Vehicle intelligent detection and maintenance system, method, electronic device and storage medium

Abstract

This application discloses a vehicle intelligent inspection and maintenance system, method, electronic device, and storage medium, relating to the field of vehicle inspection. The system includes the following steps: natural language commands are collected via a voice interaction terminal, parsed into standardized control commands by a large-scale model voice interaction module, and sent to an edge computing unit; the edge computing unit generates an automated task flow through a process orchestration module, driving multiple types of actuators to perform corresponding actions; multimodal sensing devices collect vehicle status data, process it, and generate inspection results; the inspection results are summarized and transmitted back to a cloud service platform, where a structured analysis report is automatically generated and associated with fault repair suggestions, while voice feedback is output via the voice interaction terminal. This application achieves intelligent and automated execution of vehicle inspection and maintenance, effectively improving the efficiency and convenience of vehicle inspection and maintenance.

Description

Technical Field

[0001] This invention relates to the field of vehicle inspection, and in particular to a vehicle intelligent inspection and maintenance system, a vehicle intelligent inspection and maintenance method, electronic equipment, and storage medium. Background Technology

[0002] With the rapid development of automotive intelligence and connectivity, the in-vehicle central control screen has become the core interactive carrier of the car cabin, integrating multiple functions such as navigation, entertainment, and vehicle control. Its performance stability and functional integrity directly affect the driving experience and driving safety. Currently, the central control screen needs to undergo comprehensive functional testing before leaving the factory to ensure that all operation commands respond normally and the display is accurate. Related testing technologies have gradually integrated technologies such as robotic arm automation and voice interaction, developing towards high efficiency and intelligence. However, in practical applications, there are still many problems that need to be solved.

[0003] Traditional robotic arm detection is currently the mainstream method for detecting physical button triggers on in-vehicle central control screens. Its core logic is as follows: by manually pre-setting the robotic arm's motion path and operating commands, the robotic arm triggers each physical button on the central control screen one by one according to a fixed program, simulating user operation, and thus detecting the button response sensitivity and functional effectiveness. This type of solution relies on motion control technology to achieve precise robotic arm movements, but its control logic remains at the level of traditional fixed trajectory control, failing to achieve dynamic environmental adaptive adjustment.

[0004] This solution has significant shortcomings: the detection process lacks dynamic adaptability and cannot cope with changes in detection requirements brought about by screen UI updates or function iterations. The main reason for this is that traditional robotic arm detection uses a fixed programming model, lacking real-time perception and dynamic decision-making capabilities. It cannot recognize changes such as adjustments to the central control screen UI layout or the addition / removal of function buttons, requiring manual re-adjustment of paths and modification of the program to achieve adaptation. The core difficulty in solving this problem lies in the fact that dynamic path adjustment requires real-time recognition of UI changes, automatic reconstruction of detection logic, and precise linkage of robotic arm movements. Existing technologies struggle to balance the accuracy of multi-joint robotic arm movements with dynamic adaptation efficiency, and program debugging consumes significant manpower and time, greatly reducing detection efficiency. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide a vehicle intelligent detection and maintenance system, a vehicle intelligent detection and maintenance method, an electronic device and a storage medium, which aims to achieve adaptive detection of the central control screen through dynamic detection logic, as well as deep coupling of voice commands with the robotic arm, to solve the technical problems in the prior art that it is difficult to balance the motion accuracy and dynamic adaptation efficiency of multi-joint robotic arms, and that program debugging requires a lot of manpower and time costs, which greatly reduces the detection efficiency.

[0006] This invention provides the following solution:

[0007] According to one aspect of this application, a vehicle intelligent detection and maintenance system is provided, comprising:

[0008] The cloud control layer, edge scheduling layer, and terminal execution perception layer collaborate bidirectionally through communication links.

[0009] The cloud-based control layer includes a cloud service platform and a large-scale model voice interaction module. The cloud service platform is used to store all detection data, generate structured analysis reports, and maintain the fault matching database. The large-scale model voice interaction module is used to parse natural language commands into standardized control commands and generate voice feedback information.

[0010] The edge scheduling layer is an edge computing unit that serves as the core control hub of the system. It includes an actuator management module, a multi-source perception and analysis module, a process orchestration module, and a data interaction module, which are used for instruction parsing, terminal device scheduling, perception data processing, task process orchestration, and result aggregation and feedback.

