Vehicle fault diagnosis method and apparatus

Abstract

Provided in the present application are a vehicle fault diagnosis method and apparatus. The method comprises: acquiring first fault description data of a first vehicle, and then inputting the first fault description data of the first vehicle into a fault diagnosis model to obtain a first diagnosis result, the fault diagnosis model being used for describing a correspondence between fault description data and a diagnosis result of a vehicle, and the first diagnosis result being used for instructing a fault diagnosis agent module to execute a fault diagnosis operation corresponding to the first diagnosis result. Using the fault diagnosis model to analyze the first fault description data of the first vehicle can timely and efficiently obtain the first diagnosis result, so as to replace manual diagnosis of vehicle faults, thus helping to reduce the time for vehicle fault diagnosis, and improving the efficiency of diagnosing vehicle faults.

Description

Vehicle fault diagnosis method and device

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on December 11, 2023, with application number 202311692701.1 and application name “A Vehicle Fault Diagnosis Method and Device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present application relates to the field of vehicle networking technology, and in particular to a vehicle fault diagnosis method and device. Background Art

[0004] With the rapid development of new energy technologies, electric vehicles have also seen rapid growth and have begun to be introduced to the market on a large scale, garnering widespread attention. Among these factors, after-sales service and maintenance are crucial factors in purchasing decisions and a crucial component of the user experience. Furthermore, electric vehicles incorporate a variety of intelligent components, and the software in these components is constantly being updated. While these updates help continuously deliver new features throughout the vehicle's lifecycle, they also inevitably introduce certain vehicle failures.

[0005] At present, the industry has provided some solutions for handling electric vehicle failures. However, these solutions either require users to drive their electric vehicles to a 4S car sales service store for manual inspection and location of the vehicle failure and repair of the failure, or require users to call customer service, describe the vehicle failure phenomenon to the customer service, and wait for the customer service to provide a solution. However, these solutions use manual methods, which makes vehicle fault diagnosis time-consuming and leads to low vehicle fault location efficiency and slow fault diagnosis response.

[0006] Summary of the Invention

[0007] The present application provides a vehicle fault diagnosis method and device to improve the diagnosis efficiency of vehicle faults.

[0008] In the first aspect, the present application provides a vehicle fault diagnosis method, which can be applied to the field of electric vehicles, the field of operation and maintenance, or any field of networked vehicles, etc. Optionally, the method can be performed by a vehicle fault diagnosis device or a component (such as a chip, a chip system or a circuit, etc.) that can support the vehicle fault diagnosis device to implement the functions required by the method. Exemplarily, the vehicle fault diagnosis device can be a functional module (such as a first functional module) configured with a fault diagnosis model or a device (such as a first computing device) configured with a fault diagnosis model, or it can also be a fault diagnosis agent module configured with a fault diagnosis model, or it can also be an integrated module (or can be called an integrated unit) of the first functional module (or the first computing device) and the fault diagnosis agent module, etc., or it can also be other devices with vehicle fault diagnosis functions or functional elements (such as plug-ins, components or chips, etc.) provided in other devices with vehicle fault diagnosis functions. Optionally, taking the vehicle fault diagnosis device executing the vehicle fault diagnosis method as an example, in this method, the vehicle fault diagnosis device can first obtain first fault description data of the first vehicle, and then the vehicle fault diagnosis device can input the first fault description data into the fault diagnosis model to obtain a first diagnosis result, wherein the fault diagnosis model can be used to describe the correspondence between the vehicle's fault description data and the diagnosis result, and the first diagnosis result can be used to instruct the fault diagnosis agent module to perform a fault diagnosis operation corresponding to the first diagnosis result.

[0009] In this method, by using a fault diagnosis model to analyze the first fault description data of the first vehicle (or it can be understood as a description of the vehicle's fault phenomenon), the corresponding diagnostic results (such as the first diagnostic results) can be obtained in a timely and effective manner, which can replace manual diagnosis of vehicle faults, help reduce the diagnosis time of vehicle faults, and thus improve the diagnostic efficiency of vehicle faults.

[0010] In one possible design, the method further includes: the vehicle fault diagnosis device can generate a first fault handling report based on the first diagnosis result, and then the vehicle fault diagnosis device can feed back the first fault handling report to the first vehicle.

[0011] In the above design, when the vehicle fault diagnosis device is an integrated module of the first functional module (or the first computing device) and the fault diagnosis agent module, the vehicle fault diagnosis device can generate a first fault handling report for the first vehicle based on the first diagnostic result after obtaining the first diagnostic result, and can promptly feed back the first fault handling report of the first vehicle to the first vehicle, so that the user of the first vehicle can promptly understand the fault condition of the first vehicle, thereby facilitating the user of the first vehicle to take corresponding fault handling measures in a targeted manner.

[0012] In one possible design, the method further includes: the vehicle fault diagnosis device can send a first diagnosis result to the fault diagnosis agent module, and the first diagnosis result is used to generate a first fault handling report.

[0013] In the above design, when the vehicle fault diagnostic device is the first functional module, the vehicle fault diagnostic device can promptly send the first diagnostic result to the fault diagnostic agent module so that the fault diagnostic agent module can accurately perform corresponding diagnostic operations based on the first diagnostic result. For example, the fault diagnostic agent module can generate a first fault handling report based on the first diagnostic result, or the fault diagnostic agent module can also send corresponding information to the corresponding fault diagnostic module.

[0014] In one possible design, the vehicle fault diagnostic device generates a first fault handling report based on the first diagnostic result, including: when the first diagnostic result includes information of the first fault diagnostic module, the vehicle fault diagnostic device can send first information to the first fault diagnostic module, wherein the first information may include information of the first vehicle (such as the vehicle identification or vehicle name of the first vehicle, the model and series of the first vehicle, or the time (or time period) when the first vehicle fails, etc.), and the first information is used to indicate fault diagnosis of the first vehicle. Afterwards, the vehicle fault diagnostic device can obtain a second diagnostic result from the first fault diagnostic module, and then, the vehicle fault diagnostic device can generate a first fault handling report based on the second diagnostic result.

[0015] In the above design, when the vehicle fault diagnosis device is an integrated module of a first functional module (or a first computing device) and a fault diagnosis agent module, the vehicle fault diagnosis device can, when the first diagnostic result includes information from the first fault diagnosis module, send the first information to the first fault diagnosis module to further determine (or locate or identify or perceive) the fault of the first vehicle with the help of the first fault diagnosis module, thereby effectively locating the vehicle fault. In this way, by utilizing the fault diagnosis agent module, the method can enable the fault diagnosis model to have the ability to call the corresponding fault diagnosis module, thereby realizing fully automated operations for vehicle fault analysis, vehicle fault diagnosis, and vehicle fault determination, which helps to significantly improve the efficiency of vehicle fault diagnosis (or vehicle fault location or vehicle fault detection).

[0016] In a possible design, the first fault description data may be obtained by formatting the second fault description data of the first vehicle, wherein the second fault description data may be obtained through user input.

[0017] In one possible design, the data type of the second fault description data may include at least one of the following: voice, text, picture, or recording.

[0018] In the above design, the second fault description data of the first vehicle can be obtained through human-computer interaction, so that the user can submit the fault phenomenon description of the first vehicle in a timely and accurate manner through the interactive interface. In addition, by converting the format of the second fault description data of the first vehicle, fault description data in the input data format (or understandable as input data type) that meets the requirements of the fault diagnosis model can be obtained, so the fault diagnosis model can perceive input data of different data types (for example, the user can submit fault phenomenon descriptions of different data types at the same time (for example, the user can submit any multiple of voice descriptions of fault phenomena, text descriptions of fault phenomena, pictures containing fault phenomena, or recordings (or sounds) containing fault phenomena) at the same time)).

[0019] In one possible design, the fault diagnosis model can be obtained by training a generative artificial intelligence (AI) model (such as the Pangu model) based on fault training samples, where the fault training samples may include fault description data and fault causes (part of the content included in the diagnosis results). Optionally, the fault training samples may also include information about the fault diagnosis module (such as whether the fault diagnosis module needs to be used for confirmation (or re-diagnosis) or attribute information of the fault diagnosis module (such as identification, name, or API).

[0020] In the above design, by utilizing the learning ability of the generative AI model to learn vehicle fault diagnosis knowledge (such as the relevant content contained in the fault training sample), a fault diagnosis model for determining vehicle faults can be obtained. For example, the multimodal understanding ability of the fault diagnosis model can be utilized to analyze the vehicle fault. This can replace manual diagnosis of vehicle faults, help reduce the diagnosis time of vehicle faults, and thus improve the diagnosis efficiency of vehicle faults.

[0021] In one possible design, the generative AI model can be a large multimodal model.

[0022] In the above design, the multimodal understanding capability of the multimodal large model is utilized to perceive input data of different data types, thereby being able to fully understand the fault phenomenon description submitted by the user, thereby determining the vehicle fault.

[0023] In one possible design, the first fault handling report may include at least one of the following: a fault cause, a fault level, or a handling solution corresponding to the fault cause.

[0024] In the above design, by including one or more of the fault cause, fault level or handling solutions corresponding to the fault cause in the first fault handling report, the vehicle user can promptly understand the vehicle's fault condition, thereby facilitating the user of the first vehicle to take corresponding fault handling measures in a timely manner.

[0025] On the second aspect, the present application provides a vehicle fault diagnosis method, which can be applied to the field of electric vehicles, the field of operation and maintenance, or any field of networked vehicles, etc. Optionally, the method can be performed by a vehicle fault diagnosis device or a component (such as a chip, a chip system or a circuit, etc.) that can support the vehicle fault diagnosis device to implement the functions required by the method. Exemplarily, the vehicle fault diagnosis device can be a fault diagnosis agent module, or it can also be a fault diagnosis agent module that configures a fault diagnosis model, or it can also be an integrated module (or it can be called an integrated unit) of a first functional module (or a first computing device) and a fault diagnosis agent module, etc., or it can also be other devices with vehicle fault diagnosis functions or functional elements (such as plug-ins, components or chips, etc.) provided in other devices with vehicle fault diagnosis functions. Optionally, taking the vehicle fault diagnosis device executing the vehicle fault diagnosis method as an example, in this method, the vehicle fault diagnosis device can first receive a first diagnostic result, wherein the first diagnostic result is associated with the first fault description data and the fault diagnosis model of the first vehicle, the fault diagnosis model can be used to describe the correspondence between the vehicle's fault description data and the diagnostic result, and the first diagnostic result can be used to instruct the fault diagnosis agent module to execute a fault diagnosis operation corresponding to the first diagnostic result. Afterwards, the vehicle fault diagnosis device can execute the fault diagnosis operation corresponding to the first diagnostic result based on the first diagnostic result.

[0026] The technical effects that can be achieved in the second aspect can be referred to the technical effects that can be achieved in the first aspect mentioned above, and will not be repeated here.

[0027] In one possible design, the vehicle fault diagnostic device performs a fault diagnostic operation corresponding to the first diagnostic result based on the first diagnostic result, including: the vehicle fault diagnostic device can generate a first fault handling report based on the first diagnostic result.

[0028] In the above design, a first fault handling report for the first vehicle can be effectively generated based on the first diagnostic result.

[0029] In one possible design, when the first diagnostic result includes information of the first fault diagnostic module, the method also includes: the vehicle fault diagnostic device can send first information to the first fault diagnostic module, wherein the first information may include information of the first vehicle, and the first information can be used to indicate fault diagnosis of the first vehicle, after which the vehicle fault diagnostic device can obtain a second diagnostic result from the first fault diagnostic module, wherein the second diagnostic result can be used to generate a first fault handling report.

[0030] In the above design, the vehicle fault diagnostic device sends the first information to the first fault diagnostic module, thereby further determining the fault of the first vehicle through the first fault diagnostic module, thereby effectively locating the vehicle fault. In this way, by utilizing the fault diagnosis agent module, the method can enable the fault diagnosis model to call the corresponding fault diagnosis module, thereby achieving fully automated operations for vehicle fault analysis, vehicle fault diagnosis, and vehicle fault determination, which helps to significantly improve the efficiency of vehicle fault diagnosis (or vehicle fault location or vehicle fault detection).

[0031] In one possible design, the method further includes: the vehicle fault diagnosis device can feed back a first fault handling report to the first vehicle.

[0032] In the above design, by feeding back the first fault handling report of the first vehicle to the first vehicle, the user of the first vehicle can promptly understand the fault condition of the first vehicle, thereby facilitating the user of the first vehicle to take corresponding fault handling measures in a timely manner.

[0033] In a possible design, the first fault description data may be obtained by formatting the second fault description data of the first vehicle, wherein the second fault description data may be obtained through user input.

[0034] The technical effects that can be achieved by the above design can refer to the technical effects of the corresponding design in the above first aspect, and will not be repeated here.

[0035] In one possible design, the data type of the second fault description data may include at least one of the following: voice, text, picture, or recording.

[0036] In one possible design, the fault diagnosis model can be obtained by training a generative artificial intelligence (AI) model (such as the Pangu model) based on fault training samples, where the fault training samples may include fault description data and fault causes (part of the content included in the diagnosis results). Optionally, the fault training samples may also include information about the fault diagnosis module (such as whether the fault diagnosis module needs to be used for confirmation (or re-diagnosis) or attribute information of the fault diagnosis module (such as identification, name, or API).

[0037] The technical effects that can be achieved by the above design can refer to the technical effects of the corresponding design in the above first aspect, and will not be repeated here.

[0038] In one possible design, the generative AI model can be a large multimodal model.

[0039] The technical effects that can be achieved by the above design can refer to the technical effects of the corresponding design in the above first aspect, and will not be repeated here.

[0040] In one possible design, the first fault handling report may include at least one of the following: a fault cause, a fault level, or a handling solution corresponding to the fault cause.

[0041] The technical effects that can be achieved by the above design can refer to the technical effects of the corresponding design in the above first aspect, and will not be repeated here.

[0042] In a third aspect, the present application provides a possible vehicle fault diagnosis device. In one example, the vehicle fault diagnosis device comprises a vehicle fault diagnosis device (such as a first functional module or an integrated module of the first functional module and a fault diagnosis agent module) that implements the functions required by the method of the first aspect, or may be a component (such as a plug-in, component, or chip, etc.) disposed in the vehicle fault diagnosis device that implements the functions required by the method of the first aspect, or may be any other device that implements the functions required by the method of the first aspect, or may be a component disposed in any other device that implements the functions required by the method of the first aspect. In another example, the vehicle fault diagnosis device comprises a vehicle fault diagnosis device (such as a fault diagnosis agent module or an integrated module of the first functional module and a fault diagnosis agent module) that implements the functions required by the method of the second aspect, or may be a component (such as a plug-in, component, or chip, etc.) disposed in the vehicle fault diagnosis device that implements the functions required by the method of the second aspect, or may be any other device that implements the functions required by the method of the second aspect, or may be a component disposed in any other device that implements the functions required by the method of the second aspect.

