Ota upgrade method for vehicle ecu and storage medium

Abstract

The application provides an OTA upgrading method of a vehicle ECU and a storage medium. The method obtains a to-be-upgraded file of a target ECU, runs the to-be-upgraded file in a simulation twin system, then for each to-be-verified scene in a scene verification library, simulates the to-be-verified scene in the simulation twin system through an intelligent inference model, tests whether the to-be-upgraded file has a corresponding expected function in the to-be-verified scene, if not, generates an expected function code corresponding to the to-be-verified scene through the intelligent inference model, and reorganizes the to-be-upgraded file, after the simulation of all to-be-verified scenes is completed, upgrades the target ECU according to the reorganized to-be-upgraded file, so that the to-be-upgraded file can adapt to different vehicles, the to-be-upgraded file and the whole vehicle system are optimally matched, the function matching degree is improved, the performance of the whole vehicle system is ensured, and the OTA upgrading efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of OTA upgrade, in particular to an OTA upgrade method for vehicle ECU and a storage medium. BACKGROUND

[0002] Automotive OTA (Over the Air Technology) refers to over-the-air technology firmware upgrade and software upgrade. OTA downloads new software update package from remote server through network, and upgrades itself system, which not only brings more convenient vehicle upgrade approach, but also makes consumers feel more intelligent and convenient vehicle experience.

[0003] However, due to the difference of vehicle process and the error of each ECU (Electronic Control Unit) batch, engineers usually need to continuously test the function of ECU upgrade file of each vehicle, and need to rewrite the parameter file after calibration to the ECU part, which consumes a lot of manpower and time, resulting in low OTA upgrade efficiency of ECU. SUMMARY

[0004] In view of the above defects or deficiencies in the prior art, the present application aims to provide an OTA upgrade method for vehicle ECU and a storage medium, to solve the problem of low efficiency caused by manual function test and frequent rewriting of ECU part in the ECU upgrade process in the related art, and greatly improve the upgrade efficiency of ECU.

[0005] The present application provides an OTA upgrade method for vehicle ECU, which comprises:

[0006] Obtaining the to-be-upgraded file of the target ECU in the vehicle, and running the to-be-upgraded file in the simulation twin system;

[0007] For each to-be-verified scene in the scene verification library, simulating the to-be-verified scene in the simulation twin system through an intelligent inference model, and testing whether the to-be-upgraded file has the corresponding expected function in the to-be-verified scene;

[0008] In response to the to-be-upgraded file not having the expected function, generating the expected function code corresponding to the to-be-verified scene through the intelligent inference model, and recombining the to-be-upgraded file according to the expected function code;

[0009] After the simulation of all to-be-verified scenes is completed, performing OTA upgrade on the target ECU according to the recombined to-be-upgraded file.

[0010] Optionally, testing whether the to-be-upgraded file has the corresponding expected function in the to-be-verified scene comprises:

[0011] testing, by the intelligent inference model, a function of the to-be-upgraded file in the to-be-verified scene to obtain a function verification result;

[0012] determining, according to the function verification result and an expected result corresponding to the to-be-verified scene in the scene verification library, whether the to-be-upgraded file has a corresponding expected function in the to-be-verified scene.

[0013] Optionally, the function verification result includes an actual perception result, the expected result includes an expected perception result, and the determining, according to the function verification result and the expected result corresponding to the to-be-verified scene in the scene verification library, whether the to-be-upgraded file has a corresponding expected function in the to-be-verified scene includes:

[0014] if the actual perception result is different from the expected perception result, it is determined that the to-be-upgraded file does not have the expected function corresponding to the to-be-verified scene.

[0015] Optionally, the function verification result further includes an actual decision result, the expected result includes an expected decision result, and the determining, according to the function verification result and the expected result corresponding to the to-be-verified scene in the scene verification library, whether the to-be-upgraded file has a corresponding expected function in the to-be-verified scene further includes:

[0016] if the actual perception result is the same as the expected perception result, and the actual decision result is different from the expected decision result, it is determined that the to-be-upgraded file does not have the expected function corresponding to the to-be-verified scene.

[0017] Optionally, the function verification result further includes an actual control result, the expected result includes an expected control result, and the determining, according to the function verification result and the expected result corresponding to the to-be-verified scene in the scene verification library, whether the to-be-upgraded file has a corresponding expected function in the to-be-verified scene further includes:

[0018] if the actual perception result is the same as the expected perception result, the actual decision result is the same as the expected decision result, and the actual control result is different from the expected control result, it is determined that the to-be-upgraded file does not have the expected function corresponding to the to-be-verified scene.

[0019] Optionally, after the to-be-upgraded file is reorganized according to the expected function code, the method further includes:

[0020] testing, by the intelligent inference model, whether the reorganized to-be-upgraded file has a corresponding expected function in the to-be-verified scene;

[0021] If not, the expected function code corresponding to the to-be-verified scene is generated by the intelligent inference model, and the reorganized to-be-upgraded file is refiled according to the expected function code until the reorganized to-be-upgraded file has the expected function corresponding to the to-be-verified scene.

[0022] Optionally, the method further comprises:

[0023] running the whole vehicle system of the vehicle in the simulation twin system;

[0024] In the process of testing whether the to-be-upgraded file has the corresponding expected function in the to-be-verified scene, whether the whole vehicle system is abnormal is tested by the intelligent inference model;

[0025] In response to the abnormality of the whole vehicle system, system adjustment code corresponding to the to-be-verified scene is generated by the intelligent inference model, and the to-be-upgraded file is refiled according to the system adjustment code.

[0026] Optionally, after the expected function code corresponding to the to-be-verified scene is generated by the intelligent inference model, the method further comprises:

[0027] The expected function code is stored in association with the to-be-verified scene in a model expert knowledge base, so that other vehicles of the same vehicle type can obtain the expected function code from the model expert knowledge base.

[0028] Optionally, the expected function code corresponding to the to-be-verified scene is generated by the intelligent inference model, comprising:

[0029] The scene semantic features of the to-be-verified scene are determined by the intelligent inference model, and the function semantic features of the expected function are determined;

[0030] The expected function code is generated according to the scene semantic features and the function semantic features.

