Vehicle fault detection method, device and vehicle

Abstract

The application provides a vehicle fault detection method and device and a vehicle. The method comprises the following steps: in the process of driving the vehicle, a target instruction is sent to a target unmanned aerial vehicle device; the target instruction is used to instruct the target unmanned aerial vehicle device to collect target data; target data collected by the target unmanned aerial vehicle device and vehicle data collected by the vehicle are obtained; the vehicle data is used to indicate the vehicle state of the vehicle in the driving process; and a fault detection result of the vehicle is obtained based on the target data and the vehicle data. The method can improve the accuracy of vehicle fault detection.

Description

Technical Field

[0001] This application relates to the field of vehicles, and more specifically, to a vehicle fault detection method, apparatus, and vehicle in the field of vehicles. Background Technology

[0002] In existing technologies, when a vehicle malfunctions, manual inspection methods are typically used to detect the fault, or data is acquired and analyzed using onboard diagnostic devices. However, with the rapid development of the automotive industry and the widespread adoption of intelligent technologies, traditional manual inspection methods have low accuracy and cannot accurately detect vehicle malfunctions. Therefore, improving the accuracy of vehicle fault detection is a key technical problem that needs to be addressed. Summary of the Invention

[0003] This application provides a vehicle fault detection method, device, and vehicle. The method collects target data through an unmanned aerial vehicle (UAV) and obtains vehicle fault detection results based on the target data and vehicle data collected by the vehicle, thereby improving the accuracy of vehicle fault detection.

[0004] Firstly, a vehicle fault detection method is provided, the method comprising:

[0005] During vehicle operation, a target command is sent to the target drone device; the target command instructs the target drone device to collect target data; the target data includes target images; the target images include external images of the vehicle body and images of the driving environment within a preset range of the vehicle.

[0006] Acquire target data collected by the target drone equipment and vehicle data collected by the vehicle; among which, the vehicle data is used to indicate the vehicle status during the driving process;

[0007] Based on the target data and vehicle data, the vehicle fault detection results are obtained.

[0008] In the embodiments of this application, during vehicle operation, a target command is sent to the target drone device. The target command instructs the target drone device to collect target data. Therefore, upon receiving the target command, the target drone device begins collecting target data of the vehicle. The vehicle obtains the vehicle's fault detection result based on the target data collected by the target drone device and the vehicle data collected by the vehicle. Since the target drone device can fly around the vehicle, it can collect target data including images of the vehicle's exterior and the vehicle's driving environment. Therefore, this solution ensures that vehicle fault detection is based on more comprehensive detection data by using the target drone device to collect target data and the vehicle data collected by the vehicle. Furthermore, this solution uses external vehicle images and images of the vehicle's driving environment to detect external faults, ensuring that external fault detection information can be obtained by combining these images. It also uses vehicle data to detect internal faults, obtaining internal fault detection information. Because this solution can obtain both external target data and internal vehicle data, it can acquire more comprehensive detection data, thereby generating both external and internal fault detection information. This ensures more comprehensive and accurate fault detection results and improves the accuracy of vehicle fault detection.

[0009] In conjunction with the first aspect, some implementations of the first aspect also include:

[0010] Acquire first target data and first vehicle data when the vehicle is in a normal state; wherein, the first target data includes a first external image of the vehicle body;

[0011] Based on the target data and the vehicle data, the fault detection results of the vehicle are obtained, including:

[0012] First detection information is obtained based on the first similarity between the target data and the first target data; second detection information is obtained based on the second similarity between the vehicle data and the first vehicle data; and fault detection result is obtained based on the first detection information and the second detection information.

[0013] In the embodiments of this application, first target data and first vehicle data of a vehicle in a normal state are obtained; that is, if the vehicle is in a normal state, the target data of the vehicle is represented as the first target data, and the vehicle data of the vehicle is represented as the first vehicle data; first detection information is obtained based on the first similarity between the target data and the first target data; second detection information is obtained based on the second similarity between the vehicle data and the first vehicle data; fault detection results are obtained according to the first detection information and the second detection information; whether the vehicle is in a normal state is determined by the similarity, thereby determining whether the vehicle has a fault.

[0014] Combining the first aspect and the above implementation methods, in some implementation methods of the first aspect, the first detection information includes vehicle exterior detection information; based on the first similarity between the target data and the first target data, the first detection information is obtained, including:

[0015] The target image is compared with the first vehicle body exterior image. If there is an image region with a similarity less than a first preset threshold, the vehicle body exterior detection information is determined to indicate that there is a fault on the vehicle body exterior.

[0016] In conjunction with the first aspect and the above-described implementations, in some implementations of the first aspect, the target data includes vehicle emission data, and the first detection information includes emission detection information; the method further includes:

[0017] Obtain first emission data of the vehicle under normal conditions.

[0018] The first detection information obtained based on the first similarity between the target data and the first target data includes:

[0019] The emission data is compared with the first emission data. If the similarity between the emission data and the first emission data is less than the second preset threshold, the emission detection information indicates that the vehicle has an emission fault.

[0020] In the embodiments of this application, since the target image is used to detect the vehicle body and obtain external vehicle body detection information, when comparing the target image with the first external vehicle body image, the smaller the similarity, the greater the possibility of a fault in the external vehicle body. If there is an image region in the target image with a similarity less than a first preset threshold, it indicates that the vehicle body region indicated by that image region is abnormal, that is, it indicates a fault in the external vehicle body. Since the vehicle's emission data is used to detect the vehicle's emission performance and obtain emission detection information, when comparing the emission data with the first emission data, if the similarity is less than a second preset threshold, it indicates that the vehicle has an emission fault. By comparing the vehicle's target image and emission data with the first external vehicle body image and first emission data when the vehicle is in a normal state, it is ensured that first detection information including external vehicle body detection information and emission detection information can be obtained.

[0021] In conjunction with the first aspect and the above implementation methods, some implementation methods of the first aspect also include:

[0022] If the vehicle is equipped with a drone, the drone will be identified as the target drone.

[0023] If the vehicle is not equipped with drone equipment, an instruction signal is sent to a drone station within a preset distance of the vehicle, and the drone equipment identifier sent by the drone station is received; the drone equipment corresponding to the drone equipment identifier is identified as the target drone equipment; wherein, the instruction signal is used to instruct the drone station to dispatch drone equipment to perform fault detection on the vehicle.