[0043] For example, if the vehicle fault diagnostic device is a chip installed in the vehicle fault diagnostic device, the chip may include a transceiver and a processor, but no memory. The transceiver is implemented as an input / output interface, which is used by the chip to implement transmission and reception of the vehicle fault diagnostic device. The input / output interface may include an input interface and / or an output interface. The processor is configured to read and execute corresponding computer programs or instructions to implement the corresponding functions of the vehicle fault diagnostic device.

[0044] When a vehicle fault diagnostic device is used to implement any of the possible methods of the first aspect described above, the beneficial effects can be found in the corresponding description of the first aspect and are not further elaborated here. The vehicle fault diagnostic device has the functions of implementing the method of the first aspect described above. This function can be implemented through hardware or through hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions. In one possible design, the vehicle fault diagnostic device includes a communication module (or a transceiver module, transceiver unit, or communication unit, for sending and receiving data) and a processing module. The communication module is configured to obtain first fault description data of a first vehicle. The processing module is configured to input the first fault description data into a fault diagnosis model to obtain a first diagnostic result. The fault diagnosis model can be used to describe the correspondence between the vehicle fault description data and the diagnostic result; the first diagnostic result is used to instruct the fault diagnosis agent module to perform a fault diagnosis operation corresponding to the first diagnostic result. These modules can perform the corresponding functions of any of the possible designs of the first aspect described above. For details, see the detailed description of the corresponding functions of the first functional module (or the integrated module of the first functional module and the fault diagnosis agent module) in the method example, which is not further elaborated here.

[0045] When a vehicle fault diagnostic device is used to implement any of the possible methods of the second aspect, the beneficial effects can be found in the corresponding description of the second aspect and are not further elaborated here. The vehicle fault diagnostic device has the functions of implementing the method of the second aspect. This function can be implemented in hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above-mentioned functions. In one possible design, the vehicle fault diagnostic device includes a communication module and a processing module. The communication module is configured to receive a first diagnostic result. The first diagnostic result is associated with first fault description data of a first vehicle and a fault diagnosis model; the fault diagnosis model can be used to describe the correspondence between the vehicle fault description data and the diagnostic result; and the first diagnostic result can be used to instruct a fault diagnosis agent module to perform a fault diagnosis operation corresponding to the first diagnostic result. The processing module is configured to perform a fault diagnosis operation corresponding to the first diagnostic result based on the first diagnostic result. These modules can perform the corresponding functions of any of the possible designs of the second aspect. For details, see the detailed description of the corresponding functions of the fault diagnosis agent module (or an integrated module of the first functional module and the fault diagnosis agent module) in the method example, which is not further elaborated here.

[0046] In a fourth aspect, the present application provides a possible vehicle fault diagnostic device. The vehicle fault diagnostic device may be a device required to perform the vehicle fault diagnostic method provided in the present application (such as a first functional module, a fault diagnostic proxy module, or an integrated module of the first functional module and the fault diagnostic proxy module), or may be a device that includes the vehicle fault diagnostic device required to perform the communication method provided in the present application (such as a data analysis and processing system), or may be a device that has the functions required to implement the vehicle fault diagnostic method. The vehicle fault diagnostic device may include a transceiver and a processor. Optionally, the vehicle fault diagnostic device may also include a memory. The memory is used to store computer programs or instructions, and the processor is coupled to the memory and the transceiver. When the processor executes the computer program or instructions, the vehicle fault diagnostic device performs any of the possible designs of the first aspect or any of the possible designs of the second aspect. In one example, the transceiver may be a transceiver device with integrated data transceiver functionality. In another example, the transceiver may also be composed of a transmitter and a receiver, wherein the transmitter is used to send data and the receiver is used to receive data.

[0047] In a fifth aspect, the present application provides a possible vehicle fault diagnostic system, comprising the vehicle fault diagnostic device of the first aspect and / or the vehicle fault diagnostic device of the second aspect. The vehicle fault diagnostic device of the first aspect is configured to execute the method of any possible design of the first aspect, and the vehicle fault diagnostic device of the second aspect is configured to execute the method of any possible design of the second aspect. For example, the number of vehicle fault diagnostic devices included in the vehicle fault diagnostic system may be one or more, and this application does not limit this. Optionally, the vehicle fault diagnostic system may further include at least one of the following: a data storage system, a data preprocessing system, or a diagnostic result feedback system. The data storage system may be configured to store at least one of the following: first fault description data, second fault description data, a first diagnostic result, a second diagnostic result, or a first fault handling report; the data preprocessing system may be configured to preprocess the second fault description data of the first vehicle; and the diagnostic result feedback system may be configured to provide feedback of the first fault handling report to the first vehicle (or the user of the first vehicle or the manufacturer of the first vehicle). Furthermore, the vehicle fault diagnostic system may further provide a fault description interface. The fault description interface may be configured to prompt the user of the first vehicle to enter corresponding fault diagnostic requirements. For example, the fault diagnosis request may include second fault description data of the first vehicle.

[0048] In a sixth aspect, the present application provides a computer program product, which includes a computer program or instructions. When the computer program or instructions are run on a computer, the computer executes any possible design method of the first aspect or any possible design method of the second aspect.

[0049] In the seventh aspect, the present application provides a computer-readable storage medium, which stores a computer program or instruction. When the computer program or instruction is executed by a computer, the computer executes any possible design method of the first aspect or any possible design method of the second aspect.

[0050] In an eighth aspect, the present application provides a chip, which may include a processor and a memory (or the chip is coupled to the memory), wherein the chip executes program instructions in the memory to perform the method in any possible design of the first aspect or the method in any possible design of the second aspect. "Coupled" refers to the direct or indirect connection of two components to each other, such as coupling may refer to an electrical connection between two components.

[0051] In a ninth aspect, the present application further provides a chip system, which includes a processor for supporting a computer device to implement the method in any possible design of the first aspect or the method in any possible design of the second aspect. In one possible design, the chip system also includes a memory for storing programs and data necessary for the computer device. The chip system can be composed of a chip, or it can include a chip and other discrete devices.

[0052] Based on the implementation methods provided in the above aspects, this application can also be further combined to provide more implementation methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] FIG1 exemplarily shows a schematic diagram of a possible application scenario provided by an embodiment of the present application;

[0054] FIG2 exemplarily shows a schematic diagram of the functional module structure of a vehicle fault diagnosis system provided by an embodiment of the present application;

[0055] FIG3 exemplarily shows a flow chart of a vehicle fault diagnosis method provided in an embodiment of the present application;

[0056] FIG4 exemplarily shows a schematic diagram of a fault description interface provided in an embodiment of the present application;

[0057] FIG5 exemplarily shows a schematic diagram of a fault diagnosis model training provided by an embodiment of the present application;

[0058] FIG6 exemplarily shows a schematic diagram of a minimum problem fault tree for an acoustic anomaly provided by an embodiment of the present application;

[0059] FIG7 exemplarily shows a flow chart of another vehicle fault diagnosis method provided by an embodiment of the present application;

[0060] FIG8 exemplarily shows a structural diagram of a possible vehicle fault diagnosis device provided by an embodiment of the present application;

[0061] FIG9 exemplarily shows a schematic structural diagram of another possible vehicle fault diagnosis device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0062] Before introducing the technical solution provided by this application, some of the terms involved in this application are first explained to facilitate understanding by those skilled in the art.

[0063] Generative Artificial Intelligence (AI) is a type of AI that focuses on generating or creating new content. It uses machine learning to generate entirely new content using large datasets of existing text, audio, or images. Generative AI can be implemented using a variety of technologies, including deep learning and generative adversarial networks (GANs). For example, deep learning can train neural networks to learn the characteristics and patterns of input data and generate new data based on these patterns. GANs can be used to play games between two neural networks: a generator network responsible for generating new data and a discriminator network responsible for determining whether the generated data is authentic, thereby prompting the generator network to continuously improve its generation quality.

[0064] The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0065] The following describes the application scenarios to which the vehicle fault diagnosis method provided by this application is applicable. It should be noted that these descriptions are for the purpose of facilitating understanding by those skilled in the art and do not limit the scope of protection claimed by this application.

[0066] FIG1 exemplarily shows a schematic diagram of a possible application scenario applicable to an embodiment of the present application. As shown in FIG1 , the application scenario may include a terminal device 100 and a vehicle fault diagnosis system 200. Optionally, the terminal device 100 and the vehicle fault diagnosis system 200 may be communicatively connected via one or more networks. The network may be a wireless network, for example, a wireless network may be a wireless fidelity (WIREless-Fidelity, WIFI) network, or a mobile cellular network, or other forms of network, which are not limited in the embodiments of the present application.

[0067] Among them, a target application for assisting users (such as vehicle users) in diagnosing vehicle faults is installed on the terminal device 100. For example, taking the user as a vehicle user as an example, the vehicle user can edit and submit relevant information of the vehicle to be diagnosed (such as the first vehicle) (such as the vehicle's fault description information (or can be called fault phenomenon), vehicle name, model and series, purchase time, vehicle identification (or can be called vehicle index) or fault occurrence time period (or fault occurrence time), etc.) to the vehicle fault diagnosis system 200 through the target application. Optionally, the vehicle user may not provide the vehicle name (or vehicle identification) of the vehicle to be diagnosed, because each vehicle user has registered the vehicle name (or vehicle identification) of the vehicle during the registration process on the target application, so when the vehicle user transmits the fault phenomenon data stream (or can be called fault phenomenon data packet) to the vehicle fault diagnosis system 200 through the target application, the vehicle name (or vehicle identification) of the vehicle will be automatically carried.

[0068] For example, the target application can be a client (such as a vehicle client, a personal computer (PC) client, or a mobile phone client, etc.), a web application, or a small program embedded in other applications, etc., so that users can provide timely and effective feedback on vehicle fault phenomena. Optionally, the terminal device 100 can also include a display for presenting a fault description interface provided by the vehicle fault diagnosis system 200 to achieve human-computer interaction. For example, the fault description interface displays information edited by the user or information provided to the user, etc. The fault description interface is used to prompt the user of the first vehicle to input a fault diagnosis requirement. The fault diagnosis requirement may include second fault description data of the vehicle to be diagnosed, such as the second fault description data may include the vehicle's fault phenomenon, or may also include the vehicle name (or vehicle identification) of the vehicle to be diagnosed. Optionally, the fault diagnosis requirement may also include at least one of the following: the user identification corresponding to the vehicle to be diagnosed, the time period (or occurrence time) of the vehicle's fault, the time when the user submitted the fault phenomenon, the vehicle model and series, the vehicle configuration, or the purchase time of the vehicle, etc. Exemplarily, the user can provide the vehicle fault phenomenon to the vehicle fault diagnosis system 200 by using one or more input methods such as voice input (such as describing the vehicle fault phenomenon in the form of voice), text input (such as describing the vehicle fault phenomenon in the form of text), recording (or sound) upload (such as uploading a recording or sound used to describe the fault phenomenon) or picture upload (such as uploading a picture of the fault phenomenon) on the fault description interface.

[0069] Optionally, the terminal device may also be referred to as a terminal, user equipment (UE), access terminal equipment, vehicle-mounted terminal, UE unit, UE station, mobile station, mobile station (MS), mobile terminal (MT), remote station, remote terminal equipment, mobile device, UE terminal equipment, terminal equipment, wireless communication equipment, UE agent, or UE device, etc. In the embodiments of the present application, the terminal device may be fixed or mobile, and the implementation of the present application does not limit this.

[0070] For example, the terminal device 100 may be a smartphone, a tablet computer, a desktop computer, a computer with wireless transceiver capabilities (such as a laptop), a personal digital assistant (PPD), a mobile internet device (MID), an in-vehicle terminal device, a wearable device with wireless communication capabilities (such as a smart watch, smart bracelet, smart glasses, or smart helmet), a virtual reality (VR) device, or an augmented reality (AR) device. It should be understood that this application does not limit the specific device form of the terminal device.

[0071] The vehicle fault diagnosis system 200 may refer to a device (such as a cloud server or a cloud computing device) that provides vehicle fault diagnosis services to users. The vehicle fault diagnosis system 200 responds to the user's relevant operations in the target application on the terminal device 100 (such as the user describing the vehicle's fault phenomenon on the target application) and provides the user with a corresponding vehicle fault diagnosis report. Exemplarily, the vehicle fault diagnosis system 200 may be an independent physical server, or it may be a server cluster or distributed system composed of multiple physical servers. For example, the vehicle fault diagnosis system 200 may be a cloud server (or may be called a cloud, cloud end, server end or cloud computing device) for providing cloud services, cloud computing, cloud storage, cloud communications, network services, security services and big data and other cloud computing services, or it may be an ordinary data center or server or other form of computing device.

[0072] For example, taking the terminal device 100 as a smartphone and the target application as a client installed on the smartphone for assisting users in diagnosing vehicle faults, when a vehicle user (e.g., user A) experiences a fault (e.g., a battery high temperature alarm, a battery short circuit, or a sensor fault), the user can log in to the fault description interface provided by the vehicle fault diagnosis system 200 through the client installed on the smartphone, and can use voice input (or a combination of voice input and text input or other methods) on the fault description interface to describe the fault phenomenon of vehicle A, such as a voice description of the battery high temperature alarm, or a voice description of the time period when the vehicle fault occurred, or a voice description of the vehicle name (or vehicle identification, model, or series, etc.) of vehicle A. Subsequently, in response to user A's voice description operation for vehicle A on the client, the vehicle fault diagnosis system 200 can obtain the fault phenomenon of vehicle A, or the time period when the vehicle A fault occurred, or the vehicle name (or vehicle identification, etc.) of vehicle A, and then execute the vehicle fault diagnosis process for vehicle A.

[0073] Optionally, the vehicle fault diagnosis method provided in the embodiments of the present application can be applied to multiple fields (such as the electric vehicle field or any connected vehicle field, etc.). For example, the vehicle fault diagnosis method provided in the embodiments of the present application can be specifically applied in vehicle operation and maintenance or other scenarios (such as pre-sales consultation, insurance consultation, or insurance loss assessment).

