Vehicle acceleration prediction method and device, electronic equipment and storage medium

Abstract

The invention provides a vehicle acceleration prediction method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring environment information around a vehicle and vehicle running state data in real time; based on the environment information and the vehicle running state data, a dynamic model of the vehicle is constructed, and the dynamic model is used for simulating dynamic responses of the vehicle under different working conditions; target features related to vehicle acceleration changes are extracted from the environment information and the vehicle running state data, and the target features are associated with parameters in the dynamic model; based on the dynamic model associated with the target features, reverse reasoning is carried out on the vehicle acceleration change reason, and based on the reverse reasoning result of the acceleration change reason, the acceleration of the vehicle in the future time period is predicted. According to the invention, the dependence on data quality can be reduced, the calculation complexity is reduced, and the accuracy, real-time performance and wide applicability of vehicle acceleration prediction are improved.

Description

Technical Field

[0001] This application relates to the technical field of new energy vehicles, and particularly to a vehicle acceleration prediction method, device, electronic device, and storage medium. Background Art

[0002] With the development of autonomous driving technology, vehicle acceleration prediction has become a key link in vehicle control systems. By accurately predicting acceleration, vehicles can adjust operations such as vehicle speed and braking more intelligently, improving driving safety and comfort. Currently, existing technologies usually rely on environmental data and vehicle state data collected from sensors. Through preprocessing steps such as data cleaning, denoising, and normalization, eigenvalue related to acceleration are extracted, such as vehicle speed, acceleration, surrounding vehicle states, and road conditions. The extracted features are fed into an acceleration prediction model for calculation, and the output acceleration value of the model is used to guide vehicle control operations.

[0003] However, existing technologies still have the following significant defects in acceleration prediction:

[0004] First of all, acceleration prediction highly depends on the quality of data collected by vehicle sensors. If the data is inaccurate or there are deficiencies in the preprocessing link, the prediction results may deviate, affecting the decision-making of vehicle control systems.

[0005] Secondly, the acceleration prediction model needs to process a large amount of real-time data and perform complex calculations and analyses, which poses high requirements on the computing power and processing speed of vehicles. If the computing resources are insufficient, it may lead to prediction delays and affect real-time performance.

[0006] In addition, in extreme weather conditions (such as rain and snow) or complex road conditions (such as rough roads and slippery roads), the performance of sensors is often affected, resulting in a decline in data quality. Moreover, existing models often lack sufficient adaptability when dealing with different road types or traffic conditions and are difficult to maintain prediction accuracy in various scenarios. Summary of the Invention

[0007] In view of this, embodiments of this application provide a vehicle acceleration prediction method, device, electronic device, and storage medium to solve the problems of strong dependence on data quality, high computational complexity, and poor environmental adaptability existing in the prior art.

[0008] In the first aspect of the embodiments of the present application, a vehicle acceleration prediction method is provided, including: collecting real-time environmental information around the vehicle and vehicle operation state data; constructing a dynamic model of the vehicle based on the environmental information and vehicle operation state data, where the dynamic model is used to simulate the dynamic response of the vehicle under different working conditions; extracting target features related to vehicle acceleration changes from the environmental information and vehicle operation state data, and associating the target features with the parameters in the dynamic model; based on the dynamic model after associating the target features, performing reverse reasoning on the reasons for vehicle acceleration changes, and predicting the acceleration of the vehicle in a future time period based on the reverse reasoning results of the reasons for acceleration changes.

[0009] In the second aspect of the embodiments of the present application, a vehicle acceleration prediction device is provided, including: a collection module configured to collect real-time environmental information around the vehicle and vehicle operation state data; a construction module configured to construct a dynamic model of the vehicle based on the environmental information and vehicle operation state data, where the dynamic model is used to simulate the dynamic response of the vehicle under different working conditions; an association module configured to extract target features related to vehicle acceleration changes from the environmental information and vehicle operation state data, and associate the target features with the parameters in the dynamic model; a prediction module configured to perform reverse reasoning on the reasons for vehicle acceleration changes based on the dynamic model after associating the target features, and predict the acceleration of the vehicle in a future time period based on the reverse reasoning results of the reasons for acceleration changes.

