Method and device for determining monitoring strategy of vehicle, storage medium and processor

Abstract

The invention discloses a method and a device for determining a monitoring strategy of a vehicle, a storage medium and a processor. The method comprises the steps that driving environment data of a vehicle and driving habit data of a driving object of the vehicle are obtained, and the driving habit data are used for representing vehicle driving behavior habits of the driving object; the driving environment data and the driving habit data are input into a target driving prediction model, target driving safety information of the vehicle is predicted, and the target driving prediction model is obtained by training historical driving environment data of the vehicle and historical driving habit data of a driving object of the vehicle; the target driving safety information is used for indicating safety information of the vehicle in the driving process; based on the target driving safety information, a target monitoring strategy of the vehicle is determined, and the target monitoring strategy is used for monitoring rules of functional safety of the vehicle. The technical problem that the cost of monitoring vehicle function safety is too high is solved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle functional safety technology, and in particular to a method, device, storage medium and processor for determining a vehicle monitoring strategy. Background Art

[0002] At present, most functional safety development is to meet the needs of scientific research and technological development, but scientific research and technological development often costs a lot of money, which is contrary to the cost reduction goal of vehicle engineering development at this stage. However, functional safety has become a top priority for the vehicle industry today and in the future, and vehicle safety has always been the focus of people's attention.

[0003] In related technologies, the costs of many functional safety mechanisms are still very high, and in many cases they cannot meet functional safety requirements. At the same time, many controllers currently carry out functional safety monitoring and triggering of safety mechanisms throughout the entire process, and need to record data and perform calculations at all times. As a result, the controllers are easily overloaded and have a high damage rate, which leads to the need to improve indicators in all aspects of the chip, which invisibly increases costs. Therefore, there is a technical problem that the cost of monitoring vehicle functional safety is too high.

[0004] With regard to the above-mentioned technical problem of excessively high cost of monitoring vehicle functional safety, no effective solution has been proposed so far. Summary of the invention

[0005] Embodiments of the present invention provide a method, device, storage medium, and processor for determining a vehicle monitoring strategy, so as to at least solve the technical problem of excessively high cost for monitoring vehicle functional safety.

[0006] According to one aspect of an embodiment of the present invention, a method for determining a monitoring strategy for a vehicle is provided. The method may include: obtaining the driving environment data of the vehicle and the driving habit data of the driving subject of the vehicle, wherein the driving habit data is used to indicate the behavioral habits of the driving subject in driving the vehicle; inputting the driving environment data and the driving habit data into a target driving prediction model to predict the target driving safety information of the vehicle, wherein the target driving prediction model is trained using the historical driving environment data of the vehicle and the historical driving habit data of the driving subject of the vehicle, and the target driving safety information is used to indicate the safety information of the vehicle during driving; based on the target driving safety information, determining the target monitoring strategy of the vehicle, wherein the target monitoring strategy is used to monitor the functional safety rules of the vehicle.

[0007] Optionally, based on the target driving safety information, a target monitoring strategy for the vehicle is determined, including: matching the target driving safety information with the driving safety information stored in the cloud to obtain a matching result, wherein the matching result is used to indicate the degree of matching between the target driving safety information and the driving safety information stored in the cloud; based on the matching result, determining the target monitoring strategy for the vehicle.

[0008] Optionally, based on the matching result, determining a target monitoring strategy for the vehicle includes: in response to the matching result being greater than or equal to a matching threshold, determining a monitoring strategy corresponding to driving safety information stored in the cloud; and determining the monitoring strategy as the target monitoring strategy.

[0009] Optionally, the method for determining the vehicle monitoring strategy further includes: in response to the matching result being less than a matching threshold, storing the target driving safety information in the cloud.

[0010] Optionally, the method for determining the vehicle's monitoring strategy also includes: obtaining the vehicle's historical driving environment data and the driving subject's historical driving habit data; using the historical driving environment data and the historical driving habit data to train an initial driving prediction model to obtain a target driving prediction model.

[0011] Optionally, the target monitoring strategy includes at least: an operating mechanism of a sensor, an operating mechanism of an actuator, and an operating mechanism of a controller, and a functional safety state that the vehicle needs to achieve.

[0012] According to another aspect of an embodiment of the present invention, a device for determining a monitoring strategy of a vehicle is also provided. The device may include: an acquisition unit, used to acquire the driving environment data of the vehicle and the driving habit data of the driving object of the vehicle, wherein the driving habit data is used to represent the behavioral habits of the driving object in driving the vehicle; a prediction unit, used to input the driving environment data and the driving habit data into a target driving prediction model to predict the target driving safety information of the vehicle, wherein the target driving prediction model is trained using the historical driving environment data of the vehicle and the historical driving habit data of the driving object of the vehicle, and the target driving safety information is used to indicate the safety information of the vehicle during driving; a determination unit, used to determine the target monitoring strategy of the vehicle based on the target driving safety information, wherein the target monitoring strategy is used to monitor the functional safety rules of the vehicle.

