Vehicle remote diagnosis method and system and medium

Abstract

The invention relates to a vehicle remote diagnosis method and system and a medium, and the method comprises the steps: collecting diagnosis data from a vehicle, and the diagnosis data comprises vehicle controller area network data, vehicle electronic control unit logs, fault diagnosis codes and vehicle driving data; transmitting the diagnosis data to a cloud platform through a wireless network; analyzing the diagnosis data on the cloud platform by using an artificial intelligence model, wherein the artificial intelligence model comprises a fault diagnosis model and a fault prediction model; generating a diagnosis result based on an analysis result of the artificial intelligence model, wherein the diagnosis result comprises current fault diagnosis and potential fault prediction; sending the diagnosis result to the vehicle or the user equipment; and executing corresponding maintenance or preventive maintenance operation based on the diagnosis result. According to the invention, real-time monitoring, remote diagnosis and predictive maintenance of vehicle faults can be realized, so that the diagnosis efficiency is improved, and the maintenance cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle diagnosis, and in particular to a vehicle remote diagnosis method, system and medium. Background Art

[0002] With the rapid development of the automotive industry, vehicle diagnostic technology is also constantly advancing. Currently, vehicle diagnostics are primarily performed through on-board diagnostic systems (OBD) and specialized diagnostic equipment. OBD systems monitor vehicle status in real time and store fault codes, while specialized diagnostic equipment can read fault codes and perform more in-depth diagnostic analysis. These technologies provide strong support for vehicle fault detection and repair.

[0003] However, existing vehicle diagnostic technology still has several limitations. First, the diagnostic capabilities of the OBD system are limited, making it incapable of comprehensively analyzing complex faults. Second, specialized diagnostic equipment is often expensive and complex to operate, requiring specialized technicians. Furthermore, traditional diagnostic methods often require the vehicle to be sent to a repair shop for inspection, which is time-consuming and labor-intensive. Therefore, developing a more intelligent, convenient, and comprehensive vehicle diagnostic solution is crucial. Summary of the Invention

[0004] In view of the shortcomings of the prior art described above, the purpose of the present invention is to provide a vehicle remote diagnosis method, system and medium that can realize real-time monitoring, remote diagnosis and predictive maintenance of vehicle faults, thereby improving diagnostic efficiency, reducing maintenance costs, and providing more convenient and comprehensive diagnostic services for vehicle owners and maintenance personnel.

[0005] To achieve the above objectives, the present invention adopts the following technical solutions.

[0006] In a first aspect, the present invention provides a vehicle remote diagnosis method, comprising: collecting diagnostic data from the vehicle, the diagnostic data including vehicle controller area network data, vehicle electronic control unit logs, fault diagnostic codes, and vehicle driving data; Transmitting the diagnostic data to a cloud platform via a wireless network; Analyzing the diagnostic data using an artificial intelligence model on the cloud platform, the artificial intelligence model including a fault diagnosis model and a fault prediction model; Generate a diagnostic result based on the analysis result of the artificial intelligence model, wherein the diagnostic result includes current fault diagnosis and potential fault prediction; sending the diagnosis result to the vehicle or user device; and Corresponding repair or preventive maintenance operations are performed based on the diagnosis results.

[0007] Furthermore, in the above-mentioned vehicle remote diagnosis method, collecting diagnostic data from the vehicle includes: Collect the vehicle controller area network data and the fault diagnostic code in real time through the on-board diagnostic system interface; extracting the vehicle electronic control unit log from each ECU of the vehicle; and The vehicle driving data is collected by on-board sensors, and the vehicle driving data includes vehicle speed, acceleration, battery status and engine parameters.

[0008] Furthermore, in the above-mentioned vehicle remote diagnosis method, the transmitting of the diagnostic data to the cloud platform includes: encrypting the diagnostic data; Transmitting the encrypted diagnostic data to the cloud platform in batches; and The received diagnostic data is decrypted and integrity verified on the cloud platform.

[0009] Furthermore, in the above-mentioned vehicle remote diagnosis method, the use of an artificial intelligence model to analyze the diagnostic data includes: Performing feature extraction on the diagnostic data using a deep learning algorithm; The extracted features are input into the pre-trained fault diagnosis model to identify the current faults; Inputting the diagnostic data into a fault prediction model to predict possible future faults; and The artificial intelligence model is continuously optimized based on historical diagnostic data and maintenance records.

[0010] Furthermore, in the above-mentioned vehicle remote diagnosis method, generating a diagnosis result includes: Assign severity ratings to identified current faults; Calculate the probability and estimated time of occurrence of predicted failures; Generate a failure cause analysis report; and Generate targeted repair or preventive maintenance recommendations.

[0011] Furthermore, in the above-mentioned vehicle remote diagnosis method, the sending of the diagnosis result to the vehicle or user equipment includes: Displaying the diagnostic results in the form of a graphical interface on the central control screen of the vehicle; Pushing the diagnostic results to the user's smartphone via a mobile application; and Send a detailed diagnostic report to the vehicle manufacturer or an authorized repair station.

[0012] Furthermore, the above vehicle remote diagnosis method further includes the following steps: Based on the diagnostic results, remotely perform vehicle software updates or parameter adjustments; Recording the diagnostic results and operations performed to form a vehicle health record; and Analyze diagnostic data from multiple vehicles to identify common issues and optimize vehicle designs.

[0013] Furthermore, in the above-mentioned vehicle remote diagnosis method, the cloud platform includes: A data storage module for storing raw diagnostic data and processed data; Computing resource pool to support the operation of artificial intelligence models; A task scheduling module for managing parallel diagnostic tasks; and Security authentication module, used to ensure the security of data transmission and access.

