New energy vehicle operation and maintenance method and system based on product whole cycle knowledge graph retrieval enhancement

Abstract

The application discloses a new energy vehicle operation and maintenance method based on product whole cycle knowledge graph retrieval enhancement, and comprises the following steps: step one, constructing a new energy vehicle whole life cycle operation and maintenance knowledge graph; step two, constructing a new energy vehicle fault diagnosis model: constructing a new energy vehicle fault diagnosis model based on vehicle-mounted sensor signals to obtain fault diagnosis models of different subsystems; step three, knowledge graph retrieval enhancement: establishing cross-modal mapping between the fault diagnosis models of different subsystems and fault phenomena and reasons in the new energy vehicle whole life cycle operation and maintenance knowledge graph; step four, generating an operation and maintenance decision scheme: using the new energy vehicle whole life cycle operation and maintenance knowledge graph to enhance the semantic understanding and context perception ability of a large language model in the new energy vehicle operation and maintenance field to obtain a generative operation and maintenance decision scheme. The application further discloses a new energy vehicle operation and maintenance system based on product whole cycle knowledge graph retrieval enhancement.

Description

Technical Field

[0001] This invention belongs to the field of automotive operation and maintenance technology, specifically a new energy vehicle operation and maintenance method and system based on product lifecycle knowledge graph retrieval enhancement. Background Technology

[0002] In actual operation, new energy vehicles are affected not only by objective factors such as road conditions, external environment, and aging of vehicle components, but also by subjective factors such as driving habits, leading to malfunctions. When malfunctions occur, timely repair is necessary, especially for those that may pose significant safety hazards. However, as complex electromechanical products, new energy vehicles not only contain the mechanical components of traditional vehicles but also integrate highly complex electronic systems, advanced battery technology, and diverse information elements. This raises the bar for both users and maintenance personnel in the operation and maintenance of new energy vehicles. Furthermore, specific troubleshooting methods still require experienced maintenance personnel to determine on-site, sometimes necessitating consultation with vehicle fault repair manuals for diagnosis, which significantly impacts the efficiency of new energy vehicle operation and maintenance.

[0003] Current operation and maintenance solutions mainly rely on human experience. Although some preliminary intelligent operation and maintenance solutions exist, such as expert systems and knowledge graphs, these methods can solve some new energy vehicle operation and maintenance problems. However, they still have limitations, such as narrow applicability and the ability to only process structured text data. In addition, the knowledge sources of these methods are limited to the operation and maintenance phase and have not broken down the barriers between different stages of the new energy vehicle's entire life cycle. As a result, the solutions to some faults or problems are only temporary and do not address the root cause.

[0004] As intelligent products, new energy vehicles generate a large amount of status data during operation, which can be collected, transmitted, and processed through sensors and other devices. However, currently, a large amount of new energy vehicle status signals are in a "data black hole," and a barrier still exists between status signal data and maintenance knowledge. Therefore, it is crucial to monitor new energy vehicle status signal data, identify fault characteristics hidden within these signals, and map these fault characteristics to corresponding maintenance measures to construct a complete identification-diagnosis-maintenance decision-making process.

[0005] A knowledge graph is a knowledge management tool that links knowledge from different modalities and lifecycles together in the form of triples. Constructing a full-lifecycle operation and maintenance knowledge graph for new energy vehicles would allow this graph to contain a large amount of knowledge in the vertical domain of new energy vehicle operation and maintenance. However, because some new energy vehicle operation and maintenance needs occur infrequently, and are largely caused by user behavior rather than vertical domain issues, relying solely on a new energy vehicle operation and maintenance knowledge graph is insufficient to meet the operation and maintenance needs of these low-frequency, general domains.

[0006] like Figure 6 As shown, current new energy vehicle maintenance is largely reactive, meaning that the cause of a fault is only identified and corrective measures are derived after it occurs. Specifically, when a fault occurs, the ECUs of several related components or subsystems will return error codes. Maintenance personnel will diagnose the cause based on these error codes and comprehensively consider all ECU codes to determine a maintenance plan for the new energy vehicle. Even after determining the maintenance plan, it still needs manual verification. If problems are found, further modifications are required, and only after confirmation will the maintenance plan be implemented. This existing maintenance path relies heavily on manual experience, including fault manuals from various new energy vehicle suppliers and OEMs. This significantly impacts the efficiency of new energy vehicle maintenance. Furthermore, the rapid technological iteration and product updates in the current new energy vehicle market place higher demands on maintenance personnel. Summary of the Invention

[0007] In view of this, the purpose of this invention is to provide a new energy vehicle operation and maintenance method and system based on product lifecycle knowledge graph retrieval enhancement, which breaks down the knowledge barriers of operation and maintenance knowledge throughout the entire lifecycle of new energy vehicle products, and realizes the complete process of new energy vehicle operation and maintenance from fault identification to fault diagnosis, and finally achieves intelligent operation and maintenance.

