcast testing method, the method including: Creating at least one browser instance, and opening the live broadcast to be tested based on each browser instance, where each browser simulates a different user; For each browser instance, obtaining corresponding live broadcast feedback based on a large language model, and feeding back the live broadcast feedback as a simulated comment of the corresponding user of the browser instance; Monitoring the quality of the live broadcast to be tested.

[0006] Further, the creating at least one browser instance includes: Creating at least one browser instance based on playwright.

[0007] Further, after opening the live broadcast to be tested based on each browser instance and before monitoring the quality of the live broadcast to be tested, it further includes: Simulating user behaviors by calling a user behavior script; where the user behaviors are commenting, liking, and exiting the live broadcast.

[0008] Further, the obtaining corresponding live broadcast feedback based on a large language model includes: Identifying the voice in the live broadcast to be tested and the conversation information in the comment area; Input the text content corresponding to the voice and the conversation information into a large language model to obtain the live broadcast feedback output by the large language model.

[0009] Further, the step of inputting the text content corresponding to the voice and the conversation information into a large language model to obtain the live broadcast feedback output by the large language model includes: Input the text content corresponding to the voice, the conversation information, and the pre - saved prompt text into a large language model to obtain the live broadcast feedback output by the large language model, where the prompt text is used to prompt the large language model to output corresponding feedback.

[0010] Further, the step of monitoring the quality of the live broadcast to be tested includes: Obtain screenshots of each browser instance. If each screenshot shows information indicating normal interaction, determine that the quality is compliant and the test passes; If any screenshot shows information indicating interaction errors, determine that the quality is non - compliant and the test fails.

[0011] Further, it further includes: Send each screenshot and the test result.

[0012] In a second aspect, an embodiment of the present invention provides a live broadcast testing device, and the device includes: A processing module, configured to create at least one browser instance, and open the live broadcast to be tested based on each browser instance, where each browser simulates a different user; A feedback acquisition module, configured to, for each browser instance, obtain corresponding live broadcast feedback based on a large language model, and use the live broadcast feedback as a simulated comment of the user corresponding to the browser instance for feedback; A monitoring module, configured to monitor the quality of the live broadcast to be tested.

[0013] Further, the processing module is specifically configured to create at least one browser instance based on playwright.

[0014] Further, the processing module is further configured to simulate user behaviors by calling user behavior scripts; where the user behaviors include commenting, liking, and exiting the live broadcast.

[0015] Further, the feedback acquisition module is specifically configured to identify the voice in the live broadcast to be tested and the conversation information in the comment area; input the text content corresponding to the voice and the conversation information into a large language model to obtain the live broadcast feedback output by the large language model.

[0016] Further, a feedback acquisition module is specifically configured to input the text content corresponding to the voice, the conversation information, and a pre-saved prompt text into a large language model, and obtain the live feedback output by the large language model, where the prompt text is used to prompt the large language model to output corresponding feedback.

[0017] Further, the monitoring module is further configured to obtain screenshots of each browser instance. If each screenshot shows information indicating normal interaction, it is determined that the quality is compliant and the test passes; if any screenshot shows information indicating an interaction error, it is determined that the quality is non-compliant and the test fails.

[0018] Further, the processing module is further configured to send each of the screenshots and the test results.

[0019] In a third aspect, an embodiment of the present invention provides an electronic device, which includes a processor and a memory. The memory is used to store program instructions, and the processor is used to implement the steps of the above live test method when executing the computer program stored in the memory.

[0020] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program, and the computer program implements the steps of the above live test method when executed by a processor.