[0014] Furthermore, in the above-mentioned vehicle remote diagnosis method, the performing of corresponding repair or preventive maintenance operations includes: In case of emergency failure, the nearest rescue service is automatically notified; For faults that can be repaired remotely, perform remote software repair or parameter adjustment; For faults requiring on-site repair, automatically schedule an appointment at the nearest repair station and send a diagnostic report; and For predicted potential failures, a preventive maintenance plan is developed and users are reminded to perform it.

[0015] Furthermore, the above vehicle remote diagnosis method further includes the following steps: Build a vehicle knowledge graph, including vehicle structure, system relationships, and failure modes; Combining the diagnostic data with the vehicle knowledge graph to improve the accuracy of fault diagnosis and prediction; and Based on the diagnosis results and maintenance feedback, the vehicle knowledge graph is continuously updated and improved.

[0016] In a second aspect, the present invention provides a vehicle remote diagnosis system, which adopts the following technical solution: applied to the vehicle remote diagnosis method as described in any one of the first aspects above, the system includes: A vehicle-side acquisition module is used to collect diagnostic data from the vehicle, wherein the diagnostic data includes vehicle controller area network data, vehicle electronic control unit log, fault diagnostic codes and vehicle driving data; Cloud platform functional modules include: a vehicle large model analysis unit, configured to analyze the diagnostic data using an artificial intelligence model, wherein the artificial intelligence model includes a fault diagnosis model and a fault prediction model; An intelligent remote diagnosis unit, configured to generate a diagnosis result based on the analysis result of the artificial intelligence model, wherein the diagnosis result includes current fault diagnosis and potential fault prediction; a communication interface for transmitting the diagnostic data from the vehicle to the cloud platform functional module and sending the diagnostic results to the vehicle or user device; and An execution module is used to execute corresponding repair or preventive maintenance operations based on the diagnosis result.

[0017] In a third aspect, the present invention provides a readable storage medium, which adopts the following technical solution: A readable storage medium stores computer instructions, wherein the computer instructions, when executed by a processor, implement the method as described in any one of the first aspects above.

[0018] In summary, compared with the prior art, the present invention has at least one of the following beneficial technical effects: By collecting multi-dimensional diagnostic data from vehicles and analyzing it using AI models on a cloud platform, accurate diagnosis of current faults and prediction of potential failures can be achieved. This approach improves the accuracy and timeliness of fault diagnosis, reduces repair costs, and extends vehicle life. Furthermore, by transmitting diagnostic results to the vehicle or user device and performing appropriate repair or preventive maintenance, vehicle reliability and safety can be improved, accidents caused by vehicle failures can be reduced, and the user experience can be enhanced. Furthermore, this remote diagnostic approach can reduce unnecessary repair station visits, saving time and resources, and providing a more intelligent and efficient solution for vehicle management and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 It is a structural diagram of a specific embodiment of a vehicle remote diagnosis system of the present invention.

[0021] Figure 2 It is a structural diagram of another specific embodiment of a vehicle remote diagnosis system of the present invention.

[0022] Figure 3 This is a flowchart of a specific embodiment of a vehicle remote diagnosis method of the present invention.

[0023] Figure 4The flowchart of a specific embodiment of a vehicle remote diagnosis method of the present invention.

[0024] Figure 5 This is a signal flow diagram of a specific embodiment of a vehicle remote diagnosis method of the present invention.

[0025] Figure 6 It is a flow chart of another specific embodiment of a vehicle remote diagnosis method of the present invention.

[0026] Figure 7 It is a flow chart of another specific embodiment of a vehicle remote diagnosis method of the present invention. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of this application. In addition, it should be understood that the specific embodiments described herein are only used to illustrate and explain the present application and are not used to limit the present application.

[0028] It should be noted that the order of description of the following embodiments does not limit the preferred order of the embodiments of the present application. In addition, in the following embodiments, the description of each embodiment has its own focus. For parts not described in detail in one embodiment, please refer to the relevant description of other embodiments.

[0029] The method steps described in the embodiments of the present invention may be executed in the order described in the specific implementation manner, or the execution order of each step may be adjusted according to actual needs, provided that the technical problem can be solved. The execution order of each step will not be listed here one by one.

[0030] With the continuous development of automotive technology and the increasing level of intelligence, the complexity of vehicle fault diagnosis and maintenance has also increased. Traditional vehicle diagnostic methods often rely on manual experience and on-site testing, which are subject to problems such as low efficiency, high cost, and limited accuracy. To address these issues, the present invention proposes a vehicle remote diagnostic system and method. Utilizing advanced artificial intelligence technology, big data analysis, and a cloud computing platform, this system enables remote real-time monitoring, intelligent diagnosis, and predictive maintenance of vehicle faults. The present invention will be described in detail below with reference to specific implementation methods.

[0031] Reference Figure 1 ,The vehicle remote diagnosis system includes a vehicle acquisition module, a cloud ,platform function module, an intelligent remote diagnosis module and an ,execution module.

[0032] The vehicle-side acquisition module is used to collect diagnostic data from the vehicle. In some embodiments, this diagnostic data includes vehicle controller area network data, vehicle electronic control unit logs, fault diagnostic codes, and vehicle driving data. The vehicle-side acquisition module collects this data in real time through the vehicle's onboard diagnostic interface and various sensors.

[0033] The cloud platform functional module is the system's core processing unit. This module includes a vehicle model analysis unit, which uses artificial intelligence models to analyze diagnostic data. In some embodiments, the artificial intelligence models include fault diagnosis models and fault prediction models. The vehicle model analysis unit uses deep learning algorithms to extract and analyze features from diagnostic data, identifying current faults and predicting potential future faults.