[0008] To achieve the above objectives, the present invention provides the following technical solution:

[0009] This invention first proposes a new energy vehicle operation and maintenance method based on product lifecycle knowledge graph retrieval enhancement, comprising the following steps:

[0010] Step 1: Construct a knowledge graph for the entire lifecycle operation and maintenance of new energy vehicles

[0011] Clearly define the data, information, and knowledge content involved in the operation and maintenance of new energy vehicles throughout their entire life cycle, and construct a knowledge graph of the operation and maintenance of new energy vehicles throughout their entire life cycle.

[0012] Step 2: Constructing a fault diagnosis model for new energy vehicles

[0013] Based on the signals from on-board sensors, a fault diagnosis model for new energy vehicles is constructed, and fault diagnosis models for different subsystems are obtained.

[0014] Step 3: Enhanced Knowledge Graph Retrieval

[0015] Establish cross-modal mapping between fault diagnosis models of different subsystems and fault phenomena and causes in the knowledge graph of operation and maintenance throughout the entire life cycle of new energy vehicles, forming an integrated process of monitoring, diagnosis and operation and maintenance of new energy vehicles;

[0016] Step 4: Generate Operation and Maintenance Decision Plan

[0017] By leveraging the knowledge graph of the entire lifecycle operation and maintenance of new energy vehicles, we can enhance the semantic understanding and context awareness capabilities of large language models in the field of new energy vehicle operation and maintenance, and obtain generative operation and maintenance decision-making schemes.

[0018] Furthermore, in step one, the method for constructing a knowledge graph for the entire lifecycle operation and maintenance of new energy vehicles includes the following steps:

[0019] 11) Obtain operation and maintenance related data and information from the entire life cycle of new energy vehicles, including product design information in the R&D stage, product production information in the manufacturing stage, and user feedback information in the service stage;

[0020] 12) Based on the product history maintenance database, and combined with relevant operation and maintenance data throughout the entire life cycle of new energy vehicles, a new energy vehicle operation and maintenance database will be formed;

[0021] 13) For the new energy vehicle operation and maintenance database, use multimodal knowledge mining algorithms to present operation and maintenance knowledge of different modalities in text form and form an operation and maintenance knowledge graph in the form of triples.

[0022] Furthermore, in step two, the method for constructing a fault diagnosis model for new energy vehicles comprises the following steps:

[0023] 21) Under the guidance of domain experts, based on the subsystems composed of related components, the diagnostic object is to acquire all sensor signals within the subsystem and form a signal database for each subsystem;

[0024] 22) Based on the experience of component and subsystem operation and maintenance, combined with signal analysis technology, perform sensitivity analysis on the data in the signal database of each system to obtain the status signals most relevant to subsystem failures;

[0025] 23) Using relevant state signals as model inputs and corresponding subsystem faults as labels, construct fault diagnosis models for different subsystems based on supervised deep learning algorithms.

[0026] Furthermore, in step three, the method for enhancing knowledge graph retrieval comprises the following steps:

[0027] 31) Based on the diagnostic results obtained from the subsystem fault diagnosis model, a combined representation is formed by combining the ECU error codes;

[0028] 32) Using relevant entity recognition models, identify related entities in the composite representation;

[0029] 33) Input the identified relevant entities into the knowledge graph of operation and maintenance of new energy vehicles throughout their entire life cycle, link the entities, and obtain an entity retrieval subgraph with a certain neighborhood in the knowledge graph of operation and maintenance, with the relevant entities as the core.

[0030] Furthermore, in step four, the method for generating the operation and maintenance decision plan includes the following steps:

[0031] 51) Encode the information in the obtained entity retrieval subgraph into contextual information, and encode the combined representation at the same time. Combine the two encodings to construct the prompt of the large language model.