[0031] The embodiment of the application also provides an electronic device, which comprises:

[0032] A processor and a memory;

[0033] The processor calls the program or instruction stored in the memory to execute the steps of the OTA upgrading method of the vehicle ECU provided in any embodiment of the application.

[0034] The embodiment of the application also provides a computer readable storage medium, which stores a program or instruction, and the program or instruction makes the computer execute the steps of the OTA upgrading method of the vehicle ECU provided in any embodiment of the application.

[0035] In summary, the application provides an OTA upgrading method for vehicle ECU, which obtains a to-be-upgraded file of a target ECU in a vehicle, runs the to-be-upgraded file in a simulation twin system, and then for each to-be-verified scene in a scene verification library, simulates the to-be-verified scene in the simulation twin system through an intelligent inference model, tests whether the to-be-upgraded file has the corresponding expected function in the to-be-verified scene, if not, generates the expected function code corresponding to the to-be-verified scene through the intelligent inference model, and reorganizes the to-be-upgraded file according to the expected function code, after the simulation of all to-be-verified scenes is completed, the target ECU can be OTA upgraded according to the reorganized to-be-upgraded file, which verifies the function of the to-be-upgraded file in each scene before the ECU is OTA upgraded, so as to ensure that the to-be-upgraded file can adapt to different vehicles, so that the to-be-upgraded file and the whole vehicle system achieve optimal matching, improve the function matching degree, thereby ensuring the performance of the whole vehicle system, and the method tests the function in each scene through the intelligent inference model, and generates the corresponding expected function code, which can improve the test efficiency, thereby improving the OTA upgrading efficiency, the function verification before the ECU is OTA upgraded can also avoid frequent repeated flashing of the ECU, and further improve the OTA upgrading efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the specific embodiments or prior art of the present application, the drawings needed in the description of the specific embodiments or prior art will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0037] Figure 1 is a flowchart of an OTA upgrading method for vehicle ECU provided by an embodiment of the present application;

[0038] Figure 2 is a whole vehicle architecture diagram provided by an embodiment of the present application;

[0039] Figure 3 is an upgrading flowchart of ECU provided by an embodiment of the present application;

[0040] Figure 4 is a communication schematic diagram provided by an embodiment of the present application;

[0041] Figure 5 is a schematic diagram of converting from DoIP data to UDS data provided by an embodiment of the present application;

[0042] Figure 6 is a schematic diagram of converting from UDS data to DoIP data provided by an embodiment of the present application;

[0043] Figure 7 is a whole framework diagram of OTA upgrading provided by an embodiment of the present application.

[0044] Figure 8 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0045] The present application will be further described in detail below with reference to the accompanying drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the related application, and not to limit the application. In addition, it should be noted that, for the convenience of description, only the parts related to the application are shown in the drawings.

[0046] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings and embodiments.

[0047] Before the method provided by the embodiments of the present application is described in detail, the technical problems solved by the method will be described.

[0048] In the traditional ECU upgrading scheme, after obtaining the to-be-upgraded file of the target ECU, the to-be-upgraded file needs to be written to the target ECU, and after the upgrading is completed, the target ECU is restarted, and then manual testing is performed according to the vehicle system quality requirements. This process may need to modify and adjust the calibration parameters, and after the calibration parameters are modified, the file is repackaged and upgraded again, resulting in that the ECU upgrading needs to be written and tested multiple times to match the vehicle quality requirements, and the ECU upgrading efficiency is low.

[0049] Therefore, in order to solve the above technical problems, the present application provides an OTA upgrading method for vehicle ECU. The method places the obtained to-be-upgraded file of the target ECU in a simulation twinborn environment based on a real vehicle system to run, so as to test whether the to-be-upgraded file has corresponding expected functions in each scene, and optimizes the to-be-upgraded file, so that after the target ECU is written, the vehicle can reach an optimal state.

[0050] As mentioned in the background, in order to solve the problems in the prior art, the present application provides an OTA upgrading method for vehicle ECU. Figure 1 is a flowchart of an OTA upgrading method for vehicle ECU provided by an embodiment of the present application. Referring to Figure 1 , the OTA upgrading method for vehicle ECU specifically includes:

[0051] S110, obtaining a to-be-upgraded file of a target ECU in a vehicle, and running the to-be-upgraded file in a simulation twinborn system.

[0052] The target ECU is an ECU to be upgraded in the vehicle, and the file to be upgraded is a file required for the target ECU to be flashed. The file to be upgraded can be actively issued by the OTA cloud when detecting version update.

[0053] In the embodiment of the present application, the file to be upgraded can be obtained by the OTA upgrade master, and the OTA upgrade master can download the file to be upgraded to the audio and video controller after passing the OTA legal authentication.

[0054] Specifically, the embodiment of the present application can use a distributed communication system, which includes an OTA upgrade master deployed in an audio and video controller of a vehicle, and an OTA upgrade agent deployed in a vehicle gateway of the vehicle; the ECU of the vehicle can be regarded as an OTA upgrade slave. The audio and video controller and the vehicle gateway can be connected through Ethernet, the vehicle gateway can be connected with one or more ECUs, and the vehicle gateway can be connected with each ECU connected below through Ethernet or CAN (Controller Area Network).

[0055] Exemplarily, Figure 2 is a vehicle architecture diagram provided by the embodiment of the present application, as Figure 2 shown, the audio and video controller (carrying the OTA upgrade master) can communicate with the OTA cloud through the 4G or 5G network, and the audio and video controller can communicate with the vehicle gateway 1~vehicle gateway 4 (carrying the OTA upgrade agent) through Ethernet; the vehicle dynamic controller is mainly used for controlling the vehicle body. The vehicle gateway 1~vehicle gateway 4 are connected with one or more ECUs, for example, the vehicle gateway 1 is connected with ECU1-1~ECU1-n, the vehicle gateway 2 is connected with ECU2-1~ECU2-n, and the vehicle gateway can be connected with each ECU below through Ethernet or CAN bus.