[0034] The intelligent remote diagnostic module generates diagnostic results based on the analysis results of the vehicle large-scale model analysis unit. In some embodiments, the diagnostic results include current fault diagnosis and potential fault prediction. This module categorizes the severity of identified current faults, calculates the predicted probability and estimated time of occurrence of the fault, and generates a fault cause analysis report and targeted repair recommendations.

[0035] The execution module performs corresponding repair or preventive maintenance actions based on the diagnostic results. In some embodiments, the execution module can remotely perform vehicle software updates or parameter adjustments, automatically schedule appointments with the nearest repair station for faults requiring on-site repair, and develop preventive maintenance plans.

[0036] The system architecture also includes multiple auxiliary modules, such as the Identity and Access Management (IAM) module, the Firmware Over-the-Air (FOTA) module, the Dynamic Data Collection (DDC) module, and the Remote Diagnostic System (DOTA) module. These modules work together to ensure system security, data integrity, and diagnostic accuracy.

[0037] The communication interface is responsible for securely transmitting diagnostic data from the vehicle to the cloud platform functional module and sending the diagnostic results to the vehicle or user device. In some embodiments, the diagnostic results are displayed in the form of a graphical interface on the vehicle's central control screen or pushed to the user's smartphone via a mobile application.

[0038] Through the close collaboration of various modules, the vehicle remote diagnosis system realizes full-process intelligent diagnosis from data collection, analysis and processing to result output and execution, providing an efficient and accurate solution for vehicle fault diagnosis and preventive maintenance.

[0039] Reference Figure 1 and Figure 2 ,The cloud platform includes data storage module, computing resource pool, task ,scheduling module and security authentication module, which together support the ,efficient operation of the intelligent diagnosis system.

[0040] The data storage module is used to store raw diagnostic data and processed data. In some embodiments, the data storage module uses a tiered storage architecture, including an object storage service (OSS), a relational database (RDS), and a non-relational database (MongoDB). OSS is used to store log files uploaded by administrators, RDS is used to store structured diagnostic data, and MongoDB is used to store unstructured diagnostic results and historical records.

[0041] The computing resource pool provides powerful computing support for the operation of artificial intelligence models. In some embodiments, the computing resource pool uses a distributed computing architecture, including GPU clusters and CPU clusters, to meet the computing needs of different types of AI models. The elastic scalability of the computing resource pool ensures that additional resources can be quickly allocated during peak diagnostic workloads.

[0042] The task scheduling module is responsible for managing parallel diagnostic tasks. In some implementations, the task scheduling module uses a priority-based scheduling algorithm to dynamically allocate computing resources based on task urgency and resource requirements. The task scheduling module also implements task load balancing to ensure efficient utilization of system resources.

[0043] The security authentication module is used to ensure the security of data transmission and access. In some embodiments, the security authentication module uses a multi-factor authentication mechanism, including identity verification, rights management, and data encryption. The security authentication module also implements end-to-end encryption of data transmission to prevent illegal interception or tampering of data during transmission.

[0044] These modules are interconnected via an internal high-speed network, forming a highly integrated cloud platform. The cloud platform's distributed architecture and modular design make the intelligent diagnostic system highly scalable and reliable, capable of supporting the real-time diagnostic needs of large fleets.

[0045] The embodiment of the present invention also discloses a vehicle remote diagnosis method.

[0046] Reference Figure 3 , the vehicle remote diagnosis method includes the following steps.

[0047] S1. Collecting diagnostic data from the vehicle. In some embodiments, the diagnostic data includes vehicle controller area network data, vehicle electronic control unit logs, fault diagnostic codes (DTCs), and vehicle driving data. The on-board diagnostic system (OBD) collects CAN data and DTCs in real time via the OBD interface. Log data from each electronic control unit is extracted and stored. On-board sensors collect driving data such as vehicle speed, acceleration, battery status, and engine parameters.

[0048] S2: Transmit the diagnostic data to the cloud platform via a wireless network. In some embodiments, the diagnostic data is encrypted before transmission and transmitted to the cloud platform in batches. Upon receiving the data, the cloud platform decrypts and verifies its integrity to ensure data security and accuracy.

[0049] S3. Analyze the diagnostic data using an AI model on the cloud platform. In some embodiments, the AI ​​model includes a fault diagnosis model and a fault prediction model. A deep learning algorithm extracts features from the diagnostic data. These features are then fed into a pre-trained fault diagnosis model to identify current faults. The diagnostic data is also fed into a fault prediction model to predict future faults. The system continuously optimizes the AI ​​model based on historical diagnostic data and maintenance records.

[0050] S4. Generate a diagnostic result based on the analysis results of the AI ​​model. In some embodiments, the diagnostic result includes a current fault diagnosis and a potential fault prediction. The system categorizes the severity of the identified current fault and calculates the predicted probability and estimated time of occurrence of the fault. The system then generates a fault cause analysis report and targeted repair or preventive maintenance recommendations.

[0051] S5: Send the diagnostic results to the vehicle or user's device. In some embodiments, the diagnostic results are displayed on the vehicle's central control screen in the form of a graphical interface. The system pushes the diagnostic results to the user's smartphone via a mobile application. The system sends a detailed diagnostic report to the vehicle manufacturer or authorized repair station.

