Vehicle communication method and device, electronic equipment and medium
By using a neural network model in vehicle-mounted ECU communication to construct the request message and feedback function identification relationship of the service interface, the problems of high equipment cost and long learning cycle in the existing technology are solved, and efficient vehicle communication development is achieved.
Patent Information
- Application Number
- CN202511086634.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-05
- Publication Date
- 2025-10-17
AI Technical Summary
In the existing vehicle-mounted ECU communication debugging, professional equipment is expensive, the learning cycle is long, and the flexibility is poor. It is difficult to adapt to the needs of agile development, and the maintenance workload of the self-developed protocol stack is large.
A neural network model is used to construct the correspondence between the request message and feedback function identifier of the service interface, and the feedback function is generated and verified through a large language model, reducing development costs and improving testing efficiency.
It reduces vehicle communication development costs, improves testing efficiency, and adapts to agile development needs.
Smart Images
Figure CN120812094A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of vehicle communication, in particular to a communication method and device of a vehicle, an electronic device and a medium. BACKGROUND
[0002] In the field of vehicle ECU communication debugging, the application of SOME / IP protocol is increasingly widespread, but the existing test scheme has significant limitations. The mainstream method is divided into two categories: one relies on professional devices such as Canoe and Tongxing for signal simulation, but the high hardware cost leads to resource centralization and low efficiency per capita. The complex bus configuration process requires testers to have a deep understanding of CAN / LIN bus and CAPL scripts, and beginners need to learn for several months. Moreover, the modification of preset test cases requires secondary development through special software, which is difficult to meet the needs of agile development. The second method is to develop test tools using self-developed SOME / IP protocol stack, which improves flexibility, but requires additional investment in protocol stack authorization fees and UI framework development costs. When the definition of vehicle services changes, the serialization logic, SD discovery mechanism and TCP / UDP transport layer code need to be modified simultaneously, resulting in an exponential increase in maintenance workload. SUMMARY
[0003] Therefore, the present application aims to provide a communication method and device of a vehicle, an electronic device and a medium, which overcome at least one of the above-mentioned defects.
[0004] In a first aspect, a communication method of a vehicle is provided. The method comprises: receiving a target request message sent by a target requestor of the vehicle; inputting the target request message into a neural network model to obtain a target feedback function identifier corresponding to the target request message, wherein the neural network model is based on interface information and message protocol of each service interface to build a corresponding relationship between request messages of the service interface and feedback function identifiers of the service interface; executing a corresponding target feedback function according to the target feedback function identifier to obtain a target response message; and sending the target response message to the target requestor.
[0005] In one possible implementation, the neural network model is constructed by: obtaining a business protocol, inputting the business protocol into a large language model, the business protocol including interface information and message protocol corresponding to each service interface; for each service interface, the large language model generates a feedback function corresponding to the service interface according to the interface information and message protocol of the service interface, and verifies the feedback function. When the feedback function passes the verification, the real request message corresponding to the service interface and the feedback function are saved to a training data set; and the real request message of each service interface in the training data set and the feedback function corresponding to the service interface are represented by the neural network model.
[0006] In a possible implementation, the feedback function is determined to pass the verification by: inputting a real request message of each service interface into the corresponding feedback function to obtain an output response message; and determining that the feedback function passes the verification when the output response message matches a real response message corresponding to the real request message.
[0007] In a possible implementation, the large language model generates the feedback function corresponding to the service interface by: for each service interface, determining interface information and message protocol of the service interface according to a preset instruction, determining communication characteristics and data types of parameters of the service interface according to the interface information and the message protocol, generating the feedback function of the service interface according to the communication characteristics and the data types of the parameters, and saving the communication characteristics and the data types of the parameters and the feedback function of the service interface into a database.
[0008] In a possible implementation, the method further includes: for a service interface of a periodic triggering type, executing the feedback function of the service interface according to a periodic communication period value of the service interface to obtain a periodic response message, and sending the periodic response message to the service interface.