[0056] In the embodiment of the present application, after the OTA upgrade master obtains the file to be upgraded, the file to be upgraded can be further placed in the simulation twin system for running. The simulation twin system can be used to simulate the real vehicle system and the real physical environment.

[0057] S120, for each to-be-verified scene in the scene verification library, simulating the to-be-verified scene in the simulation twin system through the intelligent inference model, and testing whether the file to be upgraded has the corresponding expected function in the to-be-verified scene.

[0058] Specifically, after the OTA upgrade master places the to-be-upgraded file in the simulation twin system for running, the OTA upgrade master can call the intelligent inference model to simulate various driving scenarios in the simulation twin system. For example, the intelligent inference model can generate a simulation command for simulating a driving scenario and send the simulation command to the simulation twin system to make the simulation twin system simulate various driving scenarios.

[0059] The intelligent inference model can be used for scenario simulation, function testing of the to-be-upgraded file, and generating expected function code corresponding to the scenario. The intelligent inference model can be a special language model related to the whole vehicle. For example, a large language model can be optimized and trained through vehicle control instructions, vehicle transmission signals, and running information of the whole vehicle system to obtain the intelligent inference model.

[0060] For example, simulation commands for part of the driving scenarios can be generated in advance. The simulation commands can be constructed in the form of vehicle control instructions, and then the pre-generated simulation commands are input into the large language model to train the large language model to have the ability to generate simulation commands for various driving scenarios.

[0061] In addition, function test commands for part of the driving scenarios can be generated in advance. The function test commands can be constructed in the form of vehicle control instructions, and then the pre-generated function test commands are input into the large language model to train the large language model to have the ability to test whether the to-be-upgraded file has the corresponding expected function under various driving scenarios.

[0062] In addition, expected function code corresponding to part of the scenarios can be generated in advance. The expected function code can include vehicle transmission signals and running information of the whole vehicle system, and then the expected function code corresponding to the scenario is input into the large language model to train the large language model to have the ability to generate expected function code corresponding to various scenarios.

[0063] The optimized and trained large language model has the ability to generate simulation commands for various driving scenarios, test whether the to-be-upgraded file has the corresponding expected function under various driving scenarios, and generate expected function code corresponding to various scenarios. The optimized and trained large language model can be determined as the intelligent inference model.

[0064] Specifically, a scenario verification library can be constructed in advance, which includes various to-be-verified scenarios. The intelligent inference model can simulate each to-be-verified scenario in the scenario verification library in sequence, that is, generate simulation commands corresponding to each to-be-verified scenario in sequence, send each simulation command to the simulation twin system, and make the simulation twin system simulate each to-be-verified scenario in sequence. The to-be-verified scenario can be a specific weather driving scenario, a specific obstacle driving scenario, a specific vehicle speed driving scenario, or a specific road type driving scenario, etc.

[0065] In the embodiments of the present application, for each to-be-verified scene, the intelligent reasoning model can simulate the to-be-verified scene in the simulation twin system. For example, an obstacle such as a conical bucket or a stone is placed in the middle of the road.

[0066] After simulating the to-be-verified scene, the intelligent reasoning model can test whether the to-be-upgraded file has the corresponding expected function in the to-be-verified scene. The expected function can refer to the intelligent driving function that the ECU file should have in the to-be-verified scene, for example, an obstacle avoidance function, a risk deceleration function, etc.

[0067] For example, the intelligent reasoning model can generate a function test command for testing the function of the to-be-upgraded file in the to-be-verified scene, and send the function test command to the simulation twin system, so that the simulation twin system tests whether the to-be-upgraded file has the corresponding expected function in the to-be-verified scene.

[0068] For example, the expected results of each to-be-verified scene can be stored in the scene verification library in advance, the intelligent reasoning model can test the function of the to-be-upgraded file in the to-be-verified scene to obtain a function verification result, and determine whether the to-be-upgraded file has the expected function corresponding to the to-be-verified scene based on the function verification result and the expected result.

[0069] In a specific implementation, testing whether the to-be-upgraded file has the corresponding expected function in the to-be-verified scene includes:

[0070] Testing the function of the to-be-upgraded file in the to-be-verified scene by the intelligent reasoning model to obtain a function verification result;

[0071] Determining whether the to-be-upgraded file has the corresponding expected function in the to-be-verified scene according to the function verification result and the expected result corresponding to the to-be-verified scene in the scene verification library.

[0072] The function verification result can be a result executed by the to-be-upgraded file in the to-be-verified scene during running, for example, whether to avoid obstacles, whether to decelerate, whether to accelerate, whether to adjust the suspension height, etc. The expected result can be a result executed by the to-be-upgraded file in the to-be-verified scene when having the corresponding expected function, for example, avoiding obstacles, decelerating, accelerating, adjusting the suspension height, etc.

[0073] Specifically, the intelligent reasoning model can test the result executed by the to-be-upgraded file in the to-be-verified scene after running, i.e., the function verification result, and then determine whether the function verification result is the same as the expected result. If they are the same, it means that the to-be-upgraded file has the corresponding expected function in the to-be-verified scene.

[0074] For example, the to-be-verified scene is a static obstacle driving scene, that is, a cone-shaped bucket or a stone block is placed in the middle of the road as an obstacle, and the expected result corresponding to the to-be-verified scene is braking torque deceleration or obstacle avoidance. The deceleration braking torque can be determined according to the distance of the obstacle. If the function verification result of the to-be-upgraded file is not deceleration and not obstacle avoidance, it indicates that the to-be-upgraded file does not have the ability and function to process the to-be-verified scene, and it can be determined that the to-be-upgraded file does not have the corresponding braking obstacle avoidance function in the static obstacle driving scene.

[0075] The above embodiment can test the function in the to-be-verified scene through the intelligent reasoning model, determine whether the to-be-upgraded file has the expected function corresponding to the to-be-verified scene according to whether the tested function verification result matches the expected result, and realize function verification of the to-be-upgraded file in each scene, which can ensure verification accuracy and verification efficiency.