[0010] In the third aspect of the embodiments of the present application, an electronic device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of the above method when executing the computer program.

[0011] In the fourth aspect of the embodiments of the present application, a readable storage medium is provided, where the readable storage medium stores a computer program, and the computer program implements the steps of the above method when executed by a processor.

[0012] The above at least one technical solution adopted in the embodiments of the present application can achieve the following beneficial effects:

[0013] By collecting real-time environmental information around the vehicle and vehicle operation state data; based on the environmental information and vehicle operation state data, constructing a dynamic model of the vehicle, where the dynamic model is used to simulate the dynamic response of the vehicle under different working conditions; extracting target features related to vehicle acceleration changes from the environmental information and vehicle operation state data, and associating the target features with the parameters in the dynamic model; based on the dynamic model after associating the target features, performing reverse reasoning on the reasons for vehicle acceleration changes, and based on the reverse reasoning results of the acceleration change reasons, predicting the acceleration of the vehicle in the future time period. This application can reduce the dependence on data quality, reduce the computational complexity, and improve the accuracy, real-time performance, and wide applicability of vehicle acceleration prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0015] Figure 1 It is a flowchart of the vehicle acceleration prediction method provided by the embodiment of the present application;

[0016] Figure 2 It is a structural schematic diagram of the vehicle acceleration prediction device provided by the embodiment of the present application;

[0017] Figure 3 It is a structural schematic diagram of the electronic device provided by the embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system structures and technologies are presented to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0019] Acceleration prediction is one of the key links in autonomous driving technology, aiming to process the data collected by vehicle sensors, predict the acceleration of the vehicle, and use it as the input of the vehicle control system to achieve automatic adjustment of operations such as vehicle speed and braking.

[0020] The acceleration prediction process of the prior art usually includes the following steps:

[0021] First, various sensors of the vehicle (such as speed sensors, acceleration sensors, cameras, radars, etc.) collect data on the vehicle and its surrounding environment. This data may include the current speed, acceleration, the status of surrounding vehicles, road conditions, etc. Before further using this data, it must undergo preprocessing operations such as cleaning, denoising, and normalization to ensure the quality and consistency of the data.

[0022] Next, the preprocessed data will be analyzed to extract features related to acceleration prediction. These features may include the current speed, acceleration, surrounding traffic conditions, road type, and weather conditions of the vehicle. The extracted features are the key data that make up the input of the prediction model.

[0023] Then, the extracted features are input into the acceleration prediction model for calculation. This model is usually based on machine learning or statistical algorithms and can predict the future acceleration of the vehicle according to the input features. This predicted value will be used as the input of the vehicle control system to adjust functions such as vehicle speed and control brakes to ensure driving safety and comfort.

[0024] Although the existing technologies have been able to provide a certain degree of acceleration prediction, the existing technologies still have the following disadvantages:

[0025] 1. Strong data dependence: The accuracy of acceleration prediction highly depends on the quality of the data collected by vehicle sensors. If there is noise, loss, or error in the sensor data, or if there are problems in the data preprocessing and feature extraction steps, it may lead to inaccurate prediction results. In addition, the performance of the algorithm also directly affects the prediction accuracy. Therefore, any fluctuations in the data source or degradation of the algorithm performance may seriously affect the prediction effect.

[0026] 2. High computational complexity: Acceleration prediction requires real-time processing of a large amount of data and complex computational analysis. This means that the system must have sufficient computing power and fast data processing capabilities, otherwise it cannot ensure the real-time and accuracy of the prediction. In practical applications, if the vehicle has limited computing resources or a high computing load, it may lead to prediction delays or performance degradation, affecting driving decisions.

[0027] 3. Poor environmental adaptability: In extreme weather (such as heavy rain, snow) or complex road conditions (such as rough roads), the performance of sensors is easily affected. This may lead to inaccurate data collected by sensors, thus affecting the accuracy of acceleration prediction. In addition, existing acceleration prediction models are usually optimized for specific driving conditions. When facing different road types (such as urban roads, highways, rural paths) or traffic conditions, the adaptability of the model is limited, and it is difficult to maintain consistent prediction performance in various scenarios.