[0011] The terminal execution perception layer includes multiple types of actuators, multimodal sensing devices, and vehicle-mounted controlled systems. The actuators are used to perform mechanical actions and vehicle triggering operations, the sensing devices are used to collect voice and visual data, and the vehicle-mounted controlled systems are used to respond to control commands and provide feedback on vehicle status.

[0012] Among them, the edge scheduling layer has a built-in dynamic adaptation detection algorithm that can automatically generate a detection path that adapts to the object being tested based on perception data; the large model voice interaction module is deeply coupled with the edge scheduling layer, which compiles natural language instructions into action sequences of the actuator.

[0013] Furthermore, including:

[0014] The fault matching database of the cloud service platform automatically matches anomaly detection data with repair solutions through correlation analysis algorithms, and the accuracy of repair suggestions is no less than a preset threshold.

[0015] Furthermore, the multi-source perception analysis module includes a visual analysis unit, which is used to identify the status information and abnormal features of the vehicle display interface, as well as the status verification of specific function indicator lights.

[0016] Furthermore, various types of actuators are equipped with multimodal sensing sensors and adaptive execution components to achieve hardware status detection and adaptive maintenance operations.

[0017] Furthermore, the multimodal sensing device includes a voice interaction terminal for collecting natural language commands, recognizing them in real time, and generating voice feedback.

[0018] Furthermore, the communication link includes wired communication links and wireless communication networks, which are used for short-range command interaction, high-speed data transmission, and long-range data interaction, respectively.

[0019] According to two aspects of this application, a vehicle intelligent detection and maintenance method is provided, comprising the following steps:

[0020] Natural language commands are collected through a voice interaction terminal, parsed into standardized control commands by the large model voice interaction module, and then sent to the edge computing unit.

[0021] The edge computing unit generates automated task flows through the process orchestration module, driving various types of actuators to perform corresponding actions.

[0022] Multimodal sensing devices collect vehicle status data, which is then processed to generate detection results;

[0023] The test results are compiled and sent back to the cloud service platform, which automatically generates a structured analysis report and associates fault repair suggestions. At the same time, voice feedback is output through the voice interaction terminal.

[0024] Furthermore, including:

[0025] The edge computing unit uses a dynamic adaptation detection algorithm to automatically generate a detection path that adapts to the object being tested based on the sensing data.

[0026] According to three aspects of this application, an electronic device is provided, comprising: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0027] The memory stores a computer program, which, when executed by a processor, causes the processor to perform steps of a vehicle intelligent detection and maintenance method.

[0028] According to four aspects of this application, a computer-readable storage medium is provided that stores a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of a vehicle intelligent detection and maintenance method.

[0029] Compared with the prior art, the present invention has the following advantages:

[0030] This application adopts a three-layer bidirectional collaborative architecture consisting of a cloud-based control layer, an edge scheduling layer, and a terminal execution perception layer. Combined with the dynamic adaptation detection algorithm built into the edge scheduling layer, it can automatically generate detection paths adapted to the tested object based on perception data, realizing AI adaptive dynamic detection of functions of devices such as in-vehicle central control screens without the need for manual writing and updating of test scripts. At the same time, it achieves full-link automation from status detection and report generation to fault self-diagnosis, without the need for manual intervention throughout the process, significantly improving the efficiency of vehicle pre-delivery inspection and significantly reducing the labor costs and cycle investment in the inspection process.

[0031] This application achieves precise compilation of natural language commands into standardized action sequences for terminal actuators through deep coupling of a large-model voice interaction module and an edge scheduling layer. It supports the parsing and execution of complex voice commands. With the help of adaptive execution components for multiple types of actuators, it can complete high-precision hardware detection and maintenance operations. Users can trigger professional-grade vehicle hardware maintenance through natural voice, balancing ease of operation and execution accuracy.

[0032] This application, by relying on a fault matching database and correlation analysis algorithm, can automatically match and intelligently recommend abnormal detection data with repair solutions, and the accuracy of repair suggestions meets the preset threshold. Combined with the visual analysis unit of the multi-source perception analysis module, it can accurately identify the status of the vehicle display interface, abnormal function characteristics and indicator light status, realize accurate fault identification and efficient closed-loop handling, and greatly improve the intelligence level of vehicle fault diagnosis and repair.