[0013] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided, which includes a stored program, wherein when the program is executed by a processor, the device where the storage medium is located is controlled to execute the method for determining the vehicle monitoring strategy in an embodiment of the present invention.

[0014] According to another aspect of an embodiment of the present invention, a processor is further provided. The processor is used to run a program, wherein when the program is run, the method for determining a vehicle monitoring strategy in an embodiment of the present invention is executed.

[0015] According to another aspect of an embodiment of the present invention, a vehicle is further provided, wherein the vehicle is used to execute the method for determining a monitoring strategy for a vehicle according to an embodiment of the present invention.

[0016] In an embodiment of the present invention, the driving environment data of the vehicle and the driving habit data of the driving object of the vehicle are obtained, wherein the driving habit data is used to represent the behavioral habits of the driving object in driving the vehicle; the driving environment data and the driving habit data are input into the target driving prediction model to predict the target driving safety information of the vehicle, wherein the target driving prediction model is trained by using the historical driving environment data of the vehicle and the historical driving habit data of the driving object of the vehicle, and the target driving safety information is used to indicate the safety information of the vehicle during driving; based on the target driving safety information, the target monitoring strategy of the vehicle is determined, wherein the target monitoring strategy is used to monitor the rules of the functional safety of the vehicle. That is to say, in an embodiment of the present invention, by obtaining the driving environment of the vehicle and the driving habits of the driving object, the target driving safety information of the vehicle is predicted by using the target driving prediction model, so as to determine the target monitoring strategy of the vehicle according to the target driving safety information. Since the present invention can determine the monitoring strategy of the vehicle according to the driving habit learning, the present invention focuses more on the indicators of the chip under the requirements of complex scenarios, and the comprehensive indicators of various aspects do not need to be very high, so as to achieve the purpose of determining the cost of the vehicle monitoring strategy, thereby solving the technical problem of the high cost of monitoring the functional safety of the vehicle, and achieving the technical effect of reducing the cost of monitoring the functional safety of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0018] Figure 1 is a flow chart of a method for determining a vehicle monitoring strategy according to an embodiment of the present invention;

[0019] Figure 2 is a flow chart of a method for determining a functional safety monitoring mechanism according to an embodiment of the present invention;

[0020] Figure 3 is a schematic diagram of a device for determining a vehicle monitoring strategy according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, functional component or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, functional components or devices.

[0023] According to an embodiment of the present invention, an embodiment of a method for determining a monitoring strategy for a vehicle is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0024] Figure 1 is a flow chart of a method for determining a vehicle monitoring strategy according to an embodiment of the present invention, such as Figure 1 As shown, the method may include the following steps:

[0025] Step S101, obtaining the driving environment data of the vehicle and the driving habit data of the driving subject of the vehicle.

[0026] In the technical solution provided in the above step S101 of the present invention, the driving habit data is used to represent the driving behavior habits of the driving subject.

[0027] In this embodiment, the driving environment data of the vehicle and the driving habit data of the driver of the vehicle are obtained. For example, the driving environment data of the vehicle and the driving habit data of the driver of the vehicle are obtained through different sensors. This is only an example and does not limit the specific method of obtaining the driving environment data of the vehicle and the driving habit data of the driver of the vehicle.

[0028] Optionally, by acquiring the vehicle's driving environment data and the driving habit data of the driver, it can help analyze driving behavior and road conditions, and promptly discover potential safety hazards, thereby improving the accuracy of determining the vehicle target monitoring strategy.

[0029] Step S102, inputting the driving environment data and the driving habit data into a target driving prediction model to predict target driving safety information of the vehicle.

[0030] In the technical solution provided in step S102 of the present invention, the target driving prediction model is trained using the historical driving environment data of the vehicle and the historical driving habit data of the driving object of the vehicle, and the target driving safety information is used to indicate the safety information of the vehicle during driving. The target driving prediction model can also be called a driving habit estimation model, and the target driving safety information can also be called a driving habit estimation result.

[0031] In this embodiment, after the driving environment data of the vehicle and the driving habit data of the driving subject of the vehicle are acquired in step S101, the driving environment data and the driving habit data are input into the target driving prediction model to predict the target driving safety information of the vehicle.