[0028] In view of the problems existing in the above-mentioned prior art, the present application proposes an acceleration prediction technology based on multi-sensor data, which solves the problems of dependence on data quality, high computational complexity, and poor environmental adaptability in acceleration prediction in the prior art. The technical solution of the present application realizes more accurate and real-time acceleration prediction by integrating steps such as environmental perception, vehicle dynamic model, feature extraction and association, reverse reasoning, binocular speed measurement, acceleration prediction, and feedback correction.

[0029] The content of the technical solution of the present application will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0030] Figure 1 It is a schematic flow chart of the vehicle acceleration prediction method provided by the embodiment of the present application. As Figure 1 shown, the vehicle acceleration prediction method may specifically include:

[0031] S101, collect the environmental information around the vehicle and the vehicle operation state data in real time;

[0032] S102, based on the environmental information and the vehicle operation state data, construct a dynamic model of the vehicle, and the dynamic model is used to simulate the dynamic response of the vehicle under different working conditions;

[0033] S103, extract target features related to the vehicle acceleration change from the environmental information and the vehicle operation state data, and associate the target features with the parameters in the dynamic model;

[0034] S104, based on the dynamic model after associating the target features, perform reverse reasoning on the reasons for the vehicle acceleration change, and based on the reverse reasoning result of the reasons for the acceleration change, predict the acceleration of the vehicle in the future time period.

[0035] In some embodiments, collecting the environmental information around the vehicle and the vehicle operation state data in real time includes:

[0036] Use multiple sensors to collect the environmental information around the vehicle and the vehicle operation state data in real time, where the sensors include image sensors, vehicle speed sensors, acceleration sensors, and engine speed sensors, and the environmental information includes road conditions, traffic signal states, and dynamic information of surrounding vehicles and pedestrians.

[0037] Specifically, this embodiment provides a method for collecting the environmental information around the vehicle and the vehicle operation state data in real time. This method obtains the environmental data around the vehicle and the state data of the vehicle through multiple sensors, and the accuracy and comprehensiveness of the data provide a reliable basis for acceleration prediction.

[0038] First, the system is configured with multiple sensors, including but not limited to the following types:

[0039] Image sensor: Obtains visual information around the vehicle through a camera mounted on the vehicle. The image sensor can not only capture the situation of the road ahead, but also identify traffic lights, road signs, the dynamics of pedestrians and other vehicles.

[0040] Vehicle speed sensor: Used to monitor the current driving speed of the vehicle in real time to ensure that the system can accurately obtain the dynamic information of the vehicle.

[0041] Acceleration sensor: Used to detect the acceleration change of the vehicle and provide key parameters of the current motion state of the vehicle.

[0042] Engine speed sensor: Used to monitor the working state and speed of the engine, so as to further evaluate the power output of the vehicle.

[0043] In practical applications, the image sensor captures visual data of the road ahead through a camera mounted in front of the vehicle. Through image processing technology, the system can analyze the image data and extract relevant environmental information. For example, the system can provide a reference for subsequent acceleration prediction by identifying road signs (such as speed limit signs, prohibition signs, etc.). In addition, the camera can also capture the road surface conditions, such as detecting abnormal conditions such as the wetness and potholes of the road, and these factors will affect the acceleration or deceleration operation of the vehicle.

[0044] In addition to visual data, the image sensor can also detect the dynamics of surrounding vehicles and pedestrians, such as the distance, speed of the vehicle ahead, and the situation of pedestrians suddenly entering the road. The system uses image processing algorithms to track these dynamic targets in real time and takes them as one of the important features affecting acceleration prediction.

[0045] In addition, the vehicle speed sensor and acceleration sensor of the vehicle continuously monitor the motion state of the vehicle. The vehicle speed sensor provides the system with the instantaneous speed data of the vehicle, while the acceleration sensor can measure the current acceleration or deceleration of the vehicle. The engine speed sensor obtains the working state data of the engine in real time, reflecting the power output level of the vehicle, which plays an important role in predicting the acceleration change of the vehicle in a specific environment.