[0024] In the embodiments of this application, if the vehicle is equipped with a drone device, the drone device on the vehicle is directly identified as the target drone device; if the vehicle is not equipped with a drone device, an instruction signal is sent to a drone station within a preset distance, and the drone device dispatched by the drone station is taken as the target drone device; this ensures that whether the vehicle is equipped with a drone device or not, target data can be collected through the drone device to achieve vehicle fault detection.

[0025] In conjunction with the first aspect and the above implementation methods, some implementation methods of the first aspect also include:

[0026] If a detection command is detected for a target component in the vehicle, the target location corresponding to the target component is determined; where the target location is the location where the target drone equipment collects target data.

[0027] Send target commands to the target drone equipment, including:

[0028] Send target commands and target location to the target drone device so that the target drone device can fly to the target location and collect target data.

[0029] In the embodiments of this application, the fault detection of the vehicle can be the fault detection of the entire vehicle or the fault detection of a target component in the vehicle; if a detection command for a target component in the vehicle is detected, the target position corresponding to the target component is determined; and the target command and target position are sent to the target drone device so that the target drone device flies to the target position and collects target data; so as to realize the fault detection of a specific target component in the vehicle.

[0030] In conjunction with the first aspect and the above implementation methods, some implementation methods of the first aspect also include:

[0031] If a detection command corresponds to at least two target components, the detection priority of the at least two target components is determined based on the degree of impact of the at least two target components on vehicle safety; wherein, the detection priority is positively correlated with the degree of impact.

[0032] The detection order is determined based on the detection priority;

[0033] Send target commands and target location to the target drone equipment, including:

[0034] Send target commands, target location, and detection order to the target drone equipment so that the target drone equipment can acquire target data in the detection order.

[0035] In the embodiments of this application, if the detection command corresponds to at least two target components, the detection order is determined based on the detection priority of the at least two target components, and the target command and detection order are sent to the target drone device, so that the target drone device collects target data according to the detection order when collecting target data; since the detection priority is positively correlated with the degree of impact of the target component on vehicle safety; for example, the detection priority of the vehicle headlight is higher than the detection priority of the vehicle exhaust pipe; therefore, the target data is acquired and fault detection is performed according to the detection priority; ensuring that vehicle components with a higher degree of impact on vehicle safety can be detected first.

[0036] In conjunction with the first aspect and the above implementation methods, some implementation methods of the first aspect also include:

[0037] Based on the target vehicle model, a solution database for vehicle faults is determined; the solution database includes the fault type of the vehicle fault and the corresponding solution for the fault type.

[0038] Based on the database of target fault types and solutions indicated by fault detection results, the solution corresponding to the target fault type is determined.

[0039] In the embodiments of this application, a solution database for vehicle faults is determined based on the target vehicle model. Since the solution database includes vehicle fault types and corresponding solutions, it is possible to determine the solution corresponding to the target fault type in the solution database based on the target fault type indicated by the fault detection result, ensuring that the corresponding solution can be obtained when the fault detection result indicates that the vehicle has a fault.

[0040] Secondly, a vehicle fault detection device is provided, the device comprising:

[0041] The sending module is used to send target commands to the target drone device during vehicle operation; wherein, the target commands are used to instruct the target drone device to collect target data; the target data includes target images; the target images include external images of the vehicle body and images of the driving environment within a preset range of the vehicle.

[0042] The acquisition module is used to acquire target data collected by the target drone equipment and vehicle data collected by the vehicle; among which, the vehicle data is used to indicate the vehicle status during the driving process.

[0043] The detection module is used to obtain vehicle fault detection results based on target data and vehicle data.

[0044] Thirdly, a vehicle is provided, including a memory and a processor, the memory for storing executable program code, and the processor for calling and running the executable program code from the memory, causing the vehicle to perform the methods of the first aspect or any possible implementation thereof.

[0045] Fourthly, a computer program product is provided, comprising: computer program code, which, when run on a computer, causes the computer to perform the methods described in the first aspect or any possible implementation thereof.

[0046] Fifthly, a computer-readable storage medium is provided that stores instructions which, when executed on a vehicle, cause the vehicle to perform the method described in the first aspect or any possible implementation thereof. Attached Figure Description

[0047] Figure 1 This is a schematic diagram of a scenario provided in an embodiment of this application;

[0048] Figure 2 This is a schematic flowchart of a vehicle fault detection method provided in an embodiment of this application;

[0049] Figure 3 This is a schematic flowchart of another vehicle fault detection method provided in the embodiments of this application;

[0050] Figure 4 This is a schematic flowchart of another vehicle fault detection method provided in the embodiments of this application;

[0051] Figure 5 This is a schematic diagram of the structure of a vehicle fault detection device provided in an embodiment of this application;

[0052] Figure 6 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application. Detailed Implementation

[0053] The technical solutions in this application will be clearly and thoroughly described below with reference to the accompanying drawings. In the description of the embodiments of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. "And / or" in the text 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. Furthermore, in the description of the embodiments of this application, "multiple" refers to two or more than two.

[0054] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0055] In existing technologies, when a vehicle malfunctions, manual inspection methods are typically used to detect the fault, or data is acquired and analyzed using onboard diagnostic devices. However, with the rapid development of the automotive industry and the widespread adoption of intelligent technologies, traditional manual inspection methods have low accuracy and cannot accurately detect vehicle malfunctions. Therefore, improving the accuracy of vehicle fault detection is a key technical problem that needs to be addressed.

[0056] In view of this, this application provides a vehicle fault detection method, device, and vehicle. Through the embodiments of this application, target data is collected by a drone, and vehicle fault detection results are obtained based on the target data and vehicle data collected by the vehicle, which can improve the accuracy of vehicle fault detection.

[0057] Figure 1 This is a schematic diagram of a scenario provided in an embodiment of this application.

[0058] For example, such as Figure 1 As shown, scenario 100 includes a vehicle 110 and a drone device 120. When the vehicle 110 is driving, it sends a target instruction to the drone device 120. The target instruction is used to instruct the drone device 120 to collect target data. After receiving the target instruction, the drone device 120 starts collecting target data and sends the collected target data to the vehicle so that the vehicle can perform fault detection based on the target data and the vehicle data acquired by the vehicle.

[0059] For example, when the vehicle 110 is in motion, the direction of movement of the drone device 120 is consistent with the direction of travel of the vehicle 110.

[0060] The following is about Figures 2 to 4 The vehicle fault detection method provided in the embodiments of this application will be described in detail.

[0061] Figure 2 This is a schematic flowchart of a vehicle fault detection method provided in an embodiment of this application.