[0074] It should be noted that Figure 1 only schematically provides a possible application scenario, and this schematic application scenario is for the purpose of more clearly illustrating the technical solution of the embodiment of the present application, and does not constitute a limitation on the application scenario of the vehicle fault diagnosis method provided by the present application. In addition, the form and quantity of each device in the application scenario shown in Figure 1 above are only used for example, and do not constitute a limitation on the present application. Furthermore, the name of each device in the application scenario shown in Figure 1 is only an example, and the name of each device in the specific implementation may also be other names, and the present application does not make specific limitations on this. In addition, it is known to those skilled in the art that with the emergence of new application scenarios, the technical solution provided in the embodiment of the present application is also applicable to similar technical problems.

[0075] Based on the application scenario shown in Figure 1, the present application also provides a functional module structure of a vehicle fault diagnosis system. Referring to Figure 2, according to the logical function division, the vehicle fault diagnosis system may include a data analysis and processing system (or may be called a data analysis and processing device or a data analysis and processing module). Optionally, the data analysis and processing system may include a vehicle fault diagnosis device (or may be called a vehicle fault diagnosis module or a vehicle fault diagnosis unit), or the data analysis and processing system may include a vehicle fault diagnosis device and one or more fault diagnosis modules (or may be called a fault detection service or a fault detection microservice or a fault diagnosis tool or a fault detection tool or a fault diagnosis service). In this way, one or more fault diagnosis modules (such as fault diagnosis module 1, fault diagnosis module 2, etc.) may be located in the data analysis and processing system, or may exist independently of the data analysis and processing system. It should be understood that when one or more fault diagnosis modules exist independently of the data analysis and processing system, one or more fault diagnosis modules are also located in the vehicle fault diagnosis system. Exemplarily, the fault diagnosis module may include but is not limited to: a battery fault diagnosis module (or may be called a battery detection service), a motor fault diagnosis module (or may be called a motor detection service), a chassis fault diagnosis module (or may be called a chassis detection service) or other component fault diagnosis modules (such as a window fault diagnosis module or a headlight fault diagnosis module, etc.).

[0076] Optionally, the vehicle fault diagnosis system may also include at least one of the following: a data storage system (or may be called a data storage module or a data storage device), a data preprocessing system (or may be called a data preprocessing module or a data preprocessing device) or a diagnostic result feedback system (or may be called a diagnostic result feedback module or a diagnostic result feedback device).

[0077] For example, in one example, the vehicle fault diagnosis device can be a functional module (which can be called a functional component or functional element) configured (or running or set) with a fault diagnosis model, which can be simply referred to as a first functional module (or first functional component or first functional element), or it can also be a computing device configured with a fault diagnosis model, which can be simply referred to as a first computing device, or it can also be a fault diagnosis agent module configured with a fault diagnosis model. It should be understood that hereinafter, the functional module configured with a fault diagnosis model is simply referred to as the first functional module, and the computing device configured with a fault diagnosis model is simply referred to as the first computing device. In another example, the vehicle fault diagnosis device can also be a fault diagnosis agent module (such as a fault detection agent, or can be called a fault diagnosis agent). In yet another example, the vehicle fault diagnosis device can also be a unit (or module) formed by integrating the first functional module (or first computing device) with a fault diagnosis agent module (or can be called a fault diagnosis agent service or a fault diagnosis agent device or a fault diagnosis agent device or a fault diagnosis agent component or a fault diagnosis agent component). The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. It should be understood that the first functional module (or the first computing device) and the fault diagnosis agent module are both located in the data analysis and processing system.

[0078] For example, the functions of the vehicle fault diagnosis device are briefly introduced below through the following possible examples.

[0079] Example 1: When the vehicle fault diagnosis device is a first functional module (or a first computing device), the vehicle fault diagnosis device is used to obtain a first diagnosis result through a fault diagnosis model.

[0080] Example 2: When the vehicle fault diagnosis device is a fault diagnosis agent module, the vehicle fault diagnosis device is used to identify the first diagnostic result after receiving the first diagnostic result from, and determine whether the first diagnostic result contains information of the first fault diagnosis module (such as fault diagnosis module 1). For example, the vehicle fault diagnosis device can parse the first diagnostic result to obtain the parsed first diagnostic result, and identify whether the parsed first diagnostic result contains information of the first fault diagnosis module. Exemplarily, the parsed first diagnostic result may contain the first fault cause of the vehicle to be diagnosed, or may not contain the first fault cause of the vehicle to be diagnosed (that is, the fault diagnosis model determines that there is no fault in the vehicle to be diagnosed). It should be understood that regardless of whether the parsed first diagnostic result contains the first fault cause of the vehicle to be diagnosed, the parsed first diagnostic result may contain information of the first fault diagnosis module, or may not contain information of the first fault diagnosis module.

[0081] When the first diagnostic result does not contain the information of the first fault diagnostic module, the vehicle fault diagnostic device can generate a fault handling report for the vehicle to be diagnosed based on the first diagnostic result. Afterwards, the vehicle fault diagnostic device can feedback the fault handling report of the vehicle to be diagnosed to the vehicle to be diagnosed (or the user of the vehicle to be diagnosed or the manufacturer corresponding to the vehicle to be diagnosed). Optionally, when the vehicle fault diagnostic system includes a diagnostic result feedback system, the vehicle fault diagnostic device can also send the first diagnostic result (such as the cause of the fault of the vehicle to be diagnosed or the absence of a fault in the vehicle to be diagnosed) to the diagnostic result feedback system after determining that the first diagnostic result does not contain the information of the first fault diagnostic module, and the diagnostic result feedback system will generate a fault handling report for the vehicle to be diagnosed.

[0082] When the first diagnostic result contains information from the first fault diagnostic module, the vehicle fault diagnostic device can call the first fault diagnostic module (such as sending a call indication or call instruction to the first fault diagnostic module) or send the first information to the first fault diagnostic module, and can generate a fault handling report for the vehicle to be diagnosed based on the second diagnostic result from the first fault diagnostic module. Afterwards, the vehicle fault diagnostic device can feedback the fault handling report of the vehicle to be diagnosed to the vehicle to be diagnosed (or the user of the vehicle to be diagnosed or the manufacturer corresponding to the vehicle to be diagnosed). Among them, the first information (or call indication or call instruction) is used to instruct the vehicle to be diagnosed to perform a fault diagnosis. The first information (or call indication or call instruction) may include relevant information of the vehicle to be diagnosed (or may be referred to as information of the vehicle to be diagnosed). For example, the relevant information of the vehicle to be diagnosed may include but is not limited to: the vehicle identification (or vehicle name) of the vehicle to be diagnosed, the model and series of the vehicle to be diagnosed, the time (or time period) when the vehicle to be diagnosed fails, or the time when the user submits the fault phenomenon, etc. Optionally, when the vehicle fault diagnostic system includes a diagnostic result feedback system, the vehicle fault diagnostic device may also, after receiving the second diagnostic result (such as the cause of the fault of the vehicle to be diagnosed or the absence of a fault in the vehicle to be diagnosed) from the first fault diagnostic module, send the second diagnostic result to the diagnostic result feedback system, and the diagnostic result feedback system may generate a fault handling report for the vehicle to be diagnosed. For example, the second diagnostic result may include the second cause of the fault of the vehicle to be diagnosed, or may not include the second cause of the fault of the vehicle to be diagnosed (i.e., the first fault diagnostic module determines that the vehicle to be diagnosed does not have a fault).

[0083] For example, take the example of a vehicle fault diagnosis device sending a call instruction to the first fault diagnosis module. The vehicle fault diagnosis device can generate a call instruction (such as the post https: / / xxx.service.com / start / {id:xxx,time:202307081230 instruction) based on the relevant information of the vehicle to be diagnosed (such as the vehicle name (or vehicle identification), model and series, purchase time or fault occurrence time, etc.), and can send the call instruction to the first fault diagnosis module. The call instruction is used to instruct the vehicle to be diagnosed to perform a fault diagnosis. For example, the call instruction may include the vehicle identification (or vehicle name) of the vehicle to be diagnosed, or the call instruction may include the vehicle identification (or vehicle name) of the vehicle to be diagnosed and the current time, or the call instruction may include the vehicle identification (or vehicle name) of the vehicle to be diagnosed and the fault occurrence time (or fault occurrence time period), or the call instruction may include the vehicle identification (or vehicle name) of the vehicle to be diagnosed, the current time, the fault occurrence time (or fault occurrence time period), the model and series of the vehicle to be diagnosed, etc.

[0084] Exemplarily, the fault handling report of the vehicle to be diagnosed may include but is not limited to: the cause of the fault of the vehicle to be diagnosed (or may be called the fault type), the fault level corresponding to the cause of the fault of the vehicle to be diagnosed, the handling plan corresponding to the cause of the fault of the vehicle to be diagnosed (or may be called the handling suggestion), or whether the vehicle to be diagnosed is faulty, etc.

[0085] Example 3: When the vehicle fault diagnosis device is an integrated unit of a first functional module (or a first computing device) and a fault diagnosis agent module (or a fault diagnosis agent module configured with a fault diagnosis model), the vehicle fault diagnosis device is used to obtain a first diagnostic result through the fault diagnosis model, identify the first diagnostic result, and determine whether the first diagnostic result contains information from the first fault diagnosis module. When the first diagnostic result does not contain information from the first fault diagnosis module, the vehicle fault diagnosis device can generate a fault handling report for the vehicle to be diagnosed based on the first diagnostic result, and can feedback the fault handling report of the vehicle to be diagnosed to the vehicle to be diagnosed (or the user of the vehicle to be diagnosed or the manufacturer corresponding to the vehicle to be diagnosed). When the first diagnostic result contains information from the first fault diagnosis module, the vehicle fault diagnosis device can call the first fault diagnosis module or send the first information to the first fault diagnosis module, and can generate a fault handling report for the vehicle to be diagnosed based on the second diagnostic result from the first fault diagnosis module. Afterwards, the vehicle fault diagnosis device can feedback the fault handling report of the vehicle to be diagnosed to the vehicle to be diagnosed (or the user of the vehicle to be diagnosed or the manufacturer corresponding to the vehicle to be diagnosed). Optionally, when the vehicle fault diagnosis system includes a diagnosis result feedback system, the vehicle fault diagnosis device can also send the second diagnosis result to the diagnosis result feedback system after receiving the second diagnosis result from the first fault diagnosis module, and the diagnosis result feedback system will generate a fault handling report for the vehicle to be diagnosed.

[0086] The following is a brief introduction to the functions of each fault diagnosis module.

[0087] Each fault diagnosis module is configured to, upon receiving a call indication (or call command or first information), perform fault diagnosis on the vehicle to be diagnosed and obtain a second diagnostic result. For example, assuming the vehicle to be diagnosed is vehicle A, the first diagnostic result includes a first fault cause for the vehicle to be diagnosed as a possible battery fault, and the first diagnostic result includes information from a fault diagnosis module indicating that a battery detection service is required for confirmation. Upon receiving the call indication (or call command or first information), the battery detection service obtains battery data reported by vehicle A for a period of time before and after the current time from a database (or data storage node or data storage area) used to store data reported by vehicles (such as controller area network (CAN) signal data, local interconnect network (LIN) signal data, or Ethernet (ETH) signal data). The battery detection service can then analyze and process the battery data for a period of time before and after the current time to obtain the second diagnostic result for vehicle A.

[0088] Optionally, the battery testing service may also retrieve the battery data reported by vehicle A at 9:00 AM on xx / xx / xxxx from a database (or data storage node or data storage area) used to store vehicle-reported data, based on the time when vehicle A experienced the fault (e.g., 9:00 AM on xx / xx / xxxx). The battery testing service may then analyze and process the battery data at 9:00 AM on xx / xx / xxxx to obtain a second diagnostic result for vehicle A. Optionally, the battery testing service may also retrieve the battery data reported by vehicle A within a period of time (e.g., 8:50-9:10 AM) before and after 9:00 AM on xx / xx / xxxx from a database (or data storage node or data storage area) used to store vehicle-reported data, and analyze and process the battery data within a period of time (e.g., 8:50-9:10 AM) before and after 9:00 AM on xx / xx / xxxx to obtain a second diagnostic result for vehicle A.

[0089] To facilitate illustration of the technical solutions provided by the embodiments of the present application, FIG2 illustrates the functions of the data analysis and processing system, taking as an example a data analysis and processing system comprising two vehicle fault diagnosis devices (i.e., a first functional module and a fault diagnosis agent module) and one or more fault diagnosis modules (e.g., fault diagnosis module 1, fault diagnosis module 2, etc.). In FIG2 , data is exchanged between the fault diagnosis agent module and fault diagnosis module 1, such as the fault diagnosis agent module sending first information to fault diagnosis module 1, and fault diagnosis module 1 sending second diagnostic results to the fault diagnosis agent module.

[0090] It should be noted that the connection relationship between the various functional modules shown in Figure 2 is only an example and does not constitute a limitation of the present application. The functions of each functional module are described below.

[0091] When the vehicle fault diagnosis system includes a data preprocessing system, the data preprocessing system is used to obtain the second fault description data of the vehicle to be diagnosed from the data storage system, or it can directly obtain the second fault description data of the vehicle to be diagnosed submitted by the user through the target application on the terminal device, and preprocess the second fault description data (such as data cleaning and data extraction) to obtain the first fault description data of the vehicle to be diagnosed. Optionally, when the vehicle fault diagnosis system includes a data storage system, the data preprocessing system can store the first fault description data in the data storage system. When the data preprocessing system directly obtains the second fault description data submitted by the user through the target application on the terminal device, the data preprocessing system can also store the second fault description data in the data storage system. Optionally, the data preprocessing system can also store other content included in the fault diagnosis request submitted by the user through the target application on the terminal device (such as one or more of the following: the user ID corresponding to the vehicle to be diagnosed, the time period (or time) of the vehicle fault occurrence, the time when the user submitted the fault phenomenon, the vehicle model and series, the vehicle configuration, or the vehicle purchase time) in the data storage system.

[0092] For example, when the data preprocessing system performs data cleaning on the second fault description data, it can clean out the noise data and the like present in the second fault description data to obtain the cleaned second fault description data. Afterwards, the data preprocessing system can perform data extraction on the cleaned second fault description data, for example, it can extract the relevant information of the vehicle (such as the vehicle name (or vehicle identification), model and series, purchase time or fault occurrence time, etc.) and fault description information (or it can be understood as the fault phenomenon, such as fault information described by voice or fault information described by text or other methods) from the cleaned second fault description data. Then, the data preprocessing system can send the relevant information of the vehicle to the fault diagnosis agent module (or the integrated unit of the first functional module and the fault diagnosis agent module).