[0021] In the embodiments of the present invention, at least one browser instance is created, and each instance independently opens the live content to be tested to simulate the viewing behaviors of different users. By integrating a large language model, feedback related to the live content can be automatically obtained and generated, and these feedbacks are used as simulated comments for submission. At the same time, the quality performance of the live broadcast is continuously monitored. This method not only realizes the simulation of multi-user concurrent viewing of the live broadcast but also successfully simulates the behavior of user comments, thereby effectively monitoring and evaluating the quality of the live broadcast to be tested. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0023] Figure 1 It is a schematic diagram of the process of a live test method provided by an embodiment of the present invention; Figure 2 It is a detailed schematic diagram of a live test provided by an embodiment of the present invention; Figure 3 It is a schematic diagram of the structure of a live test device provided by an embodiment of the present invention; Figure 4 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0024] In order to make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0025] To accurately and effectively implement live broadcast testing, an embodiment of the present invention provides a live broadcast testing method, device, electronic device, and medium. Embodiment 1

[0026] Figure 1 A process schematic diagram of a live broadcast testing method provided by an embodiment of the present invention, the process includes the following steps: S101: Create at least one browser instance, and open the live broadcast to be tested based on each browser instance, where each browser simulates a different user.

[0027] S102: For each browser instance, obtain the corresponding live broadcast feedback based on the large language model, and use the live broadcast feedback as the simulated comment of the corresponding user of the browser instance for feedback.

[0028] S103: Monitor the quality of the live broadcast to be tested.

[0029] In the embodiment of the present invention, at least one browser instance is created, and each instance independently opens the live broadcast content to be tested to simulate the viewing behaviors of different users. By integrating the large language model, feedback related to the live broadcast content can be automatically obtained and generated, and these feedbacks are used as simulated comments for submission. At the same time, continuously monitor the quality performance of the live broadcast. This method not only realizes the simulation of multi-user concurrent viewing of the live broadcast, but also successfully simulates the behavior of user comments, thereby effectively monitoring and evaluating the quality of the live broadcast to be tested.

[0030] The live broadcast testing method provided by the embodiment of the present invention is applied to an electronic device, and the electronic device can be an intelligent device such as a PC or a server.

[0031] To accurately and effectively implement live broadcast testing, the electronic device can use automated testing tools such as Selenium, Puppeteer, etc. or browser automation frameworks to create at least one browser instance according to the test requirements. And the type of the browser, such as Chrome, Firefox, etc., version, and startup parameters can be configured according to needs to simulate the browser environment of different users.

[0032] Among them, each browser instance has an independent browser context, and each context has its own cookies and session information, that is, each instance represents a different simulated user.

[0033] To implement live broadcast testing, different user identities can be assigned to each browser instance, which can be achieved by setting different browser profiles, such as user data directories, Cookies, etc. A proxy server or VPN can be used to assign different IP addresses to each user to simulate users from different geographical locations.

[0034] In each browser instance, the live broadcast page to be tested can be opened. This can be achieved by entering the URL of the live broadcast page in the browser address bar or using the navigation function provided by the automated testing tool.

[0035] In the above S101, the specific implementation steps are as follows: Read configuration: First, read the number of users user_num, the viewing time view_time of each user, the detailed information of the simulated users (nickname, account), and the address of the live broadcast room to be tested from the configuration file.

[0036] Create browser instances: Based on the number of users user_num read, dynamically create the corresponding number of browser instances. Each browser instance will run independently and simulate a different user.

[0037] Open the live broadcast room: Each browser instance uses its corresponding live broadcast room address to open the live broadcast page to be tested.

[0038] Simulate user login and settings: In each browser instance, perform the login operation according to the provided user information (account, nickname), and set the nickname of the user (if additional settings are required after login).

[0039] Watch the live broadcast: The users in each browser instance will continuously watch the live broadcast content according to the configured viewing time view_time.

[0040] In the above S102, the electronic device can, for each browser instance, input the collected live broadcast information into a large language model, such as Chatgpt, by docking with the large language model, and obtain the user Q&A information output by the large language model. This user Q&A information is the live broadcast feedback, and this live broadcast feedback is used as the simulated comment of the user corresponding to the browser instance for feedback.

[0041] After the feedback operation is completed, the electronic device can monitor the quality of the live stream to be tested. In the embodiments of the present invention, by monitoring the quality of the live stream in real time, including the clarity, latency, etc. of the live stream, the accuracy of the test results is ensured. Embodiment 2

[0042] In order to perform live stream testing accurately and effectively, based on the above embodiments, in the embodiments of the present application, the creating of at least one browser instance includes: Creating at least one browser instance based on playwright.