[0052] S6. Based on the diagnostic results, the system performs appropriate repair or preventive maintenance operations. In some embodiments, for urgent faults, the system automatically notifies the nearest rescue service. For faults that can be repaired remotely, the system performs remote software repairs or parameter adjustments. For faults requiring on-site repair, the system automatically schedules a reservation with the nearest repair station and sends a diagnostic report. For predicted potential faults, the system creates a preventive maintenance plan and reminds the user to execute it.

[0053] Reference Figure 4 ,The ,issuance and callback process of the diagnostic task includes the ,following steps.

[0054] Administrators create diagnostic tasks through a browser and define the task scope, such as specific vehicles, fault types, and diagnostic cycles. The browser submits the task information to the AIDOTA system via an HTTP request. After receiving the request, the AIDOTA system sends the diagnostic task details to the AI ​​Big Model platform via the messaging system. The AI ​​Big Model platform prepares and parses the data required for the task, such as logs, DTC codes, and CAN signals. The AI ​​Big Model platform performs specific algorithmic reasoning processes, such as matching rules, identifying fault causes, and generating prediction results. The AI ​​Big Model platform pushes the diagnostic results back to the AIDOTA platform via a messaging channel. After receiving the diagnostic results, the AIDOTA platform performs data classification, chart generation, and problem trend analysis. The processed data, including diagnostic details, statistical reports, and risk warnings, is presented to the administrator via the browser.

[0055] Reference Figure 1 The vehicle-side acquisition module is used to collect diagnostic data from the vehicle. In some embodiments, the on-board diagnostic system collects vehicle controller area network data and fault diagnostic codes in real time via an on-board diagnostic interface (ODI). The ODI is connected to the vehicle's electronic control unit (ECU) and can read real-time data and fault code information from each control unit.

[0056] In some implementations, the vehicle-side acquisition module extracts vehicle electronic control unit logs from each of the vehicle's electronic control units. These logs contain important information such as the control unit's operating status, error logs, and system parameters. By analyzing these logs, the diagnostic system can gain a deeper understanding of the operating conditions of each vehicle subsystem.

[0057] In some embodiments, the vehicle-side acquisition module collects vehicle driving data using onboard sensors. This data includes vehicle speed, acceleration, battery status, and engine parameters. Vehicle speed and acceleration data are acquired using wheel speed sensors and accelerometers. Battery status data, including parameters such as battery voltage, current, and temperature, is provided by the battery management system. Engine parameters, including speed, temperature, and oil pressure, are collected by the engine control unit.

[0058] The collected diagnostic data provides comprehensive vehicle status information to the vehicle remote diagnostic system, enabling the system to accurately analyze the vehicle's operating status and potential problems.

[0059] Reference Figure 2 The process of transmitting diagnostic data to the cloud platform includes data encryption, batch transmission, and data decryption verification. In some embodiments, diagnostic data is encrypted before transmission. The encryption algorithm uses a high-strength symmetric encryption method, such as AES-256, to ensure data security during transmission. The encryption key is pre-distributed to the onboard device and the cloud platform via a secure channel.

[0060] In some implementations, encrypted diagnostic data is transmitted to the cloud platform in batches. This batch transmission mechanism takes into account network bandwidth, data priority, and real-time requirements. High-priority diagnostic trouble codes and critical sensor data are transmitted first, while large log files are transmitted during network downtime. The transmission protocol utilizes the reliable TCP / IP protocol and incorporates breakpoint-resume technology to ensure data transmission integrity and efficiency.

[0061] In some implementations, after receiving encrypted diagnostic data, the cloud platform distributes the data to the corresponding processing nodes through load balancing and service routing modules. The processing nodes decrypt the data using a preset decryption key. After decryption, the system performs integrity verification on the data, including checksum checks and data format verification. Data that passes verification is marked as valid and enters the subsequent analysis and processing process. For data that fails verification, the system records an error log and triggers a retransmission mechanism.

[0062] In some implementations, the cloud platform implements multi-layered security measures. The network layer uses HTTPS for encrypted transmission, and the access layer implements strict identity authentication and access control. Data transmission is end-to-end encrypted throughout, ensuring that data cannot be decrypted or tampered with by unauthorized parties, even during data transfer.

[0063] This multi-protection data transmission mechanism ensures the security and reliability of vehicle diagnostic data from collection to cloud platform analysis, providing a solid data foundation for the remote diagnostic system.

[0064] Reference Figure 5 and Figure 6 ,The process of the AI ​​large model platform using artificial intelligence models to analyze diagnostic data includes feature extraction, fault diagnosis and prediction.

[0065] In some embodiments, a deep learning algorithm is used to extract features from diagnostic data. Using a multi-layered neural network structure, the deep learning model automatically learns and extracts key features from raw diagnostic data. These features include, but are not limited to, signal waveform characteristics, spectral characteristics, and statistical features. This feature extraction process reduces data redundancy and improves the efficiency and accuracy of subsequent analysis.

[0066] In some implementations, the extracted features are fed into a pre-trained fault diagnosis model to identify the current fault. The fault diagnosis model, trained on a large amount of historical fault data and expert knowledge, can quickly and accurately map input features to specific fault types and severity. The diagnosis model utilizes multi-classification algorithms, such as support vector machines (SVMs) or random forests, to identify a variety of fault types.

[0067] In some implementations, diagnostic data is simultaneously fed into a fault prediction model to predict future faults. This model utilizes time series analysis and machine learning algorithms, such as long short-term memory (LSTM) or recurrent neural networks (RNN), to analyze vehicle status trends and make predictions. This model considers multiple factors, including vehicle operating environment, mileage, and maintenance history, to improve prediction accuracy and reliability.

