Vehicle function defect automatic repairing method, electronic equipment and vehicle

Abstract

The invention provides a vehicle function defect automatic repairing method, electronic equipment and a vehicle, and relates to the technical field of vehicle control. The method comprises the steps of obtaining real-time operation diagnosis data of at least one vehicle function module of a vehicle; according to the real-time operation diagnosis data of the at least one vehicle function module, a target function module in the at least one vehicle function module and the defect type of the target function module are identified, and the target function module is a vehicle function module suspected to have software defects; and repairing the program of the target function module according to a repairing strategy corresponding to the defect type. The method and the device are used for automatically monitoring and repairing functional defects of the vehicle.

Description

Technical Field

[0001] This disclosure relates to the field of vehicle control technology, specifically to an automatic repair method for vehicle functional defects, electronic equipment, and a vehicle. Background Technology

[0002] With the rapid development of intelligent connected vehicles, vehicles are gradually becoming mobile platforms integrating various advanced technologies and complex software systems. These vehicles are not only equipped with a wealth of onboard sensors and actuators, but also achieve real-time communication and data exchange with the external environment through vehicle-to-everything (V2X) technology. However, this high degree of interconnectivity and intelligence also brings significant safety challenges.

[0003] The software system of intelligent connected vehicles typically comprises multiple layers, including operating systems, applications, and firmware. Each layer may contain undiscovered vulnerabilities or backdoors, which could be exploited by malicious attackers to gain control of the vehicle, steal user privacy data, or cause traffic accidents. Therefore, designing a security protection system capable of proactively detecting and quickly patching software vulnerabilities is crucial. Summary of the Invention

[0004] In view of this, embodiments of the present disclosure provide an automatic repair method, electronic device, and vehicle for vehicle functional defects, so as to realize automatic monitoring and repair of vehicle functional defects.

[0005] In a first aspect, this disclosure provides an automatic repair method for vehicle functional defects, including:

[0006] Acquire real-time operational diagnostic data for at least one vehicle functional module;

[0007] Based on the real-time operational diagnostic data of the at least one vehicle functional module, identify the target functional module and the defect type of the target functional module, wherein the target functional module is a vehicle functional module suspected of having a software defect.

[0008] The program of the target functional module is repaired according to the repair strategy corresponding to the defect type.

[0009] Secondly, this disclosure provides an electronic device, including:

[0010] At least one processor; and

[0011] A memory communicatively connected to the at least one processor; wherein,

[0012] The memory stores at least one computer program that can be executed by the at least one processor, the at least one computer program being executed by the at least one processor to enable the at least one processor to perform the automatic repair method for vehicle functional defects as described in the first aspect.

[0013] Thirdly, this disclosure provides a computer program product, which includes a computer program that, when run in a processor, implements the automatic repair method for vehicle functional defects described in the first aspect.

[0014] The embodiments provided in this disclosure acquire and analyze real-time operational diagnostic data of at least one functional module of a vehicle to automatically identify target functional modules with suspected software defects and the defect types of those target functional modules. Then, the target functional modules are automatically repaired according to the repair strategy corresponding to the defect type. This enables proactive monitoring and automatic repair of vehicle functional defects, achieving rapid repair of vehicle software defects and improving the safety of the vehicle system. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0016] Figure 1 The diagram shown is a schematic flowchart of the automatic repair method for vehicle software defects in an embodiment of this disclosure.

[0017] Figure 2 The diagram shown is a schematic representation of an example of the automatic software defect repair process in an embodiment of this disclosure;

[0018] Figure 3 The diagram shown is an example of an automatic repair process for a defect type of vulnerability class in an embodiment of this disclosure;

[0019] Figure 4 The diagram shown is a block diagram of an automatic vehicle software defect repair device according to an embodiment of this disclosure;

[0020] Figure 5 The diagram shown is a structural schematic of an electronic device in an embodiment of this disclosure. Detailed Implementation

[0021] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0022] Where there is no conflict, the various embodiments of this disclosure and the features thereof in the embodiments may be combined with each other.

[0023] As used herein, the term “and / or” includes any and all combinations of one or more related enumerated entries.

[0024] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. As used herein, the singular forms “a” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that when the terms “comprising” and / or “made of” are used in this specification, the presence of the stated feature, integral, step, operation, element, and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof is not excluded. Words such as “connected” or “linked” are not limited to physical or mechanical connections but can include electrical connections, whether direct or indirect.

[0025] Unless otherwise specified, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and this disclosure, and will not be interpreted as having an idealized or overly formal meaning, unless expressly so defined herein.

[0026] Exemplary System

[0027] Based on the above analysis, this disclosure provides an automatic repair method for vehicle functional defects. In this method, based on real-time operational diagnostic data of at least one vehicle functional module, it identifies whether there is a target functional module with suspected software defects and the defect type of the target functional module. Then, based on the repair strategy corresponding to the automatically acquired and identified defect type, it repairs the program of the corresponding target functional module.

[0028] The executing entity of this automatic vehicle functional defect repair method can be a vehicle or its controller, which executes code programs to implement the automatic vehicle functional defect repair method. This controller can be, but is not limited to, a high-performance processor (such as a GPU, TPU, or CPU).

[0029] The controller and vehicle function modules can also be connected to a large-capacity storage device to store the raw data, intermediate process data and final processing result data obtained during the automatic repair of vehicle functional defects.

[0030] The controller acquires real-time operational diagnostic data from the vehicle's functional modules via a communication module. This communication module may include, but is not limited to, high-speed in-vehicle network communication modules and / or wireless communication modules; the high-speed in-vehicle network communication module can be used for data transmission between in-vehicle devices and may include, but is not limited to, CAN bus and / or Ethernet communication modules; the wireless communication module can be used for data interaction with the cloud / server / other vehicles and may include, but is not limited to, 5G communication modules and / or V2X communication modules.

[0031] The controller can also acquire real-time operational diagnostic data of vehicle functional modules through onboard sensors. Onboard sensors may include, but are not limited to, accelerometers, vision sensors, distance sensors, and temperature sensors.

[0032] Exemplary methods

[0033] The automatic repair method for vehicle functional defects provided in this disclosure embodiment, such as Figure 1 As shown, the main steps include:

[0034] Step 101: Obtain real-time operational diagnostic data for at least one vehicle functional module.