[0032] 52) Input the prompt into the large language model. The large model obtains a generative operation and maintenance decision scheme by understanding the prompt.

[0033] This invention also proposes a new energy vehicle operation and maintenance system based on product lifecycle knowledge graph retrieval enhancement, including cloud, edge nodes and terminals;

[0034] The terminal monitors the status of various vehicle components in real time through functional ECUs and on-board sensors, and feeds back the real-time status of the components to the edge nodes for further data processing and decision-making.

[0035] The edge node includes an in-vehicle domain controller and an in-vehicle central computing platform, which are used to perform preliminary processing on raw data from the terminal to reduce the latency and bandwidth requirements of data transmission to the cloud. At the same time, it is used to store key status data and decision results to ensure that the vehicle can still operate normally when the network is unstable or interrupted, and to synchronize data with the cloud after the network is restored.

[0036] The cloud includes a cloud computing center, which receives and stores the data transmitted by the edge nodes and executes the new energy vehicle operation and maintenance method enhanced by product lifecycle knowledge graph retrieval as described above. The cloud computing center runs a new energy vehicle lifecycle operation and maintenance knowledge graph and a new energy vehicle fault diagnosis model. The fault diagnosis models of each subsystem in the new energy vehicle lifecycle operation and maintenance knowledge graph and the new energy vehicle fault diagnosis model are trained and updated by the data stored in the cloud computing center.

[0037] Furthermore, it also includes an after-sales service system;

[0038] The after-sales service system receives generative operation and maintenance decision schemes from the cloud computing center: when a new energy vehicle has a major fault or safety hazard, the after-sales service system contacts the new energy vehicle owner and provides a corresponding operation and maintenance decision scheme; or, when the new energy vehicle has a minor fault, it sends a warning message and a corresponding operation and maintenance decision scheme to the vehicle display terminal through the cloud.

[0039] The beneficial effects of this invention are as follows:

[0040] This invention provides a new energy vehicle operation and maintenance method enhanced by product lifecycle knowledge graph retrieval, which has the following advantages:

[0041] (1) This invention uses knowledge graph as a carrier to break down the knowledge barrier of operation and maintenance knowledge throughout the entire life cycle of new energy vehicle products. All new energy vehicle operation and maintenance knowledge is stored in the knowledge graph in the form of triples. The corresponding knowledge graph can be dynamically adjusted according to the dynamic updates of products or technologies, so as to realize the continuous updating and dynamic evolution of operation and maintenance knowledge and effectively promote the degree of knowledge reuse.

[0042] (2) The present invention introduces a large language model, which enables the new energy vehicle operation and maintenance system to have a higher general domain understanding ability. Under the premise of having professional knowledge in the field of new energy vehicle operation and maintenance, it can fully understand user needs and provide professional, relevant and highly understandable generative operation and maintenance decision-making solutions.

[0043] (3) This invention uses knowledge graphs as a bridge to construct a subsystem fault diagnosis model based on fault-sensitive state signal data in different components or subsystems of new energy vehicles. At the same time, it breaks down the modal barrier between state signal data and operation and maintenance knowledge, realizing the complete process of new energy vehicles from fault identification to fault diagnosis, and finally realizing intelligent operation and maintenance.

[0044] (4) This invention constructs a cloud-edge-device collaborative new energy vehicle operation and maintenance system. By rationally allocating cloud-edge-device tasks, it realizes a complete process from data collection and transmission to processing, making full use of different resources. At the same time, by judging the size of the fault, the operation and maintenance plan for minor problems is directly sent to the display terminal to interact with the customer, which initially improves the user's self-operation and maintenance capabilities. Attached Figure Description

[0045] To make the objectives, technical solutions, and beneficial effects of this invention clearer, the following figures are provided for illustration:

[0046] Figure 1 This is a flowchart of the new energy vehicle operation and maintenance method based on product lifecycle knowledge graph retrieval enhancement according to the present invention.

[0047] Figure 2 This is a schematic diagram of a generative operation and maintenance decision-making scheme.

[0048] Figure 3 A flowchart for enhancing knowledge graph retrieval;

[0049] Figure 4 This is a schematic diagram of the new energy vehicle operation and maintenance system based on product lifecycle knowledge graph retrieval enhancement of the present invention;

[0050] Figure 5 A schematic diagram illustrating the interaction between the operation and maintenance system and the user in a new energy vehicle.