[0076] In the embodiment of the present application, considering that the function of the to-be-upgraded file in each scene can be divided into three processes of perception, decision and control, the intelligent reasoning model can be used to verify the perception ability, decision ability and control ability of the expected function corresponding to the to-be-upgraded file in the to-be-verified scene in turn. If the to-be-upgraded file does not have the perception ability in the expected function in the to-be-verified scene, the to-be-upgraded file can be adjusted in time without waiting for the test of the decision ability and the control ability, which can further improve the verification efficiency.

[0077] In an example, the function verification result includes an actual perception result, the expected result includes an expected perception result, and whether the to-be-upgraded file has the corresponding expected function in the to-be-verified scene is determined according to the function verification result and the expected result corresponding to the to-be-verified scene in the scene verification library, including:

[0078] If the actual perception result is different from the expected perception result, it is determined that the to-be-upgraded file does not have the expected function corresponding to the to-be-verified scene.

[0079] Specifically, the actual perception result of the to-be-upgraded file in the to-be-verified scene, that is, whether the to-be-upgraded file can recognize the set object in the to-be-verified scene, can be tested through the AI perception module in the intelligent reasoning model.

[0080] If the actual perception result is different from the expected perception result, it can be determined that the to-be-upgraded file does not have the perception ability in the expected function corresponding to the to-be-verified scene. For example, the actual perception result is that the cone-shaped bucket is not recognized, and the expected perception result is that the cone-shaped bucket is recognized, the shape and size of the cone-shaped bucket, and the distance between the vehicle and the cone-shaped bucket. At this time, it can be determined that the to-be-upgraded file does not have the perception ability in the expected function corresponding to the to-be-verified scene, that is, the to-be-upgraded file does not have the expected function corresponding to the to-be-verified scene.

[0081] Through the above example, whether the to-be-upgraded file has the corresponding expected function can be judged by testing the perception ability of the to-be-upgraded file in the to-be-verified scene, it can be ensured that the to-be-upgraded file has the perception ability in each scene in subsequent use, and the test efficiency of the to-be-upgraded file can also be improved.

[0082] In the embodiment of the application, if it is determined by the intelligent inference model that the to-be-upgraded file has the perception ability in the expected function in the to-be-verified scene, the decision ability of the to-be-upgraded file in the to-be-verified scene can be further tested by the intelligent inference model, and if not, the to-be-upgraded file can be adjusted in time without waiting for the test control ability, which can further improve the verification efficiency.

[0083] In some embodiments, the function verification result further includes an actual decision result, the expected result includes an expected decision result, and whether the to-be-upgraded file has the corresponding expected function in the to-be-verified scene is judged according to the function verification result and the expected result corresponding to the to-be-verified scene in the scene verification library, and further comprising:

[0084] If the actual perception result is the same as the expected perception result, and the actual decision result is different from the expected decision result, it is determined that the to-be-upgraded file does not have the expected function corresponding to the to-be-verified scene.

[0085] Specifically, if it is determined by the intelligent inference model that the to-be-upgraded file has the perception ability in the to-be-verified scene, that is, the actual perception result is the same as the expected perception result, the actual decision result of the to-be-upgraded file in the to-be-verified scene, that is, whether it can make accurate decisions in the to-be-verified scene, can be further tested by the AI decision module in the intelligent inference model.

[0086] If the actual decision result is different from the expected decision result, it can be determined that the to-be-upgraded file does not have the decision ability in the expected function corresponding to the to-be-verified scene. For example, the actual decision result is that the vehicle maintains uniform speed, and the expected decision result is that the vehicle slows down, at this time it can be determined that the to-be-upgraded file does not have the decision ability in the to-be-verified scene, that is, the to-be-upgraded file does not have the expected function corresponding to the to-be-verified scene.

[0087] Through the above example, whether the to-be-upgraded file has the corresponding expected function can be judged by testing the decision ability of the to-be-upgraded file in the to-be-verified scene, it can be ensured that the to-be-upgraded file has the perception and decision ability in each scene in subsequent use, and the test efficiency of the to-be-upgraded file can also be improved.

[0088] In the embodiment of the application, if it is determined by the intelligent inference model that the to-be-upgraded file has the perception ability and the decision ability in the expected function in the to-be-verified scene, the control ability of the to-be-upgraded file in the to-be-verified scene can be further tested by the intelligent inference model, and if not, the to-be-upgraded file can be adjusted.

[0089] In some embodiments, the function verification result further includes an actual control result, the expected result includes an expected control result, and whether the to-be-upgraded file has the corresponding expected function in the to-be-verified scene is determined according to the function verification result and the expected result corresponding to the to-be-verified scene in the scene verification library, and further comprising:

[0090] If the actual perception result is the same as the expected perception result, and the actual decision result is the same as the expected decision result, and the actual control result is different from the expected control result, it is determined that the to-be-upgraded file does not have the expected function corresponding to the to-be-verified scene.

[0091] Specifically, if it is determined by the intelligent inference model that the to-be-upgraded file has the perception ability and the decision ability in the to-be-verified scene, that is, the actual perception result is the same as the expected perception result, and the actual decision result is the same as the expected decision result, the actual control result of the to-be-upgraded file in the to-be-verified scene can be further tested by the AI control module in the intelligent inference model, that is, whether it can be accurately controlled in the to-be-verified scene.

[0092] If the actual control result is different from the expected control result, it can be determined that the to-be-upgraded file does not have the control ability in the expected function corresponding to the to-be-verified scene. For example, the actual control result is that the vehicle speed is not changed, and the expected decision result is to reduce the vehicle speed. At this time, it can be determined that the to-be-upgraded file does not have the control ability in the to-be-verified scene, that is, the to-be-upgraded file does not have the expected function corresponding to the to-be-verified scene.

[0093] Through the above example, whether the to-be-upgraded file has the corresponding expected function can be determined by testing the control ability of the to-be-upgraded file in the to-be-verified scene, which can ensure that the to-be-upgraded file has the perception, decision and control ability in each scene in the subsequent use, and can also improve the testing efficiency of the to-be-upgraded file.