[0035] In this embodiment of the disclosure, the vehicle functional module can be a software system or hardware. For example, a vehicle functional module can refer to the hardware of a sensor functional module (i.e., the aforementioned sensor) or the software system of that sensor functional module. For example, a vehicle functional module can include, but is not limited to, hardware such as an accelerometer, gyroscope, vision sensor, ranging sensor, and temperature sensor on the vehicle; a vehicle functional module can also be a software system such as a powertrain system, on-board diagnostic system, or on-board network module deployed on the vehicle.

[0036] In some embodiments, the real-time operational diagnostic data includes real-time operational status data of the vehicle functional modules and / or real-time road environment data of the road environment associated with the vehicle.

[0037] For example, the operating status of vehicle functional modules is collected in real time to obtain real-time operating status data of vehicle functional modules; the road environment associated with the vehicle is collected in real time to obtain real-time road environment data of the road environment associated with the vehicle.

[0038] For example, real-time operating status data includes values ​​of at least one of the following statistics: acceleration, deceleration, attitude data, visual information, real-time distance to other traffic objects, power data, vehicle fault codes, vehicle operating status, real-time internal environment temperature, real-time external environment temperature, real-time temperature of key components, data packet characteristics, and call pattern characteristics.

[0039] Acceleration and deceleration refer to the acceleration and deceleration of a vehicle, respectively, and can be collected by, but is not limited to, acceleration sensors.

[0040] Attitude data refers to data related to the attitude of a vehicle, such as, but not limited to, the vehicle's pitch angle and / or roll angle.

[0041] Visual information refers to images and / or videos of the environment surrounding a vehicle, such as images and / or videos of lane lines and / or obstacles around the vehicle.

[0042] The real-time distance to other traffic objects refers to the distance between the vehicle and other traffic objects. Other traffic objects can be any one or any combination of other vehicles, obstacles, pedestrians, non-motorized vehicles, etc.

[0043] Power data refers to data related to the vehicle's power system, such as, but not limited to, any one or any combination of data such as vehicle speed, engine speed, throttle status, and braking status; power data can be obtained in real time via, but is not limited to, the CAN bus.

[0044] Vehicle fault codes and vehicle operating status refer to the vehicle fault codes and vehicle operating status output by the on-board diagnostic (OBD) system, respectively. The vehicle operating status of the OBD system refers to the set of parameters for the real-time operation of various systems while the vehicle is in motion, reflecting current driving conditions and component performance, and providing a basis for generating vehicle fault codes. The main parameters in this set can include, but are not limited to, any one or any combination of vehicle speed, acceleration, engine speed, gear position, engine load, coolant temperature, ambient temperature, battery voltage, and tire pressure. Vehicle fault codes can describe vehicle fault information. Vehicle fault codes can describe fault information through, but are not limited to, a pre-configured code structure. In this application embodiment, the specific settings for vehicle fault codes are not limited. For example, a vehicle fault code consists of one letter and four digits. The letter represents the system that has malfunctioned, and the letter and four digits represent the system that has malfunctioned and the fault description. Vehicle fault code P0107 indicates a powertrain system fault, and the fault description is: the intake pressure sensor voltage of the powertrain system is too low. Vehicle fault codes can be analyzed in conjunction with the vehicle's operating status. For example, if the fault code describes a spark plug failure, the engine load and engine speed during vehicle operation can be further analyzed to confirm whether the vehicle has actually experienced a "spark plug failure".

[0045] Real-time interior temperature refers to the ambient temperature inside the vehicle, which can be obtained by detecting temperature sensors deployed inside the vehicle. The temperature sensors can be deployed in locations such as, but are not limited to, behind the vehicle's dashboard or in ventilation ducts.

[0046] Real-time external ambient temperature refers to the ambient temperature outside the vehicle. It is obtained by detecting the ambient temperature outside the vehicle through temperature sensors deployed on the outside of the vehicle body. The ambient temperature outside the vehicle body is the temperature of the space in which the vehicle is located. The outside of the vehicle body may include, but is not limited to, the front bumper or rearview mirror.

[0047] The real-time temperature of critical components refers to the temperature of key vehicle components, including but not limited to any one or any combination of the engine, battery, power battery, and brake pads. The temperature of these critical components is obtained by detecting the temperature of the components themselves using temperature sensors deployed on them.

[0048] Data packet characteristics refer to the characteristics of data packets transmitted by the vehicle network module (such as any one or any combination of data volume, frequency of use, data source, etc.), for example, abnormal traffic on a certain network port;

[0049] Call pattern characteristics refer to at least one of the call characteristics (such as the call frequency and timing of a certain sub-function) and memory operation characteristics (such as the data write frequency to memory and the number of processes accessing memory simultaneously) of at least one sub-function in the vehicle network module. The sub-function is implemented through a key function.

[0050] In some embodiments, when the vehicle functional module is an acceleration sensor deployed on the vehicle, the real-time operating status data includes at least one of the acceleration and deceleration of the acceleration sensor;

[0051] When the vehicle functional module is a gyroscope sensor deployed on the vehicle, the real-time operating status data includes the vehicle's attitude data.

[0052] When the vehicle functional module is a vision sensor deployed on the vehicle, the real-time operating status data includes visual information about the vehicle's surrounding environment.

[0053] When the vehicle functional module is a ranging sensor (including but not limited to radar or laser sensor) deployed on the vehicle, the real-time operating status data includes the real-time distance to other traffic objects;

[0054] When the vehicle functional module is a power system deployed on the vehicle, the real-time operating status data includes at least one of the following power data: vehicle speed, engine speed, throttle status, and braking status.

[0055] When the vehicle functional module is an on-board diagnostic system deployed on the vehicle, the real-time operating status data includes at least one of vehicle fault codes and vehicle operating status.

[0056] When the vehicle functional module is a temperature sensor deployed on the vehicle, the real-time operating status data includes at least one of the real-time temperature of the vehicle's internal environment, the real-time temperature of the external environment, and the real-time temperature of key components.

[0057] When the vehicle functional module is an in-vehicle network module deployed on the vehicle, the real-time operating status data includes at least one of data packet characteristics and call mode characteristics; the data packet characteristics are determined based on at least one of data volume, usage frequency, and data source; the call mode characteristics are determined based on at least one of the call characteristics of at least one sub-function of the in-vehicle network module and memory operation characteristics.