[0051] Figure 6 This is a flowchart for the operation and maintenance of existing new energy vehicles. Detailed Implementation

[0052] The present invention will be further described below with reference to the accompanying drawings and specific embodiments, so that those skilled in the art can better understand and implement the present invention. However, the embodiments described are not intended to limit the present invention.

[0053] like Figure 1-2 As shown in the figure, this embodiment of the new energy vehicle operation and maintenance method based on product lifecycle knowledge graph retrieval enhancement includes the following steps.

[0054] Step 1: Construct a knowledge graph for the entire lifecycle operation and maintenance of new energy vehicles

[0055] Identify the data, information, and knowledge involved in the operation and maintenance of new energy vehicles throughout their entire lifecycle, and construct a knowledge graph for the operation and maintenance of new energy vehicles throughout their entire lifecycle.

[0056] Specifically, in this embodiment, the method and steps for constructing a knowledge graph of the entire lifecycle operation and maintenance of new energy vehicles are as follows:

[0057] 11) Obtain operation and maintenance related data and information from the entire life cycle of new energy vehicles, including product design information in the R&D stage, product production information in the manufacturing stage, and user feedback information in the service stage;

[0058] 12) Based on the product history maintenance database, and combined with relevant operation and maintenance data throughout the entire life cycle of new energy vehicles, a new energy vehicle operation and maintenance database will be formed;

[0059] 13) For the new energy vehicle operation and maintenance database, use multimodal knowledge mining algorithms to present operation and maintenance knowledge of different modalities in text form and form an operation and maintenance knowledge graph in the form of triples.

[0060] Step 2: Constructing a fault diagnosis model for new energy vehicles

[0061] A fault diagnosis model for new energy vehicles is constructed based on on-board sensor signals, and fault diagnosis models for different subsystems are obtained.

[0062] Specifically, in this embodiment, the method and steps for constructing a fault diagnosis model for new energy vehicles are as follows:

[0063] 21) Under the guidance of domain experts, based on the subsystems composed of related components, the diagnostic object is to acquire all sensor signals within the subsystem and form a signal database for each subsystem;

[0064] 22) Based on the experience of component and subsystem operation and maintenance, combined with signal analysis technology, perform sensitivity analysis on the data in the signal database of each system to obtain the status signals most relevant to subsystem failures;

[0065] 23) Using relevant state signals as model inputs and corresponding subsystem faults as labels, construct fault diagnosis models for different subsystems based on supervised deep learning algorithms.

[0066] Step 3: Enhanced Knowledge Graph Retrieval

[0067] Establish cross-modal mapping between fault diagnosis models of different subsystems and fault phenomena and causes in the knowledge graph of operation and maintenance throughout the entire life cycle of new energy vehicles, forming an integrated process of monitoring, diagnosis and operation and maintenance of new energy vehicles.

[0068] Specifically, such as Figure 3 As shown, in this embodiment, the steps of the knowledge graph retrieval enhancement method are as follows:

[0069] 31) Based on the diagnostic results obtained from the subsystem fault diagnosis model, a combined representation is formed by combining the ECU error codes;

[0070] 32) Using relevant entity recognition models, identify related entities in the composite representation;

[0071] 33) Input the identified relevant entities into the knowledge graph of operation and maintenance of new energy vehicles throughout their entire life cycle, link the entities, and obtain an entity retrieval subgraph with a certain neighborhood in the knowledge graph of operation and maintenance, with the relevant entities as the core.

[0072] Step 4: Generate Operation and Maintenance Decision Plan

[0073] By leveraging the knowledge graph of the entire lifecycle operation and maintenance of new energy vehicles, we can enhance the semantic understanding and context awareness capabilities of large language models in the field of new energy vehicle operation and maintenance, and obtain generative operation and maintenance decision-making schemes.

[0074] Specifically, in this embodiment, the method steps for generating an operation and maintenance decision plan are as follows:

[0075] 51) Encode the information in the obtained entity retrieval subgraph into contextual information, and encode the combined representation at the same time. Combine the two encodings to construct the prompt of the large language model.

[0076] 52) Input the prompt into the large language model. The large model obtains a generative operation and maintenance decision scheme by understanding the prompt.