[0043] In the embodiments of the present invention, the electronic device can create at least one browser instance based on Playwright to perform automated testing or simulate user behavior.

[0044] It should be noted that playwright, as a powerful automated testing tool, supports multiple browsers such as Chromium, Firefox, WebKit, etc., and can simulate real user interactions. By writing concise scripts, the creation, management of browser instances and the simulation of user operations can be easily achieved.

[0045] In order to perform live stream testing accurately and effectively, based on the above embodiments, in the embodiments of the present application, after opening the live stream to be tested based on each browser instance and before monitoring the quality of the live stream to be tested, it further includes: Simulating user behavior by calling a user behavior script; wherein, the user behavior includes commenting, liking, and exiting the live stream.

[0046] In order to simulate the randomness of real users, a timer including multiple random time periods can be set in the embodiments of the present application. These time periods can simulate the natural pauses and thinking processes of users when watching a live stream. At the end of each random time period, the electronic device will call a preset user behavior script to simulate operations such as question and answer, comment, and like among users. In this way, a browser instance can perform multiple interactions such as commenting and liking during the process of watching a live stream, thus more realistically simulating user behavior. Embodiment 3

[0047] In order to perform live stream testing accurately and effectively, based on the above embodiments, in the embodiments of the present application, the obtaining of the corresponding live stream feedback based on the large language model includes: Identifying the voice in the live stream to be tested and the conversation information in the comment area; Inputting the text content corresponding to the voice and the conversation information into the large language model to obtain the live stream feedback output by the large language model.

[0048] To accurately and effectively conduct live broadcast tests, the electronic device can identify the voices in the live broadcast to be tested and the conversation information in the comment area. Specifically, the electronic device can use monitoring components, such as collecting specific page elements, real-time capturing of audio copywriting based on Tencent Cloud intelligent subtitles, etc., to extract information from the voices of the host during the live broadcast and the conversations in the dialog boxes in real time.

[0049] After obtaining the voice of the host during the live broadcast, the electronic device can identify the corresponding text content of the voice, input the text content and the conversation information in the comment area into the large language model, and obtain the live broadcast feedback output by the large language model.

[0050] To accurately and effectively conduct live broadcast tests, based on the above embodiments, in the embodiments of the present application, the inputting the text content corresponding to the voice and the conversation information into the large language model to obtain the live broadcast feedback output by the large language model includes: Inputting the text content corresponding to the voice, the conversation information, and the pre-saved prompt text into the large language model to obtain the live broadcast feedback output by the large language model, where the prompt text is used to prompt the large language model to output the corresponding feedback.

[0051] In the embodiments of the present invention, to accurately and effectively obtain live broadcast feedback, the electronic device locally pre-saves prompt text, which is used to prompt the large language model to output corresponding feedback based on the input content. Specifically, the electronic device can input the text content corresponding to the obtained voice, the conversation information, and the pre-saved prompt text into the large language model to obtain the live broadcast feedback output by the large language model. Embodiment 4

[0052] To accurately and effectively conduct live broadcast tests, based on the above embodiments, in the embodiments of the present application, the monitoring the quality of the live broadcast to be tested includes: Obtaining screenshots of each browser instance. If each screenshot shows information indicating normal interaction, it is determined that the quality is compliant and the test passes; If any screenshot shows information indicating an interaction error, it is determined that the quality is non-compliant and the test fails.

[0053] During the test process, the electronic device can obtain screenshots of each browser instance after the operation is completed and carefully check the content of these screenshots. If all screenshots show information indicating normal interaction, it can be determined that the test quality is compliant and the test passes. On the contrary, if any one screenshot shows information indicating an interaction error, then the electronic device can determine that the quality is non-compliant, indicating that this test fails.

[0054] To accurately and effectively conduct live broadcast tests, based on the above embodiments, in the embodiments of the present application, it further includes: Send each screenshot and test result.