[0033] This application constructs a stable two-way communication channel through wired communication links and wireless communication networks to ensure the reliability of short-range command interaction, high-speed data transmission, and remote data interaction; the multimodal sensing device can realize real-time acquisition, recognition, and voice feedback of natural language commands, forming a complete closed loop of perception, parsing, scheduling, execution, and feedback, comprehensively improving the adaptability, stability, and intelligence of the vehicle intelligent detection and maintenance system. Attached Figure Description

[0034] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0035] Figure 1 This is an architecture diagram of a vehicle intelligent detection and maintenance system provided by one or more embodiments of the present invention.

[0036] Figure 2 This is a flowchart of a vehicle intelligent detection and maintenance method provided by one or more embodiments of the present invention.

[0037] Figure 3 This is an architecture diagram of a vehicle intelligent detection and maintenance system provided by one or more embodiments of the present invention.

[0038] Figure 4 This is a flowchart of a vehicle intelligent detection and maintenance method provided by one or more embodiments of the present invention.

[0039] Figure 5 This is a block diagram of an electronic device for a vehicle intelligent detection and maintenance method provided in one or more embodiments of the present invention. Detailed Implementation

[0040] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0041] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the application. The singular forms “a,” “said,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0042] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0043] It should be understood that although the terms first, second, third, etc., may be used in the embodiments of this application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, first may also be referred to as second without departing from the scope of the embodiments of this application, and similarly, second may also be referred to as first.

[0044] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0045] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0046] It should be noted that any symbols and / or numbers present in the specification that are not marked in the accompanying drawings are not reference numerals.

[0047] Figure 1 This is an architecture diagram of a vehicle intelligent detection and maintenance system provided by one or more embodiments of the present invention.

[0048] like Figure 1 As shown, it includes:

[0049] The cloud control layer, edge scheduling layer, and terminal execution perception layer collaborate bidirectionally through communication links.

[0050] The cloud-based control layer includes a cloud service platform and a large-scale model voice interaction module. The cloud service platform is used to store all detection data, generate structured analysis reports, and maintain the fault matching database. The large-scale model voice interaction module is used to parse natural language commands into standardized control commands and generate voice feedback information.

[0051] The edge scheduling layer is an edge computing unit that serves as the core control hub of the system. It includes an actuator management module, a multi-source perception and analysis module, a process orchestration module, and a data interaction module, which are used for instruction parsing, terminal device scheduling, perception data processing, task process orchestration, and result aggregation and feedback.

[0052] The terminal execution perception layer includes multiple types of actuators, multimodal sensing devices, and vehicle-mounted controlled systems. The actuators are used to perform mechanical actions and vehicle triggering operations, the sensing devices are used to collect voice and visual data, and the vehicle-mounted controlled systems are used to respond to control commands and provide feedback on vehicle status.

[0053] Among them, the edge scheduling layer has a built-in dynamic adaptation detection algorithm that can automatically generate a detection path that adapts to the object being tested based on perception data; the large model voice interaction module is deeply coupled with the edge scheduling layer, which compiles natural language instructions into action sequences of the actuator.

[0054] In one embodiment, the fault matching database of the cloud service platform automatically matches anomaly detection data with repair solutions through a correlation analysis algorithm, and the accuracy of repair suggestions is not lower than a preset threshold.

[0055] In one embodiment, the multi-source perception analysis module includes a visual analysis unit for identifying status information and abnormal features of the vehicle display interface, as well as the status verification of specific function indicator lights.

[0056] In one embodiment, the multi-type actuator is equipped with a multimodal sensing sensor and an adaptive execution component to enable hardware status detection and adaptive maintenance operations.

[0057] In one embodiment, the multimodal sensing device includes a voice interaction terminal for acquiring natural language commands, recognizing them in real time, and generating voice feedback.

[0058] In one embodiment, the communication link includes a wired communication link and a wireless communication network, used for short-range command interaction, high-speed data transmission, and long-range data interaction, respectively.

[0059] Specifically, it adopts a three-layer collaborative architecture consisting of a cloud-based control layer, an edge scheduling layer, and a terminal execution and perception layer. Each layer independently performs its functions and operates in conjunction with each other through a two-way communication link, realizing the layered decoupling and modular deployment of control, scheduling, execution, and perception functions. Compared with traditional centralized detection systems, it has stronger scalability, higher operational stability, and more flexible function iteration, and can be adapted to detection and maintenance scenarios of multiple vehicle models and multiple devices.