[0009] In a possible implementation, the method further includes: receiving a natural language instruction sent by a master requestor of the vehicle; sending the natural language instruction to the large language model, so that the large language model finds a master request message corresponding to the natural language instruction from the database; inputting the master request message into the neural network model to obtain a feedback function identifier corresponding to the master request message, and executing the corresponding feedback function according to the feedback function identifier to obtain a master response message, and sending the master response message to the master requestor.
[0010] In a second aspect, the application provides a communication device of a vehicle, the device comprising: a receiving module configured to receive a target request message sent by a target requestor of the vehicle; an input module configured to input the target request message into a neural network model to obtain a target feedback function identifier corresponding to the target request message, wherein the neural network model is configured to construct a corresponding relationship between a request message of each service interface and a feedback function identifier of the service interface based on interface information and message protocol of the service interface; and a sending module configured to execute a corresponding target feedback function according to the target feedback function identifier to obtain a target response message, and send the target response message to the target requestor.
[0011] In a possible implementation, the input module is further configured to: obtain a service protocol, and input the service protocol to the large language model, the service protocol including interface information and message protocols corresponding to each service interface; for each service interface, the large language model generates a feedback function corresponding to the service interface according to the interface information and the message protocols of the service interface, and verifies the feedback function, and when the feedback function passes the verification, saves a real request message corresponding to the service interface and the feedback function to a training data set; and represents the real request message of each service interface and the feedback function corresponding to the service interface in the training data set by using the neural network model.
[0012] In a third aspect, the present application also provides an electronic device, comprising: a processor, a memory and a bus, the memory stores machine readable instructions executable by the processor, when the electronic device is running, the processor and the memory communicate through the bus, and the machine readable instructions are executed by the processor to perform the steps of the above method.
[0013] In a fourth aspect, the present application also provides a computer readable storage medium, the computer readable storage medium stores a computer program, and the computer program is executed by the processor to perform the steps of the above method.
[0014] The present application provides a communication method and device of a vehicle, an electronic device and a medium, wherein the method comprises: receiving a target request message sent by a target requestor of the vehicle; inputting the target request message into a neural network model to obtain a target feedback function identifier corresponding to the target request message, wherein the neural network model is based on interface information and message protocols of a service interface corresponding to each request message to construct a corresponding relationship between the request message of the service interface and the feedback function identifier of the service interface; executing a corresponding target feedback function according to the target feedback function identifier to obtain a target response message, and sending the target response message to the target requestor. Through the present application, the development cost of vehicle communication is reduced, and the test work efficiency is improved.
[0015] In order to make the above objectives, characteristics and advantages of the present application more apparent and easy to understand, the following preferred embodiments are specifically described below, and the accompanying drawings are described in detail as follows. BRIEF DESCRIPTION OF DRAWINGS
[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor.
[0017] Figure 1 A flowchart of a communication method of a vehicle provided by an embodiment of the present application; Figure 2 A flowchart of constructing a neural network model provided by an embodiment of the present application; Figure 3 A flowchart of another communication method of a vehicle provided by an embodiment of the present application; Figure 4 A structural schematic diagram of a communication device of a vehicle provided by an embodiment of the present application; Figure 5 A structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION
[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the following will be combined with the accompanying drawings for the embodiments of the present application to make a clear and complete description of the technical solutions of the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. The components of the embodiments of the present application described and shown in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, every other embodiment obtained by a person skilled in the art without creative work belongs to the scope of protection of the present application.
[0019] First, the application scenarios applicable to the present application are introduced. The present application can be applied to vehicle-mounted communication.