[0093] With respect to the fault description information, the data preprocessing system may send the fault description information as first fault description data to the first functional module (or an integrated unit of the first functional module and the fault diagnosis agent module), or may convert the format of the fault description information to obtain converted fault description information, and send the converted fault description information to the first functional module (or an integrated unit of the first functional module and the fault diagnosis agent module). For example, the data type of the fault description information may include, but is not limited to, voice, text, pictures, or recordings (or sounds); the data type of the converted fault description information may include, but is not limited to, numerical values ​​or vectors.

[0094] The data analysis and processing system is used to perform fault diagnosis on a vehicle to be diagnosed (such as a first vehicle) to obtain a first diagnostic result, and can be used to generate a fault handling report for the vehicle to be diagnosed based on the first diagnostic result.

[0095] In one example, when the vehicle fault diagnosis system includes a data preprocessing system, the data analysis and processing system is configured to obtain first fault description data of the vehicle to be diagnosed from the data preprocessing system and process the first fault description data of the vehicle to be diagnosed via a first functional module to obtain a first diagnostic result. In another example, when the vehicle fault diagnosis system does not include a data preprocessing system, if the data analysis and processing system has data preprocessing capabilities, the data analysis and processing system may preprocess (e.g., perform data cleaning and data extraction) the second fault description data of the vehicle to be diagnosed to obtain the first fault description data of the vehicle to be diagnosed. Subsequently, the data analysis and processing system is configured to process the first fault description data of the vehicle to be diagnosed via the first functional module to obtain a first diagnostic result. After obtaining the first diagnostic result, the data analysis and processing system may, when the fault diagnosis agent module determines that the first diagnostic result contains information from a fault diagnosis module (e.g., fault diagnosis module 1), perform fault diagnosis on the vehicle to be diagnosed via fault diagnosis module 1 to obtain a second diagnostic result. For example, when the vehicle fault diagnosis system includes a data storage system, the data analysis and processing system may store the first diagnostic result, the second diagnostic result, or a fault handling report for the vehicle to be diagnosed, etc., in the data storage system.

[0096] For example, the first diagnostic result may include the first fault cause of the vehicle to be diagnosed (or may be called the first fault type) and / or information about the fault diagnosis module (such as whether a certain fault diagnosis module (such as fault diagnosis module 1) needs to be used for confirmation (or whether an operating instruction (or may be called an operating instruction) of a certain fault diagnosis module (such as fault diagnosis module 1) needs to be called to perform fault diagnosis on the vehicle to be diagnosed), and attribute information of a certain fault diagnosis module (such as fault diagnosis module 1) (such as identification, name or application programming interface (API))), or the first diagnostic result does not include the first fault cause of the vehicle to be diagnosed (i.e., the fault diagnosis model determines that the vehicle to be diagnosed does not have a fault) and does not include information about the fault diagnosis module. For example, the second diagnostic result may include the second fault cause of the vehicle to be diagnosed, or may not include the second fault cause of the vehicle to be diagnosed (i.e., the fault diagnosis module 1 determines that the vehicle to be diagnosed does not have a fault). The fault handling report of the vehicle to be diagnosed may include but is not limited to: the fault cause of the vehicle to be diagnosed (or may be called the fault type), the fault level corresponding to the fault cause of the vehicle to be diagnosed, the handling plan corresponding to the fault cause of the vehicle to be diagnosed, or whether the vehicle to be diagnosed has a fault, etc.

[0097] When the vehicle fault diagnosis system includes a data storage system, the data storage system is used to store at least one of the following: first fault description data, second fault description data, first diagnostic result, second diagnostic result, fault handling report, user identification, vehicle fault occurrence time period (or occurrence time), time when the user submits the fault phenomenon, vehicle model and series, vehicle identification, vehicle name, vehicle configuration or vehicle purchase time, etc.

[0098] When the vehicle fault diagnosis system includes a diagnostic result feedback system, the diagnostic result feedback system is used to generate a fault handling report for the vehicle to be diagnosed based on the first diagnostic result after receiving the first diagnostic result, and to feedback the fault handling report of the vehicle to be diagnosed to the vehicle to be diagnosed (or the user of the vehicle to be diagnosed or the manufacturer corresponding to the vehicle to be diagnosed). Alternatively, the diagnostic result feedback system can also be used to generate a fault handling report for the vehicle to be diagnosed based on the second diagnostic result after receiving the second diagnostic result, and to feedback the fault handling report of the vehicle to be diagnosed to the vehicle to be diagnosed (or the user of the vehicle to be diagnosed or the manufacturer corresponding to the vehicle to be diagnosed). For example, when the vehicle fault diagnosis system includes a data storage system, after generating the fault handling report for the vehicle to be diagnosed, the diagnostic result feedback system can store the fault handling report of the vehicle to be diagnosed in the data storage system.

[0099] Optionally, the data analysis and processing system, the vehicle fault diagnosis device, one or more fault diagnosis modules, the first functional module, the fault diagnosis agent module, the data storage system, the data preprocessing system or the diagnostic result feedback system can all be implemented by software, or can all be implemented by hardware. For example, the implementation of the fault diagnosis agent module will be described below using the fault diagnosis agent module as an example. Similarly, the implementation of the data analysis and processing system, the vehicle fault diagnosis device, one or more fault diagnosis modules, the first functional module, the data storage system, the data preprocessing system or the diagnostic result feedback system can refer to the implementation of the fault diagnosis agent module, and will not be repeated here.

[0100] When implemented via software, the fault diagnosis agent module can be an application or code block running on a computing device (or control unit, etc.) with data processing capabilities in a data analysis and processing system (or vehicle fault diagnosis system). The computing device can be at least one of a physical host, a virtual machine, a container, or other computing device. Furthermore, the computing device can be one or more. For example, the object detection module can be an application running on multiple hosts / virtual machines / containers.

[0101] When implemented through hardware, the fault diagnosis agent module may include at least one computing device, such as a server. Alternatively, the object detection module may be implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD). The PLD may be a complex programmable logical device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0102] In addition, it should be noted that the division of modules in the embodiments of the present application is schematic and is merely a logical function division. In actual implementation, there may be other division methods. The functional modules in the embodiments of the present application may be integrated into one module, or each module may exist physically alone, or two or more modules may be integrated into one module. For example, the first functional module and the fault diagnosis agent module may be integrated into one module, or the first functional module and the fault diagnosis agent module may be the same module. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit.

[0103] The following is a detailed introduction to the specific implementation of the vehicle fault diagnosis method in the embodiment of the present application based on the application scenario shown in Figure 1 and the vehicle fault diagnosis system shown in Figure 2.

[0104] FIG3 exemplarily shows a flow chart of a vehicle fault diagnosis method provided by an embodiment of the present application. The method can be applicable to, but not limited to, the application scenario illustrated in FIG1 . The method can be executed by a vehicle fault diagnosis device or an element (such as a chip, a chip system, or a circuit, etc.) that can support the vehicle fault diagnosis device to implement the functions required by the method. In one example, the vehicle fault diagnosis device can be a vehicle fault diagnosis device included in the vehicle fault diagnosis system 200 illustrated in FIG1 , or it can be a functional module (such as a plug-in, a component, or a chip, etc.) provided in the vehicle fault diagnosis device included in the vehicle fault diagnosis system 200 illustrated in FIG1 , and the functional module (or functional component or functional element) has the function of implementing the vehicle fault diagnosis method. Exemplarily, the vehicle fault diagnosis device can be a first functional module (or a first computing device), or it can be a fault diagnosis agent module configured with a fault diagnosis model, or it can be an integrated module (or an integrated unit) of the first functional module (or the first computing device) and the fault diagnosis agent module, etc. In another example, the vehicle fault diagnosis device may also be other devices (such as other computing devices or diagnostic units) with vehicle fault diagnosis functions in the vehicle fault diagnosis system 200 shown in FIG1 , or may also be functional modules (such as plug-ins, components, or chips, etc.) provided in other devices with vehicle fault diagnosis functions in the vehicle fault diagnosis system 200 shown in FIG1 . To facilitate the introduction of the technical solutions provided in the embodiments of the present application, the following description will take the vehicle fault diagnosis method executed by the vehicle fault diagnosis device as an example. As shown in FIG3 , the method includes steps 301-302.

[0105] Step 301: The vehicle fault diagnosis device obtains first fault description data of a first vehicle.

[0106] Optionally, the first fault description data may be obtained by format conversion of the second fault description data (or problem log) of the first vehicle, or the second fault description data (or problem log) of the first vehicle may be directly used as the first fault description data. Optionally, the second fault description data of the first vehicle may be obtained through user input (for example, the user submits it through a terminal device using one or more input methods such as voice input, text input, recording (or sound) upload, or picture upload). For example, the first vehicle may be any electric car or any other connected vehicle. Furthermore, the first vehicle may refer to a faulty vehicle that needs to be diagnosed, or it may refer to a vehicle that interacts with the cloud, such as a faulty vehicle or a complete vehicle (such as a normal vehicle). It is understandable that in some scenarios, the problem log may refer to the second fault description data.

[0107] Exemplarily, the data type of the second fault description data may include but is not limited to voice, text, picture, or recording (or sound), etc.

[0108] For example, the second fault description data of the first vehicle can be provided by the user of the first vehicle through the target application installed on the terminal device using one or more input methods such as voice description, text description, recording (or sound) upload or picture upload.

[0109] For example, taking the terminal device as an on-board terminal device on a first vehicle and the target application as a client installed on the on-board terminal device for assisting users in diagnosing vehicle faults, when a user of the first vehicle experiences a fault in the first vehicle (e.g., the motor cannot start), the user can log in to the fault description interface provided by the vehicle fault diagnosis system 200 through the client installed on the on-board terminal device and can use text input (or a combination of text input and image upload or other methods) on the fault description interface to describe the fault phenomenon of the first vehicle, such as a text description of the phenomenon that the motor of the first vehicle cannot start, or a text description of the time period when the vehicle fault occurred, or a text description of the vehicle name (or vehicle identification, model, series, etc.) of the first vehicle. Subsequently, in response to the first vehicle user's operation on the client to describe the fault file for the first vehicle, the vehicle fault diagnosis system 200 can obtain second fault description data for the first vehicle, such as the second fault description data may include the fault phenomenon of the first vehicle, the time period when the first vehicle fault occurred, or the vehicle name (or vehicle identification) of the first vehicle. For example, a schematic diagram of the fault description interface displayed on the target application can be seen in FIG4. In the fault description interface shown in FIG4 , some relevant information that the user needs to edit is displayed (such as the fault phenomenon of the first vehicle, the vehicle identification (or vehicle name) of the first vehicle, or the time when the fault occurred (or the time period during which the fault occurred)). For example, taking vehicle A as the first vehicle, the user can input the identification of vehicle A, the time when the fault occurred, the fault phenomenon, etc. of vehicle A in the form of voice description (or text description or picture upload or recording upload) on the fault description interface. In this example, the user can also take a picture of the fault (such as a picture of a battery high temperature alarm) and upload it while using text to describe the fault phenomenon. That is to say, the user can submit fault phenomenon descriptions of different data types at the same time on the fault description interface.

[0110] When the vehicle fault diagnosis system 200 includes a data preprocessing system, the vehicle fault diagnosis system 200 can provide the second fault description data to the data preprocessing system. After obtaining the second fault description data, the data preprocessing system can preprocess the second fault description data (such as data cleaning, data extraction) to obtain the first fault description data. For example, the data preprocessing system can first clean the noise data and the like present in the second fault description data to obtain the cleaned second fault description data. Afterwards, the data preprocessing system can perform data extraction on the cleaned second fault description data, for example, relevant information of the first vehicle (such as vehicle name (or vehicle identification), model and series, purchase time or fault occurrence time, etc.) and fault description information (or can be understood as a fault phenomenon, such as fault information described in text or fault information contained in a picture or fault information described in other ways) can be extracted from the cleaned second fault description data.

[0111] In one example, when the vehicle fault diagnosis device is the first functional module (or the first computing device), the data preprocessing system can convert the format of the fault description information to obtain the converted fault description information, and the converted fault description information can be used as the first fault description data. Afterwards, the data preprocessing system can provide the first fault description data to the vehicle fault diagnosis device. For example, if the data type of the second fault description data is text (or a combination of text and pictures or other types), then the data type of the fault description information is also text (or a combination of text and pictures or other types); the data type of the first fault description data is a numerical value (or a vector). Optionally, the data preprocessing system can also directly provide the fault description information as the first fault description data to the vehicle fault diagnosis device. In addition, the data preprocessing system can provide the relevant information of the first vehicle contained in the second fault description data to the fault diagnosis agent module.

[0112] In another example, when the vehicle fault diagnosis device is a fault diagnosis agent module, the data preprocessing system can provide the relevant information of the first vehicle contained in the second fault description data to the fault diagnosis agent module. In addition, the data preprocessing system can convert the format of the fault description information to obtain the converted fault description information, and the converted fault description information can be used as the first fault description data. Afterwards, the data preprocessing system can provide the first fault description data to the first functional module (or the first computing device). Afterwards, the first functional module (or the first computing device) obtains the first diagnostic result after passing the first fault description data through the fault diagnosis model, and can provide the first diagnostic result to the fault diagnosis agent module.

[0113] Optionally, the data preprocessing system may also directly provide the fault description information as first fault description data to the first functional module (or first computing device). The first functional module (or first computing device) then passes the first fault description data through the fault diagnosis model to obtain a first diagnostic result, and may provide the first diagnostic result to the fault diagnosis agent module.

[0114] In another example, when the vehicle fault diagnosis device is an integrated unit of a first functional module (or a first computing device) and a fault diagnosis agent module (or a fault diagnosis agent module configured with a fault diagnosis model), the data preprocessing system can provide the relevant information of the first vehicle contained in the second fault description data to the vehicle fault diagnosis device. In addition, the data preprocessing system can perform format conversion on the fault description information to obtain the converted fault description information, and the converted fault description information can be used as the first fault description data. Afterwards, the data preprocessing system can also provide the first fault description data to the vehicle fault diagnosis device. Optionally, the data preprocessing system can also directly provide the fault description information as the first fault description data to the vehicle fault diagnosis device.