[0060] By using the edge scheduling layer as the core control center of the system, instruction parsing, equipment scheduling, data processing and process orchestration are completed locally. Combined with the built-in dynamic adaptation detection algorithm, the system can automatically generate adaptation detection paths based on perception data, realize AI adaptive updates of detection logic, get rid of the dependence on manual writing and maintenance of test scripts, and truly achieve unmanned and automated operation of the entire chain from detection and analysis to report generation and fault self-inspection.

[0061] By deeply coupling the cloud-based large-scale model voice interaction module with the edge scheduling layer, natural language commands are standardized and procedurally compiled into action sequences of terminal actuators, realizing integrated closed-loop control of voice commands, edge scheduling, and mechanical execution. This supports the accurate implementation of complex operation and maintenance commands, significantly improving the interactive convenience and operational intelligence level of vehicle equipment detection and maintenance.

[0062] The cloud-based management layer is responsible for storing all data, generating structured reports, and maintaining the fault database. It uses correlation analysis algorithms to automatically match abnormal data with repair solutions, forming a collaborative model of real-time edge execution and intelligent cloud decision-making. This ensures real-time detection while achieving high accuracy and standardization in fault diagnosis and solution recommendation.

[0063] The terminal execution perception layer integrates multiple types of actuators, multimodal perception devices, and vehicle-mounted controlled systems to construct a complete control link of perception acquisition, edge analysis, terminal execution, and status feedback. In conjunction with units such as visual analysis and multimodal sensing, it enables accurate identification of hardware status and adaptive maintenance operations. While improving the accuracy of detection and maintenance, it further strengthens the collaborative execution capability of the three-layer architecture.

[0064] It is worth noting that although only some basic functional modules are disclosed in this embodiment, it does not mean that the composition of this system is limited to the above-mentioned basic functional modules. On the contrary, what this embodiment intends to express is that, based on the above-mentioned basic functional modules, those skilled in the art can arbitrarily add one or more functional modules in combination with existing technology to form an infinite number of embodiments or technical solutions. That is to say, this system is open rather than closed. The fact that this embodiment only discloses a few basic functional modules does not mean that the scope of protection of the claims of this invention is limited to the disclosed basic functional modules. At the same time, for the convenience of description, the above device is described separately according to its functions as various units and modules. Of course, in implementing this invention, the functions of each unit and module can be implemented in one or more software and / or hardware.

[0065] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0066] Figure 2 This is a flowchart of a vehicle intelligent detection and maintenance method provided by one or more embodiments of the present invention.

[0067] like Figure 2 As shown, it includes the following steps:

[0068] Step S1: Natural language commands are collected through the voice interaction terminal, parsed into standardized control commands by the large model voice interaction module, and sent to the edge computing unit;

[0069] In step S2, the edge computing unit generates an automated task flow through the process orchestration module, driving multiple types of actuators to perform corresponding actions;

[0070] Step S3: The multimodal sensing device collects vehicle status data, processes it, and generates detection results;

[0071] Step S4: The test results are summarized and sent back to the cloud service platform. The platform automatically generates a structured analysis report and associates fault repair suggestions, while outputting voice feedback through the voice interaction terminal.

[0072] In one embodiment, the edge computing unit automatically generates a detection path adapted to the object under test based on the sensing data using a dynamic adaptation detection algorithm.

[0073] Figure 3 This is an architecture diagram of a vehicle intelligent detection and maintenance system provided by one or more embodiments of the present invention.

[0074] like Figure 3 As shown, it includes: cloud, edge, terminal devices, actuators, sensing devices, and vehicle systems.

[0075] The cloud is used to store test data and generate test reports.

[0076] The edge is used as the core scheduling hub, responsible for actuator control (robotic arm / trigger), image recognition (SOS light / screen detection), process orchestration, test result aggregation and reporting;

[0077] Actuators include a 6-DOF robotic arm, a Bluetooth key trigger, and a brake pedal trigger;

[0078] The sensing devices include: high-definition cameras (monitoring the driver and passenger screens / instrument screens / SOS lights), and an ESP32 voice module (for voice command interaction);

[0079] The in-vehicle system includes: Vehicle Settings, a core functional module used to uniformly manage the vehicle's electronic and electrical configurations;

[0080] HVAC (Air Conditioning System Module) is a module responsible for maintaining vehicle interior temperature, ventilation, defrosting, and comfort.

[0081] Launcher (vehicle infotainment desktop / launcher) is used to manage user desktop interactions.

[0082] Figure 4 This is a flowchart of a vehicle intelligent detection and maintenance method provided by one or more embodiments of the present invention.