[0032] For example, the driving habit data is input into the driving habit prediction model, and the driving habit is identified according to the driving habit data to obtain the driving habit output by the driving habit prediction model and the driving habit prediction result corresponding to the driving habit.

[0033] Step S103: determining a target monitoring strategy for the vehicle based on the target driving safety information.

[0034] In the technical solution provided in the above step S103 of the present invention, the target monitoring strategy is used to monitor the functional safety rules of the vehicle. The target monitoring strategy can also be called a functional safety mechanism.

[0035] In this embodiment, after the target driving safety information of the vehicle is predicted in step S102, a target monitoring strategy for the vehicle is determined according to the target driving safety information.

[0036] For example, the target driving safety information is uploaded to the cloud and deep neural network learning is performed to derive the functional safety trigger mechanism of the vehicle at that time.

[0037] Optionally, the target driving safety information is matched with the driving safety information stored in the cloud to obtain a matching result, wherein the matching result is used to indicate the degree of matching between the target driving safety information and the driving safety information stored in the cloud, thereby determining the target monitoring strategy of the vehicle based on the matching result.

[0038] For example, when the matching result is greater than or equal to the matching threshold, it means that the target driving safety information has storage records and corresponding monitoring strategies in the cloud. Based on this, the monitoring strategy corresponding to the driving safety information stored in the cloud can be determined; and the monitoring strategy can be determined as the target monitoring strategy.

[0039] For another example, when the matching result is less than the matching threshold, it means that there is no storage record of the target driving safety information and the corresponding monitoring strategy in the cloud. Based on this, the target driving safety information can be stored in the cloud.

[0040] Optionally, the target monitoring strategy includes at least: an operating mechanism of a sensor, an operating mechanism of an actuator, and an operating mechanism of a controller, and a functional safety state that the vehicle needs to achieve.

[0041] Optionally, by determining the target monitoring strategy, in future functional safety development, there is no need for the controller to monitor and calculate throughout the entire process. Instead, the computing power can be increased and monitoring can be performed only when the sensor or actuator senses that the driver has similar driving behavior habits, thereby reducing the cost of monitoring vehicle functional safety.

[0042] It should be noted that the above embodiment can be executed by a device for determining a vehicle monitoring strategy.

[0043] In the above steps S101 to S103 of the present invention, the driving environment data of the vehicle and the driving habit data of the driving object of the vehicle are obtained, wherein the driving habit data is used to indicate the behavior habits of the driving object in driving the vehicle; the driving environment data and the driving habit data are input into the target driving prediction model to predict the target driving safety information of the vehicle, wherein the target driving prediction model is trained by using the historical driving environment data of the vehicle and the historical driving habit data of the driving object of the vehicle, and the target driving safety information is used to indicate the safety information of the vehicle during driving; based on the target driving safety information, the target monitoring strategy of the vehicle is determined, wherein the target monitoring strategy is used to monitor the rules of the functional safety of the vehicle. That is to say, in the embodiment of the present invention, by obtaining the driving environment of the vehicle and the driving habits of the driving object, the target driving safety information of the vehicle is predicted by using the target driving prediction model, so as to determine the target monitoring strategy of the vehicle according to the target driving safety information. Since the present invention can determine the monitoring strategy of the vehicle according to the driving habit learning, the present invention focuses more on the indicators of the chip under the requirements of complex scenarios, and the comprehensive indicators of various aspects do not need to be very high, so as to achieve the purpose of determining the cost of the vehicle monitoring strategy, thereby solving the technical problem of the high cost of monitoring the functional safety of the vehicle, and achieving the technical effect of reducing the cost of monitoring the functional safety of the vehicle.

[0044] The above method of this embodiment is further introduced below.

[0045] As an optional implementation method, based on the target driving safety information, a target monitoring strategy for the vehicle is determined, including: matching the target driving safety information with the driving safety information stored in the cloud to obtain a matching result, wherein the matching result is used to indicate the degree of matching between the target driving safety information and the driving safety information stored in the cloud; based on the matching result, determining the target monitoring strategy for the vehicle.

[0046] In this embodiment, the target driving safety information is matched with the driving safety information stored in the cloud to obtain a matching result; based on the matching result, the target monitoring strategy of the vehicle is determined.

[0047] Optionally, by matching with driving safety information stored in the cloud, the driving condition of the target vehicle can be discovered in a timely manner, thereby improving the accuracy of determining the vehicle target monitoring strategy.

[0048] As an optional implementation method, based on the matching result, the target monitoring strategy of the vehicle is determined, including: in response to the matching result being greater than or equal to a matching threshold, determining the monitoring strategy corresponding to the driving safety information stored in the cloud; and determining the monitoring strategy as the target monitoring strategy.