[0094] S130, in response to the to-be-upgraded file not having the expected function, generating an expected function code corresponding to the to-be-verified scene by the intelligent inference model, and performing file reorganization on the to-be-upgraded file according to the expected function code.

[0095] Specifically, if it is determined by the intelligent inference model that the to-be-upgraded file does not have the expected function corresponding to the to-be-verified scene, the expected function code corresponding to the to-be-verified scene can be generated by the intelligent inference model. The expected function code is a code for realizing the corresponding expected function in the to-be-verified scene, and then the to-be-upgraded file can be reorganized according to the generated expected function code.

[0096] For example, the intelligent inference model can generate the expected function code corresponding to the to-be-verified scene through an optimization algorithm. It should be noted that after the file reorganization of the to-be-upgraded file, it can be tested whether the reorganized to-be-upgraded file has the corresponding expected function under the to-be-verified scene. If not, the to-be-upgraded file continues to be optimized and reorganized until it has the corresponding expected function under the to-be-verified scene. The above step can be returned to simulate and test the next to-be-verified scene, and test whether the reorganized to-be-upgraded file has the corresponding expected function under the next to-be-verified scene, until the test of all to-be-verified scenes is completed.

[0097] In some embodiments, after the file reorganization of the to-be-upgraded file according to the expected function code, the method further comprises:

[0098] Through the intelligent inference model, it is tested whether the reorganized to-be-upgraded file has the corresponding expected function in the to-be-verified scene.

[0099] If not, the intelligent inference model generates the expected function code corresponding to the to-be-verified scene, and reorganizes the reorganized to-be-upgraded file according to the expected function code, until the reorganized to-be-upgraded file has the expected function corresponding to the to-be-verified scene.

[0100] Specifically, after the file reorganization of the to-be-upgraded file through the generated expected function code, the reorganized to-be-upgraded file can be retested through the intelligent inference model whether it has the corresponding expected function in the to-be-verified scene.

[0101] If the reorganized to-be-upgraded file still does not have the expected function corresponding to the to-be-verified scene, the intelligent inference model can be used to generate the expected function code corresponding to the to-be-verified scene again, and the reorganized to-be-upgraded file is reorganized according to the newly generated expected function code. Repeat this process until the reorganized to-be-upgraded file has the expected function corresponding to the to-be-verified scene.

[0102] Through the above embodiments, it can be ensured that the to-be-upgraded file has the corresponding expected function under each to-be-verified scene, and further ensures that the to-be-upgraded file can adapt to different vehicles, so that the to-be-upgraded file and the whole vehicle system are optimally matched, the function matching degree is improved, and the performance of the whole vehicle system is ensured.

[0103] In the embodiment of the present application, the expected function corresponding to the to-be-verified scene can be divided into perception ability, decision-making ability and control ability. If the to-be-upgraded file does not have the perception ability in the expected function, the corresponding expected function code can be generated and the to-be-upgraded file can be reorganized until it has the perception ability. Then, whether the reorganized to-be-upgraded file has the corresponding expected function is tested until the to-be-upgraded file can accurately perceive, decide and control in the to-be-verified scene, and the test of the next to-be-verified scene can be performed.

[0104] In an example, the expected function code corresponding to the to-be-verified scene is generated by the intelligent inference model, comprising:

[0105] The scene semantic features of the to-be-verified scene are determined by the intelligent inference model, and the function semantic features of the expected function are determined. The expected function code is generated according to the scene semantic features and the function semantic features.

[0106] The intelligent inference model can extract the scene semantic features describing the to-be-verified scene according to the scene information of the to-be-verified scene, such as weather conditions, road types, obstacle types, and environmental temperatures. In addition, the intelligent inference model can extract the function semantic features describing the expected function according to the function information of the expected function corresponding to the to-be-verified scene, such as expected results.

[0107] Further, the intelligent inference model can generate the expected function code according to the scene semantic features and the function semantic features, for example, generate a corresponding function template according to the function semantic features, then generate a scene statement according to the scene semantic features, and write the scene statement into the function template to obtain the expected function code.

[0108] The above example can extract scene semantic features and function semantic features to generate an expected function code that can achieve the expected function in the to-be-verified scene, ensuring the accuracy of the code implementation.

[0109] In order to further improve the file verification efficiency of other vehicles, in the embodiment of the present application, after the expected function code is generated by the intelligent inference model, it can be stored in the model expert knowledge base, so that other vehicles of the same vehicle type can directly obtain the code from the model expert knowledge base, or the code can also be pushed to other vehicles of the same vehicle type through the model expert knowledge base, improving the ECU upgrading efficiency of other vehicles of the same vehicle type.

[0110] In a specific implementation, after the expected function code corresponding to the to-be-verified scene is generated by the intelligent inference model, it further comprises:

[0111] The expected function code is stored in the model expert knowledge base in association with the to-be-verified scene, so that other vehicles of the same vehicle type can obtain the expected function code through the model expert knowledge base.

[0112] Specifically, after the expected function code corresponding to the to-be-verified scene is generated by the intelligent inference model, the expected function code can be stored in association with the to-be-verified scene in the model expert knowledge base, for example, the expected function code can be stored in association with the to-be-verified scene, or the expected function code, the to-be-verified scene, and the vehicle model identifier are stored in association.

[0113] After being stored in the model expert knowledge base, other vehicles of the same vehicle model can obtain the expected function code in the model expert knowledge base, so as to reorganize the upgrade file of the ECU thereof.

[0114] Through the above implementation, the ECU upgrade efficiency of other vehicles of the same vehicle model can be further improved, and the other vehicles do not need to repeatedly test the scene and generate the expected function code in real time.

[0115] It should be noted that in the embodiments of the present application, in addition to verifying whether the to-be-upgraded file has the corresponding expected function under each scene, it can also be verified whether the running of the to-be-upgraded file will affect the whole vehicle system, so as to ensure the compatibility between the to-be-upgraded file and the whole vehicle system.