[0083] like Figure 4 As shown, specifically:

[0084] Instruction triggering phase

[0085] User voice commands: Users initiate test requests using natural language (such as "Start STR test").

[0086] ESP32 Voice Capture and Wake-up: The ESP32 voice module collects voice signals through the microphone to complete wake-up word detection and voice capture.

[0087] Speech recognition (STT, local / cloud): Converts speech signals into text commands using models such as SenseVoice, supporting local or cloud recognition modes.

[0088] Text instructions: Output standardized text instructions for subsequent large model parsing.

[0089] Qwen Large Model Instruction Parsing and Task Planning: Calls the Qwen 235B large model to perform intent recognition, task decomposition, and path planning on text instructions, generating executable test tasks.

[0090] Structured test instruction sequence: Convert the task planning results into machine-parseable structured instructions, such as unlock vehicle → power on → SOS light detection → multi-screen verification → lock vehicle.

[0091] via UART / Wi-Fi: Structured instructions are sent to the Jetson main controller via UART or Wi-Fi communication protocols.

[0092] Execution scheduling phase

[0093] Jetson Main Controller (Process Scheduling Engine): As the core scheduling unit, it synchronously drives the execution of test tasks in both main branches:

[0094] Actuator control branch:

[0095] Control the robotic arm to simulate screen clicks: Drive the 6-DOF robotic arm through MyCobotSDK to simulate user clicks, swipes and other operations on the vehicle's infotainment screen, used to switch test views or trigger functions.

[0096] Trigger the key / brake pedal to power on / off the vehicle: The Bluetooth key trigger and brake pedal trigger are driven by simple_servo_controller.py to complete operations such as unlocking, powering on, and locking the vehicle.

[0097] Execution status feedback: The operation results of the actuator (such as "unlocked successfully" or "power-on completed") are fed back to Jetson.

[0098] State detection branch:

[0099] Real-time camera capture: A camera connected via USB captures real-time images of key areas such as the driver and passenger screens, instrument panel, and SOS lights.

[0100] Visual model analysis (SOS light, screen content): Calls visual models such as sos_detection.py and screen_detect_view1.py, and uses image recognition and OCR technology to detect the SOS light status and screen display content (such as function prompts and parameter values).

[0101] Test result feedback: The visual analysis results (such as "SOS light is normal" and "multi-screen display is consistent") are fed back to Jetson.

[0102] Results aggregation stage

[0103] Jetson data aggregation and result judgment: The main_controller.py aggregates execution status feedback and detection results, and performs intelligent judgment based on preset rules (such as "if the SOS light is not lit, the test is deemed to have failed") to generate test conclusions.

[0104] Generate test reports: Organize test conclusions, anomalies, time consumption, and other information into standardized test reports.

[0105] The system is on standby awaiting the next instruction: After the test is completed, the system enters a low-power standby state, waiting for the next round of voice or remote instructions.

[0106] In another embodiment, it includes: a hardware layer, a communication layer, and an application layer;

[0107] Among them, the hardware layer

[0108] Jetson Platform: The core computing unit, integrating three core functions: actuator control (MyCobotSDK, simple_servo_controller.py), image recognition (sos_detection.py, screen_detect_view1.py), and process scheduling (main_controller.py).

[0109] ESP32 Voice Module: Responsible for voice interaction (microphone acquisition, SenseVoice recognition, TTS feedback) and linkage with large models (calling Qwen 235B to generate test commands).

[0110] End effectors include a 6-DOF robotic arm (simulating screen operation), a Bluetooth key trigger (unlocking / locking), and a brake pedal trigger (triggered when the vehicle is powered on).

[0111] Camera: Connects to Jetson via USB to capture real-time images from the vehicle's infotainment screen, SOS lights, etc.

[0112] Communication layer

[0113] UART: Used for instruction exchange between Jetson and ESP32, and the end effector.

[0114] USB: Used for video streaming between Jetson and the camera.

[0115] Application layer

[0116] Automated testing scenario: After receiving the ESP32 voice command, automatically execute the full-link test process of "unlocking → powering on → multi-screen detection → SOS light verification → locking and hibernation".

[0117] One of the specific tests on air conditioning systems includes the following steps:

[0118] Voice command trigger (e.g., "Start HVAC special test") → ESP32 recognition → Qwen large model generates module-level test sequence (e.g., "Automatic air conditioning → Dual-zone temperature control → Defrosting mode → Seat heating").