[0062] For example, Figure 2 The method 200 shown can be executed by vehicle 110; or it can be executed by a processor or chip in vehicle 110.

[0063] like Figure 2As shown, the vehicle fault detection method 200 includes S210 to S230, and S210 to S230 are described in detail below.

[0064] S210 sends target commands to the target drone equipment while the vehicle is in motion.

[0065] The target instruction is used to instruct the target UAV equipment to collect target data; the target data includes target images; the target images include external images of the vehicle body and images of the vehicle's driving environment within a preset range; that is, the target images include images of the vehicle body and images of the vehicle's driving environment; the images of the vehicle body and images of the vehicle's driving environment are used to determine whether there are faults on the surface of the vehicle body and the external structure of the vehicle.

[0066] For example, the target drone is equipped with a high-definition camera for acquiring target images; when the target drone receives a target command sent by the vehicle, the target drone begins to acquire target data; the vehicle and the target drone can use high-speed wireless communication technology in the prior art to ensure real-time data transmission and command control between the drone and the vehicle.

[0067] Alternatively, the high-definition camera used to capture images may employ wide dynamic range technology to ensure that relatively clear images are captured in high-contrast environments (such as shaded areas under direct sunlight).

[0068] It should be noted that the drone in this application embodiment can be a drone device mounted on a vehicle or a drone device at a drone station.

[0069] In one implementation, if the vehicle is equipped with a drone device, the drone device is identified as the target drone device.

[0070] If the vehicle is not equipped with drone equipment, an instruction signal is sent to a drone station within a preset distance of the vehicle, and the drone equipment identifier sent by the drone station is received; the drone equipment corresponding to the drone equipment identifier is identified as the target drone equipment; wherein, the instruction signal is used to instruct the drone station to dispatch drone equipment to perform fault detection on the vehicle.

[0071] For example, if the vehicle is equipped with a drone device (e.g., a vehicle-mounted drone device), the drone device on the vehicle is identified as the target drone device; if the vehicle is not equipped with a drone device, when it is necessary to use a drone to detect vehicle faults, an instruction signal is sent to a drone station within a preset distance (e.g., 300m); when the drone station receives the instruction signal, it dispatches the drone device to the location of the vehicle and collects the target data of the vehicle.

[0072] For example, a drone station is a management station for drone equipment, containing multiple drone devices capable of malfunction detection for auxiliary vehicles. When a vehicle sends an instruction signal to the drone station, the station dispatches the drone based on its status information and simultaneously sends the drone's identifier to the vehicle. The vehicle then establishes a communication connection with the drone based on the identifier. The drone's status information includes its battery level and idle status; the drone station prioritizes dispatching fully charged, idle drones to detect malfunctions in the vehicle.

[0073] In the embodiments of this application, if the vehicle is equipped with a drone device, the drone device on the vehicle is directly identified as the target drone device; if the vehicle is not equipped with a drone device, an instruction signal is sent to a drone station within a preset distance, and the drone device dispatched by the drone station is taken as the target drone device; this ensures that whether the vehicle is equipped with a drone device or not, target data can be collected through the drone device to achieve vehicle fault detection.

[0074] Optionally, the structure and performance of the target drone equipment can be improved to enable it to better collect target data. Specifically, this includes: adopting a multi-rotor design to ensure stable flight even in complex environments (such as strong winds and rain); using lightweight, high-strength carbon fiber composite materials for the fuselage to reduce its weight; designing a collision protection shield and landing buffer device on the fuselage to ensure its safety; and integrating a navigation system into the target drone equipment, combined with visual recognition technology, to achieve high-precision positioning and autonomous navigation.

[0075] For example, the target drone equipment adopts a standardized interface, and all data acquisition detection devices (e.g., high-definition cameras, temperature sensors, etc.) are designed with standardized electrical and data interfaces; and additional interfaces and power supplies are reserved in the target drone equipment to enable the installation of other types of sensors, such as radar thickness gauges, ultraviolet fluorescence detectors, etc., to adapt to the fault detection needs of different vehicle models and vehicles.

[0076] It should be noted that when performing fault detection on a vehicle, it can be done on the entire vehicle or on a specific component within the vehicle.

[0077] In one implementation, if a detection command for a target component in a vehicle is detected, the target location corresponding to the target component is determined; wherein, the target location is the location where the target drone device collects target data; a target command and the target location are sent to the target drone device so that the target drone device flies to the target location and collects target data.

[0078] For example, the detection command for the target component of the vehicle can be triggered through the vehicle's central control screen, or it can be triggered through the driver's voice control command. If the detection command for the target component of the vehicle is detected, the target position of the target component of the vehicle is determined, and the target command and target position are sent to the target drone device. The target command is used to instruct the drone to collect target data, and the target position is used to instruct the drone to collect target data at the location where the target data is collected.

[0079] For example, if the driver selects to inspect the vehicle's exhaust pipe on the vehicle's central control screen, the vehicle sends a target command and the exhaust pipe's location information to the target drone device, causing the target drone device to fly to the location of the exhaust pipe and collect the target data of the exhaust pipe; if a command to inspect the vehicle's headlights is detected, the vehicle sends the vehicle's headlights' location information to the target drone device, causing the target drone device to fly to the location of the vehicle's headlights and collect the target data of the vehicle's headlights.

[0080] It should be noted that the above is an example of the detection component, and this application does not limit it.

[0081] In the embodiments of this application, the fault detection of the vehicle can be the fault detection of the entire vehicle or the fault detection of a target component in the vehicle; if a detection command for a target component in the vehicle is detected, the target position corresponding to the target component is determined; and the target command and target position are sent to the target drone device so that the target drone device flies to the target position and collects target data; thereby realizing the detection of the target component in the vehicle.

[0082] In one implementation, if a detection command corresponds to at least two target components, the detection priority of the at least two target components is determined based on the degree of influence of the at least two target components on vehicle safety; wherein, the detection priority is positively correlated with the degree of influence.

[0083] Based on detection priority, the detection order is determined; target instructions, target location, and detection order are sent to the target UAV equipment so that the target UAV equipment can acquire target data in the detection order.

[0084] For example, if a detection command corresponds to at least two target components, the detection priority of the at least two target components is determined based on their impact on vehicle safety; that is, the greater the impact of a target component on vehicle safety, the higher its detection priority; the detection order is then determined based on the detection priority. For example, the impact of a vehicle's headlights on vehicle safety is greater than that of its exhaust pipe; therefore, if the target components are the vehicle's headlights and exhaust pipe, the detection priority of the headlights is higher than that of the exhaust pipe; target data is acquired and fault detection is performed according to the detection priority; ensuring that vehicle components with a higher impact on vehicle safety are detected first.