[0058] In some embodiments, the real-time road environment data includes at least one of the following: road surface physical state data, meteorological data, traffic dynamic data, and road topology data.

[0059] For example, the road surface physical state data includes at least one of road surface water depth, road surface icing state, road surface snow state, road surface friction coefficient, and road surface smoothness; the meteorological data includes at least one of visibility, temperature, humidity, wind speed, wind direction, and precipitation intensity; the traffic dynamic data includes at least one of the current road environment information of the vehicle, such as traffic signal status information, traffic accident information, traffic congestion information, and traffic construction information; and the road topology data includes at least one of road slope, curve curvature, lane lines, and traffic signs.

[0060] This disclosure does not limit the specific method of obtaining real-time road environment data. For example, it can involve real-time acquisition of road surface physical state data and road topology data using any one or more acquisition devices such as visual sensors, lidar, and inertial measurement units installed on the vehicle; real-time acquisition of temperature and humidity data from meteorological data using temperature sensors and humidity sensors installed on the vehicle; acquisition of visibility, wind speed, wind direction, and precipitation intensity from meteorological data via vehicle-to-everything (V2X) communication; and acquisition of traffic dynamic data from road infrastructure (traffic lights, etc.) via vehicle-to-infrastructure (V2I) communication. It should be noted that this is merely an example, and real-time road environment data can be obtained through a combination of multiple methods. This document does not limit the specific method used. For methods that use multiple methods to obtain real-time road environment data, spatiotemporal alignment is performed on the real-time road environment data from multiple data sources.

[0061] For example, after collecting the real-time operating status data of each vehicle functional module and the real-time road environment data, preprocessing is performed, including data cleaning, standardization, and then organizing into feature vectors.

[0062] Among them, real-time road environment data is used to describe the road environment corresponding to the real-time operating status data of each vehicle functional module, and is used to verify whether the real-time operating status data is compatible with the road environment, so as to identify whether the real-time operating status data is abnormal.

[0063] Step 102: Based on the real-time operational diagnostic data of the at least one vehicle functional module, identify the target functional module and the defect type of the target functional module, wherein the target functional module is a vehicle functional module suspected of having a software defect.

[0064] In some embodiments, identifying a target functional module and its defect type based on real-time operational diagnostic data of the at least one vehicle functional module includes: performing the following processing on each vehicle functional module of the at least one vehicle functional module:

[0065] Based on the real-time operational diagnostic data of the vehicle functional modules, the real-time behavioral characteristics of the vehicle functional modules are determined; based on the deviation between the real-time behavioral characteristics of the vehicle functional modules and the baseline behavioral characteristics of the vehicle functional modules, it is determined whether the vehicle functional modules are target functional modules; and, in response to the vehicle functional modules being target functional modules, the defect type of the target functional modules is identified; the baseline behavioral characteristics are determined based on the real-time operational diagnostic data of the vehicle functional modules in normal operating conditions.

[0066] In some embodiments, the real-time operational diagnostic data includes real-time operational status data of the vehicle functional module and real-time road environment data of the road environment associated with the vehicle; determining the real-time behavioral characteristics of the vehicle functional module based on the real-time operational diagnostic data of the vehicle functional module; and determining whether the vehicle functional module is a target functional module based on the deviation between the real-time behavioral characteristics of the vehicle functional module and the baseline behavioral characteristics of the vehicle functional module, includes: determining the real-time behavioral characteristics matching each statistic based on at least two values ​​of each statistic in the real-time operational status data of the vehicle functional module; and determining whether the vehicle functional module is a target functional module based on the deviation between the real-time behavioral characteristics matching each statistic and the baseline behavioral characteristics of each statistic; the baseline behavioral characteristics include the behavioral characteristics of each statistic when the vehicle functional module is operating normally under road conditions matching the real-time road environment data.

[0067] In some embodiments, determining the real-time behavioral features matching each statistic based on at least two values ​​of each statistic in the real-time running status data includes: determining at least one sub-behavioral feature corresponding to each statistic as the real-time behavioral feature matching each statistic based on at least two values ​​of each statistic in the real-time running status data, wherein the sub-behavioral feature includes any one or any combination of real-time data range, real-time behavioral pattern, and real-time performance index.

[0068] Specifically, in the real-time operating status data of the vehicle functional modules under normal operating conditions, any one or any combination of the baseline data range, baseline behavior pattern, and baseline performance index corresponding to each statistical quantity is determined as the baseline behavior feature of each statistical quantity.

[0069] In some embodiments, the deviation between the real-time behavioral characteristics and the baseline behavioral characteristics of any statistic of the vehicle functional module includes at least one of the following: data range difference, behavioral pattern difference, and performance index difference.

[0070] If a statistical quantity's real-time behavioral feature does not match the baseline behavioral feature, then the vehicle functional module corresponding to that statistical quantity is the target functional module. In this embodiment, if at least one target behavioral feature exists among the sub-behavioral features corresponding to a statistical quantity, then the real-time behavioral feature of that statistical quantity is considered to be inconsistent with the baseline behavioral feature. The target behavioral feature is the sub-behavioral feature of the aforementioned statistical quantity that does not match its corresponding baseline sub-feature. If the sub-behavioral feature is the real-time data range of the statistical quantity, and if the real-time data range does not completely fall within the corresponding baseline data range (i.e., the baseline sub-feature corresponding to the real-time data range), then the real-time data range of the statistical quantity is considered to be the target behavioral feature. If the sub-behavioral feature is the real-time behavioral pattern of the statistical quantity, and if the real-time behavioral pattern is different from the corresponding baseline behavioral pattern (i.e., the baseline sub-feature corresponding to the real-time behavioral pattern), then the real-time behavioral pattern of the statistical quantity is considered to be the target behavioral feature. If the sub-behavioral feature is the real-time performance index of the statistical quantity, and if the difference between the real-time performance index and the corresponding baseline performance index (i.e., the baseline sub-feature corresponding to the real-time performance index) exceeds a threshold, then the real-time performance index is considered to be the target behavioral feature.