[0068] In some implementations, the system continuously optimizes the AI ​​model based on historical diagnostic data and maintenance records. This optimization process includes periodic model retraining, parameter adjustments, and feature extraction updates. Through continuous learning and optimization, the model's diagnostic and predictive capabilities are continuously enhanced, adapting to emerging fault types and changes in vehicle technology.

[0069] Reference Figure 5 The diagnostic algorithm model uses Flink to efficiently process and analyze diagnostic task messages. As a stream processing engine, Flink supports real-time data processing at the millisecond level, making it suitable for handling the large amount of diagnostic data continuously generated by vehicles. Flink is combined with the Kafka message queue to form a high-throughput data processing pipeline. TOS (Object Storage Service) is used to store high-frequency signal logs, the RDS relational database is used to store structured diagnostic data, and MongoDB is used to store unstructured diagnostic results and historical records. This multi-layer storage architecture optimizes data read and write efficiency and query performance.

[0070] Reference Figure 6 The workflow of the AI ​​large model platform includes steps such as data access, preprocessing, feature extraction, scenario calculation, and result mapping. The data access service is responsible for receiving diagnostic data from the vehicle. The data processing and preprocessing module cleans and normalizes the raw data. The text extraction module extracts key field information from the diagnostic log. The scenario calculation module compares the actual data with the preset diagnostic rules and triggers the corresponding diagnostic logic. The result mapping and backfill module maps the inference results to the vehicle model and database.

[0071] In some implementations, the AI ​​large-scale model platform achieves highly concurrent task processing capabilities. Through task classification and diversion, the system assigns different types of diagnostic tasks (such as DTC tasks and DID tasks) to corresponding processing channels. The Job1 module is responsible for calculating the diagnostic channel, while the Job2 module performs signal extraction and processing. This parallel processing architecture significantly improves the system's throughput and response speed.

[0072] In some implementations, the AI ​​large-scale model platform utilizes a distributed computing framework to support parallel model training and inference. GPU clusters are used to accelerate the training of deep learning models, while CPU clusters are used to handle routine data analysis tasks. The system enables dynamic loading and unloading of models, flexibly scheduling computing resources based on diagnostic task requirements.

[0073] Through this advanced AI large model platform, the vehicle remote diagnosis system achieves efficient and accurate fault diagnosis and prediction, providing strong technical support for vehicle maintenance and fault handling.

[0074] Further references Figure 6 The process of generating diagnostic results involves multiple steps. In some embodiments, the system assigns a severity rating to the identified current fault. This rating is based on the fault's impact on vehicle performance, safety, and service life, typically classified as minor, moderate, or severe. Minor faults do not immediately impact normal vehicle operation, moderate faults require prompt attention but do not affect short-term use, and severe faults require immediate vehicle shutdown and repair.

[0075] In some implementations, the system calculates the probability and estimated time of predicted failures. The prediction model analyzes multiple dimensions of information, including historical data, vehicle usage, and environmental factors. The system assigns a probability value to each predicted failure and estimates the timeframe within which the failure is likely to occur. This information helps vehicle owners and maintenance personnel prepare in advance, avoiding losses caused by unexpected failures.

[0076] In some implementations, the system generates a fault cause analysis report. This report includes a description of the fault, possible causes, scope of impact, and recommended solutions. Leveraging an expert knowledge base and historical repair data, the system conducts an in-depth analysis of the fault and provides detailed technical instructions and repair guidance. This report not only helps maintenance personnel quickly locate the problem but also provides a clear explanation of the problem for the vehicle owner.

[0077] In some embodiments, the system generates targeted repair or preventive maintenance recommendations. For current faults, the system provides detailed repair steps, required tools, and parts information. For predicted faults, the system develops a preventive maintenance plan, including recommended inspection items, maintenance intervals, and precautions. These recommendations take into account the vehicle's operating environment, mileage, and historical maintenance records, ensuring targeted and effective maintenance measures.

[0078] In some embodiments, diagnostic results are consolidated and optimized via a results aggregation module. This module comprehensively analyzes the outputs from different diagnostic models, eliminating redundant information and resolving potentially conflicting results. This aggregated diagnostic result is more comprehensive and consistent, providing users with a clear and accurate report on the vehicle's health status.

[0079] Further references Figure 4 The process of sending and displaying diagnostic results involves multiple steps. In some embodiments, diagnostic results are displayed on the vehicle's central control screen in the form of a graphical interface. This graphical interface includes information such as fault warnings, vehicle health scores, and maintenance recommendations. The interface design uses intuitive icons and color coding to enable the driver to quickly understand the vehicle's condition. The central control screen also provides a detailed fault description and treatment suggestions, facilitating timely decision-making by the driver.

[0080] In some implementations, the system pushes diagnostic results to the user's smartphone via a mobile application. The mobile application receives diagnostic data from the cloud platform in real time and presents it in a user-friendly format. Application functions include fault alerts, maintenance scheduling, and maintenance record inquiries. Users can check vehicle status and receive important notifications anytime, anywhere via their smartphone, enhancing vehicle management convenience.

[0081] In some embodiments, the system sends detailed diagnostic reports to vehicle manufacturers or authorized repair stations. These reports contain comprehensive fault information, historical data analysis, and repair recommendations. The reports are formatted in a standardized format, making them easy for repair personnel to quickly understand and process. Manufacturers use this data for quality analysis and product improvements. Authorized repair stations use these reports to pre-prepare necessary parts and tools, improving repair efficiency.

[0082] The multi-channel delivery and display of diagnostic results ensures timely information transfer and effective utilization. Vehicle owners, maintenance personnel, and manufacturers can access diagnostic information based on their needs, enabling intelligent management of the vehicle's entire life cycle.