[0020] It is found through research that in the field of vehicle-mounted ECU communication debugging, the application of SOME / IP protocol is increasingly widespread, but the existing test scheme has significant limitations. The mainstream method is divided into two categories: one relies on professional devices such as Canoe and Tongxing for signal simulation, but the high hardware cost leads to resource centralization and low efficiency per capita; the complex bus configuration process requires testers to have a deep foundation in CAN / LIN bus and CAPL script, and beginners take up to several months to learn; and the modification of preset test cases requires secondary development through special software, which is difficult to adapt to agile development needs. The second is to develop test tools using self-developed SOME / IP protocol stack, which improves flexibility, but requires additional investment in protocol stack authorization fees and UI framework development costs; when the vehicle-mounted service definition changes, the serialization logic, SD discovery mechanism, and TCP / UDP transport layer code need to be modified simultaneously, resulting in an exponential increase in maintenance workload.
[0021] Based on this, the embodiment of the application provides a communication method, device, electronic equipment and medium of a vehicle, aiming to reduce the development cost of vehicle communication and improve the work efficiency of development.
[0022] Please refer to Figure 1 , Figure 1 A flowchart of a communication method of a vehicle provided by the embodiment of the application is shown in FIG. 1. Figure 1 As shown in FIG. 1, the communication method of the vehicle provided by the embodiment of the application comprises the following steps. S101, receiving a target request message sent by a target requestor of a vehicle.
[0023] Here, the target request message is a SOME / IP message, and when the target request message is received, the target request message needs to be vectorized first. The base module is included in the vehicle-mounted ECU, and the base module is used to receive the target request message sent by the target requestor and send the corresponding target response message to the target requestor.
[0024] S102, inputting the target request message into a neural network model to obtain a target feedback function identifier corresponding to the target request message.
[0025] Here, the neural network model is based on the interface information and the message protocol of each request message corresponding to a service interface, and constructs the corresponding relationship between the request message of the service interface and the feedback function identifier of the service interface.
[0026] Specifically, the message protocol is a SOME / IP protocol.
[0027] The specific process of constructing the neural network model will be introduced below. Figure 2
[0028] Figure 2 A flowchart of constructing the neural network model provided by the embodiment of the application is shown in FIG. 2.
[0029] S201, obtaining a business protocol and inputting the business protocol into a large language model.
[0030] Here, the business protocol includes the interface information and the message protocol corresponding to each service interface, and a real Ethernet message recorded in advance also needs to be obtained, and the real Ethernet message includes a real request message and a corresponding real response message.
[0031] S202, for each service interface, the large language model generates a feedback function corresponding to the service interface according to the interface information and the message protocol of the service interface, and verifies the feedback function. When the feedback function passes the verification, the real request message corresponding to the service interface and the feedback function are saved to a training data set.
[0032] Here, the Agent module included in the vehicle-mounted ECU is used to automatically traverse each service interface (such as event, field, and method) in the business protocol, input the interface information corresponding to the service interface, the SOME / IP protocol, and a preset instruction as a prompt word to the large language model, so that the large language model generates a feedback function corresponding to the service interface.
[0033] Specifically, the preset instruction can be specifically "as a SOME / IP communication expert, help me to form a SOME / IP binary message packet from the current service interface, and meet the following requirements: (1) identify the communication characteristics of the service interface, including the sending period, the triggering method, and the data format, call the [save communication characteristics] method in the Agent module, and store the identification result in the database; (2) extract the data entities involved in the message, including the Event reporting data, the Field read-write data, or the Method parameter / return value, call the [save parameter] method in the Agent module, and store the data entity name, data type, and value range in the database; (3) generate the Python code of the feedback function, call the [save feedback function] method in the Agent module, and save the code to the database." As an example, for the Event / Field Getter / Method Response type interface, the feedback function reads the parameter value from the database and forms a response message; for the Field Setter / Method Request type interface, the feedback function parses the request message and updates the database parameter value.
[0034] Here, each generated feedback function also needs to be verified, and the feedback function is determined to pass the verification in the following way: input the real request message of each service interface into the corresponding feedback function to obtain the output response message; when the output response message matches the real response message corresponding to the real request message, it is determined that the feedback function passes the verification.