[0085] S220 acquires target data collected by the target drone equipment and vehicle data collected by the vehicle.

[0086] The target data can be the target data of the whole vehicle or the target data of the target component in the vehicle; vehicle data is used to indicate the vehicle status during the driving process; for example, vehicle data includes: engine-related data, driving and braking data, transmission and chassis data, electrical and electronic system data, body and safety data, etc.

[0087] Specifically, engine-related data includes: engine speed, torque, ignition status, and fuel injection; driving and braking data includes vehicle speed, mileage, and braking system status; transmission and chassis data includes gear information, transmission oil temperature, oil pressure, tire data, and the status of the suspension system's shock absorbers; electrical and electronic system data includes battery status, lighting system status, and air conditioning system status; and vehicle body and safety data includes: seat belt usage, airbag status, and the status of the vehicle's anti-lock braking system.

[0088] S230 obtains vehicle fault detection results based on target data and vehicle data.

[0089] For example, vehicle fault detection is performed based on target data collected by drones and vehicle data collected by vehicles to obtain fault detection results; the process of obtaining fault detection results is described in detail below.

[0090] For example, the target data includes images of the vehicle's exterior, images of the driving environment within a preset range, and vehicle emission data; wherein, the images of the vehicle's exterior and the images of the driving environment within the preset range are used for fault detection of the vehicle's exterior; and the emission data and vehicle data are used for fault detection of the vehicle's interior.

[0091] For example, images of the vehicle's driving environment can affect fault detection on the vehicle's exterior. For instance, there may be areas on the vehicle's surface that are obscured by shadows, such as the shadows of trees. If fault detection on the exterior of the vehicle is performed based on images of the vehicle's exterior, the shadowed areas may be misidentified as areas with faults. Therefore, by combining images of the vehicle's driving environment with images of the vehicle's exterior, it is possible to obtain image information of the vehicle's surface more accurately, thereby enabling more accurate fault detection on the exterior of the vehicle.

[0092] In one implementation, first target data and first vehicle data of the vehicle in a normal state are acquired;

[0093] The above-mentioned vehicle fault detection results, based on target data and vehicle data, include:

[0094] First detection information is obtained based on the first similarity between the target data and the first target data; second detection information is obtained based on the second similarity between the vehicle data and the first vehicle data; and fault detection result is obtained based on the first detection information and the second detection information.

[0095] For example, first target data and first vehicle data of a vehicle in normal condition are acquired; that is, if the vehicle is in normal condition, the target data of the vehicle is represented as the first target data, and the vehicle data of the vehicle is represented as the first vehicle data; first detection information is obtained based on the first similarity between the target data and the first target data; second detection information is obtained based on the second similarity between the vehicle data and the first vehicle data; fault detection result is obtained based on the first detection information and the second detection information; that is, the similarity determines whether the vehicle is in normal condition, thereby determining whether the vehicle has a fault; if the similarity is higher, it indicates that the probability of the vehicle having a fault is lower, and if the similarity is lower, it indicates that the probability of the vehicle having a fault is higher.

[0096] For example, since the first detection information is used to represent fault detection information outside the vehicle body, and the second detection information is used to represent fault detection information inside the vehicle, the internal and external faults of the vehicle are determined by combining the first detection information and the second detection information.

[0097] Optionally, the first detection information and the second detection information can be directly determined as the vehicle's fault detection result; that is, the external fault detection result and the internal fault detection result of the vehicle can be determined respectively; or, the first detection information and the second detection information can be comprehensively analyzed to determine the vehicle's fault detection result.

[0098] For example, if the first detection information indicates that the vehicle has an emission fault; if the second detection information indicates that the vehicle's fuel injection is abnormal, it is inferred that the vehicle's emission fault is caused by a problem with the vehicle's fuel system; if the second detection information indicates that the vehicle's engine speed or torque is abnormal, it is inferred that the vehicle's emission fault is caused by a mechanical fault in the engine.

[0099] In one implementation, the first detection information includes vehicle exterior detection information; based on a first similarity between the target data and the first target data, the first detection information is obtained, including:

[0100] The target image is compared with the first vehicle body exterior image. If there is an image region with a similarity less than a first preset threshold, the vehicle body exterior detection information is determined to indicate that there is a fault on the vehicle body exterior.

[0101] For example, similarity can be determined by comparing the pixel values ​​of the target image with those of the first vehicle exterior image; where pixel value refers to the brightness and color information of the pixels that make up the image; for example, pixel value can be RGB value; by calculating the similarity between the pixel values ​​of the target image and the first vehicle exterior image, the similarity between the target image and the first vehicle exterior image can be determined.

[0102] Specifically, the target image and the first vehicle exterior image are first adjusted to the same size. Each pixel of each image is traversed row by row and column by column to obtain the pixel value at each pixel position, that is, the RGB value of each pixel. For pixels at the same position, the difference between each color channel of the pixel value of the target image and the first vehicle exterior image is calculated. The difference values ​​at all pixel positions are accumulated. The accumulated difference value is normalized by dividing by the total number of pixels to obtain a similarity score. The smaller the score, the greater the similarity.

[0103] Optionally, similarity can be determined by matching the feature information of the images. Feature extraction is performed on the target image and the first vehicle exterior image to identify different regions and feature information in the images. The feature information of different regions in the target image is compared with the feature information of different regions in the first vehicle exterior image to calculate the matching degree of the feature information. The higher the matching degree of the feature information, the higher the similarity. Thus, the similarity between the target image and the first vehicle exterior image is determined.

[0104] It should be noted that the above is an example of calculating image similarity, and this application does not specifically limit the method for calculating image similarity.

[0105] In one implementation, the target data includes vehicle emission data, and the first detection information includes emission detection information; the first emission data of the vehicle in normal condition is obtained; the emission data is compared with the first emission data, and if the similarity between the emission data and the first emission data is less than a second preset threshold, the emission detection information is determined to indicate that the vehicle has an emission fault.

[0106] For example, the target drone is equipped with a gas analyzer that uses a high-precision sensor array to detect various gas components, including but not limited to carbon monoxide (CO), nitrogen oxides (NOx), and hydrocarbons (HC), ensuring a comprehensive assessment of the vehicle's emissions performance. The emissions data acquired by the target drone can be the concentration of different gas components in the vehicle's exhaust. The vehicle compares this emissions data with first emissions data. Since the first emissions data represents emissions under normal vehicle conditions, if the similarity between the emissions data and the first emissions data is less than a second preset threshold, it indicates an emissions malfunction in the vehicle.