[0055] In an embodiment of the present invention, the electronic device can send each screenshot and test result.

[0056] Specifically, after operating in the browser instance, a page screenshot can be taken, the page screenshot can be written into the test report, and the test report can be output. For example, if the screenshots in the live broadcast room all show normal interaction, the test passes; if there is an interaction error, the test fails. After each test is completed, the test person in charge can be notified by email.

[0057] It should be noted that the method provided in the embodiments of the present application can concurrently test multiple live broadcast rooms; when designing the test system, scalability is considered, and more user behavior simulations can be provided in the future while ensuring the performance and stability of the system.

[0058] The method provided in the embodiments of the present invention can simulate the real behaviors of multiple users, such as logging in, watching live broadcasts, liking, sending messages, etc., and simulate the behaviors of users joining and leaving the live broadcast room; and interface with advanced large language models, such as Chatgpt, etc., to simulate real user comments; monitor the quality of the live stream in real time, including the clarity and latency of the live broadcast, etc., to ensure the accuracy of the test results; ensure that the test system can be easily extended to support more user simulations and more complex test scenarios.

[0059] Figure 2 It is a detailed process schematic diagram of a live broadcast test provided by an embodiment of the present invention.

[0060] As Figure 2 can be seen, the electronic device can first read the configuration, read the number of users user_num, the viewing time view_time of each user, the detailed information of the simulated users (nickname, account), and the address of the live broadcast room to be tested from the configuration file, create browser instances based on the read number of users user_num, and each browser instance uses its corresponding live broadcast room address to open the live broadcast page to be tested. In each browser instance, perform a login operation according to the provided user information (account, nickname), and set the nickname of the user, and watch the live broadcast based on the configured viewing time. And obtain the live broadcast room information, the live broadcast room information includes the title, lecturer, etc., simulate user behaviors, perform liking / question answering. If liking, then simulate clicking the like button on the page. If question answering, then interface with the AI large language model, input the live broadcast room information, simulate question answering, and simulate sending messages. After liking or question answering is completed, determine whether the live broadcast has ended. Among them, the end of the live broadcast means that the host ends the live broadcast, or a certain browser instance reaches the corresponding viewing time. If the live broadcast ends, it ends. If the live broadcast has not ended, then re-judge the liking / question answering until the live broadcast ends. Embodiment 5

[0061] Based on the above embodiments, Figure 3 FIG. is a schematic structural diagram of a live broadcast testing device provided by an embodiment of the present invention. The device includes: A processing module 301, configured to create at least one browser instance, and open a live broadcast to be tested based on each browser instance, wherein each browser simulates a different user; An acquisition feedback module 302, configured to obtain corresponding live broadcast feedback for each browser instance based on a large language model, and feed back the live broadcast feedback as a simulated comment of the corresponding user of the browser instance; A monitoring module 303, configured to monitor the quality of the live broadcast to be tested.

[0062] Further, the processing module 301 is specifically configured to create at least one browser instance based on playwright.

[0063] Further, the processing module 301 is further configured to simulate user behaviors by calling user behavior scripts; wherein the user behaviors include commenting, liking, and exiting the live broadcast.

[0064] Further, the acquisition feedback module 302 is specifically configured to identify the voice in the live broadcast to be tested and the conversation information in the comment area; input the text content corresponding to the voice and the conversation information into the large language model to obtain the live broadcast feedback output by the large language model.

[0065] Further, the acquisition feedback module 302 is specifically configured to input the text content corresponding to the voice, the conversation information, and a pre-saved prompt text into the large language model to obtain the live broadcast feedback output by the large language model, wherein the prompt text is used to prompt the large language model to output corresponding feedback.

[0066] Further, the monitoring module 303 is further configured to obtain screenshots of each browser instance. If each screenshot shows information indicating normal interaction, it is determined that the quality is compliant and the test passes; if any screenshot shows information indicating an interaction error, it is determined that the quality is non-compliant and the test fails.