[0083] Reference Figure 5 The external system modules in the vehicle remote diagnosis system, especially the FOTA part, perform remote software updates, record vehicle health records and analyze data from multiple vehicles based on the diagnosis results.

[0084] In some embodiments, the system remotely performs vehicle software updates or parameter adjustments based on the diagnostic results. The FOTA module receives the diagnostic results from the AIDOTA platform and determines the software modules that need to be updated or the parameters that need to be adjusted. The FOTA module generates a customized update package containing software code to repair faults or optimize performance. The update package is transmitted to the vehicle's electronic control unit through a secure encrypted channel. The on-board system verifies the integrity and compatibility of the update package in a safe environment, and then performs software installation or parameter modification. During the update process, the system monitors the update status in real time to ensure that the update is successfully completed. If the update process is interrupted, the system automatically rolls back to the previous stable version to ensure that the vehicle function is not affected.

[0085] In some implementations, the system records diagnostic results and performed operations to form a vehicle health profile. Information such as the results of each diagnostic task, remote update operations performed, and vehicle response status is systematically recorded and stored. These records include fault codes, sensor data, software version change history, and repair recommendations. The vehicle health profile uses a structured data format to facilitate subsequent analysis and retrieval. The system regularly backs up and encrypts the health profile to ensure data security and integrity. Vehicle owners and authorized maintenance personnel, after passing security authentication, can access the vehicle health profile and learn about the vehicle's complete maintenance history.

[0086] In some embodiments, the system analyzes diagnostic data from multiple vehicles to identify common issues and optimize vehicle design. The big data analytics platform aggregates diagnostic data from a large number of vehicles and uses machine learning algorithms to identify failure patterns and trends. The system compares and analyzes vehicle data from different models, geographic regions, and operating environments to identify potential design flaws or quality issues. The analysis results are used to guide vehicle design optimization, such as improving the durability of specific components, adjusting control strategies, and optimizing software algorithms. This analysis, based on large-scale, real-world operational data, provides a scientific basis for continuous vehicle improvement.

[0087] Through remote software updates, health record recording and multi-vehicle data analysis, the vehicle remote diagnosis system realizes intelligent management and continuous optimization of the vehicle's entire life cycle, improving the vehicle's reliability and performance.

[0088] Furthermore, the execution module performs corresponding repair or preventive maintenance actions based on the diagnostic results. In some embodiments, the system automatically notifies the nearest rescue service in the event of an emergency. The system utilizes the vehicle's GPS location information, combined with a geographic information system, to quickly locate the nearest rescue service provider. This notification includes the vehicle's location, fault type, and severity, enabling rescue personnel to be fully prepared.

[0089] In some implementations, for faults that can be repaired remotely, the system performs remote software repairs or parameter adjustments. This remote repair process includes operations such as software updates, parameter resets, and system reboots. The system sends repair instructions to the vehicle's onboard control unit via a secure, encrypted channel and monitors the repair process in real time. After the repair is complete, the system performs an automatic test to confirm that the fault has been resolved.

[0090] In some embodiments, for faults requiring on-site repair, the system automatically schedules an appointment with the nearest repair station and sends a diagnostic report. The system selects the most appropriate repair station based on the vehicle's location, fault type, and the repair station's expertise. The appointment information includes the recommended repair time, required parts, and estimated repair duration. The diagnostic report details the fault symptoms, possible causes, and recommended repair steps, helping repair personnel prepare in advance.

[0091] In some embodiments, for predicted potential failures, the system creates a preventive maintenance plan and reminds the user to perform it. This preventive maintenance plan takes into account vehicle usage, environmental factors, and the manufacturer's recommended maintenance intervals. The plan includes specific actions such as inspection items, part replacements, and parameter adjustments. The system sends maintenance reminders to the user via the vehicle's display and mobile app, providing detailed instructions.

[0092] Through these intelligent repair and maintenance operations, the execution module achieves timely processing and prevention of vehicle problems, thereby improving vehicle reliability and service life.

[0093] Furthermore, the vehicle remote diagnostic system builds and updates a vehicle knowledge graph and integrates it with diagnostic data to improve diagnostic and prediction accuracy. In some embodiments, the system builds a vehicle knowledge graph encompassing vehicle structure, system relationships, and fault modes. This knowledge graph is stored in a graph database, with nodes representing vehicle components, systems, and fault types, and edges representing relationships between components and the association between faults and symptoms. The system continuously updates and refines the vehicle knowledge graph based on diagnostic results and repair feedback. The system integrates diagnostic data with the vehicle knowledge graph to improve the accuracy of fault diagnosis and prediction. In some embodiments, the system utilizes tiered storage and multi-database collaborative optimization. The hot data layer uses TOS (object storage) to store high-frequency signal logs, supporting fast writes and temporary storage. The warm data layer uses RDS (Remote Data Storage) to store DTC / DID signals, supporting dynamic association queries. The cold data layer uses MongoDB to store diagnostic results and historical logs, enabling long-term storage and fast retrieval. In some embodiments, the system embeds a node-level fault frame calculation model in the Job2 module. This model independently analyzes and extracts features from each signal frame to generate node-level diagnostic results. In some implementations, the system implements dynamic task classification and a dual-channel processing mechanism based on task number type (DTC / DID-DTC). The system automatically assigns different types of diagnostic tasks to corresponding processing channels, enabling parallel processing. In some implementations, the system employs a real-time computing architecture that integrates stream and batch processing. The system uses the Flink streaming computing engine, combined with the Kafka message queue, to achieve millisecond-level response across the entire "signal reception - classification - storage - computation - output" chain.