[0107] Optionally, the vehicle generates an emission trend map based on the acquired historical emission data; the emission trend map is used to represent the concentration change trend of each gas component in the emission data, so as to help users monitor changes in vehicle emission performance and discover potential problems in a timely manner.

[0108] In the embodiments of this application, since the target image is used to detect the vehicle body and obtain external vehicle body detection information, when comparing the target image with the first external vehicle body image, the lower the similarity, the greater the possibility of a fault in the vehicle body's exterior. If there is an image region in the target image with a similarity less than a first preset threshold, it indicates a fault in the vehicle body's exterior. Similarly, since the vehicle's emission data is used to detect the vehicle's emission performance and obtain emission detection information, when comparing the emission data with the first emission data, if the similarity is less than a second preset threshold, it indicates an emission fault in the vehicle. By comparing the vehicle's target image and emission data with the first external vehicle body image and first emission data when the vehicle is in a normal state, it is ensured that first detection information including external vehicle body detection information and emission detection information can be obtained.

[0109] In one possible implementation, the target data also includes temperature data, sound data, and vibration data; the vehicle's temperature data is collected by an infrared thermal imager configured in the target drone equipment; and the vehicle's sound data and vibration data are obtained by sound and vibration sensors configured in the target drone equipment.

[0110] For example, the first detection information also includes temperature detection information. The vehicle acquires temperature data of the vehicle body area collected by the target drone equipment, compares the temperature data with the vehicle's preset temperature model, and determines the abnormal temperature area of ​​the vehicle, thus obtaining the temperature detection information of the vehicle.

[0111] Optionally, temperature data of the vehicle body area can be marked and displayed in the target image to provide users with a more intuitive view of the fault and facilitate the identification of abnormal temperature areas in the vehicle.

[0112] For example, the first detection information also includes sound detection information: the vehicle acquires sound data and vibration data collected by the target drone equipment; the sound data and vibration data are filtered to remove interference from environmental noise (such as wind noise, road noise, etc.); ensuring that the mechanical vibration and abnormal sounds of the vehicle during operation can be accurately acquired; a preset algorithm (e.g., fast Fourier transform algorithm) is used to perform spectrum analysis on the sound data and vibration data to identify characteristic signals in different frequency bands; and the characteristic signals are compared with the characteristic signals of the sound data and vibration data under normal vehicle conditions to determine the abnormal components of the vehicle, thus obtaining the sound detection information of the vehicle.

[0113] In the embodiments of this application, vehicle fault detection is performed using multi-dimensional data to ensure a more comprehensive fault detection. When generating fault detection results, the data of each dimension can be analyzed separately to obtain preliminary fault diagnosis conclusions. Then, multiple preliminary fault diagnosis conclusions are combined using methods such as weighted summation or Bayesian fusion to obtain the final fault diagnosis result.

[0114] Optionally, target data and vehicle data are uploaded to the cloud; the target data and vehicle data are processed through the cloud data center; and multiple algorithms such as deep learning and machine learning are integrated to analyze the target data and vehicle data, automatically identify and generate vehicle fault detection results.

[0115] In one implementation, a solution database for vehicle faults is determined based on the target vehicle model; wherein, the solution database includes the fault type of the vehicle fault and the corresponding solution for the fault type;

[0116] Based on the database of target fault types and solutions indicated by fault detection results, the solution corresponding to the target fault type is determined.

[0117] For example, different vehicle models require different solutions for different faults; therefore, a solution database for vehicle faults is determined based on the target vehicle model. This database includes the vehicle's fault types and corresponding solutions. It ensures that the solution corresponding to the target fault type indicated by the fault detection results can be determined from the solution database. It also ensures that when the fault detection results indicate a vehicle fault, the corresponding solution can be obtained. For example, the solution database can be shown in Table 1.

[0118] Table 1

[0119] Fault type Solution Fault 1 Solution 1 Fault 2 Solution 2 …… ……

[0120] For example, if the target fault type indicated by the fault detection result is fault 1, then the corresponding solution is solution 1; if the target fault type indicated by the fault detection result is fault 2, then the corresponding solution is solution 2. It should be noted that the solution database is updated as fault data accumulates.

[0121] In the above embodiments, the vehicle obtains fault detection results based on target data collected by the target drone equipment and vehicle data collected by the vehicle. Since the target drone equipment can fly around the vehicle, it can collect images including the vehicle's exterior, the vehicle's driving environment, and the vehicle itself. Therefore, this solution ensures that fault detection is based on more comprehensive detection data by using target data collected by the target drone equipment and vehicle data collected by the vehicle. Furthermore, this solution uses both external vehicle images and driving environment images to perform external fault detection, ensuring that external fault detection information is obtained by combining these images. Similarly, it uses vehicle emission data and vehicle data to perform internal fault detection, obtaining internal fault detection information. Because this solution can obtain both external target data and internal vehicle data, it can acquire more comprehensive detection data, thereby generating both external and internal fault detection information, ensuring more comprehensive and accurate fault detection results, and improving the accuracy of vehicle fault detection.

[0122] Figure 3 This is a schematic flowchart of another vehicle fault detection method provided in the embodiments of this application.

[0123] For example, Figure 3 The method 300 shown can be executed by vehicle 110; or it can be executed by a processor or chip in vehicle 110.

[0124] like Figure 3As shown, the vehicle fault detection method 300 includes S301 to S310, and S301 to S310 are described in detail below.

[0125] S301, the vehicle sends target commands to the target drone equipment.

[0126] Alternatively, the implementation of S301 can be found in [reference needed]. Figure 2 The relevant description of S210 will not be repeated here.

[0127] S302, acquire target data collected by the target drone equipment and vehicle data collected by the vehicle.

[0128] Alternatively, the implementation of S302 can be found in [reference needed]. Figure 2 The relevant description of S220 will not be repeated here.

[0129] S303, acquire the first target data and the first vehicle data.

[0130] For example, the first target data and the first vehicle data can be pre-stored in the vehicle; the first target data is the target data of the vehicle in a normal state; the first vehicle data is the vehicle data of the vehicle in a normal state during driving; the first target data includes a first vehicle body exterior image and first emission data.

[0131] S304, determine the first similarity between the target data and the first target data.

[0132] For example, the similarity between the target image in the target data and the first vehicle exterior image is determined, as well as the similarity between the emission data in the target data and the first emission data.