[0049] In this embodiment, when the matching result is greater than or equal to the matching threshold, the monitoring strategy corresponding to the driving safety information stored in the cloud is determined; and the monitoring strategy is determined as the target monitoring strategy.

[0050] For example, assuming the matching threshold is 85%, the matching result between the target driving safety information and the driving safety information stored in the cloud is 90%. Since 90%>85%, that is, the matching result between the target driving safety information and the driving safety information stored in the cloud is greater than the matching threshold, based on this, the monitoring strategy corresponding to the driving safety information stored in the cloud can be determined as the target monitoring strategy.

[0051] As an optional implementation manner, based on the matching result, a target monitoring strategy for the vehicle is determined, including: in response to the matching result being less than a matching threshold, storing the target driving safety information in the cloud.

[0052] In this embodiment, when the matching result is less than the matching threshold, the target driving safety information is stored in the cloud.

[0053] For example, assuming the matching threshold is 85%, the matching result between the target driving safety information and the driving safety information stored in the cloud is 80%. Since 80%<85%, that is, the matching result between the target driving safety information and the driving safety information stored in the cloud is less than the matching threshold, the target driving safety information can be stored in the cloud.

[0054] As an optional implementation method, the method for determining the vehicle's monitoring strategy also includes: obtaining the vehicle's historical driving environment data and the driving subject's historical driving habit data; using the historical driving environment data and the historical driving habit data to train an initial driving prediction model to obtain a target driving prediction model.

[0055] In this embodiment, the historical driving environment data of the vehicle and the historical driving habit data of the driving object are acquired and used to train the initial driving prediction model to obtain the target driving prediction model.

[0056] Optionally, by using the historical driving environment data of the vehicle and the historical driving habit data of the driving object to train the initial driving model, the target driving prediction model is determined, the accuracy of the target driving prediction model is ensured, thereby improving the accuracy of determining the vehicle target monitoring strategy.

[0057] As an optional implementation method, the target monitoring strategy includes at least: an operating mechanism of a sensor, an operating mechanism of an actuator, and an operating mechanism of a controller, as well as a functional safety state that the vehicle needs to achieve.

[0058] In this embodiment, the target monitoring strategy includes at least: an operating mechanism of a sensor, an operating mechanism of an actuator, and an operating mechanism of a controller, and a functional safety state that the vehicle needs to achieve.

[0059] Optionally, the monitoring strategy needs to clarify the functional safety states that the vehicle needs to achieve, including compliance with traffic regulations, collision avoidance, and passenger safety. By monitoring the operating states of sensors, actuators, and controllers, it is ensured that the vehicle can achieve these functional safety states during operation.

[0060] It should be noted that the above embodiment can be executed by a device for determining a vehicle monitoring strategy.

[0061] In this embodiment, the driving environment data of the vehicle and the driving habit data of the driving object of the vehicle are obtained, wherein the driving habit data is used to represent the behavior habits of the driving object in driving the vehicle; the driving environment data and the driving habit data are input into the target driving prediction model to predict the target driving safety information of the vehicle, wherein the target driving prediction model is trained by using the historical driving environment data of the vehicle and the historical driving habit data of the driving object of the vehicle, and the target driving safety information is used to indicate the safety information of the vehicle during driving; based on the target driving safety information, the target monitoring strategy of the vehicle is determined, wherein the target monitoring strategy is used to monitor the rules of the functional safety of the vehicle. That is to say, in the embodiment of the present invention, by obtaining the driving environment of the vehicle and the driving habits of the driving object, the target driving safety information of the vehicle is predicted by using the target driving prediction model, so as to determine the target monitoring strategy of the vehicle according to the target driving safety information. Since the present invention can determine the monitoring strategy of the vehicle according to the driving habit learning, the present invention focuses more on the indicators of the chip under the requirements of complex scenarios, and the comprehensive indicators of various aspects do not need to be very high, so as to achieve the purpose of determining the cost of the vehicle monitoring strategy, thereby solving the technical problem of the high cost of monitoring the functional safety of the vehicle, and achieving the technical effect of reducing the cost of monitoring the functional safety of the vehicle.

[0062] The technical solution of the embodiment of the present invention is illustrated below in conjunction with preferred implementation modes.

[0063] At present, most functional safety development is to meet the needs of scientific research and technological development, but scientific research and technological development often costs a lot of money, which is contrary to the cost reduction goal of vehicle engineering development at this stage. However, functional safety has become a top priority for the vehicle industry today and in the future, and vehicle safety has always been the focus of people's attention.