[0115] When the vehicle fault diagnosis system 200 does not include a data preprocessing system, the vehicle fault diagnosis system 200 may provide the second fault description data to the data analysis and processing system. When the data analysis and processing system does not have a data preprocessing function, if the vehicle fault diagnosis device is an integrated unit of the first functional module (or first computing device) and the fault diagnosis agent module, or the fault diagnosis agent module or the first functional module (or first computing device), the data analysis and processing system may provide the second fault description data to the vehicle fault diagnosis device.

[0116] When the data analysis and processing system has a data preprocessing function, the data analysis and processing system can first clean the noise data and other data present in the second fault description data to obtain the cleaned second fault description data. Afterwards, the data analysis and processing system can perform data extraction on the cleaned second fault description data. For example, it can extract relevant information and fault description information about the first vehicle from the cleaned second fault description data. The data analysis and processing system can then perform format conversion on the fault description information to obtain converted fault description information, which can be used as the first fault description data. Optionally, the data analysis and processing system can also directly use the fault description information as the first fault description data.

[0117] When the vehicle fault diagnosis device is the first functional module (or the first computing device), the data analysis and processing system can provide the first fault description data to the vehicle fault diagnosis device. In addition, the data analysis and processing system can provide relevant information of the first vehicle to the fault diagnosis agent module.

[0118] When the vehicle fault diagnosis device is a fault diagnosis agent module, the data analysis and processing system can provide the relevant information of the first vehicle to the vehicle fault diagnosis device. In addition, the data analysis and processing system can provide the first fault description data to the first functional module (or the first computing device).

[0119] When the vehicle fault diagnosis device is an integrated unit of the first functional module (or the first computing device) and the fault diagnosis agent module, the data analysis and processing system can provide the first fault description data and relevant information of the first vehicle to the vehicle fault diagnosis device.

[0120] Step 302: The vehicle fault diagnosis device inputs the first fault description data into the fault diagnosis model to obtain a first diagnosis result.

[0121] Among them, the fault diagnosis model (or it can be called a fault detection model or operation and maintenance model) is used to describe the correspondence between the vehicle's fault description data and the diagnostic results. The first diagnostic result can be used to instruct the fault diagnosis agent module to perform a fault diagnosis operation corresponding to the first diagnostic result (such as the operation of generating a first fault handling report based on the first diagnostic result, or the operation of sending corresponding information (such as the first information) to the corresponding fault diagnosis module based on the first diagnostic result). For example, the fault diagnosis model can refer to a trained AI model, or it can also refer to a combination of a diagnostic tree knowledge base + a trained AI model. Among them, the trained AI model is used to understand or identify the user's problem description (such as the second fault description data or the problem log), or it can also be used to extract keywords in the user's problem description.

[0122] The following is an introduction to the training process of an AI model:

[0123] For example, consider a generative AI model. The generative AI model can be trained by a functional module or a computing device. Optionally, this functional module or computing device can be located within or outside the vehicle fault diagnosis system 200.

[0124] For example, take a computing device (such as computing device A) to train a generative AI model as an example. After computing device A obtains multiple fault training samples (or can be called fault training data), it can use the multiple fault training samples to train (or iteratively train) the generative AI model (such as the Pangu model) until the generative AI model converges or meets the training times, thereby obtaining a trained generative AI model. Optionally, the generative AI model is a multimodal large model. By utilizing the multimodal understanding ability of the multimodal large model, it can perceive input data of different data types (for example, the user can submit fault phenomenon descriptions of different data types at the same time (for example, the user can submit any multiple of voice descriptions of fault phenomena, text descriptions of fault phenomena, pictures containing fault phenomena, or recordings (or sounds) containing fault phenomena) at the same time)), so as to fully understand the fault phenomenon descriptions submitted by the user.

[0125] Exemplarily, the fault training samples may include questionnaires (or may be understood as fault questionnaires), maintenance orders (or may be understood as fault repair orders), maintenance training materials (or may be understood as fault repair training materials), etc. For example, the questionnaire, maintenance order and maintenance training materials may all include but are not limited to fault phenomena (or may be referred to as fault description information or fault description data), fault causes (or may be referred to as fault types), etc. Optionally, the questionnaire, maintenance order and maintenance training materials may also include information about the fault diagnosis module (such as whether the fault diagnosis module needs to be used for confirmation (or re-diagnosis) or attribute information of the fault diagnosis module (such as identification, name or API), etc.). As an example, the content format of the questionnaire (or maintenance order or maintenance training materials) can be found in Table 1. It should be understood that Table 1 is only an example, which is provided for the convenience of illustrating the technical solutions in the embodiments of the present application and does not constitute a limitation on the technical solutions in the embodiments of the present application.

[0126] Table 1

[0127] Optionally, the training process of the above-mentioned generative AI model can be encapsulated into a fault diagnosis training task (or can be called a fault detection training task). See Figure 5, which is a schematic diagram of a generative AI model training provided by an embodiment of the present application. As shown in Figure 5, when the training device (such as computing device A) obtains the training instruction (training instruction is used to instruct the training of Pangu model, and the training instruction contains Pangu model) issued by the user through the terminal device (such as a smart phone, laptop or desktop computer, etc.), it can obtain fault training samples (such as questionnaires, repair orders, maintenance training materials, etc.) from the database (or data storage area) used to store fault training samples, and execute the fault diagnosis training task, so as to obtain a trained generative AI model. Optionally, computing device A can also obtain Pangu model in advance, and after obtaining the training instruction (training instruction is used to instruct the training of Pangu model) issued by the user through the terminal device, it can obtain fault training samples (such as questionnaires, repair orders, maintenance training materials, etc.) from the database (or data storage area) used to store fault training samples, and execute the fault diagnosis training task, so as to obtain a trained generative AI model.

[0128] By way of example, the following describes the implementation process of the vehicle fault diagnosis device inputting the first fault description data into the fault diagnosis model to obtain the first diagnosis result through the following possible implementation methods.

[0129] Implementation method 1: When the vehicle fault diagnosis device is the first functional module (or the first computing device), after obtaining the first fault description data, the vehicle fault diagnosis device can input the first fault description data into the fault diagnosis model to obtain a first diagnosis result.

[0130] In one example, the first diagnostic result includes the first fault cause of the first vehicle. In another example, the first diagnostic result includes the first fault cause of the first vehicle and information of the first fault diagnostic module (such as whether the first fault diagnostic module needs to be used for confirmation or attribute information of the first fault diagnostic module (such as identification, name or API), etc.). In another example, the first diagnostic result does not include the first fault cause of the first vehicle (that is, the fault diagnosis model determines that there is no fault in the first vehicle), nor does it include information of any fault diagnostic module (such as the first fault diagnostic module). In another example, the first diagnostic result does not include the first fault cause of the first vehicle, but includes information of the first fault diagnostic module.

[0131] Optionally, the first diagnostic result can be used to instruct a fault diagnosis agent module to perform a fault diagnosis operation corresponding to the first diagnostic result. After obtaining the first diagnostic result, the first functional module (or the first computing device) can send the first diagnostic result to the fault diagnosis agent module. After receiving the first diagnostic result, the fault diagnosis agent module can perform a fault diagnosis operation corresponding to the first diagnostic result based on the first diagnostic result.

[0132] Exemplarily, the following describes several possible examples of how a fault diagnosis agent module performs a fault diagnosis operation corresponding to a first diagnostic result based on a first diagnostic result. Optionally, after receiving the first diagnostic result, the fault diagnosis agent module may identify the first diagnostic result and determine whether the first diagnostic result includes information from the first fault diagnosis module. For example, the fault diagnosis agent module may parse the first diagnostic result to obtain a parsed first diagnostic result.

[0133] Example 1: When the parsed first diagnostic result does not include information from the first fault diagnostic module, the fault diagnostic agent module can generate a first fault handling report for the first vehicle based on the first diagnostic result. For example, assuming the first diagnostic result includes the first fault cause of the first vehicle, the fault diagnostic agent module can determine the fault level corresponding to the first fault cause based on the first fault cause and obtain the handling solution (or handling method, handling suggestion, fault handling solution, fault handling method, or fault handling suggestion) corresponding to the first fault cause from a database (or data storage area) used to store handling solutions corresponding to the fault causes. The fault diagnostic agent module can then generate a first fault handling report for the first vehicle based on the first fault cause, the fault level corresponding to the first fault cause, and the handling solution corresponding to the first fault cause. The fault diagnostic agent module can then send the first fault handling report for the first vehicle to the first vehicle (or the user of the first vehicle or the manufacturer of the first vehicle). Optionally, the fault diagnostic agent module can also submit the diagnostic record of the first vehicle to the manufacturer of the first vehicle to facilitate the manufacturer's appropriate repairs for the first vehicle. In this embodiment of the present application, the user of the first vehicle can also promptly perform the corresponding after-sales repair reservations based on the first fault handling report.

[0134] Example 2: When the parsed first diagnostic result contains information of the first fault diagnosis module, the fault diagnosis agent module can call the first fault diagnosis module (for example, send a call indication or call instruction to the first fault diagnosis module) or send the first information to the first fault diagnosis module based on the information of the first fault diagnosis module.

[0135] For example, take the example of a fault diagnosis agent module sending first information to a first fault diagnosis module. The fault diagnosis agent module can generate first information based on the relevant information of the first vehicle obtained (such as the vehicle name (or vehicle identification), vehicle model and series, purchase time or fault occurrence time, etc.), and can send the first information to the first fault diagnosis module. The first information is used to indicate that a fault diagnosis is to be performed on the first vehicle. Exemplarily, the first information can include the vehicle identification (or vehicle name) of the first vehicle, or the first information can include the vehicle identification (or vehicle name) of the first vehicle and the current time, or the first information can include the vehicle identification (or vehicle name) of the first vehicle and the fault occurrence time (or fault occurrence time period), or the first information can include the vehicle identification (or vehicle name) of the first vehicle, the current time, the fault occurrence time (or fault occurrence time period), the vehicle model and series of the first vehicle, etc. After obtaining the first information from the fault diagnosis agent module, the first fault diagnosis module can perform a fault diagnosis on the first vehicle, obtain a second diagnosis result, and can send the second diagnosis result to the fault diagnosis agent module. For example, the second diagnostic result may include the second fault cause of the first vehicle, or may not include the second fault cause of the first vehicle (ie, the first fault diagnostic module determines that there is no fault in the first vehicle).

[0136] After obtaining the second diagnostic result from the first fault diagnostic module, the fault diagnosis agent module can generate a first fault handling report for the first vehicle based on the second diagnostic result. For example, take the second diagnostic result including the second fault cause of the first vehicle as an example. The fault diagnosis agent module can determine the fault level corresponding to the second fault cause based on the second fault cause, and can obtain the handling solution corresponding to the second fault cause from a database (or data storage area) for storing handling solutions corresponding to the fault cause. Afterwards, the fault diagnosis agent module can generate a first fault handling report for the first vehicle based on the second fault cause, the fault level corresponding to the second fault cause, and the handling solution corresponding to the second fault cause. Then, the fault diagnosis agent module can send the first fault handling report for the first vehicle to the first vehicle (or the user of the first vehicle or the manufacturer corresponding to the first vehicle). Optionally, the fault diagnosis agent module can also submit the diagnostic record of the first vehicle to the manufacturer corresponding to the first vehicle, so that the manufacturer can perform corresponding repairs on the first vehicle. In an embodiment of the present application, the user of the first vehicle can also perform corresponding after-sales maintenance scheduled operations in a timely manner based on the first fault handling report.

[0137] For example, after obtaining the first information, the first fault diagnosis module can query the data corresponding to the first fault diagnosis module of the first vehicle from the database (or data storage area) used to store the data reported by the vehicle based on the first information, and can analyze and process the data corresponding to the first fault diagnosis module to obtain a second diagnostic result of the first vehicle.

[0138] Exemplarily, take the first fault diagnosis module as a battery fault diagnosis module as an example. In one example, when the first information includes the vehicle identification (or vehicle name) of the first vehicle, the battery fault diagnosis module can query the historical battery data of the first vehicle from the database (or data storage area) for storing data reported by the vehicle based on the vehicle identification (or vehicle name) of the first vehicle. Afterwards, the battery fault diagnosis module can analyze and process the historical battery data of the first vehicle to obtain a second diagnostic result for the first vehicle. In another example, when the first information includes the vehicle identification (or vehicle name) and current time of the first vehicle, the battery fault diagnosis module can query the battery data of the first vehicle at the current time from the database (or data storage area) for storing data reported by the vehicle based on the vehicle identification (or vehicle name) of the first vehicle and current time. Afterwards, the battery fault diagnosis module can analyze and process the battery data of the first vehicle at the current time to obtain a second diagnostic result for the first vehicle. In another example, when the first information includes the vehicle identification (or vehicle name) and the time of fault occurrence (or time period when the fault occurs) of the first vehicle, the battery data of the first vehicle at the time of fault occurrence (or time period when the fault occurs) can be queried from the database (or data storage area) for storing data reported by the vehicle based on the vehicle identification (or vehicle name) and the time of fault occurrence (or time period when the fault occurs). Afterwards, the battery fault diagnosis module can analyze and process the battery data of the first vehicle at the time of fault occurrence (or time period when the fault occurs) to obtain the second diagnostic result of the first vehicle. It should be understood that the above content is only an illustrative introduction to several possible examples of how the battery fault diagnosis module determines the second diagnostic result of the first vehicle. The battery fault diagnosis module can also determine the second diagnostic result of the first vehicle through other possible examples, which will not be listed one by one in the embodiments of the present application.

[0139] Implementation method 2: When the vehicle fault diagnosis device is an integrated unit of a first functional module (or a first computing device) and a fault diagnosis agent module (or a fault diagnosis agent module configured with a fault diagnosis model), after obtaining the first fault description data, the vehicle fault diagnosis device can input the first fault description data into the fault diagnosis model to obtain a first diagnostic result. Optionally, for the description of the contents of the first diagnostic result in Implementation method 2, please refer to the description of the contents of the first diagnostic result in Implementation method 1 above, which will not be repeated here. After obtaining the first diagnostic result, the vehicle fault diagnosis device can perform a fault diagnosis operation corresponding to the first diagnostic result based on the first diagnostic result.

[0140] By way of example, the following describes several possible examples of how a vehicle fault diagnostic device may perform a fault diagnostic operation corresponding to a first diagnostic result based on the first diagnostic result. Optionally, after obtaining the first diagnostic result, the vehicle fault diagnostic device may identify the first diagnostic result to determine whether the first diagnostic result includes information from the first fault diagnostic module. For example, the vehicle fault diagnostic device may parse the first diagnostic result to obtain a parsed first diagnostic result.