[0116] In a specific implementation, the method provided by the embodiments of the present application further includes:

[0117] running the whole vehicle system of the vehicle in the simulation twin system;

[0118] in the process of testing whether the to-be-upgraded file has the corresponding expected function in the to-be-verified scene, testing whether the whole vehicle system is abnormal by the intelligent inference model;

[0119] in response to the abnormality of the whole vehicle system, generating a system adjustment code corresponding to the to-be-verified scene by the intelligent inference model, and reorganizing the to-be-upgraded file according to the system adjustment code.

[0120] Specifically, the whole vehicle system of the vehicle can be run in the simulation twin system at the same time as the to-be-upgraded file is run in the simulation twin system. Further, in the process of testing whether the to-be-upgraded file has the corresponding expected function in the to-be-verified scene by the intelligent inference model, the whole vehicle system can also be tested for abnormality by the intelligent inference model.

[0121] Further, if the whole vehicle system is detected to be abnormal, a system adjustment code corresponding to the to-be-verified scene can be generated by the intelligent inference model, which can be used to ensure the normal running of the whole vehicle system when the to-be-upgraded file is running. After the system adjustment code is generated, the to-be-upgraded file can be reorganized by the system adjustment code.

[0122] The above embodiment can ensure that the running of the to-be-upgraded file does not affect the running of the whole vehicle system, so as to ensure the stability of the whole vehicle system, by running the whole vehicle system in the simulation twin system and verifying whether it is abnormal by the intelligent inference model, while ensuring that the to-be-upgraded file has the expected function.

[0123] S140, after simulation of all to-be-verified scenes is completed, performing OTA upgrade on the target ECU according to the reorganized to-be-upgraded file.

[0124] Specifically, after simulation of all to-be-verified scenes is completed, that is, after the expected functions in all to-be-verified scenes are tested by the intelligent inference model in sequence and the file is reorganized, the reorganized to-be-upgraded file can be used to perform OTA upgrade on the target ECU.

[0125] Exemplarily, Figure 3 is an ECU upgrade flowchart provided by the embodiment of the application, as Figure 3 shown, the OTA cloud end can perform software upgrade management and software version management, the software upgrade management can be used to obtain the latest version information from the software version management, and the to-be-upgraded file is issued to the OTA upgrade master control in the car-end audio and video entertainment controller when the version information changes.

[0126] The OTA authentication module in the OTA upgrade master control can perform OTA upgrade verification, after verification, the OTA download module in the OTA upgrade master control can download the to-be-upgraded file, place the to-be-upgraded file in the twin simulation module in the OTA upgrade master control for running, the inference module in the OTA upgrade master control can call the AI special language model (that is, the intelligent inference model), simulate the to-be-verified scene in the twin simulation module, and perform AI perception, AI decision and AI control through the artificial intelligence algorithm of the model, so as to test the perception ability, decision ability and control ability of the to-be-upgraded file in the to-be-verified scene, if the perception ability, decision ability or control ability in the expected function does not exist, the inference module can call the optimization algorithm of the model to generate the expected function code corresponding to the to-be-verified scene, and write it into the AI self-growth expert knowledge base (that is, the model expert knowledge base), and then the file reorganization module in the OTA upgrade master control reorganizes the to-be-upgraded file, and continues to return to scene verification after reorganization.

[0127] After all to-be-verified scene tests are completed, the final to-be-upgraded file can be used to perform OTA upgrade on the target ECU, and the target ECU is controlled to run after the upgrade is completed.

[0128] In the embodiment of the present application, after completing all the to-be-verified scene tests, the OTA upgrade master can first create an OTA application upgrade program corresponding to the target ECU. It should be noted that if the number of target ECUs is multiple, the number of OTA application upgrade programs is the same as the number of target ECUs. After creating the OTA application upgrade program corresponding to the target ECU, the corresponding upgrade client can be continued to be created by the OTA application upgrade program. The upgrade client adopts the UDS (Unified Diagnostic Services) and DoIP protocols, and the upgrade client is used to communicate with the server in the vehicle gateway. The upgrade client and the server are in a many-to-one relationship. After the server receives the communication message (i.e., the to-be-upgraded file) sent by the upgrade client, the message can be forwarded according to the address of the target ECU, and the to-be-upgraded file is transmitted to the target ECU for upgrade and flashing.

[0129] Exemplarily, Figure 4 is a communication schematic diagram provided by the embodiment of the present application. As shown in Figure 4 , the OTA upgrade master in the audio and video entertainment controller can create a corresponding client for each target ECU, such as client 1~client n, and then each client can send the reorganized to-be-upgraded file to the server in the vehicle gateway through Ethernet. The server can be regarded as an OTA upgrade agent for protocol conversion. The server sends the received to-be-upgraded file to each target ECU, such as ECU1~ECUn, through Ethernet or a controller area network.

[0130] In the embodiment of the present application, considering that different ECUs support different communication protocols, the OTA upgrade agent can perform protocol conversion, i.e., data conversion, on the to-be-upgraded file before sending the to-be-upgraded file to the target ECU.

[0131] Exemplarily, for the target ECU supporting Ethernet function, the DoIP protocol can be used for OTA upgrade and flashing. For the target ECU not supporting Ethernet function, the UDS protocol can be used for OTA upgrade and flashing. Therefore, for the target ECU not supporting Ethernet function, it can be determined that data conversion is needed to convert the data of the upgrade package into a protocol type supported by the target ECU, such as UDS data.

[0132] Figure 5 is a schematic diagram of converting from DoIP data to UDS data provided by the embodiment of the present application. As shown in Figure 5As shown, for the target ECU which does not support the Ethernet function, the upgrade package can be converted from the DoIP type to the UDS type. The DoIP data frame can be composed of an Ethernet header (EthHead), an IP header (IPHead), a transport layer header (TCP / UDP Head), a DoIP header (DoIPHead), a source address, a target address, and DoIP data. The UDS data frame can be composed of a CAN identifier (CANID), a data length code (DLC), protocol control information (DoCAN PCI), and UDS data.