[0064] In related technologies, the cost of many functional safety mechanisms is still very high, and in many cases, they cannot meet the functional safety requirements. At the same time, many controllers at this stage are monitoring functional safety and triggering safety mechanisms throughout the entire process, and need to record data and calculate at all times. Therefore, it is easy for the controller to reach the load, and the damage rate is high, which leads to the need to improve the indicators of various aspects of the chip, which also adds costs invisibly. Therefore, there is a technical problem that the cost of monitoring vehicle functional safety is too high. In response to the above-mentioned technical problem of the high cost of monitoring vehicle functional safety, no effective solution has been proposed.

[0065] However, an embodiment of the present invention proposes a method for determining a functional safety monitoring mechanism, by acquiring driving habit data and scenario data of a target vehicle user, inputting the driving habit data into a driving habit prediction model, obtaining driving habits output by the driving habit prediction model and driving habit prediction results corresponding to the driving habits, and determining a strategy for functional safety monitoring of the vehicle based on the prediction results; thereby solving the technical problem of excessively high cost of monitoring vehicle functional safety and achieving the technical effect of reducing the cost of monitoring vehicle functional safety.

[0066] The embodiments of the present invention are further described below.

[0067] Figure 2 is a flow chart of a method for determining a functional safety monitoring mechanism according to an embodiment of the present invention. Figure 2 As shown, the method comprises the following steps:

[0068] Step S201, obtaining driving habit data of a driver of a target vehicle.

[0069] In this embodiment, the driving habit data of the target vehicle's driver is obtained. For example, the driving habit data of the target vehicle's driver is obtained through a sensor.

[0070] Optionally, the driving habit data may include the following: driving speed, route preference, driving behavior during driving hours, driving style, vehicle maintenance, and driving records.

[0071] Optionally, the driving speed may include data such as average speed, maximum speed, number of rapid accelerations and rapid decelerations, etc.

[0072] Optionally, route preferences may include data such as frequently visited places, frequently travelled routes, and frequent stops.

[0073] Alternatively, the driving period may include data such as the driver's preferred driving time period, such as morning, afternoon or evening.

[0074] Optionally, the driving behavior may include data such as whether a mobile phone or other devices are frequently used, whether a seat belt is worn, and whether traffic regulations are obeyed.

[0075] Optionally, the driving style may include data such as whether the driver drives smoothly, changes lanes frequently, or exceeds the speed limit.

[0076] Optionally, vehicle maintenance may include data such as whether regular maintenance is performed, vehicle condition is checked, and parts are replaced.

[0077] Optionally, the driving record may include data such as past accident records, violation records, etc.

[0078] Optionally, these driving habit data can be obtained through vehicle-mounted equipment, driving recorders, insurance companies and other channels, and used to analyze the driver's driving habits, thereby providing a reference for vehicle management and safety.

[0079] Step S202, identifying the safety measures of the vehicle at this time and the actions when the vehicle reaches a safe state.

[0080] In this embodiment, after the driving habit data of the target object is acquired in step S201, the safety measures of the vehicle at this time and the actions of the vehicle when it reaches a safe state are identified based on the acquired driving habit data of the target object.

[0081] Optionally, identify the safety measures taken by sensors, controllers, and actuators at this time and the actions taken when the vehicle reaches a safe state.

[0082] Step S203, inputting the identified data into a driving behavior habit prediction model to obtain driving behavior habits and driving behavior habit prediction results.

[0083] In this embodiment, after the safety measures of the vehicle and the actions of the vehicle when it reaches a safe state are identified in step S202, the identified data is input into the driving behavior habit prediction model to obtain the driving behavior habits and the driving behavior habit prediction results.

[0084] Optionally, these data are input into a driving behavior habit prediction model, and such data are uploaded to the cloud to perform driving behavior habit recognition based on the driver behavior habit data to obtain the driving behavior habits output by the model and the driving behavior habit prediction results corresponding to the driving behavior habits. The driving behavior habit prediction model is based on the user triggering the functional safety mechanism in the controller for this situation to perform incremental learning and update.

[0085] Step S204, estimating the result based on the driving behavior habit and triggering the functional safety mechanism in this case.

[0086] In this embodiment, after the driving behavior habits and the driving behavior habit prediction results are determined in step S203, the functional safety mechanism in this case is triggered according to the driving behavior habit prediction results.

[0087] Optionally, the driving behavior habits are estimated and the functional safety mechanism in this case is triggered, the status of the sensors, controllers, and actuators at this time is output and the driver is prompted.

[0088] Optionally, deep neural network learning is carried out to draw conclusions and trigger safety mechanisms when encountering similar driver behavior habits.