[0141] Example 1: When the parsed first diagnostic result does not include information from the first fault diagnostic module, the vehicle fault diagnostic device can generate a first fault handling report for the first vehicle based on the first diagnostic result. For example, take the first diagnostic result including the first fault cause of the first vehicle as an example. The vehicle fault diagnostic device can determine the fault level corresponding to the first fault cause based on the first fault cause, and can obtain the handling solution corresponding to the first fault cause from a database (or data storage area) for storing handling solutions corresponding to the fault causes. Thereafter, the vehicle fault diagnostic device can generate a first fault handling report for the first vehicle based on the first fault cause, the fault level corresponding to the first fault cause, and the handling solution corresponding to the first fault cause. The vehicle fault diagnostic device can then send the first fault handling report for the first vehicle to the first vehicle (or the user of the first vehicle or the manufacturer corresponding to the first vehicle). Optionally, the vehicle fault diagnostic device can also submit the diagnostic record of the first vehicle to the manufacturer corresponding to the first vehicle to facilitate the manufacturer to perform corresponding repairs on the first vehicle. In an embodiment of the present application, the user of the first vehicle can also perform corresponding after-sales maintenance scheduled operations in a timely manner based on the first fault handling report.

[0142] Example 2: When the parsed first diagnostic result contains information of the first fault diagnostic module, the vehicle fault diagnostic device can call the first fault diagnostic module (for example, send a call indication or call instruction to the first fault diagnostic module) or send the first information to the first fault diagnostic module based on the information of the first fault diagnostic module.

[0143] For example, consider the case where a vehicle fault diagnostic device sends a call instruction to a first fault diagnostic module. The vehicle fault diagnostic device can generate a call instruction based on acquired information about the first vehicle (such as the vehicle name (or vehicle identification), vehicle model and series, purchase date, or fault occurrence time), and can send the call instruction to the first fault diagnostic module. The call instruction instructs the first vehicle to perform a fault diagnosis. For example, the call instruction can include the vehicle identification (or vehicle name) of the first vehicle, or the vehicle identification (or vehicle name) and current time, or the vehicle identification (or vehicle name) of the first vehicle and fault occurrence time (or fault occurrence time period), or the vehicle identification (or vehicle name), current time, fault occurrence time (or fault occurrence time period), and vehicle model and series of the first vehicle. After receiving the call instruction from the fault diagnostic agent module, the first fault diagnostic module can perform a fault diagnosis on the first vehicle, obtain a second diagnostic result, and send the second diagnostic result to the vehicle fault diagnostic device. For example, the second diagnostic result can include or exclude the second fault cause of the first vehicle.

[0144] After obtaining the second diagnostic result from the first fault diagnostic module, the vehicle fault diagnostic device can generate a first fault handling report for the first vehicle based on the second diagnostic result. For example, take the second diagnostic result including the second fault cause of the first vehicle as an example. The vehicle fault diagnostic device can determine the fault level corresponding to the second fault cause based on the second fault cause, and can obtain the processing solution corresponding to the second fault cause from a database (or data storage area) for storing processing solutions corresponding to the fault cause. Afterwards, the vehicle fault diagnostic device can generate a first fault handling report for the first vehicle based on the second fault cause, the fault level corresponding to the second fault cause, and the processing solution corresponding to the second fault cause. Then, the vehicle fault diagnostic device can send the first fault handling report of the first vehicle to the first vehicle (or the user of the first vehicle or the manufacturer corresponding to the first vehicle). Optionally, the vehicle fault diagnostic device can also submit the diagnostic record of the first vehicle to the manufacturer corresponding to the first vehicle to facilitate the manufacturer to perform corresponding repairs on the first vehicle. In an embodiment of the present application, the user of the first vehicle can also perform corresponding after-sales maintenance scheduled operations in a timely manner based on the first fault handling report.

[0145] It should be understood that the above-mentioned implementation method 1 and implementation method 2 are described for the fault diagnosis model being a trained AI model (such as a trained generative AI model).

[0146] Implementation method three: When the vehicle fault diagnosis device is the first functional module (or the first computing device), after obtaining the first fault description data (or problem log), the vehicle fault diagnosis device can input the first fault description data into the trained AI model to obtain one or more keywords. Afterwards, the vehicle fault diagnosis device can match at least one fault diagnosis tree corresponding to one or more keywords from the diagnostic tree knowledge base. Optionally, after obtaining one or more keywords, the vehicle fault diagnosis device can also send one or more keywords to the fault diagnosis agent module. After obtaining one or more keywords, the fault diagnosis agent module can match at least one fault diagnosis tree corresponding to one or more keywords from the diagnostic tree knowledge base. Among them, the at least one fault diagnosis tree can constitute a fault diagnosis tree group adapted to the first fault description data, and the fault diagnosis tree group is used to determine the first diagnostic result of the first vehicle; the diagnostic tree knowledge base can include multiple fault diagnosis trees.

[0147] It is understood that when the vehicle fault diagnosis device does not find a fault diagnosis tree corresponding to one or more keywords in the diagnostic tree knowledge base, it can construct a minimum problem fault diagnosis tree that matches the one or more keywords based on the one or more keywords and historical fault log information related to the same model and series of vehicles as the first vehicle. The vehicle fault diagnosis device can then update the constructed minimum problem fault diagnosis tree that matches the one or more keywords to the diagnostic tree knowledge base.

[0148] Optionally, after obtaining the fault diagnosis tree group, the vehicle fault diagnosis device can obtain historical fault log information related to the same model and series of vehicles corresponding to the first vehicle, as well as the real-time vehicle condition log currently uploaded by the first vehicle (such as the operation log of the audio module-related components, the operation log of the Bluetooth module-related components, the operation log of the power supply system module, and the vehicle-mounted environment perception information log, etc.). Afterwards, the vehicle fault diagnosis device can determine the first diagnostic result based on the historical fault log information related to the same model and series of vehicles, the real-time vehicle condition log currently uploaded by the first vehicle, and the fault diagnosis tree group. It should be understood that after obtaining the real-time vehicle condition log currently uploaded by the first vehicle, the vehicle fault diagnosis device can update the real-time vehicle condition log currently uploaded by the first vehicle to the vehicle condition log library. For example, historical fault log information related to the same model and series of vehicles corresponding to the first vehicle can be stored in the vehicle condition log library.

[0149] In an embodiment of the present application, the vehicle fault diagnosis device can determine the fault matching probability corresponding to at least one fault diagnosis tree included in the fault diagnosis tree group based on the historical fault log information related to the same model and series corresponding to the first vehicle. Among them, the greater the fault matching probability, the more likely the fault diagnosis tree is to match (or be close to) the actual fault of the first vehicle. Afterwards, the vehicle fault diagnosis device can select the fault diagnosis tree with the highest fault matching probability, and combine it with the real-time vehicle condition log currently uploaded by the first vehicle to determine the first diagnosis result of the first vehicle. Optionally, the vehicle fault diagnosis device can also combine at least one fault diagnosis tree with the real-time vehicle condition log currently uploaded by the first vehicle to determine the first diagnosis result of the first vehicle.

[0150] For example, let's take the case where the first fault description data is "I don't know why my vehicle has been making a buzzing sound from the current, and the mobile phone is also intermittent when playing songs when connected to Bluetooth", and the trained AI model is a trained generative AI model. The vehicle fault diagnosis device inputs the first fault description data "I don't know why my vehicle has been making a buzzing sound from the current, and the mobile phone is also intermittent when playing songs when connected to Bluetooth" into the trained generative AI model, and obtains multiple keywords, namely the keyword "abnormal sound" and the keyword "Bluetooth abnormality". Afterwards, the vehicle fault diagnosis device matches multiple fault diagnosis trees in the diagnostic tree knowledge base based on the keywords "abnormal sound" and "Bluetooth abnormality", such as the minimum problem fault tree for audio abnormality, the minimum problem fault tree for Bluetooth abnormality, the minimum problem fault tree for power supply abnormality, etc. The multiple fault diagnosis trees can constitute a fault diagnosis tree group that is adapted to the first fault description data "I don't know why my vehicle has been making a buzzing sound from the current, and the mobile phone is also intermittent when playing songs when connected to Bluetooth". Afterwards, the vehicle fault diagnosis device can obtain the historical fault log information related to the same model and series of vehicles corresponding to the first vehicle, as well as the real-time vehicle condition log currently uploaded by the first vehicle. Then, the vehicle fault diagnosis device can determine the fault matching probabilities corresponding to the multiple fault diagnosis trees included in the fault diagnosis tree group based on the historical fault log information related to the same model and series of vehicles corresponding to the first vehicle, such as the fault matching probability corresponding to the minimum audio abnormality problem fault tree is a, the fault matching probability corresponding to the minimum Bluetooth abnormality problem fault tree is b, the fault matching probability corresponding to the minimum power supply abnormality problem fault tree is c, etc. Assuming that the fault matching probability a corresponding to the minimum audio abnormality problem fault tree is the largest, the vehicle fault diagnosis device can determine the first diagnostic result of the first vehicle based on the minimum audio abnormality problem fault tree and the real-time vehicle condition log currently uploaded by the first vehicle. Optionally, the vehicle fault diagnosis device can also combine multiple fault diagnosis trees with the real-time vehicle condition log currently uploaded by the first vehicle to determine the first diagnostic result of the first vehicle.

[0151] The following describes the construction process of the diagnostic tree knowledge base.

[0152] A vehicle fault diagnosis device or cloud server (or vehicle cloud server) can divide multiple diagnostic tree knowledge bases according to vehicle series and models. It uses the minimum problem (such as unstable tire pressure, abnormal audio sound, air conditioning failure, etc.) as the top event. This top event is decomposed into multiple levels according to the relevant vehicle components, forming several intermediate events. This process continues until the minimum problem is classified as a specific component problem, thereby constructing a fault diagnosis tree for the minimum problem. This can ultimately lead to the construction of multiple fault diagnosis trees for the minimum problem. The vehicle fault diagnosis device or cloud server can then construct a diagnostic tree knowledge base based on the fault diagnosis trees for the multiple minimum problems.

[0153] For example, let's take the minimal problem of abnormal audio sound as an example to illustrate the process of constructing a minimum fault diagnosis tree. As shown in Figure 6, the vehicle fault diagnosis device or cloud server uses the abnormal audio sound as the top event and decomposes it based on the relevant vehicle components. The next levels of the abnormal audio sound are audio equipment failure, environmental impact, and human factors. The vehicle fault diagnosis device or cloud server then decomposes the audio equipment failure into power supply failure and speaker failure, decomposes the environmental impact into electromagnetic interference and temperature and humidity, and decomposes the human factor into improper use. In this way, the vehicle fault diagnosis device or cloud server constructs the minimum fault tree for the abnormal audio sound, as shown in Figure 6. It should be noted that the "and (or can be called and) / or" in the leftmost part of Figure 6 is used to indicate that any one or more of audio equipment failure, usage environment influence or human factors may cause abnormal audio sound; the "and / or" in the top part of Figure 6 is used to indicate that any one or more of power failure or speaker failure may cause audio equipment failure; the "and / or" in the middle part of Figure 6 is used to indicate that any one or more of electromagnetic interference or temperature and humidity influence may cause usage environment influence.

[0154] In one possible implementation, the first diagnostic result for the first vehicle in the third implementation may be determined by a vehicle fault diagnostic device. The vehicle fault diagnostic device may then transmit the first diagnostic result to a fault diagnostic agent module. Upon receiving the first diagnostic result, the fault diagnostic agent module may perform a fault diagnostic operation corresponding to the first diagnostic result based on the first diagnostic result.

[0155] In another possible implementation, after obtaining the fault diagnosis tree group, the vehicle fault diagnosis device in the third implementation may send the fault diagnosis tree group to a fault diagnosis agent module. The fault diagnosis agent module may then determine a first diagnostic result for the first vehicle based on the fault diagnosis tree group. The fault diagnosis agent module may then perform a fault diagnosis operation corresponding to the first diagnostic result based on the first diagnostic result.

[0156] In another possible implementation, after obtaining one or more keywords, the vehicle fault diagnosis device in the third implementation described above may send the one or more keywords to a fault diagnosis agent module. After obtaining the one or more keywords, the fault diagnosis agent module may match at least one fault diagnosis tree corresponding to the one or more keywords from a diagnostic tree knowledge base. The at least one fault diagnosis tree may constitute a fault diagnosis tree group adapted to the first fault description data. Thereafter, the fault diagnosis agent module may determine a first diagnostic result for the first vehicle based on the fault diagnosis tree group. Thereafter, the fault diagnosis agent module may perform a fault diagnosis operation corresponding to the first diagnostic result based on the first diagnostic result.

[0157] Optionally, the implementation process of the fault diagnosis agent module in implementation method three performing the fault diagnosis operation corresponding to the first diagnostic result can refer to the implementation process of the fault diagnosis agent module in implementation method one above performing the fault diagnosis operation corresponding to the first diagnostic result, which will not be repeated here.

[0158] Implementation method four: When the vehicle fault diagnosis device is an integrated unit of the first functional module (or the first computing device) and the fault diagnosis agent module, the vehicle fault diagnosis device can input the first fault description data into the fault diagnosis model after obtaining the first fault description data (or problem log), obtain a trained AI model, and obtain one or more keywords. Afterwards, the vehicle fault diagnosis device can match at least one fault diagnosis tree corresponding to one or more keywords from the diagnostic tree knowledge base. Among them, the at least one fault diagnosis tree can constitute a fault diagnosis tree group adapted to the first fault description data, and the fault diagnosis tree group is used to determine the first diagnostic result of the first vehicle; the diagnostic tree knowledge base can include multiple fault diagnosis trees. Optionally, the construction process of the diagnostic tree knowledge base in implementation method four can refer to the construction process of the diagnostic tree knowledge base in implementation method three above, and will not be repeated here.

[0159] Optionally, after obtaining the fault diagnosis tree group, the vehicle fault diagnosis device may also determine a first diagnostic result for the first vehicle based on the fault diagnosis tree group. The specific implementation process of the vehicle fault diagnosis device determining the first diagnostic result for the first vehicle based on the fault diagnosis tree group in Implementation Method 4 can be found in the implementation process of the vehicle fault diagnosis device determining the first diagnostic result for the first vehicle in Implementation Method 3 above, and will not be repeated here.

