A vehicle screen automatic test control method based on OCR technology

Abstract

The application discloses a kind of vehicle screen automation test control methods based on OCR technology, comprising: test initialization, import test case;Based on the test case, real-time ADB screenshot and OCR identification are executed;According to whether the OCR identification result conforms to the expectation of corresponding test case, intelligent decision and instruction execution are carried out;Test result record and determination, generate test report.The vehicle screen automation test control method based on OCR technology of the application realizes the automatic closed-loop test control of vehicle screen based on OCR technology, through the whole-process automation of ADB screenshot-OCR identification-intelligent decision-instruction execution, realizes the efficient and accurate verification of vehicle screen full-scene test, can overcome the problems such as inefficiency, low compatibility and dynamic scene loss of existing vehicle screen test;Efficiency is significantly improved: replace manual operation, single vehicle type test time is shortened from 48h to 24h or less, support multi-vehicle type test.

Description

Technical Field

[0001] This invention relates to the field of vehicle screen testing technology, and more specifically, to an automated testing and control method for vehicle screens based on OCR technology. Background Technology

[0002] Vehicle screens are the core terminals of in-vehicle interaction. The effectiveness of their functions and the accuracy of their display directly affect user experience and driving safety. Vehicle screens have evolved from traditional single information display terminals into intelligent hubs that integrate multiple modules, cover multiple scenarios, and coordinate multiple interactions. The complexity and diversity of their functions are growing explosively, directly forcing the testing system to upgrade and transform from manual to automated. The core demand focuses on improving test coverage, efficiency, and accuracy.

[0003] Current vehicle screen testing primarily relies on two methods: manual testing and traditional automated testing. Manual testing involves testers observing the screen display (such as menu text, pop-up prompts, progress bars, and fault codes), manually performing clicks, swipes, and inputs, and recording the test results. Its drawbacks are high reliance on manual labor and low efficiency: manual testing requires observing dynamic screen content frame by frame (such as navigation scrolling guides and OTA upgrade progress), which is prone to misjudgment due to visual fatigue; full-scenario testing of a single vehicle model requires 3-5 people and takes ≥48 hours, making it difficult to meet the rapid iteration needs of mass-produced vehicles. Traditional automated testing is based on fixed coordinates or system protocols. These solutions use tools like Appium to simulate touch operations based on preset coordinates, or verify system status through CAN bus or ADB interface. However, due to limitations in its technical principles, it suffers from the following core shortcomings: poor compatibility and high adaptation costs: different car models have significant differences in screen resolution (e.g., 800×480, 1920×1080), UI style (e.g., floating pop-ups, embedded menus), and font design (automotive-specific sans-serif fonts, multi-language mixing). Traditional fixed-coordinate automation tools need to recalibrate the coordinates for each car model, increasing adaptation costs by more than 50%; insufficient coverage of dynamic scenarios: for sudden anomalies (e.g., network interruption pop-ups, low battery warnings) and real-time changes (e.g., speed jumps, range updates), manual or traditional tools cannot identify and trigger subsequent operations in real time (e.g., automatically clicking after recognizing a "confirm" pop-up), leading to a break in the test chain; lack of closed-loop control logic: it cannot dynamically adjust test steps based on the real-time screen status (e.g., automatically executing a "retry" command after recognizing "upgrade failure"), requiring manual intervention to complete the process, affecting the integrity of the test.

[0004] Therefore, there is an urgent need for an automated testing and control method for vehicle screens based on OCR technology. Summary of the Invention

[0005] The purpose of this invention is to provide an automated testing and control method for vehicle screens based on OCR technology, in order to solve the problems in the prior art. This method can achieve efficient and accurate verification of vehicle screen testing in all scenarios through full-process automation of ADB screenshot-OCR recognition-intelligent decision-making-instruction execution.

[0006] This invention provides an automated testing and control method for vehicle screens based on OCR technology, comprising:

[0007] Test initialization, import test cases;

[0008] Based on the aforementioned test cases, ADB screenshot and OCR recognition are performed in real time.

[0009] Based on whether the OCR recognition results meet the expectations of the corresponding test cases, intelligent decisions and instructions are executed.

[0010] Record and judge the test results, and generate a test report.