[0119] Jetson uses a robotic arm to simulate screen operations, triggering HVAC functions in sequence; simultaneously, a camera captures the status of the air conditioner screen and air vents, and a visual model analyzes temperature values, airflow direction, and blades.

[0120] Jetson aggregates execution status and test results to determine whether the function meets expectations (such as "dual-zone temperature difference ≤ 1℃"), generates a special test report, and provides voice feedback.

[0121] Figure 5 This is a block diagram of an electronic device for a vehicle intelligent detection and maintenance method provided in one or more embodiments of the present invention.

[0122] like Figure 5 As shown, this application provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0123] The memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of a vehicle intelligent detection and maintenance method.

[0124] This application also provides a computer-readable storage medium storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of a vehicle intelligent detection and maintenance method.

[0125] For the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0126] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0127] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A vehicle intelligent detection and maintenance system, characterized by, include: The cloud control layer, edge scheduling layer, and terminal execution perception layer collaborate bidirectionally through communication links. The cloud-based management and control layer includes a cloud service platform and a large-scale model voice interaction module. The cloud service platform is used to store full detection data, generate structured analysis reports, and maintain a fault matching database. The large-scale model voice interaction module is used to parse natural language commands into standardized control commands and generate voice feedback information. The edge scheduling layer is an edge computing unit that serves as the core control hub of the system. It includes an actuator management module, a multi-source perception and analysis module, a process orchestration module, and a data interaction module, which are used for instruction parsing, terminal device scheduling, perception data processing, task process orchestration, and result summary and feedback. The terminal execution perception layer includes multiple types of actuators, multimodal perception devices, and vehicle-mounted controlled systems. The actuators are used to perform mechanical actions and vehicle triggering operations, the perception devices are used to collect voice and visual data, and the vehicle-mounted controlled systems are used to respond to control commands and provide feedback on vehicle status. The edge scheduling layer automatically generates a detection path adapted to the object being tested based on the perception data; the large model voice interaction module is deeply coupled with the edge scheduling layer, compiling natural language instructions into action sequences of the actuator.

2. The vehicle intelligent detection and maintenance system according to claim 1, characterized in that, The fault matching database of the cloud service platform uses a correlation analysis algorithm to match anomaly detection data with repair solutions, and the repair suggestions obtained from the matching meet the preset accuracy requirements.

3. The vehicle intelligent detection and maintenance system according to claim 1, characterized in that, The multi-source perception and analysis module includes a visual analysis unit, which is used to identify the status information and abnormal features of the vehicle display interface, as well as the status verification of specific function indicator lights.

4. The vehicle intelligent detection and maintenance system according to claim 1, characterized in that, The various types of actuators are equipped with multimodal sensing sensors and adaptive execution components to achieve hardware status detection and adaptive maintenance operations.

5. The vehicle intelligent detection and maintenance system according to claim 1, characterized in that, The multimodal sensing device includes a voice interaction terminal, which is used to collect natural language commands, recognize them in real time, and generate voice feedback.

6. The vehicle intelligent detection and maintenance system according to claim 1, characterized in that, The communication link includes a wired communication link and a wireless communication network, which are used for short-range command interaction, high-speed data transmission, and long-range data interaction, respectively.

7. A vehicle intelligent detection and maintenance method, characterized in that, Includes the following steps: Natural language commands are collected through a voice interaction terminal, parsed into standardized control commands by the large model voice interaction module, and then sent to the edge computing unit. The edge computing unit generates automated task flows through the process orchestration module, driving various types of actuators to perform corresponding actions. Multimodal sensing devices collect vehicle status data, which is then processed to generate detection results; The test results are compiled and sent back to the cloud service platform, which automatically generates a structured analysis report and associates fault repair suggestions. At the same time, voice feedback is output through the voice interaction terminal.

8. The intelligent vehicle detection and maintenance method according to claim 7, characterized in that, The edge computing unit automatically generates a detection path adapted to the object being tested based on the sensing data using a dynamic adaptation detection algorithm.

9. An electronic device, characterized in that, include: The processor, communication interface, memory, and communication bus are connected, with the processor, communication interface, and memory communicating with each other via the communication bus. The memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the intelligent vehicle detection and maintenance method according to any one of claims 7-8.

10. A computer-readable storage medium, characterized in that, It stores a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of the intelligent vehicle detection and maintenance method according to any one of claims 7-8.

Images