[0133] Specifically, the vehicle gateway can convert the DoIP data to the UDS data, that is, convert the data format sent by the OTA upgrade master to the data format supported by the OTA upgrade slave (i.e., the ECU). In this process, the field filling content (i.e., the logical address) corresponding to the target address in the DoIP data can be converted to the field filling content (i.e., the request ID) corresponding to the CAN identifier in the UDS data.

[0134] In addition to the conversion from the DoIP data to the UDS data in the process of distributing the upgrade package to the target ECU, considering the case that the target ECU feeds back data to the vehicle gateway, for such a case, the OTA upgrade agent in the vehicle gateway can also convert the UDS data fed back by the target ECU to the DoIP data, so as to subsequently feed back the DoIP data to the OTA master through the client.

[0135] Figure 6 is a schematic diagram of conversion from UDS data to DoIP data provided by an embodiment of the present application, as Figure 6 As shown, for the target ECU which does not support the Ethernet function, the UDS data fed back by the target ECU can be converted to the DoIP data. The structures of the DoIP data frame and the UDS data frame can be referred to the foregoing description.

[0136] Specifically, the vehicle gateway can convert the UDS data to the DoIP data, that is, convert the data format supported by the OTA upgrade slave (i.e., the ECU) to the data format supported by the OTA upgrade master. In this process, the field filling content (i.e., the request ID) corresponding to the CAN identifier in the UDS data can be converted to the field filling content (i.e., the logical address) corresponding to the source address in the DoIP data.

[0137] Through the above data conversion mechanism, the ECUs supporting the Ethernet function and the ECUs not supporting the Ethernet function can be successfully upgraded and flashed, and the upgrade reliability of each ECU is ensured.

[0138] Figure 7 is a whole framework diagram of OTA upgrade provided by an embodiment of the present application, asFigure 7 As shown, the OTA upgrade master in the audio-visual entertainment controller can include an OTA authentication module, an OTA download module, an inference module, an AI self-growth expert knowledge base, a twin simulation module, an AI perception module, an AI decision module, an AI control module, a file reorganization module, and an OTA upgrade module. The OTA upgrade master can obtain the to-be-upgraded file issued by the OTA cloud through Https, and send the reorganized to-be-upgraded file to the vehicle gateway after completing all scene verifications. If protocol conversion is not required, the vehicle gateway can send the to-be-upgraded file to each ECU (i.e., OTA upgrade slave) through a two-layer channel (Ethernet). If protocol conversion is required, the OTA upgrade agent in the vehicle gateway can perform ETH to CAN conversion, and then send the to-be-upgraded file to each ECU (i.e., OTA upgrade slave) through CAN.

[0139] The OTA upgrade method for the vehicle ECU provided by the embodiment of the present application can obtain the to-be-upgraded file of the target ECU in the vehicle, run the to-be-upgraded file in the simulation twin system, simulate each to-be-verified scene in the simulation twin system through the intelligent inference model, test whether the to-be-upgraded file has the corresponding expected function in the to-be-verified scene, generate the expected function code corresponding to the to-be-verified scene through the intelligent inference model if the to-be-upgraded file does not have the expected function, reorganize the to-be-upgraded file according to the expected function code, and perform OTA upgrade on the target ECU according to the reorganized to-be-upgraded file after the simulation of all to-be-verified scenes is completed. In this way, the function of the to-be-upgraded file in each scene is verified before the ECU is upgraded, so as to ensure that the to-be-upgraded file can adapt to different vehicles, so that the to-be-upgraded file and the vehicle system are optimally matched, the function matching degree is improved, the performance of the vehicle system is ensured, the function is tested through the intelligent inference model, the corresponding expected function code is generated, the testing efficiency is improved, the OTA upgrade efficiency is improved, the function is verified before the ECU is upgraded, and frequent repeated writing of the ECU is avoided, thereby further improving the OTA upgrade efficiency.

[0140] Figure 8 FIG. 1 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. As shown in FIG. 1, the electronic device 100 includes one or more processors 101 and a memory 102. Figure 8 As shown in FIG. 1, the electronic device 100 includes one or more processors 101 and a memory 102.

[0141] The processor 101 can be a central processing unit (CPU) or other forms of processing units having data processing capability and / or instruction execution capability, and can control other components in the electronic device 100 to perform desired functions.

[0142] The memory 402 can include one or more computer program products that can include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory, for example, can include random access memory (RAM), and / or a cache, and / or the like. The non-volatile memory, for example, can include read-only memory (ROM), hard disk, flash memory, and / or the like. The computer-readable storage media can store one or more computer program instructions that, when executed by the processor 401, implement the OTA upgrade method of the vehicle ECU of any embodiment of the present application described above and / or other desired functions. Various contents such as initial extrinsic parameters, threshold values, and the like can also be stored in the computer-readable storage media.

[0143] In one example, the electronic device 400 can further include an input device 403 and an output device 404, which are interconnected through a bus system and / or other forms of connection mechanisms (not shown). The input device 403 can include, for example, a keyboard, a mouse, and / or the like. The output device 404 can output various information to the outside, including pre-warning prompt information, braking force, and the like. The output device 404 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and / or the like.

[0144] Of course, in order to simplify, Figure 8 Only some of the components in the electronic device 400 related to the present application are shown in the middle, and components such as buses, input / output interfaces, and the like are omitted. In addition, the electronic device 400 can also include any other appropriate components according to specific application cases.

[0145] In addition to the above method and device, the embodiments of the present application can also be a computer program product, which includes computer program instructions that, when executed by a processor, cause the processor to perform the steps of the OTA upgrade method of the vehicle ECU provided by any embodiment of the present application.

[0146] The computer program product can be written in any combination of one or more programming languages, including an object-oriented programming language such as Java, C++, and / or the like, and conventional procedural programming languages, such as the "C" programming language, or the like. The program code can execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.

[0147] In addition, an embodiment of the present application can also be a computer readable storage medium, having stored thereon computer program instructions which, when executed by a processor, cause the processor to perform the steps of the vehicle ECU OTA upgrading method provided by any embodiment of the present application.