[0011] The vehicle screen automated test control method based on OCR technology described above, preferably, includes the following steps: Test initialization, importing test cases, includes:

[0012] Start the vehicle's infotainment system and connect it to the test terminal;

[0013] The test terminal obtains the screen resolution via ADB;

[0014] Automatically configure OCR coordinate mapping planning;

[0015] Open the OCR recognition software and load the vehicle screen-specific model;

[0016] Set the OCR screenshot frame rate;

[0017] Import test cases.

[0018] The vehicle screen automated test control method based on OCR technology described above, preferably, involves the test terminal obtaining the screen resolution via ADB based on the test cases, including:

[0019] The test terminal executes the adb shell wm size command via ADB to obtain the screen resolution.

[0020] The vehicle screen automated test control method based on OCR technology described above preferably includes, in part, the real-time execution of ADB screenshot and OCR recognition based on the test cases, comprising:

[0021] The test terminal sends an ADB command via ADB to trigger the test;

[0022] Trigger ADB screenshot and save it to the vehicle's infotainment system;

[0023] Retrieve screenshots to the test terminal;

[0024] OCR recognizes images and outputs structured results.

[0025] The vehicle screen automated test control method based on OCR technology described above, preferably, involves the test terminal sending ADB commands via ADB to trigger the test, including:

[0026] The test terminal sends an OTA upgrade trigger command via ADB to initiate the test;

[0027] The triggering of ADB screenshot and saving it to the vehicle's infotainment system includes:

[0028] The system triggers an ADB screenshot (adb shell screencap / sdcard / ota_screen.png) at preset intervals and saves it to the vehicle's infotainment system.

[0029] The step of pulling screenshots to the test terminal includes:

[0030] The vehicle's infotainment system transmits data to the test terminal via adb pull.

[0031] The OCR recognition of images and output of structured results includes:

[0032] Use OCR software to crop the upgrade progress area in the screenshot, recognize the progress text, and output a structured result.

[0033] The vehicle screen automated test control method based on OCR technology described above, preferably, includes the step of making intelligent decisions and executing instructions based on whether the OCR recognition result meets the expectations of the corresponding test case, which includes:

[0034] Step S31: The decision module compares the OCR results with the use case description;

[0035] Step S32: The decision module determines whether the OCR result meets expectations. If yes, then steps S33 and S34 are executed in sequence. If no, then steps S35 and S34 are executed in sequence.

[0036] Step S33, Normal progress scenario: Continue to take the next screenshot;

[0037] Step S34: Single test completed;

[0038] Step S35: Then perform a retry operation.

[0039] The vehicle screen automated test control method based on OCR technology described above, preferably, includes step S35, which involves performing a retry operation, comprising:

[0040] If the "Upgrade failed, please try again" pop-up is detected, the "Click the 'Retry' button" instruction will be automatically generated.

[0041] If the message "Upgrade complete, restart to take effect" is detected, a "Confirm Restart" command will be sent, and the OCR recognition results before restart will be recorded.

[0042] The vehicle screen automated testing and control method based on OCR technology described above, preferably, includes the following steps: recording and judging the test results, and generating a test report.

[0043] Step S41: After a single test is completed, determine whether to perform a loop test. If not, proceed to step S42. If yes, proceed to steps S43 and S44 in sequence.

[0044] Step S42: Generate a test report;

[0045] Step S43: Restore the initial test conditions;

[0046] Step S44: Return to the step of sending ADB command to trigger the test.

[0047] The vehicle screen automated test control method based on OCR technology described above, preferably, includes step S42, generating a test report, which includes:

[0048] Generate ADB screenshot files named by timestamp, OCR recognition logs, and a list of execution instructions;

[0049] If the OTA upgrade process is uninterrupted, the progress recognition accuracy is 100%, and the screen displays normally after restarting, meeting the functional and recognition qualification standards, then the test is deemed qualified.