[0046] In some specific scenarios, such as when the vehicle approaches an intersection, the image sensor can capture the state of the traffic light (such as the countdown time of the red light and green light). The system predicts the future acceleration based on the signal change of the traffic light, combined with the speed and position data of the vehicle. This provides accurate input for driving behavior decision-making (such as when to decelerate or accelerate through the intersection).

[0047] In this embodiment, the vehicle collaboratively operates multiple sensors to collect real-time environmental information around the vehicle and vehicle operation state data. The system uses this data to provide a high-quality input basis for subsequent acceleration prediction. By integrating vision processing technology, the system can comprehensively perceive the driving environment of the vehicle, ensuring the accuracy and timeliness of acceleration prediction.

[0048] In some embodiments, based on the environmental information and vehicle operation state data, a dynamic model of the vehicle is constructed, including:

[0049] A physical property model is established based on the vehicle operation state data, an external environmental factor model is established based on the environmental information, and an external force model of the vehicle is established based on the external forces acting on the vehicle;

[0050] The physical property model, the external environmental factor model, and the external force model are integrated to construct a dynamic model of the vehicle.

[0051] Specifically, this embodiment also provides a method for constructing a dynamic model of a vehicle based on environmental information and vehicle operation state data. This model is used to simulate the behavior of the vehicle under different conditions and provides basic support for subsequent acceleration prediction.

[0052] First, the system establishes a physical property model of the vehicle based on the vehicle operation state data. The physical property model of the vehicle can reflect the inherent parameters of the vehicle itself, and these parameters include but are not limited to:

[0053] Vehicle mass: Different vehicle masses affect the acceleration and braking capabilities of the vehicle. A heavier vehicle will have a relatively smaller change in acceleration under the same external force.

[0054] Tire type: The grip, wear degree, and model of the tires affect the traction performance of the vehicle on different road surfaces. Especially on slippery or potholed road surfaces, tire performance plays an important role in the dynamic response of the vehicle.

[0055] Center of gravity position and inertia: The center of gravity position and inertia of the vehicle have a direct impact on the reaction speed and stability of acceleration changes, especially when the vehicle is turning or braking.

[0056] Then, the system establishes an external environmental factor model of the vehicle based on the real-time collected environmental information. This model is used to describe the external conditions in the current driving environment of the vehicle, including:

[0057] Road surface friction coefficient: Through the sensor data of the vehicle (such as cameras, acceleration sensors, etc.), the system can estimate the friction coefficient of the current road surface. For example, on a slippery or snow-covered road surface, the friction coefficient is low, resulting in limited acceleration or deceleration performance of the vehicle.

[0058] Gradient: By combining the camera with the vehicle speed sensor, the system can identify the gradient of the current road. The gradient has a direct impact on acceleration. When going uphill, the vehicle requires more power to maintain the same acceleration, while when going downhill, there may be a phenomenon of excessive acceleration.

[0059] Traffic conditions: including the status of surrounding vehicles, traffic signal conditions, etc. These information will affect the dynamic response of the vehicle. Traffic jams or complex traffic signal changes will also have a direct impact on vehicle acceleration.

[0060] Next, the system constructs an external force model based on external forces. External forces mainly refer to the external physical influences on the vehicle during driving, including:

[0061] Air resistance (wind resistance): Air resistance increases with the increase in vehicle speed. The system estimates the impact of air resistance on vehicle acceleration through vehicle speed and external wind speed measurements.

[0062] Collision force: When colliding with other vehicles, the external force model will consider the severe impact of the collision force on vehicle acceleration and simulate the severe changes in vehicle dynamics during the collision process.

[0063] Finally, the system comprehensively processes the above three models - the physical property model, the external environmental factor model, and the external force model to form a complete vehicle dynamic model. Through the comprehensive model, the system can simulate the dynamic behavior of the vehicle under various different conditions and provide an accurate prediction of future acceleration changes.