[0077] This embodiment introduces a large language model into the new energy vehicle operation and maintenance system. It enhances the large language model using a knowledge graph of the entire lifecycle of new energy vehicle operation and maintenance, enabling it to encompass both vast general domain knowledge and knowledge specific to the vertical domain of new energy vehicles. This allows the new energy vehicle operation and maintenance system to fully understand user operation and maintenance needs while also generating corresponding decision-making solutions for low-frequency general domain operation and maintenance requirements.

[0078] like Figure 4 As shown, this embodiment also proposes a new energy vehicle operation and maintenance system based on product lifecycle knowledge graph retrieval enhancement, including cloud, edge nodes and terminals.

[0079] The terminal monitors the status of various vehicle components in real time through functional ECUs and onboard sensors, acting as the "tentacles" of the operation and maintenance system. The terminal can monitor the status of various vehicle components in real time and simultaneously feed back the real-time status of these components to edge nodes for further data processing and decision-making. In other words, the terminal, as the data acquisition system of the new energy vehicle operation and maintenance system, involves various monitoring systems and sensor networks within the new energy vehicle, including the battery management system, electrode control system, and vehicle information system.

[0080] Edge nodes, located inside new energy vehicles, serve as a bridge connecting the cloud and the terminal. Edge nodes include computing nodes with high computing power, such as in-vehicle domain controllers and in-vehicle central computing platforms, which are located close to the terminal. Edge nodes perform preliminary processing on raw data from the terminal (such as data cleaning and format conversion) to reduce latency and bandwidth requirements for data transmission to the cloud. They also store critical status data and decision results, ensuring the vehicle continues to operate normally even when the network is unstable or interrupted, and synchronizing data with the cloud after network recovery.

[0081] The cloud, including the cloud computing center, is the core of the entire operation and maintenance system. The cloud computing center receives and stores data transmitted from edge nodes; that is, it stores a large amount of data, including uploaded vehicle sensor data and diagnostic and decision-making information. Simultaneously, the cloud computing center also executes the new energy vehicle operation and maintenance method enhanced by product lifecycle knowledge graph retrieval as described in this embodiment. Specifically, the cloud computing center runs a new energy vehicle lifecycle operation and maintenance knowledge graph and a new energy vehicle fault diagnosis model. These models and graphs are trained and constructed based on historical and real-time data. In other words, the fault diagnosis models of each subsystem in the new energy vehicle lifecycle operation and maintenance knowledge graph and the new energy vehicle fault diagnosis model are trained and updated using data stored in the cloud computing center to provide accurate fault prediction, diagnosis, and maintenance recommendations.

[0082] like Figure 5 As shown, the new energy vehicle operation and maintenance system enhanced by product lifecycle knowledge graph retrieval in this embodiment also includes an after-sales service system. The after-sales service system receives generative operation and maintenance decision schemes from the cloud computing center: when a new energy vehicle has a major fault or safety hazard, the after-sales service system contacts the new energy vehicle owner and provides corresponding operation and maintenance decision schemes; or, when the new energy vehicle has a minor fault, it sends warning information and corresponding operation and maintenance decision schemes to the vehicle display terminal through the cloud.

[0083] The above-described embodiments are merely preferred embodiments provided to fully illustrate the present invention, and the scope of protection of the present invention is not limited thereto. Equivalent substitutions or modifications made by those skilled in the art based on the present invention are all within the scope of protection of the present invention. The scope of protection of the present invention is defined by the claims.