[0050] This invention provides an automated testing and control method for vehicle screens based on OCR technology. It employs an ADB+OCR closed-loop testing architecture, using OCR (Optical Character Recognition) technology to achieve automated closed-loop testing and control of vehicle screens. Through the fully automated process of ADB screenshotting, OCR recognition, intelligent decision-making, and command execution, it achieves efficient and accurate verification of vehicle screen testing across all scenarios. This overcomes the inefficiencies, low compatibility, and lack of dynamic scenarios in existing vehicle screen testing methods. Efficiency is significantly improved: replacing manual operation, the testing time for a single vehicle model is reduced from 48 hours to less than 24 hours, and multi-vehicle testing is supported. It boasts strong compatibility and low adaptation costs: automatically acquiring screen parameters through ADB and adapting to multiple UI styles using a dedicated OCR model, cross-vehicle adaptation does not require recalibrating coordinates, reducing adaptation costs by more than 60%. It provides full coverage of dynamic scenarios: supporting the recognition and response to sudden pop-ups and real-time scrolling content, increasing test scenario coverage from 70% of traditional tools to 95%, avoiding test omissions due to missing dynamic scenarios. Attached Figure Description

[0051] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described below with reference to the accompanying drawings, wherein:

[0052] Figure 1 A flowchart illustrating an embodiment of the vehicle screen automated testing and control method based on OCR technology provided by the present invention;

[0053] Figure 2 This is a logic diagram of an embodiment of the vehicle screen automated testing and control method based on OCR technology provided by the present invention. Detailed Implementation

[0054] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. The descriptions of the exemplary embodiments are merely illustrative and are in no way intended to limit the present disclosure or its application or use. The present disclosure may be implemented in many different forms and is not limited to the embodiments described herein. These embodiments are provided so that the present disclosure will be thorough and complete, and will fully express the scope of the disclosure to those skilled in the art. It should be noted that, unless specifically stated otherwise, the relative arrangement of components and steps, the composition of materials, numerical expressions, and values ​​set forth in these embodiments should be interpreted as exemplary only and not as limiting.

[0055] The terms “first,” “second,” and similar terms used in this disclosure do not indicate any order, quantity, or importance, but are merely used to distinguish different parts. Terms such as “including” or “contains” mean that the element preceding the term encompasses the element listed after it, and do not exclude the possibility of encompassing other elements as well. Terms such as “above” and “below” are used only to indicate relative positional relationships; when the absolute position of the described object changes, this relative positional relationship may also change accordingly.

[0056] In this disclosure, when a specific component is described as being located between a first component and a second component, an intermediary component may or may not be present between the specific component and the first or second component. When a specific component is described as connecting to other components, the specific component may be directly connected to the other components without having an intermediary component, or it may not be directly connected to the other components but may have an intermediary component.

[0057] All terms used in this disclosure (including technical or scientific terms) have the same meaning as understood by one of ordinary skill in the art to which this disclosure pertains, unless otherwise specifically defined. It should also be understood that terms defined in a general dictionary, such as a dictionary, should be interpreted as having a meaning consistent with their meaning in the context of the relevant art, and not as having an idealized or highly formalized meaning, unless expressly defined herein.

[0058] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, they should be considered part of the specification.

[0059] like Figure 1 and Figure 2 As shown, the automated testing and control method for vehicle screens based on OCR technology provided in this embodiment includes the following steps in actual execution:

[0060] Step S1: Test initialization, import test cases.

[0061] In one embodiment of the vehicle screen automated testing and control method based on OCR technology of the present invention, step S1 may specifically include:

[0062] Step S11: Start the vehicle's infotainment system and connect it to the test terminal.

[0063] The vehicle infotainment system (VIS), specifically the onboard computer (model / parameters: i7-12700H processor, 32GB memory), is responsible for running OCR models and decision-making processes, and controlling ADB communication. The test terminal is the vehicle's central control screen (1920×1080 resolution), which provides the test object and displays the content to be recognized. Specifically, the test terminal establishes an ADB connection with the VIS, for example, via wired or wireless connection. For instance, a wired connection can be established by connecting the test terminal to the VIS's debugging interface via USB; alternatively, the VIS and test terminal can be connected to the same local area network, and the command `adb connect vehicle_info_ip` can be executed to establish a wireless connection.

[0064] Step S12: The test terminal obtains the screen resolution via ADB.

[0065] This invention automatically acquires basic parameters of the vehicle screen (resolution, system version) through the ADB interface, enabling one-time configuration and reuse across multiple vehicle models. Specifically, regarding resolution adaptation, the test terminal executes the `adbshell wm size` command through the ADB command execution module to obtain the screen resolution (e.g., 1920×1080), automatically converting the pixel coordinates recognized by OCR into physical screen coordinates, avoiding operational deviations caused by resolution differences between vehicle models. Regarding UI style adaptation, common UI templates such as floating pop-ups and embedded menus are preset, allowing for priority matching of template features during OCR recognition, reducing recognition errors caused by different UI styles.