[0071] In some embodiments, the deviation between the real-time behavioral characteristics and the baseline behavioral characteristics of the vehicle functional module's statistics includes one of the following: data range difference, behavioral pattern difference, and performance index difference. In this case, when this difference indicates that the real-time behavioral characteristics do not match the baseline behavioral characteristics, the vehicle functional module can be determined to be the target functional module.

[0072] In some embodiments, when the deviation between the real-time behavioral characteristics and the baseline behavioral characteristics of the statistical quantities of the vehicle functional module includes two or three of the following: differences in data range, differences in behavioral patterns, and differences in performance indicators, the vehicle functional module can be determined to be the target functional module as long as any one of the aforementioned two or three differences indicates that the real-time behavioral characteristics do not match the baseline behavioral characteristics.

[0073] Specifically, for each of the aforementioned differences in data range, behavioral patterns, and performance metrics, an explanation is provided regarding situations where real-time behavioral characteristics do not match baseline behavioral characteristics:

[0074] 1) Data range difference characterizes the situation where the real-time behavioral characteristics do not match the benchmark behavioral characteristics: the real-time data range of the statistic does not fall completely within the corresponding benchmark data range; that is, the situation where the maximum value of the real-time data range is greater than the maximum value of the benchmark data range, and the minimum value of the real-time data range is less than the minimum value of the benchmark data range, all belong to the situation where the real-time data range does not fall completely within the corresponding benchmark data range.

[0075] 2) The situation in which the real-time behavioral characteristics of the behavioral pattern do not match the baseline behavioral characteristics is: the real-time behavioral pattern of the statistical quantity is different from the corresponding baseline behavioral pattern.

[0076] 3) The situation in which the performance index difference characterizes the real-time behavioral characteristics that do not match the baseline behavioral characteristics is when the difference between the real-time performance index of the statistic and the corresponding baseline performance index exceeds the threshold.

[0077] In some embodiments, data range difference refers to the difference between the real-time data range of a statistic and the baseline data range of the statistic.

[0078] The real-time operating status data of the vehicle functional module includes at least two values ​​of each statistical quantity directly generated by the module under the current road conditions. Each statistical quantity includes at least one of the following: input quantity, output quantity, and intermediate state quantity generated during the processing of the vehicle functional module. The changes in the values ​​of these statistical quantities are monitored in real time to obtain the real-time data range corresponding to each statistical quantity. The statistical quantity corresponding to the vehicle functional module under a certain road condition can be some or all of the statistical quantities of the vehicle functional module. For example, it can be a statistical quantity pre-configured by technicians for a certain road condition, or it can be a statistical quantity selected by technicians based on the importance of defect identification. The process of determining the real-time data range corresponding to a statistical quantity includes: obtaining the minimum and maximum values ​​of the statistical quantity monitored under the current road conditions, and using the range defined by the minimum and maximum values ​​as the real-time data range of that statistical quantity.

[0079] The process for determining the baseline data range of each statistic under a certain road condition is as follows: Collect at least two values ​​of each statistic directly generated by the vehicle's functional module when it is operating normally under that road condition, including at least one of the following: input quantity, output quantity, and intermediate state quantity generated during the vehicle's functional module processing. Statistical analysis is performed on the changes in the value of each statistic to obtain the numerical range of each statistic under the normal operating conditions of the vehicle's functional module under that road condition, i.e., the baseline data range. The process for determining the baseline data range corresponding to a statistic includes: using the range defined by the minimum and maximum values ​​of the statistic when the target functional module is operating normally under that road condition as the baseline data range for that statistic.

[0080] The process of determining the difference in data range includes: comparing the real-time data range and the benchmark data range for the same statistic; if the lower limit of the real-time data range is less than the lower limit of the benchmark data range, or the lower limit of the real-time data range is greater than the upper limit of the benchmark data range, or the upper limit of the real-time data range is greater than the upper limit of the benchmark data range, or the upper limit of the real-time data range is less than the lower limit of the benchmark data range, then the real-time data range exceeds the benchmark data range, which means that the real-time behavioral characteristics do not match the benchmark behavioral characteristics.

[0081] Examples of data range discrepancies are as follows: Under certain road conditions, the real-time reading of a certain statistic of a sensor changes beyond the baseline data range of that statistic; or, under certain road conditions, the real-time traffic of a certain network port changes beyond the baseline traffic range; or, under certain road conditions, the call frequency of a certain function increases significantly, and the real-time call frequency range of that function exceeds the baseline call frequency range of that function, etc., then it can be identified that the vehicle functional module corresponding to the sensor has a suspected software defect.

[0082] In some embodiments, behavioral pattern difference refers to the difference between real-time behavioral pattern and baseline behavioral pattern.

[0083] Real-time behavior patterns indicate vehicle control-related operations performed in response to the values ​​of multiple statistical parameters of vehicle functional modules monitored in real time. Baseline behavior patterns refer to the operating mode of a vehicle functional module determined under normal driving conditions based on the values ​​of multiple statistical parameters measured by the module under specific road conditions. If the real-time behavior pattern corresponding to the statistical parameters of a vehicle functional module under a certain road condition differs from the baseline behavior pattern, it indicates a mismatch between the real-time and baseline behavior patterns, suggesting that the vehicle functional module may have a suspected software defect. For example, the behavior patterns of a vehicle's gyroscope sensors include basic measurement behavior patterns measuring roll, pitch, and yaw angles; and safety control linkage modes based on directly measured angles, such as rollover prediction and cornering assist control. If the baseline behavior pattern under a certain road condition is the basic measurement behavior pattern, but the real-time behavior pattern under the same road condition is a cornering assist control behavior pattern, this indicates a suspected software defect in the vehicle functional module.

[0084] The process of determining real-time behavior patterns includes: using the values ​​of various statistics of vehicle functional modules as input to the behavior pattern recognition algorithm corresponding to that vehicle functional module, and obtaining the real-time behavior pattern output by the behavior pattern recognition algorithm; wherein, the behavior pattern recognition algorithm includes at least one of clustering algorithms, association rule mining algorithms, and classification models. The parameters of the behavior pattern recognition algorithm are obtained through pre-training or pre-configuration. The sample data used when training the behavior pattern recognition algorithm includes sample values ​​of statistics of vehicle functional modules and corresponding sample behavior patterns.

[0085] In some embodiments, performance metric differences refer to the differences between real-time performance metrics and baseline performance metrics.