[0089] Optionally, the data obtained through monitoring is used to make an estimated judgment and uploaded to the cloud for deep neural network learning to derive the functional safety trigger mechanism at this time.

[0090] For example, if there are no unexpected situations on the way from home to work, the driver's driving behavior habits are fixed, unless there are special circumstances. For example, if someone crosses the road temporarily, the situation will be specially recorded, and deep neural network learning will be performed to estimate what kind of functional safety mechanism the vehicle will trigger if there is danger at this time, and record the actions and judgments of sensors, actuators, and controllers. In this way, when driving on this road again or when the road conditions are similar in the future, the controller does not need to monitor the entire process, but only starts to increase computing power when the sensor detects irregular movement of pedestrians or detects an intersection, and is ready to trigger the functional safety mechanism at any time.

[0091] Alternatively, deep neural network learning refers to the process of training a deep neural network to learn representations and features from data. A deep neural network is a multi-layered neural network model that typically contains multiple hidden layers and nonlinear activation functions and can learn complex nonlinear relationships.

[0092] Optionally, the process of deep neural network learning usually includes steps such as data preparation, network construction, initialization parameters, forward propagation, loss calculation, back propagation, parameter optimization and model evaluation.

[0093] Optionally, data preparation may include collecting and preparing training data, including input features and corresponding labels.

[0094] Optionally, network construction may include designing the structure of a deep neural network, including the number of neurons in an input layer, a hidden layer, and an output layer, an activation function, etc.

[0095] Optionally, the initialization parameters may include randomly initializing weights and bias parameters of the neural network.

[0096] Optionally, forward propagation may include inputting training data into the neural network and computing output results.

[0097] Optionally, calculating the loss may include evaluating the distance between the output of the neural network and the true label using a loss function.

[0098] Optionally, back-propagation may include calculating the gradient of the loss function with respect to the neural network parameters through a back-propagation algorithm, and updating the parameters to reduce the loss.

[0099] Optionally, parameter optimization may include iteratively training the neural network using an optimization algorithm such as stochastic gradient descent until the loss function converges or a specified stopping condition is reached.

[0100] Optionally, model evaluation can include evaluating the performance of the trained neural network model using a validation set or a test set.

[0101] Alternatively, deep neural network learning can be applied to various fields such as computer vision, natural language processing, speech recognition, etc., and has achieved many important results and applications.

[0102] In this embodiment, the functional safety monitoring mechanism determination method provided by the present invention is mainly to save the chip cost of the domain controller. A functional safety chip that can be equipped with ASIL D (Automotive Safety Integrity Level D) requires multiple indicators, such as Single Point Failure Metric (SPFM), Latent Failure Metric (LFM), Probabilistic Mission Hardware Failure (PMHF). These indicators directly affect the performance indicators of the chip. These indicators all need to be tested for a long time, especially the vehicle level test requires multiple scenarios. The invention learns driving habits and focuses more on the indicators of chips under complex scenarios. The comprehensive indicators of all aspects do not need to be so high. Therefore, the cost reduction effect can be achieved to a certain extent. The indicator can be composed of data such as improvement in yield, quality, accuracy and efficiency, saving in energy consumption, raw materials, and processes, and ease of processing, operation, control, and use.

[0103] Optionally, the single point failure index is an index used to measure the probability or impact of a single point failure that may occur in the system. Common single point failure indicators include availability, mean time between failures (MTBF), mean time to repair (MTTR), failure probability, and fault tolerance.

[0104] Optionally, availability refers to the availability index of the system that can be used to evaluate whether the system can continue to operate normally after encountering a single point failure. Availability is usually expressed as a percentage, for example, 99.9% availability means that the system will only be down for no more than 8.76 hours per year.

[0105] Alternatively, Mean Time Between Failures (MTBF) refers to the average time a system operates between failures. The longer the MTBF, the higher the stability and reliability of the system.

[0106] Alternatively, mean time to repair (MTTR) refers to the average time it takes for a system to be repaired after a failure. The shorter the MTTR, the faster the system will recover.

[0107] Optionally, the failure probability refers to the probability of a system failure within a certain period of time. By monitoring the failure probability, potential problems in the system can be discovered in a timely manner and measures can be taken to solve them.

[0108] Optionally, fault tolerance refers to whether the system can continue to operate normally when encountering a single point failure. A system with good fault tolerance can automatically switch to a backup channel or backup device when a failure occurs, ensuring the stability and availability of the system.