[0066] Step S13: Automatically configure OCR coordinate mapping plan.

[0067] Step S14: Open the OCR recognition software and load the vehicle screen-specific model.

[0068] The test terminal was equipped with OCR recognition software and loaded with a vehicle screen-specific OCR model.

[0069] Step S15: Set the OCR screenshot frame rate.

[0070] The OCR screenshot frame rate must meet the OTA progress capture requirements, such as 10 frames per second.

[0071] Step S16: Import test cases.

[0072] Configure a test case library in the test terminal. Specifically, in the OCR recognition software, import test cases from the preset test case library, such as OTA upgrade tests and navigation function tests. For example, import test case scripts for OTA upgrade tests and navigation function tests. The script format is .py, containing expected states and operation logic. The expected process is: trigger upgrade → recognition progress → complete upgrade → restart verification.

[0073] Step S2: Based on the test cases, perform ADB screenshot and OCR recognition in real time.

[0074] In this invention, the ADB command execution module sends decision commands to the vehicle's infotainment system via commands such as `adb shell input tap` and `adb shell input text`, completing the operation loop. In one embodiment of the vehicle screen automated testing and control method based on OCR technology of this invention, step S2 may specifically include:

[0075] Step S21: The test terminal sends an ADB command via ADB to trigger the test.

[0076] Specifically, the test terminal sends an OTA upgrade trigger command via ADB to initiate the test. The OTA upgrade command is, for example: `adb shell am start -n vehicle_system_OTA_package_name / upgrade_Activity`.

[0077] In this invention, the ADB command transmission function, image acquisition function, and ADB command execution function are implemented through the ADB debugging module. Specifically, the ADB debugging module is designed to support Android 8.0 and above in-vehicle systems and supports wired / wireless connections. Its function is to transmit screenshot commands, acquire screen data, and issue operation commands.

[0078] Step S22: Trigger ADB screenshot and save it to the vehicle's infotainment system.

[0079] Specifically, an ADB screenshot (adb shell screencap / sdcard / ota_screen.png) is triggered every preset time interval (e.g., 100ms) and saved to the vehicle's infotainment system. Since ADB screenshots are free from environmental interference, only the effective display area is cropped during preprocessing (removing screen borders and fixed button areas), eliminating the need for complex noise reduction.

[0080] Step S23: Pull the screenshot to the test terminal.

[0081] Specifically, the vehicle's infotainment system transmits data to the test terminal via adb pull.

[0082] Step S24: OCR recognizes the image and outputs structured results.

[0083] Specifically, the OCR recognition module utilizes OCR software to crop the upgrade progress area in the screenshot, with the coordinates preset to (800, 400)-(1120, 450). It recognizes the progress text (such as 30%, Upgrading) and outputs a structured result. This structured result includes the text content, screen physical coordinates (e.g., the text 'Confirm'), 30% (coordinates (500, 600)-(600, 650), (coordinates (950, 420)-(1000, 440)), and a recognition confidence level of 98%. The OCR recognition module's model / parameters are: based on the Paddle framework, loading a pre-trained model for in-vehicle scenarios; its function is to recognize screen text and output structured results (including coordinates).

[0084] Step S3: Based on whether the OCR recognition result meets the expectations of the corresponding test case, make intelligent decisions and execute instructions.

[0085] In this invention, the intelligent decision-making module compares the OCR recognition results with the expected state based on a preset test case library, and generates operation instructions (e.g., if a "confirm" pop-up is recognized, a "click (550, 625)" instruction is generated). In one embodiment of the vehicle screen automated test control method based on OCR technology of this invention, step S3 may specifically include:

[0086] Step S31: The decision module compares the OCR results with the use case description.

[0087] Step S32: The decision module determines whether the OCR result meets expectations. If yes, then steps S33 and S34 are executed sequentially. If no, then steps S35 and S34 are executed sequentially.

[0088] Step S33, for a normal progress scenario: continue with the next screenshot. For example,

[0089] Step S34: Single test completed.

[0090] Step S35: Then perform a retry operation.