[0086] Real-time performance metrics refer to one or more performance indicators calculated using a performance indicator formula based on the real-time data range of one or more statistical quantities monitored in real time. For example, the performance indicators of a vision sensor include dynamic range and high-speed capture frame rate. Dynamic range is calculated based on the maximum and minimum light signal intensity values ​​acquired by the vision sensor, while high-speed capture frame rate is calculated based on the number of frames acquired within a certain time period. Different vehicle functional modules have their own predefined performance indicators. For example, the performance indicators for vision sensors include dynamic range and high-speed capture frame rate, while the performance indicators for the vehicle's powertrain system include transmission efficiency and power response speed. Baseline performance indicators refer to one or more performance indicators calculated from the values ​​of one or more statistical quantities directly monitored under certain road conditions during normal driving.

[0087] If the difference between a real-time performance metric of a vehicle functional module and a baseline performance metric exceeds a threshold, then that vehicle functional module is a target functional module. For example, high-speed capture frame rate is a performance metric of a vision sensor. Suppose that the vision sensor has a baseline high-speed capture frame rate of 60 frames / second under certain road conditions, but a real-time high-speed capture frame rate of 50 frames / second under the same road conditions. If the deviation between the baseline high-speed capture frame rate and the real-time capture frame rate meets the condition (assuming the deviation is greater than 5 frames / second), then the vision sensor is suspected of having a software defect.

[0088] In some embodiments, the process of obtaining the benchmark behavioral features for comparison with real-time behavioral features includes: determining real-time road environment features based on real-time road environment data in the real-time operation diagnostic data of the vehicle functional module; and obtaining the benchmark behavioral features of each statistic corresponding to the benchmark road environment features that match the real-time road environment features based on the correspondence between the benchmark road environment features and the benchmark behavioral features of each statistic under normal operation of the vehicle functional module.

[0089] For example, the real-time road environment features include at least one feature dimension, which includes at least one of road surface physical state features, meteorological features, traffic dynamic features, and road topology features.

[0090] The correspondence between the baseline road environment features and the baseline behavioral features of each statistical quantity under the normal operating conditions of the vehicle functional modules includes the correspondence between each feature dimension of the baseline road environment features and the baseline behavioral features of each statistical quantity.

[0091] The baseline behavioral features of each statistic corresponding to the baseline road environment features that match the real-time road environment features, including the baseline behavioral features of each statistic corresponding to each feature dimension in the real-time road environment features.

[0092] For example, assuming the real-time road environment features include four dimensions: road surface physical state features, meteorological features, traffic dynamic features, and road topology features, the baseline behavioral features of each statistical quantity corresponding to each of these four dimensions are obtained from the correspondence between the baseline road environment features and the baseline behavioral features of each statistical quantity under the normal operating conditions of the vehicle functional modules. These baseline behavioral features are then used to calculate the differences between the real-time behavioral features of each statistical quantity and the baseline road surface physical state features.

[0093] In some embodiments, identifying the defect type of the target functional module includes: inputting the target functional module and target difference information into a defect type identification model to obtain the defect type of the target functional module output by the defect type identification model; the target difference information is determined based on the deviation between the real-time behavioral features and the baseline behavioral features; wherein the defect type identification model is constructed based on an artificial intelligence model.

[0094] For example, target difference information is determined based on at least one of the differences in data range, behavioral patterns, and performance metrics between the real-time behavioral features and the baseline behavioral features.

[0095] This section does not limit the specific type of artificial intelligence model; for example, it can be any type of neural network model. The sample data used to train the artificial intelligence model includes sample functional modules, sample difference information, and sample defect types. This sample data can be accumulated by technicians during routine defect repairs of vehicle functional modules.

[0096] In some embodiments, identifying a target functional module and its defect type based on real-time operational diagnostic data of the at least one vehicle functional module includes: inputting real-time operational diagnostic data of the at least one vehicle functional module into an anomaly detection model to obtain the target functional module and its defect type output by the anomaly detection model; the anomaly detection model is constructed based on an artificial intelligence model.

[0097] In an exemplary embodiment, the training data used to train the artificial intelligence model includes the operating status data of each vehicle functional module under normal operating conditions, road environment data, and software operation logs. Through training, the anomaly detection model stores the baseline behavioral characteristics of each vehicle functional module. After obtaining real-time operating status data and real-time road environment data, the anomaly detection model can extract real-time behavioral characteristics and compare them with the baseline behavioral characteristics, thereby identifying and outputting the target vehicle functional module suspected of having a software defect and the defect type.

[0098] The training data may include a small amount of labeled abnormal training data to validate the model against these anomalies. Abnormal training data refers to operational status data of vehicle functional modules under abnormal conditions, road environment data, and labeled defect types.

[0099] After training, the model's performance metrics (such as accuracy, recall, and F1 score) are evaluated using a validation dataset that includes anomalous training data, and the model structure or hyperparameters are adjusted based on the results.

[0100] For example, the latest model parameters and training data are periodically downloaded from the cloud to update the anomaly detection model online, thereby optimizing the model's detection accuracy. Additionally, the results of each software defect identification and repair are fed back to the anomaly detection model for subsequent optimization. Correctly identified software defects improve the accuracy of the anomaly detection model, while incorrectly identified or invalid defects are used to further optimize it.

[0101] For example, for the same type of vehicle, the already trained anomaly detection model can be transferred and used.

[0102] For example, an artificial intelligence model can be an algorithmic model based on deep learning. Examples are as follows:

[0103] 1. Unsupervised learning algorithms

[0104] A. Autoencoder (AE): Features under normal conditions are input into the autoencoder for training, enabling it to learn the data distribution under normal conditions. In actual operation, if the input data cannot be reconstructed well, it is considered to be abnormal (such as sensor failure or network attack).

[0105] B, Variational Autoencoder (VAE), is similar to AE, but introduces a probabilistic modeling mechanism, which can better capture complex data distributions.

[0106] C. Generative Adversarial Networks (GANs) use generators to produce virtual data in a normal state, and a discriminator to distinguish between real data and generated data. If the discriminator finds data that cannot be interpreted, it considers it to be an anomaly.