[0133] For example, the similarity between a target image and a first vehicle exterior image can be determined by comparing pixel values. First, the target image and the first vehicle exterior image are adjusted to the same size. Then, each pixel in each image is traversed row by row and column by column to obtain the pixel value at each pixel position, i.e., the RGB value of each pixel. For pixels at the same position, the difference between each color channel of the pixel value of the target image and the first vehicle exterior image is calculated. The difference values ​​at all pixel positions are then accumulated. The accumulated difference value is normalized by dividing by the total number of pixels to obtain a similarity score. The smaller the score, the greater the similarity.

[0134] For example, the similarity between the emission data and the first emission data can be determined by the difference in the concentration of each gas component in the emission data and the first emission data; the concentration difference of each gas component is calculated one by one, and the smaller the difference, the greater the similarity.

[0135] It should be noted that the above is an example of a method for calculating similarity, and this application does not limit it.

[0136] S305, determine the first detection information based on the first similarity.

[0137] For example, the first detection information includes vehicle exterior detection information and vehicle emission detection information; if there is an image region with a similarity less than a first preset threshold, the vehicle exterior detection information is determined to indicate a fault in the vehicle exterior; if the emission data and the first emission data have a similarity less than a second preset threshold, the emission detection information is determined to indicate an emission fault in the vehicle.

[0138] S306, determine the second similarity between the vehicle data and the first vehicle data.

[0139] For example, the difference between each data point in the vehicle data and each data point in the first vehicle data is calculated; the smaller the difference, the greater the similarity; for example, if the vehicle data includes the oil temperature and oil pressure of the vehicle's transmission, then the first oil temperature and first oil pressure at the current vehicle speed under normal vehicle conditions are obtained; the vehicle's oil temperature is compared with the first oil temperature, and the vehicle's oil pressure is compared with the first oil pressure; the corresponding similarity is determined.

[0140] S307, Determine the second detection information based on the second similarity.

[0141] For example, if the similarity of the data containing the target item in the vehicle data is less than a third preset threshold, then the second detection information is determined to be that the device corresponding to the target item is faulty. For instance, if the similarity between the oil temperature and the first oil temperature in the vehicle data is less than a third preset threshold, or the similarity between the oil pressure and the first oil pressure in the vehicle data is less than a third preset threshold, then the device corresponding to the oil temperature and oil pressure is determined to be faulty; that is, the second detection information is determined to be that the vehicle's transmission is faulty.

[0142] S308, based on the first detection information and the second detection information, the fault detection result is obtained.

[0143] For example, the fault indicated by the first detection information and the fault indicated by the second detection information are determined; the fault information is analyzed comprehensively to determine the fault detection result; for example, if the first detection information indicates that the vehicle has an emission fault; if the second detection information indicates that the vehicle's fuel injection is abnormal, then it is inferred that the vehicle's fault detection result is a vehicle emission fault caused by a problem with the vehicle's fuel system; if the second detection information indicates that the vehicle's engine speed or torque is abnormal, then it is inferred that the vehicle's fault detection result is a vehicle emission fault caused by an engine mechanical fault.

[0144] It should be noted that the above are examples of fault detection results, and this application does not limit them.

[0145] S309, a database for identifying solutions to vehicle malfunctions.

[0146] For example, since different vehicle models have different solutions for the same fault, a solution database for vehicle faults is determined based on the target vehicle model. The solution database includes the vehicle fault type and the corresponding solution.

[0147] S310 determines the corresponding solution based on the fault type indicated by the fault detection results.

[0148] Alternatively, the implementation of S310 can be found in [reference needed]. Figure 2 The relevant description of S230 will not be repeated here.

[0149] In the embodiments of this application, target data collected by the target UAV equipment and vehicle data collected by the vehicle are obtained to ensure that more comprehensive detection data can be obtained when the vehicle is being fault-detected. The target data and vehicle data are compared with the target data and vehicle data under normal vehicle conditions to determine the similarity, thereby determining the vehicle fault detection result. The smaller the similarity, the greater the difference between the vehicle and the normal vehicle condition, which means that the vehicle is more likely to have a fault. Through the similarity, it is ensured that the vehicle is in a normal condition, thereby obtaining the vehicle fault detection result.

[0150] Figure 4 This is a schematic flowchart of another vehicle fault detection method provided in the embodiments of this application.

[0151] For example, Figure 4 The method 400 shown can be executed by vehicle 110; or it can be executed by a processor or chip in vehicle 110.

[0152] like Figure 4 As shown, the vehicle fault detection method 400 includes S401 to S408, and S401 to S408 are described in detail below.

[0153] S401, a detection command for a target component in the vehicle has been detected.

[0154] For example, vehicle fault detection can be performed on the entire vehicle or on a specific target component within the vehicle. If a detection command for a target component is detected, it indicates that fault detection is currently being performed on that target component. Optionally, the implementation of S401 can be found in [reference needed]. Figure 3 The relevant description of S310 will not be repeated here.

[0155] S402, check if the command corresponds to multiple target components; if yes, execute S403; if no, execute S405.

[0156] For example, determine whether the detection command corresponds to multiple target components; if so, determine the detection order according to the detection priority of the target components; if not, directly obtain the target position of the target component.

[0157] S403, determine the inspection sequence based on the inspection priority of the target component.

[0158] For example, the detection priority is positively correlated with the degree of impact of the target component on vehicle safety; the higher the degree of impact of the target component on vehicle safety, the higher the detection priority of the target component; for example, the detection priority of the vehicle's headlights is higher than the detection priority of the vehicle's exhaust pipe.

[0159] S404 sends the detection sequence to the target drone equipment.

[0160] For example, the detection sequence is used to indicate the order in which the target drone collects target data.

[0161] S405, Obtain the target position of the target component.

[0162] For example, if the detection instruction corresponds to multiple target components, then the target position of each of the multiple target components is obtained; if the detection instruction corresponds to one target component, then the target position of that target component is obtained.

[0163] S406 sends target commands and target location to the target drone equipment.

[0164] For example, the target command is used to instruct the target drone equipment to collect target data; the vehicle sends the target command and target location to the target drone equipment.

[0165] S407: Acquire target data collected by the target drone equipment.

[0166] Alternatively, the implementation of S407 can be found in [reference needed]. Figure 2 The relevant description of S220 will not be repeated here.

[0167] S408, based on target data and vehicle data, obtains fault detection results.