[0094] Further, refer to Figure 6 , the algorithm process of the AI ​​large model platform can be further refined into the following steps.

[0095] In some implementations, the diagnostic task information is first pushed to the Job1 module via Kafka message channel 1. The Job1 module is responsible for processing the diagnostic information and classifying it according to the task information type.

[0096] For DDC signal type tasks, the system pushes the diagnostic signal list through Kafka message channel 1 and processes big data. This process may involve the collection and preliminary analysis of a large amount of vehicle sensor data.

[0097] For DID / DTC signal type tasks, the system pushes DID / DTC query information, which may include specific fault codes or diagnostic parameter identifiers.

[0098] The system processes the DID / DTC signal via Kafka message channel 2 and transmits the data to the Job2 module. The Job2 module is responsible for receiving the data statistics completion information and checking the TOS (Object Storage Service). This step may involve statistical analysis and storage verification of the received diagnostic data.

[0099] The processed data is transmitted via Kafka message channel 3 for processing DID / DTC signal data. This stage may include in-depth analysis and interpretation of fault codes and diagnostic parameters.

[0100] The system performs data analysis and storage operations, and the results are stored in a Mongo database. This process may include processing diagnostic data using advanced analytical algorithms to generate detailed fault diagnosis reports and predictive maintenance recommendations.

[0101] The system also includes steps such as parsing log data, storing TOS information, and executing Job 2 computations. Parsing log data may involve analyzing detailed operational logs extracted from the vehicle's electronic control unit. Storing TOS information may involve efficiently storing large volumes of diagnostic data in an object storage service. Job 2 computations may involve executing complex fault pattern recognition and prediction algorithms.

[0102] After completing the processing and storage operations, the entire process terminates at the result node, which may represent the generation of a final diagnostic report or the triggering of corresponding maintenance recommendations.

[0103] Throughout the entire process, Kafka message channels 1, 2, and 3 facilitate data transmission between different processing modules and storage components. This message queue-based architecture enables asynchronous communication between system components and efficient data flow management.

[0104] This structured diagnostic task processing process, combining real-time data stream processing and batch data analysis, can effectively handle the diagnostic needs of large fleets, providing fast and accurate fault diagnosis and predictive maintenance recommendations. The system's modular design and message-based communication mechanism make the entire diagnostic platform highly scalable and flexible, adapting to different diagnostic tasks and vehicle models.

[0105] Further, refer to Figure 7 ,Based on the scenario configuration-node signal configuration process, the ,vehicle remote diagnosis system realizes flexible signal configuration ,management.

[0106] The administrator initiates a signal configuration service request through the browser interface. After receiving the request, the system sends a signal pool query instruction to the AIDOTA platform. The AIDOTA platform interacts with the Dynamic Data Collection (DDC) system to obtain the available signal pool information for a specific vehicle model.

[0107] The DDC system returns signal pool data to the AIDOTA platform, which then passes this information back to the browser interface. Administrators can view the list of available signals in the browser and select and configure them. This interactive configuration allows administrators to flexibly select the required signals based on specific diagnostic needs.

[0108] After the administrator completes signal selection, they submit the signal configuration task through the browser interface. The browser packages the configuration information into a task request and sends it to the AIDOTA platform. After receiving the configuration task, the AIDOTA platform performs task analysis and verification to ensure the validity and consistency of the configuration.

[0109] In some implementations, the AIDOTA platform may optimize the configuration tasks, such as merging similar signal requests or adjusting the sampling frequency to balance data accuracy and system load. After processing is completed, the AIDOTA platform stores the optimized configuration information in the system database.

[0110] After the storage operation is completed, the AIDOTA platform may send a confirmation message to the administrator that the configuration is successful, or update the configuration status on the browser interface. This feedback mechanism ensures that the administrator understands the progress and results of the configuration process.

[0111] In some implementations, the system may support the creation and management of configuration templates. Administrators can save commonly used signal configurations as templates for quick application in future diagnostic tasks. This template-based management improves configuration efficiency while ensuring consistency across different diagnostic tasks.

[0112] The system may also implement a version control mechanism, allowing administrators to review and roll back historical configurations. This feature is particularly useful when diagnosing policy adjustments or troubleshooting, as administrators can compare the effects of different configuration versions to identify the optimal signal combination.

[0113] This flexible node signal configuration process allows the vehicle remote diagnosis system to adapt to diverse scenarios, with varying vehicle models and diagnostic requirements. Administrators can customize signal collection strategies based on specific circumstances, optimizing the pertinence and efficiency of data collection, thereby improving diagnostic accuracy and system resource utilization.

[0114] In summary, the vehicle remote diagnosis method uses an on-board acquisition module to collect multi-dimensional diagnostic data from the vehicle, securely transmits this data to a cloud platform, and utilizes an AI large-scale model platform for in-depth analysis and fault diagnosis prediction. The method generates diagnostic results, sends them to relevant parties, and finally performs the corresponding repair or preventive maintenance operations. This method combines advanced technologies such as the Internet of Things, big data, and artificial intelligence to achieve remote real-time monitoring, intelligent diagnosis, and predictive maintenance of vehicle faults. This significantly improves diagnostic efficiency and accuracy, reduces repair costs, and extends vehicle lifespan. It provides a comprehensive vehicle health management solution for owners, maintenance personnel, and manufacturers, effectively enhancing vehicle reliability, safety, and user experience.

[0115] The embodiment of the present invention also discloses a readable storage medium.