[0091] Specifically, if an "Upgrade failed, please retry" pop-up is detected, a "Click 'Retry' button" instruction is automatically generated, such as executing `adb shell input tap 600 500` based on the OCR-recognized "Retry" coordinates (600, 500); if an "Upgrade complete, restart to take effect" message is detected, a "Confirm Restart" instruction is sent, such as `adb shell input tap 900 600`, and the OCR recognition result before restart is recorded.

[0092] This invention designs a timing recognition and feedback mechanism for dynamic content on vehicle screens (such as real-time speed and scrolling prompts): it performs timing analysis on continuous ADB screenshots, calculates the content change rate (e.g., "OTA progress from 30% to 40%, taking 2 seconds"), and determines whether it meets expectations (e.g., normal upgrade progress should be 5% / s); for sudden pop-ups (e.g., "network interruption"), it calls a preset exception handling rule library and automatically executes a remedial operation of "click 'retry' → re-initiate request", without manual intervention, and can achieve adaptive decision-making in dynamic scenarios.

[0093] Step S4: Record and judge the test results, and generate a test report.

[0094] In one embodiment of the vehicle screen automated testing and control method based on OCR technology of the present invention, step S4 may specifically include:

[0095] Step S41: After a single test is completed, determine whether to perform a loop test. If not, proceed to step S42. If yes, proceed to steps S43 and S44 in sequence.

[0096] Step S42: Generate a test report.

[0097] This invention involves two rounds of testing. In one embodiment of the vehicle screen automated testing and control method based on OCR technology of this invention, step S42 may specifically include:

[0098] Step S421: Generate ADB screenshot files named according to timestamps, OCR recognition logs (including recognition results and confidence scores for each frame), and a list of execution instructions.

[0099] Step S422: If the OTA upgrade process is uninterrupted, the progress recognition accuracy is 100%, and the screen display is normal after restarting, meeting the functional qualification standard and the recognition qualification standard, then the test is deemed qualified.

[0100] Step S43: Restore the initial test conditions.

[0101] Step S44: Return to the step of sending ADB command to trigger the test.

[0102] This invention relies on the adaptation and optimization of two mature technologies: ADB screenshot technology and a vehicle-specific OCR model. It requires no additional dedicated hardware and can directly reuse existing testing resources. The ADB screenshot technology utilizes the ADB (Android Debug Bridge) debugging interface based on the Android in-vehicle system to acquire raw pixel data from the screen (avoiding reflections and angular deviations from camera capture), supporting high frame rate screenshots of 100ms / frame to meet the needs of capturing dynamic content. The vehicle-specific OCR model is trained on an in-vehicle scene dataset (covering 10+ vehicle model screen fonts, 20+ common pop-up styles, and mixed display of 5 languages), achieving a recognition accuracy of ≥96%. It supports accurate recognition of dynamic text (such as scrolling navigation guides) and special symbols (such as text descriptions next to fault icons). Moreover, this invention has the advantages of high efficiency, high compatibility, and comprehensive coverage of dynamic scenes, making it suitable for testing in-vehicle screens in both fuel-powered and new energy vehicles, and meeting the testing needs of rapid iteration in mass-produced models.

[0103] The vehicle screen automated testing and control method based on OCR technology provided in this invention adopts an ADB+OCR closed-loop testing architecture. Based on OCR (Optical Character Recognition) technology, it achieves automated closed-loop testing and control of vehicle screens. Through the full-process automation of ADB screenshot-OCR recognition-intelligent decision-making-command execution, it achieves efficient and accurate verification of vehicle screen testing across all scenarios. It overcomes the problems of inefficiency, low compatibility, and lack of dynamic scenarios in existing vehicle screen testing methods. Efficiency is significantly improved: replacing manual operation, the testing time for a single vehicle model is reduced from 48 hours to less than 24 hours, and multi-vehicle testing is supported. It has strong compatibility and low adaptation costs: by automatically acquiring screen parameters through ADB and adapting to multiple UI styles using a dedicated OCR model, cross-vehicle adaptation does not require recalibration of coordinates, reducing adaptation costs by more than 60%. It provides full coverage of dynamic scenarios: supporting the recognition and response to sudden pop-ups and real-time scrolling content, the test scenario coverage rate is increased from 70% in traditional tools to 95%, avoiding test omissions caused by the lack of dynamic scenarios.

[0104] The embodiments of this disclosure have now been described in detail. To avoid obscuring the concept of this disclosure, some details known in the art have not been described. Those skilled in the art can fully understand how to implement the technical solutions disclosed herein based on the above description.