[0109] Optionally, potential failure indicators refer to early warning indicators of possible failures during the operation of equipment or systems. These indicators can help monitor the operating status of equipment, detect problems in a timely manner and take measures to repair them, so as to avoid production interruptions or losses caused by equipment failures. Common potential failure indicators include abnormal changes in parameters such as equipment temperature, vibration frequency, noise level, current and voltage, and abnormal behavior of equipment operating status. By monitoring these indicators and establishing a corresponding early warning system, potential failures can be detected in advance and preventive maintenance can be performed to ensure the normal operation of equipment.

[0110] Optionally, the hardware random failure probability index refers to the probability of hardware failure during operation. This index is usually expressed as a decimal, for example, 0.01 means the probability of hardware failure is 1%. The hardware random failure probability index is one of the important indicators for evaluating hardware reliability. It can help users understand the stability and reliability level of the hardware, so as to take corresponding measures to prevent and handle hardware failures.

[0111] Optionally, the present invention mainly monitors controllers, chips, etc. with functional safety development through learning such as deep neural networks, and learns the information given to them by the whole vehicle or other sensors and their processing solutions when they encounter risks. In this way, preparations can be made in advance when encountering similar situations, and the system can enter a state of triggering the functional safety mechanism at any time. This can avoid load and play the original role of functional safety at critical moments, preventing damage to the whole vehicle caused by failure of electronic appliances.

[0112] In this embodiment, by acquiring the driving habit data and scenario data of the target vehicle user, the driving habit data is input into a driving habit prediction model, the driving habits output by the driving habit prediction model and the driving habit prediction results corresponding to the driving habits are obtained, and according to the prediction results, the strategy for functional safety monitoring of the vehicle is determined; thereby solving the technical problem of excessively high cost of monitoring vehicle functional safety and achieving the technical effect of reducing the cost of monitoring vehicle functional safety.

[0113] According to an embodiment of the present invention, a device for determining a monitoring strategy for a vehicle is also provided. It should be noted that the device for determining a monitoring strategy for a vehicle can be used to execute the method for determining a monitoring strategy for a vehicle in the method embodiment.

[0114] Figure 3 is a schematic diagram of a device for determining a vehicle monitoring strategy according to an embodiment of the present invention. Figure 3 As shown, the device 300 for determining the monitoring strategy of the vehicle may include: an acquisition unit 301 , a prediction unit 302 and a determination unit 303 .

[0115] The acquisition unit 301 is used to acquire the driving environment data of the vehicle and the driving habit data of the driver of the vehicle, wherein the driving habit data is used to represent the behavior habits of the driver in driving the vehicle.

[0116] The prediction unit 302 is used to input the driving environment data and the driving habit data into the target driving prediction model to predict the target driving safety information of the vehicle, wherein the target driving prediction model is trained using the historical driving environment data of the vehicle and the historical driving habit data of the driving object of the vehicle, and the target driving safety information is used to indicate the safety information of the vehicle during driving.

[0117] The determination unit 303 is used to determine a target monitoring strategy for the vehicle based on the target driving safety information, wherein the target monitoring strategy is used to monitor the functional safety rules of the vehicle.

[0118] Optionally, the determination unit 303 may include: a storage module, used to match the target driving safety information with the driving safety information stored in the cloud to obtain a matching result, wherein the matching result is used to indicate the degree of matching between the target driving safety information and the driving safety information stored in the cloud; a first determination module, used to determine the target monitoring strategy of the vehicle based on the matching result.

[0119] Optionally, the first determination module may include: a first determination submodule, used to determine the monitoring strategy corresponding to the driving safety information stored in the cloud in response to the matching result being greater than or equal to a matching threshold; and a second determination submodule, used to determine the monitoring strategy as a target monitoring strategy.

[0120] Optionally, the device 300 for determining the vehicle monitoring strategy may further include: a storage unit, configured to store the target driving safety information in the cloud in response to the matching result being less than a matching threshold.

[0121] Optionally, the device 300 for determining the vehicle monitoring strategy may further include: a first acquisition unit, used to acquire the historical driving environment data of the vehicle and the historical driving habit data of the driving object; a training unit, used to train the initial driving prediction model using the historical driving environment data and the historical driving habit data to obtain a target driving prediction model.