[0107] 2. Semi-supervised learning algorithms

[0108] If some anomalous samples are available, semi-supervised learning methods can be used. One-Class SVM: Trains a classifier using normal samples, marking all data deviating from the normal distribution as anomalous. Isolation Forest: Isolates anomalous samples using a random forest algorithm, quickly identifying outliers in a high-dimensional space.

[0109] 3. Reinforcement Learning Algorithms

[0110] In dynamic environments, reinforcement learning algorithms can be used to optimize anomaly detection strategies: define a reward function: give a positive reward when a real anomaly is detected; give a negative reward when a false alarm or missed alarm is detected; train the agent to adjust the detection threshold and strategy in dynamic environments.

[0111] The above deep learning-based algorithm models are just examples, and there are no restrictions on which specific deep learning model to use.

[0112] Step 103: Repair the program of the target functional module according to the repair strategy corresponding to the defect type.

[0113] In some embodiments, repairing the program of the target functional module according to the repair strategy corresponding to the defect type includes: obtaining the repair strategy corresponding to the defect type according to the defect type of the target functional module; the repair strategy corresponding to the defect type is obtained based on a first strategy mapping relationship and / or a second strategy mapping relationship; the first strategy mapping relationship represents the correspondence between vehicle functional modules, defect types and repair strategies, and the second strategy mapping relationship represents the correspondence between defect types and repair strategies; and repairing the program of the target functional module according to the repair strategy corresponding to the defect type.

[0114] The first and / or second strategy mapping relationships can be obtained online via the server or stored in the vehicle's local memory. Specifically, obtaining them online via the server involves: after identifying the defect type of the target functional module, obtaining the corresponding repair strategy based on the first and / or second strategy mapping relationships obtained from the server.

[0115] For defect types and repair strategies specific to certain vehicle functional modules, a correspondence is established between the vehicle functional module, the defect type, and the repair strategy. For defect types and repair strategies used by all vehicle functional modules, a correspondence is established between the defect type and the repair strategy. For example, when a software defect is an isolation-allowed class, a correspondence is established between the isolation-allowed defect type and the repair strategy of the isolation mechanism. When a software defect type is a functional impact class that affects the overall functionality of a vehicle functional module, and an alternative logic module for that vehicle functional module is pre-deployed, a correspondence is established between the vehicle functional module, the functional impact class defect type, and the deployed alternative logic module.

[0116] In some embodiments, the remediation strategy includes at least one of generating temporary patch code, deploying alternative logic modules, and permission restrictions and isolation mechanisms;

[0117] The defect types include at least one of the following: vulnerability type, functional impact type, software defect that affects the overall function of the vehicle function module, permission setting type, software defect that is related to the partial level of permissions of the vehicle function module, and software defect that is allowed to be isolated.

[0118] When the defect type is the vulnerability class, the corresponding remediation strategy is to generate temporary patch code; when the defect type is the functional impact class, the corresponding remediation strategy is to deploy alternative logic modules; when the defect type is the permission setting class, the corresponding remediation strategy is permission restriction; when the defect type is the allow isolation class, the corresponding remediation strategy is the isolation mechanism.

[0119] The vulnerability class corresponds to the generation of temporary patch code to cover the software defect. For example, when a buffer overflow is detected, boundary check logic is dynamically inserted, and the behavior of specific functions is modified to prevent the vulnerability from being exploited.

[0120] The functional impact class corresponds to the deployment of alternative logic modules, which replace the software portion of the functional module with a software defect with a pre-verified, secure version of the alternative logic module. For example, when malicious code injection is detected, an alternative communication protocol stack is enabled.

[0121] The permission setting class corresponds to the permission restrictions, which prevent the vulnerabilities of functional modules with software flaws from being further expanded. For example, restricting network access permissions for suspicious processes.

[0122] Similarly, the isolation class corresponds to the isolation mechanism, preventing the further spread of vulnerabilities in functional modules with software defects.

[0123] In some embodiments, repairing the program of the target functional module according to the repair strategy corresponding to the defect type includes: after the effectiveness and security verification of the repair strategy corresponding to the defect type are passed, repairing the program of the target functional module using the repair strategy corresponding to the defect type.

[0124] Verify the effectiveness and security of the remediation strategy, including but not limited to: simulating attack scenarios to test the effectiveness of the patch; and checking whether the patch introduces new functional defects or performance issues.

[0125] A redundancy mechanism is designed to ensure availability. Before fixing, an older version of the target functional module is retained as a backup so that if a problem is found in the new version after the fix, it can be quickly rolled back to the older version.

[0126] To facilitate hot updates of the target functional modules, the interface definitions are clearly defined when designing the target functional modules to ensure that the target functional modules run independently, so as to support dynamic loading and unloading of functional modules without affecting the normal operation of other system functions.

[0127] Record the repair process log and provide feedback to the user or cloud platform for further analysis and optimization.

[0128] In some embodiments, while acquiring real-time operational diagnostic data of at least one vehicle functional module, the method further includes: acquiring real-time software operation logs of the vehicle, the real-time software operation logs including real-time software operation logs of each of the at least one vehicle functional module; after identifying the target functional module of the at least one vehicle functional module and the defect type of the target functional module, the method further includes: displaying the real-time software operation logs. Specifically, the real-time software operation logs are displayed to back-end technical personnel to facilitate manual real-time review of the software operation logs to determine whether the identified target functional module with software defects and the defect type are correct.

[0129] The real-time software operation log includes the operation log of the vehicle control unit (ECU), such as program execution status and error codes, as well as network traffic of the vehicle system, such as HTTP requests and CAN bus communication protocols.

[0130] In some embodiments, after obtaining a repair strategy for the defect type of the target functional module, an alarm is issued to alert potential threats or trigger corresponding defensive measures.

[0131] In one exemplary embodiment, such as Figure 2The diagram illustrates an example of an automatic software defect repair process, which mainly includes: acquiring raw data (speed, acceleration, network traffic, etc.) through vehicle sensors and network communication interfaces; preprocessing the data (data cleaning, standardization, etc.) to obtain real-time operational diagnostic data of vehicle functional modules; inputting the real-time operational diagnostic data into an anomaly detection module for artificial intelligence (AI) detection; outputting the detected target functional module and defect type; issuing an alarm to trigger corresponding defensive measures; and obtaining a repair strategy matching the defect type for dynamic repair.