[0105] While specific embodiments of this disclosure have been described in detail by way of examples, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of this disclosure. Those skilled in the art should understand that modifications can be made to the above embodiments or equivalent substitutions can be made to some technical features without departing from the scope and spirit of this disclosure. The scope of this disclosure is defined by the appended claims.

Claims

1. An automated testing and control method for vehicle screens based on OCR technology, characterized in that, include: Test initialization, import test cases; Based on the aforementioned test cases, ADB screenshot and OCR recognition are performed in real time. Based on whether the OCR recognition results meet the expectations of the corresponding test cases, intelligent decisions and instructions are executed. Record and judge the test results, and generate a test report.

2. The automated testing and control method for vehicle screens based on OCR technology according to claim 1, characterized in that, The test initialization, including importing test cases, includes: Start the vehicle's infotainment system and connect it to the test terminal; The test terminal obtains the screen resolution via ADB; Automatically configure OCR coordinate mapping planning; Open the OCR recognition software and load the vehicle screen-specific model; Set the OCR screenshot frame rate; Import test cases.

3. The automated testing and control method for vehicle screens based on OCR technology according to claim 2, characterized in that, Based on the test cases, the test terminal obtains the screen resolution via ADB, including: The test terminal executes the adb shell wm size command via ADB to obtain the screen resolution.

4. The automated testing and control method for vehicle screens based on OCR technology according to claim 1, characterized in that, The real-time execution of ADB screenshot and OCR recognition based on the test cases includes: The test terminal sends an ADB command via ADB to trigger the test; Trigger ADB screenshot and save it to the vehicle's infotainment system; Retrieve screenshots to the test terminal; OCR recognizes images and outputs structured results.

5. The automated testing and control method for vehicle screens based on OCR technology according to claim 4, characterized in that, The test terminal sends ADB commands via ADB to trigger the test, including: The test terminal sends an OTA upgrade trigger command via ADB to initiate the test; The triggering of ADB screenshot and saving it to the vehicle's infotainment system includes: The system triggers an ADB screenshot (adb shell screencap / sdcard / ota_screen.png) at preset intervals and saves it to the vehicle's infotainment system. The step of pulling screenshots to the test terminal includes: The vehicle's infotainment system transmits data to the test terminal via adb pull. The OCR recognition of images and output of structured results includes: Use OCR software to crop the upgrade progress area in the screenshot, recognize the progress text, and output a structured result.

6. The automated testing and control method for vehicle screens based on OCR technology according to claim 1, characterized in that, The step of making intelligent decisions and executing instructions based on whether the OCR recognition results meet the expectations of the corresponding test cases includes: Step S31: The decision module compares the OCR results with the use case description; Step S32: The decision module determines whether the OCR result meets expectations. If yes, then steps S33 and S34 are executed in sequence. If no, then steps S35 and S34 are executed in sequence. Step S33, Normal progress scenario: Continue to take the next screenshot; Step S34: Single test completed; Step S35: Then perform a retry operation.

7. The automated testing and control method for vehicle screens based on OCR technology according to claim 6, characterized in that, Step S35 involves performing a retry operation, including: If the "Upgrade failed, please try again" pop-up is detected, the instruction "Click the 'Retry' button" will be automatically generated. If the message "Upgrade complete, restart to take effect" is detected, a "Confirm Restart" command will be sent, and the OCR recognition results before restart will be recorded.

8. The automated testing and control method for vehicle screens based on OCR technology according to claim 1, characterized in that, The test results are recorded and judged, and a test report is generated, including: Step S41: After a single test is completed, determine whether to perform a loop test. If not, proceed to step S42. If yes, proceed to steps S43 and S44 in sequence. Step S42: Generate a test report; Step S43: Restore the initial test conditions; Step S44: Return to the step of sending ADB command to trigger the test.

9. The automated testing and control method for vehicle screens based on OCR technology according to claim 1, characterized in that, Step S42, generating a test report, includes: Generate ADB screenshot files named by timestamp, OCR recognition logs, and a list of execution instructions; If the OTA upgrade process is uninterrupted, the progress recognition accuracy is 100%, and the screen displays normally after restarting, meeting the functional and recognition qualification standards, then the test is deemed qualified.

Images