Claims

1. A new energy vehicle operation and maintenance method based on product lifecycle knowledge graph retrieval enhancement, characterized in that: Includes the following steps: Step 1: Construct a knowledge graph for the entire lifecycle operation and maintenance of new energy vehicles Clearly define the data, information, and knowledge content involved in the operation and maintenance of new energy vehicles throughout their entire life cycle, and construct a knowledge graph of the operation and maintenance of new energy vehicles throughout their entire life cycle. Step 2: Constructing a fault diagnosis model for new energy vehicles Based on the signals from on-board sensors, a fault diagnosis model for new energy vehicles is constructed, and fault diagnosis models for different subsystems are obtained. Step 3: Enhanced Knowledge Graph Retrieval Establish cross-modal mapping between fault diagnosis models of different subsystems and fault phenomena and causes in the knowledge graph of operation and maintenance throughout the entire life cycle of new energy vehicles, forming an integrated process of monitoring, diagnosis and operation and maintenance of new energy vehicles; Step 4: Generate Operation and Maintenance Decision Plan By leveraging the knowledge graph of the entire life cycle of new energy vehicle operation and maintenance, we can enhance the semantic understanding and context awareness capabilities of the large language model in the field of new energy vehicle operation and maintenance, and obtain generative operation and maintenance decision-making schemes. In step one, the method for constructing a knowledge graph of the entire lifecycle operation and maintenance of new energy vehicles includes the following steps: 11) Obtain operation and maintenance related data and information from the entire life cycle of new energy vehicles, including product design information in the R&D stage, product production information in the manufacturing stage, and user feedback information in the service stage; 12) Based on the product history maintenance database, and combined with relevant operation and maintenance data throughout the entire life cycle of new energy vehicles, a new energy vehicle operation and maintenance database will be formed; 13) For the new energy vehicle operation and maintenance database, use multimodal knowledge mining algorithms to present operation and maintenance knowledge of different modalities in text form and form an operation and maintenance knowledge graph in the form of triples. In step two, the method for constructing a fault diagnosis model for new energy vehicles includes the following steps: 21) Under the guidance of domain experts, based on the subsystems composed of related components, the diagnostic object is to acquire all sensor signals within the subsystem and form a signal database for each subsystem; 22) Based on the experience of component and subsystem operation and maintenance, combined with signal analysis technology, perform sensitivity analysis on the data in the signal database of each system to obtain the status signals most relevant to subsystem failures; 23) Using relevant state signals as model inputs and corresponding subsystem faults as labels, construct fault diagnosis models for different subsystems based on supervised deep learning algorithms; In step four, the method for generating the operation and maintenance decision plan is as follows: 51) Encode the information in the obtained entity retrieval subgraph into contextual information, and encode the question combination representation to jointly construct the prompt of the large language model; 52) Input the prompt into the large language model. The large model obtains a generative operation and maintenance decision scheme by understanding the prompt.

2. The new energy vehicle operation and maintenance method based on product lifecycle knowledge graph retrieval enhancement as described in claim 1, characterized in that: In step three, the steps of the knowledge graph retrieval enhancement method are as follows: 31) Based on the diagnostic results obtained from the subsystem fault diagnosis model, a problem combination representation is formed by combining the ECU error codes; 32) Using relevant entity recognition models, identify related entities in the composite representation; 33) Input the identified relevant entities into the knowledge graph of operation and maintenance of new energy vehicles throughout their entire life cycle, link the entities, and obtain an entity retrieval subgraph with a certain neighborhood in the knowledge graph of operation and maintenance of new energy vehicles throughout their entire life cycle, with the relevant entities as the core.

3. A new energy vehicle operation and maintenance system enhanced by product lifecycle knowledge graph retrieval, characterized in that: This includes the cloud, edge nodes, and terminals; The terminal monitors the status of various vehicle components in real time through functional ECUs and on-board sensors, and feeds back the real-time status of the components to the edge nodes for further data processing and decision-making. The edge node includes an in-vehicle domain controller and an in-vehicle central computing platform, which are used to perform preliminary processing on raw data from the terminal to reduce the latency and bandwidth requirements of data transmission to the cloud. At the same time, it is used to store key status data and decision results to ensure that the vehicle can still operate normally when the network is unstable or interrupted, and to synchronize data with the cloud after the network is restored. The cloud includes a cloud computing center, which receives and stores the data transmitted by the edge nodes and executes the new energy vehicle operation and maintenance method enhanced by product lifecycle knowledge graph retrieval as described in claim 1 or 2. The cloud computing center runs a new energy vehicle lifecycle operation and maintenance knowledge graph and a new energy vehicle fault diagnosis model. The fault diagnosis models of each subsystem in the new energy vehicle lifecycle operation and maintenance knowledge graph and the new energy vehicle fault diagnosis model are trained and updated by the data stored in the cloud computing center.

4. The new energy vehicle operation and maintenance system based on product lifecycle knowledge graph retrieval enhancement as described in claim 3, characterized in that: It also includes an after-sales service system; The after-sales service system receives generative operation and maintenance decision schemes from the cloud computing center: when a new energy vehicle has a major fault or safety hazard, the after-sales service system contacts the new energy vehicle owner and provides a corresponding operation and maintenance decision scheme; or, when the new energy vehicle has a minor fault, it sends a warning message and a corresponding operation and maintenance decision scheme to the vehicle display terminal through the cloud.

Images