[0116] A readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method described in any one of the above embodiments. The computer-readable storage medium may include: any entity or device capable of carrying a computer program, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), and a software distribution medium. The computer program includes computer program code. The computer program code may be in source code form, object code form, an executable file, or some intermediate form. The computer-readable storage medium may include: any entity or device capable of carrying a computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), and a software distribution medium.

[0117] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention pertain.

[0118] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processing module, or other system that can fetch instructions from an instruction execution system, apparatus or device and execute instructions), or used in conjunction with such instruction execution systems, apparatuses or devices.

[0119] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A vehicle remote diagnosis method, characterized in that: include: collecting diagnostic data from the vehicle, the diagnostic data including vehicle controller area network data, vehicle electronic control unit logs, fault diagnostic codes, and vehicle driving data; Transmitting the diagnostic data to a cloud platform via a wireless network; Analyzing the diagnostic data using an artificial intelligence model on the cloud platform, the artificial intelligence model including a fault diagnosis model and a fault prediction model; Generate a diagnostic result based on the analysis result of the artificial intelligence model, wherein the diagnostic result includes current fault diagnosis and potential fault prediction; sending the diagnosis result to the vehicle or user device; as well as Corresponding repair or preventive maintenance operations are performed based on the diagnosis results.

2. The vehicle remote diagnosis method according to claim 1, characterized in that: The collecting of diagnostic data from the vehicle includes: Collect the vehicle controller area network data and the fault diagnostic code in real time through the on-board diagnostic system interface; extracting the vehicle electronic control unit log from each ECU of the vehicle; and The vehicle driving data is collected by on-board sensors, and the vehicle driving data includes vehicle speed, acceleration, battery status and engine parameters.

3. The vehicle remote diagnosis method according to claim 1, characterized in that: The transmitting of diagnostic data to the cloud platform includes: encrypting the diagnostic data; Transmitting the encrypted diagnostic data to the cloud platform in batches; and The received diagnostic data is decrypted and integrity verified on the cloud platform.

4. The vehicle remote diagnosis method according to claim 1, characterized in that: The analyzing the diagnostic data using an artificial intelligence model includes: Performing feature extraction on the diagnostic data using a deep learning algorithm; The extracted features are input into the pre-trained fault diagnosis model to identify the current faults; Inputting the diagnostic data into a fault prediction model to predict possible future faults; and The artificial intelligence model is continuously optimized based on historical diagnostic data and maintenance records.

5. The vehicle remote diagnosis method according to claim 4, characterized in that: Generating a diagnosis result includes: Assign severity ratings to identified current faults; Calculate the probability and estimated time of occurrence of predicted failures; Generate a failure cause analysis report; and Generate targeted repair or preventive maintenance recommendations.

6. The vehicle remote diagnosis method according to claim 1, characterized in that: The sending of the diagnosis result to the vehicle or user equipment includes: Displaying the diagnostic results in the form of a graphical interface on the central control screen of the vehicle; Pushing the diagnostic results to the user's smartphone via a mobile application; and Send a detailed diagnostic report to the vehicle manufacturer or an authorized repair station.

7. The vehicle remote diagnosis method according to any one of claims 1 to 6, characterized in that: The following steps are also included: Based on the diagnostic results, remotely perform vehicle software updates or parameter adjustments; Record the diagnostic results and operations performed to form a vehicle health record; as well as Analyze diagnostic data from multiple vehicles to identify common issues and optimize vehicle designs.

8. The vehicle remote diagnosis method according to claim 1, characterized in that: The cloud platform includes: A data storage module for storing raw diagnostic data and processed data; Computing resource pool to support the operation of artificial intelligence models; A task scheduling module for managing parallel diagnostic tasks; and Security authentication module, used to ensure the security of data transmission and access.

9. The vehicle remote diagnosis method according to claim 1, characterized in that: The execution of corresponding repair or preventive maintenance operations includes: In case of emergency failure, the nearest rescue service is automatically notified; For faults that can be repaired remotely, perform remote software repair or parameter adjustment; For faults requiring on-site repair, automatically schedule an appointment at the nearest repair station and send a diagnostic report; and For predicted potential failures, a preventive maintenance plan is developed and users are reminded to perform it.

10. The vehicle remote diagnosis method according to claim 1, characterized in that: The following steps are also included: Build a vehicle knowledge graph, including vehicle structure, system relationships, and failure modes; Combining the diagnostic data with the vehicle knowledge graph to improve the accuracy of fault diagnosis and prediction; as well as Based on the diagnosis results and maintenance feedback, the vehicle knowledge graph is continuously updated and improved.

11. A vehicle remote diagnosis system, applied to the vehicle remote diagnosis method according to any one of claims 1 to 10, characterized in that: The system comprises: A vehicle-side acquisition module is used to collect diagnostic data from the vehicle, wherein the diagnostic data includes vehicle controller area network data, vehicle electronic control unit log, fault diagnostic codes and vehicle driving data; Cloud platform functional modules include: a vehicle large model analysis unit, configured to analyze the diagnostic data using an artificial intelligence model, wherein the artificial intelligence model includes a fault diagnosis model and a fault prediction model; An intelligent remote diagnosis unit, configured to generate a diagnosis result based on the analysis result of the artificial intelligence model, wherein the diagnosis result includes current fault diagnosis and potential fault prediction; a communication interface for transmitting the diagnostic data from the vehicle to the cloud platform functional module and sending the diagnostic results to the vehicle or user device; and An execution module is used to execute corresponding repair or preventive maintenance operations based on the diagnosis result.

12. A readable storage medium, characterized in that: The readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the vehicle remote diagnosis method according to any one of claims 1 to 10 is implemented.

Images