[0148] The computer readable storage medium can take the form of one or more combinations of any type of computer readable medium. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable disc, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0149] It should be noted that the terms used in the present application are only for describing specific embodiments and are not intended to limit the scope of the present application. As shown in the specification and claims of the present application, unless the context clearly indicates otherwise, the terms "one", "a", "an", and / or "the" do not refer to the singular, but can also include the plural. The terms "include", "contain" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method or device. Without more limitations, the element defined by the statement "including a" does not exclude the presence of additional identical elements in the process, method or device including the element.

[0150] It should also be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application. Unless otherwise explicitly specified and limited, the terms "mount", "connect", "connect" and the like should be broadly understood, for example, it can be a fixed connection, or a detachable connection, or an integral connection; it can be a mechanical connection, or an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, or it can be the communication between two elements inside. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0151] The principles and implementations of the present application are described herein with specific examples. The above examples are only used to help understand the method of the present application and its core idea. The above description is only the preferred embodiments of the present application. It should be pointed out that due to the limited nature of the language expression, there are objectively infinite specific structures, and for ordinary skilled persons in the art, without departing from the principles of the present application, a number of improvements, refinements or changes can be made, or the above technical features can be combined in an appropriate manner. The improvements, refinements, changes or combinations, or the application of the inventive concept and technical solution to other occasions without improvement, shall be regarded as the protection scope of the present application.

Claims

1. An OTA upgrade method for a vehicle ECU, characterized in that, include: The upgrade file of the target ECU in the vehicle is obtained and the upgrade file is run in the simulation twin system, wherein the simulation twin system is used to simulate the real vehicle system and the real physical environment; For each scenario to be verified in the scenario verification library, the scenario to be verified is simulated in the simulation twin system using an intelligent reasoning model, and the file to be upgraded is tested to see if it has the corresponding expected function in the scenario to be verified. In response to the fact that the file to be upgraded does not have the expected function, the expected function code corresponding to the scenario to be verified is generated by the intelligent reasoning model, and the file to be upgraded is reorganized according to the expected function code; After all the scenario simulations to be verified are completed, the target ECU is upgraded via OTA according to the recombined upgrade file; The intelligent reasoning model is used for scenario simulation, functional testing of the file to be upgraded, and generation of expected functional code corresponding to the scenario; the intelligent reasoning model generates simulation commands for various driving scenarios, and generates functional test commands for testing the functionality of the file to be upgraded in the scenario to be verified.

2. The method according to claim 1, characterized in that, Testing whether the file to be upgraded has the expected functionality in the scenario to be verified includes: The function of the file to be upgraded is tested in the scenario to be verified using the intelligent reasoning model, and the function verification result is obtained. Based on the functional verification results and the expected results corresponding to the scenarios to be verified in the scenario verification library, it is determined whether the file to be upgraded has the corresponding expected functions in the scenario to be verified.

3. The method according to claim 2, characterized in that, The functional verification result includes the actual perceived result, and the expected result includes the anticipated perceived result. Based on the functional verification result and the expected result corresponding to the scenario to be verified in the scenario verification library, it is determined whether the file to be upgraded has the corresponding expected function in the scenario to be verified, including: If the actual perception result differs from the expected perception result, then it is determined that the file to be upgraded does not possess the expected function corresponding to the scenario to be verified.

4. The method according to claim 3, characterized in that, The functional verification result also includes the actual decision result, and the expected result includes the anticipated decision result. Based on the functional verification result and the expected result corresponding to the scenario to be verified in the scenario verification library, it is determined whether the file to be upgraded has the corresponding expected function in the scenario to be verified, and the method also includes: If the actual perception result is the same as the expected perception result, and the actual decision result is different from the expected decision result, then it is determined that the file to be upgraded does not have the expected function corresponding to the scenario to be verified.

5. The method according to claim 4, characterized in that, The functional verification result also includes the actual control result, and the expected result includes the anticipated control result. Based on the functional verification result and the expected result corresponding to the scenario to be verified in the scenario verification library, it is determined whether the file to be upgraded has the corresponding expected function in the scenario to be verified, and the method further includes: If the actual perception result is the same as the expected perception result, and the actual decision result is the same as the expected decision result, and the actual control result is different from the expected control result, then it is determined that the file to be upgraded does not have the expected function corresponding to the scenario to be verified.

6. The method according to claim 1, characterized in that, After reorganizing the file to be upgraded according to the expected function code, the process also includes: The intelligent reasoning model is used to test whether the recombined file to be upgraded has the expected function in the scenario to be verified. If not, the expected function code corresponding to the scenario to be verified is generated through the intelligent reasoning model, and the recombined upgrade file is recombined according to the expected function code until the recombined upgrade file has the expected function corresponding to the scenario to be verified.

7. The method according to claim 1, characterized in that, The method further includes: The vehicle's entire system runs in the simulated twin system; During the process of testing whether the file to be upgraded has the corresponding expected function in the scenario to be verified, the intelligent reasoning model is used to test whether the vehicle system is abnormal. In response to the vehicle system anomaly, the intelligent inference model generates system adjustment code corresponding to the scenario to be verified, and the file to be upgraded is reorganized according to the system adjustment code.

8. The method according to claim 1, characterized in that, After generating the expected functional code corresponding to the scenario to be verified through the intelligent reasoning model, the method further includes: The expected function code is associated with the scenario to be verified and stored in the model expert knowledge base so that other vehicles of the same model can obtain the expected function code through the model expert knowledge base.

9. The method according to claim 1, characterized in that, The intelligent reasoning model generates the expected functional code corresponding to the scenario to be verified, including: The scene semantic features of the scene to be verified are determined by the intelligent reasoning model, and the functional semantic features of the expected function are determined. The expected functional code is generated based on the scene semantic features and the functional semantic features.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program or instructions that cause a computer to perform the steps of the OTA upgrade method for a vehicle ECU as described in any one of claims 1 to 9.

Images