[0132] In another exemplary embodiment, such as Figure 3 The example shown is an automatic repair process for vulnerability-type defects. It mainly includes: after obtaining alarm information from the anomaly detection module or other security components, analyzing the software defects of the vulnerability type indicated in the alarm information, and dynamically generating repair strategies based on the specific circumstances of the vulnerability (vulnerability type, scope of impact, etc.), such as generating temporary patch code, and using the temporary patch code to cover the software defects, thereby realizing a dynamic repair mechanism with zero downtime.

[0133] The embodiments provided in this disclosure acquire and analyze real-time operational diagnostic data of at least one functional module of a vehicle to automatically identify target functional modules with suspected software defects and the defect types of those target functional modules. Then, the target functional modules are automatically repaired according to the repair strategy corresponding to the defect type. This enables proactive monitoring and automatic repair of vehicle functional defects, achieving rapid repair of vehicle software defects and improving the safety of the vehicle system.

[0134] Compared to existing intrusion detection systems (IDS) that rely on known threat signature databases for threat identification, have limited ability to identify new and unknown attacks, and require frequent updates to the known threat signature database to cope with the ever-changing threat environment, the embodiments of this disclosure can identify target functional modules with software defects by constructing benchmark behavioral features and comparing them. This eliminates the need to rely on known threat signature databases to discover unknown attacks.

[0135] Compared to the existing method of periodically pushing software patches to fix known vulnerabilities, which involves time delays in patch development and release, making it difficult to detect and fix vulnerabilities in a timely manner and affecting user experience, the embodiments of this disclosure can monitor and quickly detect target functional modules with suspected software defects in real time and automatically repair them, which is highly efficient.

[0136] In addition, the target functional module and defect type detection, or defect type detection based on the artificial intelligence model in this embodiment can improve the system's generalization ability and adaptability.

[0137] This disclosure achieves dynamic software defect repair with zero downtime through automatic detection and repair, requiring no manual intervention and not affecting the normal operation of other system functions. Compared to existing software update mechanisms that require service interruption for upgrades or intermittent installations, which may lead to vehicles being unable to respond to security threats in a timely manner in emergency situations, the zero downtime repair mechanism of this disclosure ensures that the vehicle can maintain basic functional operation even when attacked.

[0138] In this embodiment, potential threats such as target functional modules suspected of having software defects and defect types are proactively identified. Combined with isolation mechanisms such as firewalls, access control restrictions, generation of temporary patch code, deployment of alternative logic modules, and other remediation strategies, as well as rapid response and remediation based on the remediation strategies, a multi-layered system protection system is achieved, which improves the overall security and reliability of the system.

[0139] After each successful repair of the target functional module, the knowledge base is updated, and a set of data is added to the knowledge base. This set of data includes the target functional module, real-time running diagnostic data, defect types, and repair strategies. This is to optimize the defect type identification model and anomaly detection model in the future, so as to cope with potential future risks, realize the ability of adaptive learning and evolution, and maintain a long-term and efficient level of security protection.

[0140] It is understood that the various method embodiments mentioned above in this disclosure can be combined with each other to form combined embodiments without violating the principle and logic. Due to space limitations, this disclosure will not elaborate further. Those skilled in the art will understand that in the above methods of specific implementation, the specific execution order of each step should be determined by its function and possible internal logic, and the execution order between steps is not limited to implementation according to step number.

[0141] Exemplary device

[0142] Figure 4 This is a block diagram of an automatic vehicle function defect repair device provided in this embodiment of the disclosure. Specific implementation of this automatic vehicle software defect repair device can be found in the description of the method embodiments section, and will not be repeated here. The device mainly includes:

[0143] The acquisition module 401 is used to acquire real-time operational diagnostic data of at least one vehicle functional module of the vehicle.

[0144] The identification module 402 is used to identify a target functional module and the defect type of the target functional module in the at least one vehicle functional module based on the real-time operation diagnostic data of the at least one vehicle functional module. The target functional module is a vehicle functional module suspected of having a software defect.

[0145] Repair module 403 is used to repair the program of the target functional module according to the repair strategy corresponding to the defect type.

[0146] Exemplary electronic devices

[0147] Figure 5 This is a block diagram of an electronic device provided in an embodiment of the present disclosure.

[0148] Reference Figure 5 This disclosure provides an electronic device, which includes: at least one processor 501; at least one memory 502; and one or more I / O interfaces 503 connected between the processor 501 and the memory 502; wherein the memory 502 stores one or more computer programs that can be executed by the at least one processor 501, and the one or more computer programs are executed by the at least one processor 501 to enable the at least one processor 501 to perform the above-described automatic repair method for vehicle functional defects.

[0149] The modules in the aforementioned electronic devices can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0150] Exemplary vehicle

[0151] This disclosure also provides a vehicle that includes the electronic equipment described above, specifically the vehicle's main controller, etc.

[0152] Exemplary computer program products and storage media

[0153] This disclosure also provides a computer program product, including a computer program that, when run in a processor, implements the above-described automatic repair method for vehicle functional defects.

[0154] The computer program may be stored on a readable storage medium of a computer device or in the cloud; the processor of the computer device reads the computer program from the readable storage medium or in the cloud.

[0155] The aforementioned computer program product can be implemented through hardware, software, or a combination thereof. In one optional embodiment, the computer program product is specifically manifested as a computer storage medium; in another optional embodiment, the computer program product is specifically manifested as a software product, such as a software development kit (SDK), etc.

[0156] Those skilled in the art will understand that all or some of the steps, systems, and apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software can be distributed on a computer-readable storage medium, which may include computer storage media (or non-transitory media) and communication media (or transient media).

[0157] As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable program instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technologies, portable compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, it is known to those skilled in the art that communication media typically contain computer-readable program instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0158] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0159] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0160] The computer program product described herein can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0161] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0162] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0163] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0164] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0165] The above description is merely a preferred embodiment of this disclosure and is not intended to limit this disclosure. Any modifications or equivalent substitutions made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for automatically repairing vehicle functional defects, characterized in that, include: Acquire real-time operational diagnostic data for at least one vehicle functional module; Based on the real-time operational diagnostic data of the at least one vehicle functional module, identify the target functional module and the defect type of the target functional module, wherein the target functional module is a vehicle functional module suspected of having a software defect. The program of the target functional module is repaired according to the repair strategy corresponding to the defect type.