[0160] Furthermore, after obtaining the first diagnostic result for the first vehicle, the vehicle fault diagnostic device may, based on the first diagnostic result, perform a fault diagnostic operation corresponding to the first diagnostic result. The implementation process for the vehicle fault diagnostic device performing the fault diagnostic operation corresponding to the first diagnostic result in Implementation Method 4 can be found in the implementation process for the vehicle fault diagnostic device performing the fault diagnostic operation corresponding to the first diagnostic result in Implementation Method 2 above, and will not be further described here.

[0161] It should be understood that the above-mentioned implementation method three and implementation method four are described for the fault diagnosis model, which refers to a combination of a diagnostic tree knowledge base + a trained AI model (such as a trained generative AI model).

[0162] From the above steps 301 to 302, it can be seen that by using the fault diagnosis model to analyze the first fault description data of the first vehicle (or which can be understood as a description of the vehicle's fault phenomenon), a corresponding diagnostic result (such as the first diagnostic result) can be obtained in a timely and effective manner. This can replace manual diagnosis of vehicle faults, help reduce the diagnosis time of vehicle faults, and thus improve the diagnosis efficiency of vehicle faults. It should be understood that the fault diagnosis model is also obtained by learning vehicle fault diagnosis knowledge (such as fault training samples) based on the learning ability of the fault diagnosis model. Therefore, the fault diagnosis model can be used to replace manual diagnosis of vehicle faults, and the multimodal understanding ability of the fault diagnosis model (such as the ability to perceive input data of different data types) can be used to analyze vehicle faults, thereby effectively determining the vehicle fault.

[0163] Figure 7 exemplarily shows a flow chart of another vehicle fault diagnosis method provided by an embodiment of the present application. The method flow can be implemented by data interaction between multiple vehicle fault diagnosis devices (such as a first vehicle fault diagnosis device and a second vehicle fault diagnosis device) and a fault diagnosis module (such as a first fault diagnosis module). Optionally, the first vehicle fault diagnosis device can be a first functional module (or a first computing device) or an element (such as a chip, a chip system or a circuit, etc.) that can support the first functional module (or the first computing device) to implement the functions required by the method, and the second vehicle fault diagnosis device can be a fault diagnosis agent module or an element (such as a chip, a chip system or a circuit, etc.) that can support the fault diagnosis agent module to implement the functions required by the method. In order to facilitate the introduction of the technical solution provided by an embodiment of the present application, the following takes the first vehicle fault diagnosis device as the first functional module and the second vehicle fault diagnosis device as the fault diagnosis agent module as an example to introduce the process of implementing the vehicle fault diagnosis method by data interaction between the first vehicle fault diagnosis device, the second vehicle fault diagnosis device and the fault diagnosis module. As shown in Figure 7, the method includes steps 701-705:

[0164] Step 701: The first functional module sends a first diagnosis result to the fault diagnosis agent module. The fault diagnosis agent module receives the first diagnosis result.

[0165] Optionally, the first diagnostic result may be used to instruct the fault diagnosis agent module to perform a fault diagnosis operation corresponding to the first diagnostic result.

[0166] Optionally, the implementation process of the first functional module determining the first diagnostic result can refer to the implementation process of the first functional module determining the first diagnostic result in the vehicle fault diagnosis method shown in Figure 3 above, which will not be repeated here.

[0167] Step 702: When the first diagnosis result includes information of the first fault diagnosis module, the fault diagnosis agent module sends first information to the first fault diagnosis module. The first fault diagnosis module receives the first information.

[0168] The first information may be used to instruct a fault diagnosis to be performed on the first vehicle. For example, the first information may include information about the first vehicle. For example, the information about the first vehicle may include, but is not limited to: the vehicle identification (or vehicle name) of the first vehicle, the model and series of the first vehicle, the time (or time period) when the fault occurred on the first vehicle, or the time when the user submitted the fault phenomenon.

[0169] Optionally, the implementation process of step 702 may refer to the implementation process provided in example 2 of the implementation method 1 of step 302 above, and will not be repeated here.

[0170] It can be understood that when the first diagnostic result does not contain information of the first fault diagnosis module, the corresponding implementation process of the fault diagnosis agent module performing the fault diagnosis operation corresponding to the first diagnostic result can refer to the implementation process provided in Example 1 in the implementation method 1 of the above step 302, which will not be repeated here.

[0171] Step 703: The first fault diagnosis module performs fault diagnosis on the first vehicle to obtain a second diagnosis result.

[0172] In an embodiment of the present application, after obtaining the first information from the fault diagnosis agent module, the first fault diagnosis module may perform a fault diagnosis on the first vehicle to obtain a second diagnostic result. For example, the second diagnostic result may include the second fault cause of the first vehicle, or may not include the second fault cause of the first vehicle.

[0173] For example, after obtaining the first information, the first fault diagnosis module can query the data corresponding to the first fault diagnosis module of the first vehicle from the database (or data storage area) used to store the data reported by the vehicle based on the first information, and can analyze and process the data corresponding to the first fault diagnosis module to obtain a second diagnostic result of the first vehicle.

[0174] Exemplarily, take the first fault diagnosis module as a motor fault diagnosis module as an example. In one example, when the first information includes the vehicle identification (or vehicle name) of the first vehicle, the motor fault diagnosis module can query the historical motor data (such as historical motor CAN signal data) of the first vehicle from the database (or data storage area) for storing data reported by the vehicle based on the vehicle identification (or vehicle name) of the first vehicle. Afterwards, the motor fault diagnosis module can analyze and process the historical motor data of the first vehicle to obtain a second diagnostic result for the first vehicle. In another example, when the first information includes the vehicle identification (or vehicle name) and current time of the first vehicle, the motor fault diagnosis module can query the motor data (such as motor CAN signal data) of the first vehicle at the current time from the database (or data storage area) for storing data reported by the vehicle based on the vehicle identification (or vehicle name) of the first vehicle and the current time. Afterwards, the motor fault diagnosis module can analyze and process the motor data of the first vehicle at the current time to obtain a second diagnostic result for the first vehicle. In another example, when the first information includes the vehicle identification (or vehicle name) and the time of the fault occurrence (or the time period when the fault occurs) of the first vehicle, the motor data of the first vehicle at the time of the fault occurrence (or the time period when the fault occurs) can be queried from the database (or data storage area) for storing data reported by the vehicle based on the vehicle identification (or vehicle name) and the time of the fault occurrence (or the time period when the fault occurs). Afterwards, the motor fault diagnosis module can analyze and process the motor data of the first vehicle at the time of the fault occurrence (or the time period when the fault occurs) to obtain the second diagnostic result of the first vehicle. It should be understood that the above content is only an illustrative introduction to several possible examples of the motor fault diagnosis module determining the second diagnostic result of the first vehicle. The motor fault diagnosis module can also determine the second diagnostic result of the first vehicle through other possible examples, and the embodiments of the present application will no longer list them one by one.

[0175] Step 704: The first fault diagnosis module sends the second diagnosis result to the fault diagnosis agent module. The fault diagnosis agent module receives the second diagnosis result.

[0176] Step 705: The fault diagnosis agent module generates a first fault handling report for the first vehicle according to the second fault diagnosis result.

[0177] In the embodiment of the present application, after obtaining the second diagnostic result, the fault diagnosis agent module can generate a first fault handling report for the first vehicle according to the second diagnostic result.

[0178] In one example, when the second diagnostic result includes the second fault cause of the first vehicle, the fault diagnosis agent module can determine the fault level corresponding to the second fault cause based on the second fault cause, and can obtain the processing solution corresponding to the second fault cause from a database (or data storage area) for storing processing solutions corresponding to the fault causes. Afterwards, the fault diagnosis agent module can generate a first fault handling report for the first vehicle based on the second fault cause, the fault level corresponding to the second fault cause, and the processing solution corresponding to the second fault cause. Then, the fault diagnosis agent module can send the first fault handling report of the first vehicle to the first vehicle (or the user of the first vehicle or the manufacturer corresponding to the first vehicle). Optionally, the fault diagnosis agent module can also submit the diagnostic record of the first vehicle to the manufacturer corresponding to the first vehicle, so that the manufacturer can perform corresponding repairs on the first vehicle. In an embodiment of the present application, the user of the first vehicle can also perform corresponding after-sales maintenance scheduled operations in a timely manner based on the first fault handling report.

[0179] In another example, when the second diagnostic result does not include the second fault cause of the first vehicle, the fault diagnosis agent module can generate a first fault handling report for the first vehicle based on the fact that there is no fault in the first vehicle. The fault cause included in the first fault handling report is that there is no fault in the first vehicle. Afterwards, the fault diagnosis agent module can send the first fault handling report of the first vehicle to the first vehicle (or the user of the first vehicle or the manufacturer corresponding to the first vehicle). Optionally, the fault diagnosis agent module can also submit the diagnostic record of the first vehicle to the manufacturer corresponding to the first vehicle, so that the manufacturer can perform corresponding repairs on the first vehicle. In an embodiment of the present application, the user of the first vehicle can also perform corresponding after-sales maintenance scheduled operations in a timely manner based on the first fault handling report.

[0180] As can be seen from the above steps 701 to 705, when the first diagnostic result includes information from the first fault diagnosis module, the fault diagnosis agent module sends first information indicating that a fault diagnosis of the first vehicle is to be performed to the corresponding fault diagnosis module (e.g., the first fault diagnosis module), thereby further determining the vehicle fault with the help of the corresponding fault diagnosis module, thereby effectively locating the vehicle fault. In this way, by utilizing the fault diagnosis agent module, the method can enable the fault diagnosis model to have the ability to call the corresponding fault diagnosis module, thereby achieving fully automated operations for vehicle fault analysis, vehicle fault diagnosis, and vehicle fault determination, which helps to significantly improve the efficiency of vehicle fault diagnosis (or vehicle fault location or vehicle fault detection).

[0181] It should be noted that in the description of this application, "at least one" refers to one or more, and "plurality" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of A, B and C" includes A, B, C, AB, AC, BC or ABC. And, unless otherwise specified, the ordinal numbers such as "first", "second", and "third" mentioned in the embodiments of this application are used to distinguish multiple objects and are not used to limit the order, timing, priority or importance of multiple objects. In addition, the terms "including", "comprising", "having" and their variations appearing in this application all mean "including but not limited to" unless otherwise specifically emphasized.

[0182] In addition, it should be noted that each step involved in the above embodiments can be performed by a corresponding device, or by a component such as a chip, processor, or chip system within the device, and the embodiments of the present application do not limit this. The above embodiments are described only as examples of execution by corresponding devices.

[0183] It should be noted that in each of the above embodiments, some steps may be selected for implementation, and the order of the steps in the diagrams may be adjusted for implementation, and this application does not limit this. It should be understood that executing some of the steps in the diagrams, adjusting the order of the steps, or combining them for specific implementation all fall within the scope of protection of this application.

[0184] It is understandable that in order to implement the functions in the above embodiments, the various devices involved in the above embodiments include hardware structures and / or software modules corresponding to the execution of each function. It should be readily apparent to those skilled in the art that, in combination with the units and method steps of the various examples described in the embodiments disclosed in this application, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application scenario and design constraints of the technical solution.

[0185] It should be noted that the "steps" in the embodiments of this application are merely illustrative and serve as a method of expression for a better understanding of the embodiments. They do not constitute a substantial limitation on the execution of the solutions of this application. For example, the "steps" can also be understood as "features." Furthermore, the steps do not constitute any limitation on the execution order of the solutions of this application. Any changes to the order of steps, or any operations such as step merging or splitting that do not affect the implementation of the overall solution, resulting in new technical solutions, are also within the scope of this application.

[0186] Based on the same concept, the embodiments of the present application also provide a possible vehicle fault diagnosis device, which is suitable for the application scenario shown in Figure 1. In one example, the vehicle fault diagnosis device can be a vehicle fault diagnosis device included in the vehicle fault diagnosis system 200 shown in Figure 1, or it can also be a functional module (such as a plug-in, component, or chip, etc.) provided in the vehicle fault diagnosis device included in the vehicle fault diagnosis system 200 shown in Figure 1. The functional module (or functional component or functional element) has the function of implementing the vehicle fault diagnosis method. In another example, the vehicle fault diagnosis device can also be other devices (such as other computing devices or diagnostic units) with vehicle fault diagnosis functions in the vehicle fault diagnosis system 200 shown in Figure 1, or it can also be a functional module (such as a plug-in, component, or chip, etc.) provided in other devices with vehicle fault diagnosis functions in the vehicle fault diagnosis system 200 shown in Figure 1. Optionally, the vehicle fault diagnosis device can be used to implement the vehicle fault diagnosis method provided in the above embodiments, or the module (such as a chip) of the vehicle fault diagnosis device can be used to implement the vehicle fault diagnosis method provided in the above embodiments, thereby also achieving the beneficial effects of the above embodiments. For example, taking the vehicle fault diagnostic device as a chip provided in a vehicle fault diagnostic device (or vehicle fault diagnostic system 200), when the vehicle fault diagnostic device is a chip, the vehicle fault diagnostic device includes a transceiver and a processor, but no memory. The transceiver exists as an input / output interface, which is used by the chip to implement transmission and reception of the vehicle fault diagnostic device. The input / output interface may include an input interface and / or an output interface, with the input interface enabling reception by the vehicle fault diagnostic device, and the output interface enabling transmission by the vehicle fault diagnostic device. The processor is configured to read and execute corresponding computer programs or instructions to implement the corresponding functions of the vehicle fault diagnostic device. Optionally, when the chip implements the corresponding functions of the vehicle fault diagnostic device in the above-mentioned embodiments, the input / output interface may implement the transmission and reception operations performed by the vehicle fault diagnostic device in the above-mentioned embodiments; and the processor may implement other operations performed by the vehicle fault diagnostic device in the above-mentioned embodiments in addition to the transmission and reception operations. For specific details, please refer to the relevant descriptions of the method embodiments shown in Figures 3 or 7 above, and will not be described in detail here.

[0187] 8 , a vehicle fault diagnosis device 800 includes a communication module 801 (or may be referred to as a transceiver module or a transceiver unit or a communication unit, for sending and receiving data) and a processing module 802 .

[0188] Optionally, the communication module 801 may include a receiving module and / or a transmitting module. The receiving module may be used by the vehicle fault diagnosis device 800 to receive signals (information or data, etc.); the transmitting module may be used by the vehicle fault diagnosis device 800 to transmit signals (information or data, etc.). The transmitting module may transmit signals (information or data, etc.) under the control of the processing module 802, and the receiving module may receive signals (information or data, etc.) under the control of the processing module 802.