[0168] For example, the implementation of S408 can be found in [reference needed]. Figure 3 The relevant descriptions of the embodiments in S304 to S308 are not repeated here.

[0169] Optionally, after obtaining the fault detection results, a solution database for vehicle faults is determined based on the vehicle model; and the corresponding solution is determined according to the fault type indicated by the fault detection results and the solution database.

[0170] In the embodiments of this application, the number of target components indicated by the detection command is determined; target data is acquired based on the location of the target components; and it is ensured that components in the vehicle can be detected. Since the detection priority is positively correlated with the degree of impact of the target components on vehicle safety when multiple target components exist, target data is acquired and fault detection is performed according to the detection priority; this ensures that vehicle components with a higher degree of impact on vehicle safety can be detected first.

[0171] It should be noted that the target drone equipment in this solution can use high-energy-density lithium polymer batteries to provide long-term endurance. When acquiring target data, the flight strategy (such as flight speed, altitude, and route) is automatically adjusted according to the target drone equipment's flight mission and remaining power to optimize energy use efficiency. If the target drone equipment is low on power, it can be quickly charged by a vehicle to improve operational efficiency.

[0172] The above text combined Figures 1 to 4 The vehicle fault detection method provided in the embodiments of this application has been described in detail; the following will be combined with Figure 5 and Figure 6 The apparatus embodiments of this application are described in detail below. It should be understood that the apparatus in the embodiments of this application can perform the various methods described in the foregoing embodiments of this application, that is, the specific working processes of the various products described below can be referred to the corresponding processes in the foregoing method embodiments.

[0173] Figure 5 This is a schematic diagram of the structure of a vehicle fault detection device provided in an embodiment of this application.

[0174] For example, such as Figure 5 As shown, the vehicle fault detection device 500 includes:

[0175] The sending module 510 is used to send target instructions to the target drone device during vehicle operation; wherein, the target instructions are used to instruct the target drone device to collect target data; the target data includes target images; the target images include external images of the vehicle body and images of the driving environment within a preset range of the vehicle.

[0176] The acquisition module 520 is used to acquire target data collected by the target drone equipment and vehicle data collected by the vehicle; wherein, the vehicle data is used to indicate the vehicle status during the driving process.

[0177] The detection module 530 is used to obtain vehicle fault detection results based on target data and vehicle data.

[0178] Optionally, as an embodiment, the acquisition module 520 is further configured to: acquire first target data and first vehicle data when the vehicle is in a normal state; wherein, the first target data includes a first vehicle body exterior image;

[0179] The detection module 530 is specifically used for: obtaining first detection information based on the first similarity between the target data and the first target data; obtaining second detection information based on the second similarity between the vehicle data and the first vehicle data; and obtaining a fault detection result based on the first detection information and the second detection information.

[0180] Optionally, as an embodiment, the detection module 530 is specifically used to: compare the target image with the first vehicle body exterior image, and if there is an image region with a similarity less than a first preset threshold, determine that the vehicle body exterior detection information indicates that there is a fault on the exterior of the vehicle body.

[0181] Optionally, as an embodiment, the acquisition module 520 is further configured to: acquire first emission data of the vehicle under normal conditions;

[0182] The detection module 530 is specifically used to: compare the emission data with the first emission data; if the similarity between the emission data and the first emission data is less than a second preset threshold, determine that the emission detection information indicates that the vehicle has an emission fault.

[0183] Optionally, as an embodiment, it further includes a determining module, which is specifically used for: if the vehicle is equipped with a drone device, determining the drone device as the target drone device; if the vehicle is not equipped with a drone device, sending an indication signal to a drone station within a preset distance of the vehicle, and receiving the drone device identifier sent by the drone station; determining the drone device corresponding to the drone device identifier as the target drone device; wherein, the indication signal is used to instruct the drone station to dispatch a drone device to perform fault detection on the vehicle.

[0184] Optionally, as an embodiment, the determining module is further configured to: if a detection command for a target component in the vehicle is detected, determine the target location corresponding to the target component; wherein, the target location is the location where the target drone device collects target data;

[0185] The sending module 510 is specifically used to send target commands and target locations to the target UAV device, so that the target UAV device can fly to the target location and collect target data.

[0186] Optionally, as an embodiment, the determining module is further configured to: if the detection command corresponds to at least two target components, determine the detection priority of at least two target components based on the degree of influence of the at least two target components on vehicle safety; wherein the detection priority is positively correlated with the degree of influence; and determine the detection order based on the detection priority;

[0187] The sending module 510 is specifically used to send target instructions, target location and detection order to the target UAV equipment so that the target UAV equipment can acquire target data in the detection order.

[0188] Optionally, as an embodiment, the determining module is further configured to: determine a solution database for vehicle faults based on the target vehicle model; wherein the solution database includes the fault type of the vehicle fault and the corresponding solution for the fault type; and determine the solution corresponding to the target fault type based on the target fault type indicated by the fault detection result and the solution database.

[0189] It should be noted that the aforementioned vehicle fault detection device is embodied in the form of functional units. The term "module" here can be implemented in software and / or hardware, without specific limitations.

[0190] For example, a "module" can be a software program, hardware circuit, or a combination of both that implements the above functions. Hardware circuits may include application-specific integrated circuits (ASICs), electronic circuits, processors (e.g., shared processors, proprietary processors, or group processors) and memory for executing one or more software or firmware programs, combined logic circuits, and / or other suitable components that support the described functions.

[0191] Therefore, the units of the various examples described in the embodiments of this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0192] Figure 6 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application.

[0193] For example, vehicle 600 includes processor 610, memory 620 and executable program code 630.

[0194] For example, vehicle 600 includes one or more processors 610 that can support vehicle 600 in implementing the vehicle fault detection method in the method embodiment. Processor 610 can be a general-purpose processor or a special-purpose processor. For example, processor 610 can be a central processing unit (CPU), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, such as discrete gates, transistor logic devices, or discrete hardware components.

[0195] For example, processor 610 can be used to control vehicle 600, execute software programs, and process data from the software programs. Vehicle 600 may also include a communication unit for receiving and transmitting signals.

[0196] For example, the vehicle 600 may include one or more memories 620, on which executable program code 630 is stored. The executable program code 630 can be run by the processor 610 to generate instructions, causing the processor 610 to execute the vehicle fault detection method described in the above method embodiments according to the instructions.

[0197] Optionally, the memory 620 may also store data. Optionally, the processor 610 may also read data stored in the memory 620, which may be stored at the same memory address as the executable program code 630, or the data may be stored at a different memory address than the executable program code 630.