2. The method according to claim 1, characterized in that, The step of identifying a target functional module and its defect type based on real-time operational diagnostic data from at least one vehicle functional module includes: The following processing is performed on each of the at least one vehicle function module: Based on the real-time operational diagnostic data of the vehicle functional modules, the real-time behavioral characteristics of the vehicle functional modules are determined. Based on the deviation between the real-time behavioral characteristics of the vehicle functional module and the baseline behavioral characteristics of the vehicle functional module, it is determined whether the vehicle functional module is a target functional module; and, in response to the vehicle functional module being a target functional module, the defect type of the target functional module is identified; the baseline behavioral characteristics are determined based on the real-time operational diagnostic data of the vehicle functional module in normal operating condition.

3. The method according to claim 2, characterized in that, The real-time operational diagnostic data includes the real-time operational status data of the vehicle's functional modules and / or the real-time road environment data associated with the vehicle. and / or Identifying the defect type of the target functional module includes: inputting the target functional module and target difference information into a defect type identification model to obtain the defect type of the target functional module output by the defect type identification model; the target difference information is determined based on the deviation between the real-time behavior features and the baseline behavior features; wherein, the defect type identification model is constructed based on an artificial intelligence model.

4. The method according to claim 3, characterized in that, The real-time road environment data includes at least one of the following: road surface physical state data, meteorological data, traffic dynamic data, and road topology data; and / or The real-time operating status data includes values ​​of at least one of the following statistics: acceleration, deceleration, attitude data, visual information, real-time distance to other traffic objects, power data, vehicle fault codes, vehicle operating status, real-time internal environment temperature, real-time external environment temperature, real-time temperature of key components, data packet characteristics, and call mode characteristics.

5. The method according to claim 3 or 4, characterized in that, When the vehicle functional module is an acceleration sensor deployed on the vehicle, the real-time operating status data includes at least one of the acceleration and deceleration of the acceleration sensor; When the vehicle functional module is a gyroscope sensor deployed on the vehicle, the real-time operating status data includes the vehicle's attitude data. When the vehicle functional module is a vision sensor deployed on the vehicle, the real-time operating status data includes visual information about the vehicle's surrounding environment. When the vehicle functional module is a ranging sensor deployed on the vehicle, the real-time operating status data includes the real-time distance to other traffic objects. When the vehicle functional module is a power system deployed on the vehicle, the real-time operating status data includes at least one of the following power data: vehicle speed, engine speed, throttle status, and braking status. When the vehicle functional module is an on-board diagnostic system deployed on the vehicle, the real-time operating status data includes at least one of vehicle fault codes and vehicle operating status. When the vehicle functional module is a temperature sensor deployed on the vehicle, the real-time operating status data includes at least one of the real-time temperature of the vehicle's internal environment, the real-time temperature of the external environment, and the real-time temperature of key components. When the vehicle functional module is an in-vehicle network module deployed on the vehicle, the real-time operating status data includes at least one of data packet characteristics and call mode characteristics; the data packet characteristics are determined based on at least one of data volume, usage frequency, and data source; the call mode characteristics are determined based on at least one of the call characteristics of at least one sub-function of the in-vehicle network module and memory operation characteristics.

6. The method according to claim 2, characterized in that, The real-time operational diagnostic data includes the real-time operational status data of the vehicle's functional modules and the real-time road environment data associated with the vehicle. The real-time behavioral characteristics of the vehicle functional modules are determined based on the real-time operational diagnostic data of the vehicle functional modules. Determining whether a vehicle functional module is a target functional module based on the deviation between its real-time behavioral characteristics and its baseline behavioral characteristics includes: Based on at least two values ​​of each statistic in the real-time operating status data of the vehicle functional modules, determine the real-time behavioral characteristics matched by each statistic; Based on the deviation between the real-time behavioral characteristics matched by each of the statistical quantities and the baseline behavioral characteristics of each of the statistical quantities, it is determined whether the vehicle functional module is the target functional module; the baseline behavioral characteristics include the behavioral characteristics of each of the statistical quantities when the vehicle functional module is operating normally under road conditions that match the real-time road environment data.

7. The method according to claim 6, characterized in that, The step of determining the real-time behavioral characteristics matching each statistic based on at least two values ​​of each statistic in the real-time operating status data of the vehicle functional modules includes: Based on at least two values ​​of each statistic in the real-time running status data, at least one sub-behavioral feature corresponding to each statistic is determined as the real-time behavioral feature matched by each statistic. The sub-behavioral feature includes any one or any combination of real-time data range, real-time behavioral pattern, and real-time performance index.

8. The method according to claim 1, characterized in that, The step of identifying a target functional module and its defect type based on real-time operational diagnostic data of at least one vehicle functional module includes: inputting real-time operational diagnostic data of at least one vehicle functional module into an anomaly detection model to obtain the target functional module and its defect type output by the anomaly detection model; the anomaly detection model is constructed based on an artificial intelligence model. and / or The step of repairing the program of the target functional module according to the repair strategy corresponding to the defect type includes: obtaining the repair strategy corresponding to the defect type of the target functional module; repairing the program of the target functional module according to the repair strategy corresponding to the defect type; the repair strategy corresponding to the defect type is obtained based on a first strategy mapping relationship and / or a second strategy mapping relationship; the first strategy mapping relationship represents the correspondence between vehicle functional modules, defect types and repair strategies, and the second strategy mapping relationship represents the correspondence between defect types and repair strategies.

9. The method according to claim 1, characterized in that, While acquiring real-time operational diagnostic data of at least one vehicle functional module, the method further includes: acquiring real-time software operation logs of the vehicle, wherein the real-time software operation logs include real-time software operation logs of each of the at least one vehicle functional module. After identifying the target functional module of the at least one vehicle functional module and the defect type of the target functional module, the method further includes: displaying the real-time software operation log.

10. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores at least one computer program that can be executed by the at least one processor, the at least one computer program being executed by the at least one processor to enable the at least one processor to perform the automatic repair method for vehicle functional defects as described in any one of claims 1-9.

11. A vehicle, characterized in that, The vehicle is used to implement the automatic repair method for vehicle functional defects as described in any one of claims 1-9.

Images