[0122] In this embodiment, the driving environment data of the vehicle and the driving habit data of the driving object of the vehicle are obtained, wherein the driving habit data is used to represent the behavior habits of the driving object in driving the vehicle; the driving environment data and the driving habit data are input into the target driving prediction model to predict the target driving safety information of the vehicle, wherein the target driving prediction model is trained by using the historical driving environment data of the vehicle and the historical driving habit data of the driving object of the vehicle, and the target driving safety information is used to indicate the safety information of the vehicle during driving; based on the target driving safety information, the target monitoring strategy of the vehicle is determined, wherein the target monitoring strategy is used to monitor the rules of the functional safety of the vehicle. That is to say, in the embodiment of the present invention, by obtaining the driving environment of the vehicle and the driving habits of the driving object, the target driving safety information of the vehicle is predicted by using the target driving prediction model, so as to determine the target monitoring strategy of the vehicle according to the target driving safety information. Since the present invention can determine the monitoring strategy of the vehicle according to the driving habit learning, the present invention focuses more on the indicators of the chip under the requirements of complex scenarios, and the comprehensive indicators of various aspects do not need to be very high, so as to achieve the purpose of determining the cost of the vehicle monitoring strategy, thereby solving the technical problem of the high cost of monitoring the functional safety of the vehicle, and achieving the technical effect of reducing the cost of monitoring the functional safety of the vehicle.

[0123] According to an embodiment of the present invention, a computer-readable storage medium is further provided. The storage medium includes a stored program, wherein the program executes the method for determining the monitoring strategy of a vehicle in the method embodiment.

[0124] According to an embodiment of the present invention, a processor is further provided. The processor is used to run a program, wherein when the program is run, the method for determining the monitoring strategy of the vehicle in the method embodiment is executed.

[0125] According to an embodiment of the present invention, a vehicle is further provided. The vehicle is used to execute the method for determining the monitoring strategy of the vehicle in Embodiment 1.

[0126] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0127] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0128] In the several embodiments provided by the present invention, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic, for example, the division of units can be a logical function division, and there can be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0129] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0130] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0131] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent functional component, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software functional component, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc., which can store program codes.

[0132] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for determining a vehicle monitoring strategy, characterized in that: include: Acquire driving environment data of a vehicle and driving habit data of a driver of the vehicle, wherein the driving habit data is used to represent the behavior habits of the driver in driving the vehicle; Inputting the driving environment data and the driving habit data into a target driving prediction model to predict target driving safety information of the vehicle, wherein the target driving prediction model is trained using historical driving environment data of the vehicle and historical driving habit data of the driving subject of the vehicle, and the target driving safety information is used to indicate safety information of the vehicle during driving; Based on the target driving safety information, a target monitoring strategy for the vehicle is determined, wherein the target monitoring strategy is used to monitor rules for functional safety of the vehicle.

2. The method according to claim 1, characterized in that Determining a target monitoring strategy for the vehicle based on the target driving safety information includes: Matching the target driving safety information with the driving safety information stored in the cloud to obtain a matching result, wherein the matching result is used to indicate the matching degree between the target driving safety information and the driving safety information stored in the cloud; Based on the matching result, the target monitoring strategy of the vehicle is determined.

3. The method according to claim 2, characterized in that Determining the target monitoring strategy of the vehicle based on the matching result includes: In response to the matching result being greater than or equal to a matching threshold, determining a monitoring strategy corresponding to the driving safety information stored in the cloud; The monitoring strategy is determined as the target monitoring strategy.

4. The method according to claim 2, characterized in that: The method further comprises: In response to the matching result being less than a matching threshold, the target driving safety information is stored in the cloud.

5. The method according to claim 1, characterized in that The method further comprises: Acquiring the historical driving environment data of the vehicle and the historical driving habit data of the driving subject; The historical driving environment data and the historical driving habit data are used to train an initial driving prediction model to obtain the target driving prediction model.

6. The method according to any one of claims 1 to 5, characterized in that The target monitoring strategy includes at least: an operating mechanism of a sensor, an operating mechanism of an actuator, and an operating mechanism of a controller, as well as a functional safety state that the vehicle needs to achieve.

7. A device for determining a vehicle monitoring strategy, characterized in that: include: An acquisition unit, used to acquire driving environment data of a vehicle and driving habit data of a driver of the vehicle, wherein the driving habit data is used to represent the behavior habit of the driver in driving the vehicle; a prediction unit, configured to input the driving environment data and the driving habit data into a target driving prediction model to predict target driving safety information of the vehicle, wherein the target driving prediction model is trained using historical driving environment data of the vehicle and historical driving habit data of the driving subject of the vehicle, and the target driving safety information is used to indicate safety information of the vehicle during driving; A determination unit is used to determine a target monitoring strategy for the vehicle based on the target driving safety information, wherein the target monitoring strategy is used to monitor the functional safety rules of the vehicle.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed by a processor, the device where the storage medium is located is controlled to execute the method according to any one of claims 1 to 6.

9. A processor, characterized in that: The processor is used to run a program, wherein the program executes the method according to any one of claims 1 to 6 when running.

10. A vehicle, characterized in that: The vehicle is used to perform the method according to any one of claims 1 to 6.

Images