[0035] Specifically, the Agent module forms a binary message packet from the request message and the response message corresponding to the feedback function that passes the verification, and calls the [save message] method in the Agent module to store the binary message packet in the database, wherein the Agent module needs to ensure that the parameter range is appropriately covered, such as covering the normal value and the out-of-limit abnormal value of the vehicle speed at least to 0 to 500 km / h, to ensure the integrity of the training data, wherein the database should have the ability to monitor field changes when the parameters change, and can call the callback function for processing.
[0036] S203, adopt a neural network model to represent the real request message of each service interface in the training data set and the feedback function corresponding to the service interface.
[0037] Here, the recorded Ethernet message is used as evaluation data to evaluate the effectiveness of the neural network. If the neural network is not ideal, the neural network parameters are adjusted and retrained.
[0038] Return Figure 1 S103, execute the corresponding target feedback function according to the target feedback function identifier to obtain a target response message, and send the target response message to the target requester.
[0039] Figure 3 The flowchart of another communication method of a vehicle provided by the embodiment of the present application. As shown in Figure 3 The another communication method of a vehicle provided by the embodiment of the present application comprises: S301, receiving a natural language instruction sent by a master requester of a vehicle.
[0040] Here, the master requester refers to a control terminal (such as a PC / tablet of a test engineer) that sends the natural language instruction, which is not a vehicle-mounted ECU.
[0041] S302, sending the natural language instruction to a large language model to make the large language model find a master request message corresponding to the natural language instruction from a database.
[0042] S303, inputting the master request message into a neural network model to obtain a feedback function identifier corresponding to the master request message, and executing the corresponding feedback function according to the feedback function identifier to obtain a master response message, and sending the master response message to the master requester.
[0043] As an example, it also includes: for each communication feature for a periodic trigger type service interface, executing the feedback function of the service interface according to the periodic communication period value of the service interface to obtain a periodic response message, and sending the periodic response message to the service interface.
[0044] Based on the same inventive concept, the embodiment of the present application also provides a communication device of a vehicle corresponding to the communication method of the vehicle. Since the principle of solving problems in the device of the embodiment of the present application is similar to the above-mentioned communication method of the vehicle of the embodiment of the present application, the implementation of the device can be referred to the implementation of the method, and the repeated parts will not be described here.
[0045] Please refer to Fig Figure 4 , Figure 4 The structural schematic diagram of the communication device of the vehicle provided by the embodiment of the present application. As shown in Figure 4 The communication device 400 of the vehicle comprises: The receiving module 401 is configured to receive a target request message sent by a target requester of the vehicle.
[0046] The input module 402 is configured to input the target request message into a neural network model to obtain a target feedback function identifier corresponding to the target request message, wherein the neural network model is based on interface information and message protocols of a service interface corresponding to each request message to construct a corresponding relationship between request messages of the service interface and feedback function identifiers of the service interface.
[0047] The sending module 403 is configured to execute a corresponding target feedback function according to the target feedback function identifier to obtain a target response message, and send the target response message to the target requester.
[0048] Please refer to Figure 5 , Figure 5 A structural schematic diagram of an electronic device provided by an embodiment of the present application is shown in FIG. 5. Figure 5 As shown in FIG. 5, the electronic device 500 includes a processor 510, a memory 520 and a bus 530.
[0049] The memory 520 stores machine readable instructions executable by the processor 510. When the electronic device 500 is running, the processor 510 and the memory 520 communicate through the bus 530. When the machine readable instructions are executed by the processor 510, the steps of the communication method of the vehicle in the above embodiment can be executed. For details, refer to the method embodiment, which will not be described here.
[0050] The present application also provides a computer readable storage medium having a computer program stored thereon. When the computer program is run by a processor, the steps of the communication method of the vehicle in the above embodiment can be executed. For details, refer to the method embodiment, which will not be described here.
[0051] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiment, which will not be described here.
[0052] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. The described device embodiments are merely schematic, for example, the division of the units is only a logical function division, and there can be another division manner in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units, or the among different units, can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.
[0053] The units described as separated components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. In actual implementation, some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments of the present application.
[0054] In addition, each functional unit in the embodiments of the present application can be integrated in one processing unit, or each unit can exist physically as a separate unit, or two or more units can be integrated in one unit.