[0189] When the vehicle fault diagnostic device 800 is used to implement the functions of the vehicle fault diagnostic device (e.g., the first functional module or an integrated module of the first functional module and the fault diagnostic agent module) in the method embodiment shown in FIG3 , the communication module 801 is used to obtain first fault description data of a first vehicle. The processing module 802 is used to input the first fault description data into a fault diagnostic model to obtain a first diagnostic result. The fault diagnostic model can be used to describe the correspondence between the vehicle's fault description data and the diagnostic result; the first diagnostic result is used to instruct the fault diagnostic agent module to perform a fault diagnostic operation corresponding to the first diagnostic result.

[0190] When the vehicle fault diagnosis device 800 is used to implement the functions of the vehicle fault diagnosis device (such as a fault diagnosis agent module or an integrated module of the first functional module and the fault diagnosis agent module) in the above-mentioned method embodiment: the communication module 801 is used to receive a first diagnostic result. The first diagnostic result is associated with the first fault description data of the first vehicle and a fault diagnosis model; the fault diagnosis model can be used to describe the correspondence between the vehicle's fault description data and the diagnostic result; and the first diagnostic result can be used to instruct the fault diagnosis agent module to perform a fault diagnosis operation corresponding to the first diagnostic result. The processing module 802 is used to perform a fault diagnosis operation corresponding to the first diagnostic result based on the first diagnostic result.

[0191] When the vehicle fault diagnosis device 800 is used to implement the function of the first functional module in the method embodiment shown in Figure 7 above: the communication module 801 is used to send the first diagnostic result to the fault diagnosis agent module. Optionally, the first diagnostic result is used to instruct the fault diagnosis agent module to perform a fault diagnosis operation corresponding to the first diagnostic result. Optionally, the communication module 801 is also used to obtain the first fault description data of the first vehicle. The processing module 802 is used to determine the first diagnostic result, such as for inputting the first fault description data into the fault diagnosis model to obtain the first diagnostic result. Among them, the fault diagnosis model can be used to describe the correspondence between the vehicle's fault description data and the diagnostic result.

[0192] When the vehicle fault diagnosis device 800 is used to implement the functions of the fault diagnosis agent module in the method embodiment shown in FIG. 7 , the communication module 801 is configured to receive a first diagnostic result from the first functional module. Optionally, the first diagnostic result is used to instruct the fault diagnosis agent module to perform a fault diagnosis operation corresponding to the first diagnostic result. The communication module 801 is further configured to send first information to the first fault diagnosis module when the first diagnostic result includes information from the first fault diagnosis module. Optionally, the first information may be used to instruct a fault diagnosis to be performed on the first vehicle; the first information may include information about the first vehicle. The communication module 801 is further configured to receive a second diagnostic result from the first fault diagnosis module. The processing module 802 is further configured to generate a first fault handling report for the first vehicle based on the second fault diagnostic result. The processing module 802 is further configured to generate a first fault handling report for the first vehicle based on the first diagnostic result when the first diagnostic result includes information from the first fault diagnosis module. The communication module 801 is further configured to send the first fault handling report to the first vehicle (or the user of the first vehicle or the manufacturer of the first vehicle).

[0193] For a more detailed description of the communication module 801 and the processing module 802 , reference may be made to the relevant description of the vehicle fault diagnosis device in the method embodiment shown in FIG2 , which will not be repeated here.

[0194] It should be understood that the communication module 801 in the embodiment of the present application can be implemented by a transceiver or a transceiver-related circuit component, and the processing module 802 can be implemented by a processor or a processor-related circuit component.

[0195] It should be noted that the division of modules in the embodiments of the present application is illustrative and is merely a logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0196] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, or a server, etc.) or a processor to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0197] Based on the same concept, the embodiment of the present application also provides a possible vehicle fault diagnostic device, which is suitable for the application scenario shown in Figure 1. The vehicle fault diagnostic device is used to implement the technical solutions involved in the vehicle fault diagnostic device in the method embodiment shown in Figure 3 or Figure 7 above, and therefore can also achieve the beneficial effects possessed by the vehicle fault diagnostic device in the method embodiment shown in Figure 3 or Figure 7 above. Referring to Figure 9, the vehicle fault diagnostic device 900 includes: a transceiver 901 and a processor 902. Optionally, the vehicle fault diagnostic device 900 also includes a memory 903. Among them, the transceiver 901, the processor 902 and the memory 903 are interconnected. When the vehicle fault diagnostic device 900 is used to implement the technical solutions involved in the vehicle fault diagnostic device provided in the above embodiments, the transceiver 901 can be used to implement the functions of the above-mentioned communication module 801, and the processor 902 is used to implement the functions of the above-mentioned processing module 802.

[0198] Optionally, transceiver 901, processor 902, and memory 903 are interconnected via bus 904. Bus 904 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. Buses can be categorized as address buses, data buses, control buses, and the like. For ease of illustration, FIG9 shows only one thick line, but this does not imply that there is only one bus or only one type of bus.

[0199] Transceiver 901 is used to receive and transmit data. For example, when vehicle fault diagnosis device 900 is the first functional module having the functions required to implement the method, transceiver 901 can be used to communicate with a data preprocessing system or other devices (such as a fault diagnosis agent module or a data storage system). In one example, the transceiver can be a transceiver device with integrated data transmission and reception functions. In another example, the transceiver can also be composed of a transmitter and a receiver, wherein the transmitter is used to transmit data and the receiver is used to receive data.

[0200] Optionally, the transceiver 901 may include a transmitter and / or a receiver. The transmitter is used to transmit signals, messages, information, or data. The receiver is used to receive signals, messages, information, or data. Exemplarily, the transmitter transmits signals, messages, information, or data under the control of the processor 902. The receiver receives signals, messages, information, or data under the control of the processor 902.

[0201] The functions of processor 902 can refer to the description of the corresponding functions involved in the vehicle fault diagnosis device in the method embodiments shown in Figures 3 or 7 above, and will not be repeated here. Among them, processor 902 can be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and NP, etc. Processor 902 can further include a hardware chip. The above-mentioned hardware chip can be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The above-mentioned PLD can be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof. When implementing the above-mentioned functions, processor 902 can be implemented through hardware, and of course, it can also execute the corresponding software implementation through hardware.

[0202] The memory 903 may include a volatile memory (volatile memory), such as a random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage.

[0203] Memory 903 stores executable program code, and processor 902 executes the executable program code to implement the functions of the aforementioned vehicle fault diagnosis device (e.g., the communication module and the processing module), thereby implementing the vehicle fault diagnosis method provided in the embodiments of the present application. In other words, memory 903 stores computer program instructions for executing the vehicle fault diagnosis method provided in the embodiments of the present application.

[0204] Alternatively, the memory 903 stores executable code, and the processor 902 executes the executable code to implement the functions of the aforementioned vehicle fault diagnosis device (such as the communication module and the processing module), thereby implementing the vehicle fault diagnosis method provided in the embodiment of the present application. In other words, the memory 903 stores computer program instructions for executing the vehicle fault diagnosis method provided in the embodiment of the present application.

[0205] Based on the same concept, an embodiment of the present application further provides a computer program product, which includes a computer program or instructions. When the computer program or instructions are run on a computer, the computer executes the method provided in the above embodiment.

[0206] Based on the same concept, an embodiment of the present application also provides a computer-readable storage medium, which stores a computer program or instruction. When the computer program or instruction is executed by a computer, the computer executes the method provided in the above embodiment.

[0207] The storage medium may be any available medium that can be accessed by a computer. By way of example and not limitation, computer-readable media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer.

[0208] Based on the same concept, an embodiment of the present application further provides a chip, which may include a processor and a memory (or the chip is coupled to the memory), and the chip executes program instructions in the memory to perform the method provided in the above embodiment. Wherein, "coupling" refers to the direct or indirect connection between two components, such as coupling can refer to the electrical connection between two components.

[0209] Based on the same concept, an embodiment of the present application also provides a chip system, which includes a processor for supporting a computer device to implement the functions involved in the vehicle fault diagnosis device or vehicle fault diagnosis system (such as a data storage system, a data preprocessing system or a diagnostic result feedback system) or the fault diagnosis module in the above embodiments. In one possible design, the chip system also includes a memory, which is used to store the necessary programs and data for the computer device. The chip system can be composed of chips, or it can include chips and other discrete devices.

[0210] The methods provided in the embodiments of the present application can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, they can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the process or function described in the embodiments of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a high-density digital video disc (DVD)), or a semiconductor medium (eg, a solid state drive (SSD)).

[0211] The steps of the methods described in the embodiments of the present application can be directly embedded in hardware, software units executed by a processor, or a combination of the two. The software units can be stored in RAM, ROM, EEPROM, registers, hard disks, removable disks, CD-ROMs, or other storage media in any form known in the art. Exemplarily, the storage medium can be connected to the processor so that the processor can read information from the storage medium and write information to the storage medium. Alternatively, the storage medium can also be integrated into the processor. The processor and storage medium can be arranged in an ASIC.

[0212] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each flow and / or box in the flow chart and / or block diagram, as well as the combination of the flow chart and / or box in the flow chart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more flow charts and / or one or more boxes in the block diagram.

[0213] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0214] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A vehicle fault diagnosis method, characterized in that: include: Acquire first fault description data of a first vehicle; The first fault description data is input into a fault diagnosis model to obtain a first diagnosis result. The fault diagnosis model is used to describe the correspondence between the vehicle's fault description data and the diagnosis result. The first diagnosis result is used to instruct a fault diagnosis agent module to perform a fault diagnosis operation corresponding to the first diagnosis result.

2. The method according to claim 1, characterized in that The method further comprises: Generate a first fault handling report according to the first diagnostic result; The first fault handling report is fed back to the first vehicle.

3. The method according to claim 1, characterized in that The method further comprises: The first diagnosis result is sent to the fault diagnosis agent module, and the first diagnosis result is used to generate a first fault handling report.

4. The method according to claim 2, characterized in that Generating a first fault handling report according to the first diagnostic result, including: When the first diagnosis result includes information of a first fault diagnosis module, sending first information to the first fault diagnosis module, the first information including information of the first vehicle, the first information being used to instruct to perform fault diagnosis on the first vehicle; Obtain a second diagnosis result from the first fault diagnosis module, and generate the first fault handling report according to the second diagnosis result.

5. The method according to any one of claims 1 to 4, characterized in that: The first fault description data is obtained by format conversion of the second fault description data of the first vehicle, and the second fault description data is obtained through user input.

6. The method according to any one of claims 1 to 5, characterized in that: The fault diagnosis model is obtained by training a generative artificial intelligence (AI) model based on fault training samples, wherein the fault training samples include fault description data and fault causes.

7. The method according to claim 6, characterized in that The generative AI model is a large multimodal model.

8. The method according to any one of claims 2 to 4, characterized in that: The first fault handling report includes at least one of the following: a fault cause, a fault level, or a handling solution corresponding to the fault cause.

9. A vehicle fault diagnosis method, characterized in that: include: receiving a first diagnosis result, the first diagnosis result being associated with first fault description data of a first vehicle and a fault diagnosis model, the fault diagnosis model being used to describe a correspondence between the fault description data of the vehicle and the diagnosis result, the first diagnosis result being used to instruct a fault diagnosis agent module to perform a fault diagnosis operation corresponding to the first diagnosis result; According to the first diagnosis result, a fault diagnosis operation corresponding to the first diagnosis result is performed.

10. The method according to claim 9, characterized in that According to the first diagnosis result, performing a fault diagnosis operation corresponding to the first diagnosis result includes: A first fault handling report is generated according to the first diagnostic result.

11. The method according to claim 9 or 10, characterized in that When the first diagnostic result includes information of a first fault diagnosis module, the method further includes: Sending first information to the first fault diagnosis module, the first information including information of the first vehicle, the first information being used to instruct to perform fault diagnosis on the first vehicle; A second diagnosis result from the first fault diagnosis module is obtained, where the second diagnosis result is used to generate a first fault handling report.

12. The method according to claim 10 or 11, characterized in that The method further comprises: The first fault handling report is fed back to the first vehicle.

13. The method according to any one of claims 9 to 12, characterized in that: The first fault description data is obtained by format conversion of the second fault description data of the first vehicle, and the second fault description data is obtained through user input.

14. The method according to any one of claims 9 to 13, characterized in that: The fault diagnosis model is obtained by training a generative AI model based on fault training samples, and the fault training samples include fault description data and fault causes.

15. The method according to claim 14, characterized in that The generative AI model is a large multimodal model.

16. The method according to any one of claims 10 to 12, characterized in that: The first fault handling report includes at least one of the following: a fault cause, a fault level, or a handling solution corresponding to the fault cause.

17. A vehicle fault diagnosis device, characterized in that: The method comprises a module or a unit for executing the method according to any one of claims 1 to 8.

18. A vehicle fault diagnosis device, characterized in that: The method comprises a module or a unit for executing the method as claimed in any one of claims 9 to 16.

19. A vehicle fault diagnosis system, characterized in that: It includes the vehicle fault diagnosis device as claimed in claim 17 and / or the vehicle fault diagnosis device as claimed in claim 18.

20. The vehicle fault diagnosis system according to claim 19, characterized in that: The vehicle fault diagnosis system is further used to provide a fault description interface, wherein the fault description interface is used to prompt a user of the first vehicle to input a fault diagnosis requirement, wherein the fault diagnosis requirement includes second fault description data.

21. The vehicle fault diagnosis system according to claim 19 or 20, characterized in that: The vehicle fault diagnosis system also includes at least one of the following: a data storage system, a data preprocessing system or a diagnostic result feedback system; wherein the data storage system is used to store at least one of the following: first fault description data, second fault description data, a first diagnostic result, a second diagnostic result or a first fault handling report, the data preprocessing system is used to preprocess the second fault description data, and the diagnostic result feedback system is used to feed back the first fault handling report to the first vehicle.

22. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program or instruction. When the computer program or instruction is executed by a computer, the computer executes the method according to any one of claims 1 to 8 or the method according to any one of claims 9 to 16.

23. A computer program product, characterized in that The computer program product comprises a computer program or instructions, and when the computer program or instructions are run on a computer, the computer is caused to perform the method according to any one of claims 1 to 8 or the method according to any one of claims 9 to 16.

24. A chip, characterized in that: The chip includes a processor, which is coupled to a memory and is used to execute a computer program or instruction stored in the memory. When the computer program or instruction is executed, the method as described in any one of claims 1 to 8 or the method as described in any one of claims 9 to 16 is implemented.

Images