[0067] Further, the processing module 301 is further configured to send each screenshot and the test result. Embodiment 6

[0068] Figure 4 FIG. is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. Based on the above embodiments, an embodiment of the present invention further provides an electronic device, including a processor 401, a communication interface 402, a memory 404, and a communication bus 404. Among them, the processor 401, the communication interface 402, and the memory 404 complete mutual communication through the communication bus 404; A computer program is stored in the memory 404. When the program is executed by the processor 401, the processor 401 is caused to execute the steps of implementing the live test method as in the above embodiments.

[0069] For the specific implementation process, refer to the above embodiments, and the similarities will not be elaborated.

[0070] The communication bus mentioned in the above electronic device may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience in representation, only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0071] The communication interface 402 is used for communication between the above electronic device and other devices.

[0072] The memory may include a Random Access Memory (RAM), and may also include a Non-Volatile Memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located far from the aforementioned processor.

[0073] The above processor may be a general-purpose processor, including a central processing unit, a Network Processor (NP), etc.; it may also be a Digital Signal Processing (DSP), an application-specific integrated circuit, a field-programmable gate array, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Embodiment 7

[0074] Based on the above embodiments, an embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the live test method as in the above embodiments.

[0075] For the specific implementation process, refer to the above embodiments, and the similarities will not be elaborated.

[0076] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0077] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or the combination of blocks.

[0078] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or the combination of blocks.

[0079] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are performed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or the combination of blocks.

[0080] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. A live broadcast test method, characterized in that: The method comprises: Create at least one browser instance, and open the live broadcast to be tested based on each browser instance, wherein each browser simulates a different user; For each browser instance, based on the large language model, corresponding live broadcast feedback is obtained, and the live broadcast feedback is used as simulated comments of the corresponding user of the browser instance for feedback; Monitor the quality of the live broadcast to be tested.

2. The method according to claim 1, characterized in that The creating at least one browser instance comprises: Create at least one browser instance based on playwright.

3. The method according to claim 1, characterized in that After opening the live broadcast to be tested based on each browser instance and before monitoring the quality of the live broadcast to be tested, the method further includes: By calling the user behavior script, the user behavior is simulated; wherein the user behavior includes commenting, liking, and exiting the live broadcast.

4. The method according to claim 1, characterized in that The obtaining of corresponding live broadcast feedback based on the large language model includes: Identify the voice in the live broadcast to be tested and the dialogue information in the comment area; The text content corresponding to the speech and the dialogue information are input into a large language model to obtain live broadcast feedback output by the large language model.

5. The method according to claim 4, characterized in that The step of inputting the text content corresponding to the speech and the dialogue information into a large language model and obtaining live broadcast feedback output by the large language model includes: The text content corresponding to the speech, the dialogue information and the pre-saved prompt text are input into the large language model to obtain live feedback output by the large language model, wherein the prompt text is used to prompt the feedback corresponding to the output of the large language model.

6. The method according to claim 1, characterized in that The monitoring of the quality of the live broadcast to be tested includes: Get a screenshot of each browser instance. If each screenshot shows information indicating normal interaction, the quality is confirmed to be compliant and the test has passed. If any screenshot displays information indicating an interaction error, the quality is determined to be noncompliant and the test has failed.

7. The method according to claim 6, characterized in that Also includes: Send each screenshot and test result as described.

8. A live broadcast test device, characterized in that: The device comprises: A processing module, used for creating at least one browser instance, and opening the live broadcast to be tested based on each browser instance, wherein each browser simulates a different user; A feedback acquisition module is used to acquire corresponding live broadcast feedback for each browser instance based on the large language model, and use the live broadcast feedback as simulated comments of the corresponding user of the browser instance for feedback; The monitoring module is used to monitor the quality of the live broadcast to be tested.

9. An electronic device, characterized in that: The electronic device includes a processor and a memory, the memory is used to store program instructions, and the processor is used to implement the steps of the live broadcast test method as described in any one of claims 1-7 when executing the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: It stores a computer program, which, when executed by a processor, implements the steps of the live broadcast test method as described in any one of claims 1-7.

Images