[0055] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.
[0056] Finally, it should be noted that the above-described embodiments are merely specific embodiments of the present application, which are used to illustrate the technical solutions of the present application, but not to limit the same. The protection scope of the present application is not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that any skilled person in the art can still modify or easily think of changes to the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some of the technical features, within the technical scope disclosed by the present application. The modifications, changes or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.
Claims
1. A vehicle communication method, characterized in that: The method comprises: receiving a target request message sent by a target requester of the vehicle; Inputting the target request message into a neural network model to obtain a target feedback function identifier corresponding to the target request message, wherein the neural network model constructs a correspondence between the request message of the service interface and the feedback function identifier of the service interface based on the interface information and message protocol of the service interface corresponding to each request message; The corresponding target feedback function is executed according to the target feedback function identifier to obtain a target response message, and the target response message is sent to the target requester.
2. The method according to claim 1, characterized in that The neural network model is constructed in the following way: Obtaining a business agreement and inputting the business agreement into a large language model, wherein the business agreement includes interface information and a message protocol corresponding to each service interface; For each service interface, the large language model generates a feedback function corresponding to the service interface based on the interface information and message protocol of the service interface, and verifies the feedback function. When the feedback function passes the verification, the real request message corresponding to the service interface and the feedback function are saved in the training dataset; The actual request message of each service interface in the training data set and the feedback function corresponding to the service interface are represented by the neural network model.
3. The method according to claim 2, characterized in that The feedback function is verified by: Input the actual request message of each service interface into the corresponding feedback function to obtain the output response message; When the output response message matches the real response message corresponding to the real request message, it is determined that the feedback function passes the verification.
4. The method according to claim 2, characterized in that The large language model generates the feedback function corresponding to the service interface in the following way: For each service interface, the interface information and message protocol of the service interface are determined according to the preset instructions to determine the communication characteristics and parameter data types of the service interface, so as to generate the feedback function of the service interface according to the communication characteristics and parameter data types, and save the communication characteristics, parameter data types and feedback function of the service interface into the database.
5. The method according to claim 4, characterized in that Also includes: For each service interface with a periodic trigger type of communication characteristic, the feedback function of the service interface is periodically executed according to the periodic communication period value of the service interface to obtain a periodic response message, and the periodic response message is sent to the service interface.
6. The method according to claim 4, characterized in that Also includes: receiving a natural language instruction sent by a master requester of the vehicle; Sending the natural language instruction to the large language model, so that the large language model searches the database for a master control request message corresponding to the natural language instruction; The master control request message is input into a neural network model to obtain a feedback function identifier corresponding to the master control request message, and a corresponding feedback function is executed according to the feedback function identifier to obtain a master control response message, and the master control response message is sent to the master control requester.
7. A vehicle communication device, characterized in that: The device comprises: A receiving module, configured to receive a target request message sent by a target requester of the vehicle; An input module is used to input the target request message into the neural network model to obtain a target feedback function identifier corresponding to the target request message, wherein the neural network model constructs a correspondence between the request message of the service interface and the feedback function identifier of the service interface based on the interface information and message protocol of the service interface corresponding to each request message; The sending module is used to execute the corresponding target feedback function according to the target feedback function identifier to obtain a target response message, and send the target response message to the target requester.
8. The device according to claim 7, characterized in that The input module is further configured to: Obtaining a business agreement and inputting the business agreement into a large language model, wherein the business agreement includes interface information and a message protocol corresponding to each service interface; For each service interface, the large language model generates a feedback function corresponding to the service interface based on the interface information and message protocol of the service interface, and verifies the feedback function. When the feedback function passes the verification, the real request message corresponding to the service interface and the feedback function are saved in the training dataset; The actual request message of each service interface in the training data set and the feedback function corresponding to the service interface are represented by the neural network model.
9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and the processor executes the machine-readable instructions to perform the steps of any one of the methods described in claims 1 to 6.
10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are executed.