[0198] For example, the processor 610 and memory 620 can be configured separately or integrated together, for example, integrated on a system-on-chip (SOC) of the terminal device.

[0199] For example, the memory 620 can be used to store related programs of the vehicle fault detection method provided in the embodiments of this application. The processor 620 can be used to call the executable program code 630 stored in the memory 620 when controlling the vehicle to execute the vehicle fault detection method of the embodiments of this application. For example, during vehicle operation, a target instruction is sent to the target drone device. The target instruction is used to instruct the target drone device to collect target data. The target data includes target images. The target images include external images of the vehicle body and driving environment images within a preset range of the vehicle. The target data collected by the target drone device and the vehicle data collected by the vehicle are obtained. The vehicle data is used to indicate the vehicle status during operation. Based on the target data and the vehicle data, the vehicle fault detection result is obtained.

[0200] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the vehicle fault detection method of any of the foregoing embodiments.

[0201] The computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, Digital Video Discs (DVDs), Compact Disc Read-Only Memory (CD-ROM), microdrives, and magneto-optical disks, read-only memory (ROM), random access memory (RAM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), dynamic random access memory (DRAM), video random access memory (VRAM), flash memory devices, magnetic cards or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0202] This application also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned related steps to implement a vehicle fault detection method as described in the above embodiments.

[0203] In addition, the electronic device provided in the embodiments of this application may specifically be a chip, component or module. The electronic device may include a connected processor and a memory. The memory is used to store instructions. When the electronic device is running, the processor may call and execute the instructions to make the chip execute a vehicle fault detection method in the above embodiments.

[0204] The electronic devices, computer-readable storage media, computer program products or chips provided in this application are all used to execute the corresponding vehicle fault detection method provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding vehicle fault detection method provided above, and will not be repeated here.

[0205] Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0206] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0207] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A vehicle fault detection method, characterized in that, The method includes: During vehicle operation, if a detection command for a target component in the vehicle is detected, the target location corresponding to the target component is determined, and the target location is the location where the target drone equipment collects target data. If the detection command corresponds to at least two target components, the detection priority of the at least two target components is determined based on the degree of influence of the at least two target components on vehicle safety; wherein, the detection priority is positively correlated with the degree of influence. The detection order is determined based on the detection priority. The system sends a target command, the target location, and the detection sequence to the target drone device, so that the target drone device flies to the target location according to the detection sequence and collects the target data; wherein, the target command is used to instruct the target drone device to collect the target data; the target data includes target images; the target images include external images of the vehicle body and images of the vehicle's driving environment within a preset range; The target data collected by the target drone device and the vehicle data collected by the vehicle are acquired; wherein the vehicle data is used to indicate the vehicle status during the driving process. Based on the target data and the vehicle data, the fault detection result of the vehicle is obtained; The target drone device flies to the target location according to the detection sequence and collects the target data, including: The target drone device determines a flight strategy based on the remaining battery power and flight mission of the target drone. The flight strategy includes the flight speed, flight altitude and flight route of the target drone. The target drone device acquires the target data based on the flight strategy.

2. The method according to claim 1, characterized in that, Also includes: Acquire first target data and first vehicle data when the vehicle is in a normal state; wherein, the first target data includes a first external image of the vehicle body; The process of obtaining the vehicle's fault detection result based on the target data and the vehicle data includes: First detection information is obtained based on the first similarity between the target data and the first target data; Based on the second similarity between the vehicle data and the first vehicle data, second detection information is obtained; The fault detection result is obtained based on the first detection information and the second detection information.

3. The method according to claim 2, characterized in that, The first detection information includes vehicle exterior detection information; obtaining the first detection information based on the first similarity between the target data and the first target data includes: The target image is compared with the first vehicle exterior image. If there is an image region with a similarity less than a first preset threshold, the vehicle exterior detection information is determined to indicate that there is a fault on the exterior of the vehicle.

4. The method according to claim 2, characterized in that, The target data includes the vehicle's emission data, and the first detection information includes emission detection information; the method further includes: Obtain the first emission data of the vehicle under normal conditions; The first detection information obtained based on the first similarity between the target data and the first target data includes: The emission data is compared with the first emission data. If the similarity between the emission data and the first emission data is less than a second preset threshold, the emission detection information indicates that the vehicle has an emission fault.

5. The method according to claim 1, characterized in that, Also includes: If the vehicle is equipped with a drone device, the drone device is identified as the target drone device; If the vehicle is not equipped with a drone, an instruction signal is sent to a drone station within a preset distance of the vehicle, and the drone station sends an identifier of the drone; the drone corresponding to the identifier of the drone is identified as the target drone; wherein, the instruction signal is used to instruct the drone station to dispatch the drone to perform the fault detection on the vehicle.

6. The method according to any one of claims 1 to 5, characterized in that, Also includes: Based on the target vehicle model, a solution database for vehicle malfunctions is determined; wherein, the solution database includes the malfunction type of the vehicle malfunction and the corresponding solution for the malfunction type; Based on the target fault type indicated by the fault detection results and the solution database, the solution corresponding to the target fault type is determined.

7. A vehicle fault detection device, characterized in that, The device includes: A sending module is configured to, during vehicle operation, if a detection command for a target component in the vehicle is detected, determine the target location corresponding to the target component, wherein the target location is the location where the target drone device collects target data; if the detection command corresponds to at least two target components, determine the detection priority of the at least two target components based on the degree of influence of the at least two target components on vehicle safety; wherein the detection priority is positively correlated with the degree of influence; determine the detection order based on the detection priority; and send the target command, the target location, and the detection order to the target drone device, so that the target drone device flies to the target location according to the detection order and collects the target data; wherein the target command is used to instruct the target drone device to collect target data; the target data includes target images; the target images include external images of the vehicle body and driving environment images within a preset range of the vehicle; The acquisition module is used to acquire target data collected by the target drone device and vehicle data collected by the vehicle; wherein the vehicle data is used to indicate the vehicle status during the driving process; The detection module is used to obtain the fault detection result of the vehicle based on the target data and the vehicle data; Specifically, the sending module is used for: the target drone device determining a flight strategy based on the remaining battery power and flight mission of the target drone, the flight strategy including the flight speed, flight altitude and flight route of the target drone; and the target drone device acquiring the target data based on the flight strategy.

8. A vehicle, characterized in that, The vehicles include: Memory, used to store executable program code; A processor for calling and running the executable program code from the memory, causing the vehicle to perform the method as described in any one of claims 1 to 6.

Images