[0064] In some examples, the vehicle dynamic model can be adjusted in real time to adapt to vehicle behavior under different working conditions. For example, when the system detects that the road is slippery and has a large gradient, the dynamic model will combine factors such as vehicle mass, road surface friction coefficient, and gradient to output a comprehensive acceleration response that can reflect the current working condition. These outputs will be used in the acceleration prediction module to ensure that the vehicle can obtain accurate acceleration prediction values under complex driving conditions.

[0065] Through the construction of the vehicle dynamic model in this embodiment, the system can accurately simulate the dynamic response of the vehicle under various external environments and physical conditions, and thus provide reliable model support for vehicle acceleration prediction and control.

[0066] In some embodiments, target features related to vehicle acceleration changes are extracted from environmental information and vehicle operation state data, and the target features are associated with the parameters in the dynamic model, including:

[0067] Using image processing technology to analyze environmental information in order to extract the first original features related to vehicle acceleration changes from the visual data of environmental information;

[0068] Extract the second original features related to vehicle acceleration from the vehicle operation state data;

[0069] Based on association analysis or feature selection algorithms, screen out the target features related to vehicle acceleration changes from the first original features and the second original features;

[0070] Correspondingly match the target features with the physical parameters of the dynamic model, and evaluate the influence of the target features on vehicle acceleration changes.

[0071] Specifically, this embodiment also provides a method for extracting target features related to vehicle acceleration changes from environmental information and performing association analysis on these features with the parameters in the vehicle dynamic model to achieve accurate prediction of vehicle acceleration changes.

[0072] Further, the system collects visual data of the vehicle surrounding environment through an image sensor (such as a camera). Using image processing technology to analyze the collected images, extract the first original features related to vehicle acceleration changes. For example, visual data analysis may include the following:

[0073] First, by analyzing the front image captured by the camera, identify and measure the distance between the vehicle and the front obstacles (such as other vehicles, pedestrians). This information directly affects the acceleration adjustment of the vehicle, especially when emergency braking or accelerating is required.

[0074] Second, by tracking the dynamic information of the front vehicle or moving object, the system can calculate the relative speed between the vehicle and the front vehicle. This is a key factor in predicting acceleration changes, especially when driving in traffic flow.

[0075] Finally, by identifying the color and countdown time of traffic lights through image processing, the system can determine whether the current vehicle needs to decelerate or accelerate to pass through the intersection. The changes of traffic lights will directly affect the acceleration adjustment of the vehicle.

[0076] Further, at the same time, the system extracts the second original features related to acceleration from the vehicle's internal sensors (such as speed sensors, acceleration sensors). These data reflect the real-time state of the vehicle. For example, the following data may be included:

[0077] Current vehicle speed: The speed sensor provides the current driving speed of the vehicle. This information is the basis for determining the acceleration or deceleration trend of the vehicle.

[0078] Current vehicle acceleration: The acceleration sensor records the acceleration or deceleration of the vehicle in real time, which is the direct reference data for predicting future acceleration.

[0079] Furthermore, the system uses association analysis or feature selection algorithms to screen the first raw features extracted from visual data and the second raw features extracted from vehicle operating state data, and selects the target features that can best reflect the vehicle acceleration changes. For example, when the current vehicle speed is high and the vehicle ahead decelerates, the system will preferentially select the relative speed and the distance to the obstacle ahead as the key target features.

[0080] Furthermore, the system performs corresponding matching between the selected target features and the physical parameters in the vehicle dynamic model. The vehicle dynamic model contains physical characteristics such as vehicle mass, tire performance, and air resistance, and these parameters determine the acceleration or deceleration behavior of the vehicle under different conditions. Specifically, it may include the following:

[0081] When the distance to the obstacle ahead is relatively close, the system will perform association analysis between this distance and parameters such as the braking distance and vehicle mass in the vehicle dynamic model to evaluate whether the vehicle needs to decelerate rapidly.

[0082] The relative speed feature is combined with the vehicle power output characteristics (such as engine speed, vehicle mass) in the dynamic model to determine whether to accelerate or decelerate at the current vehicle speed.

[0083] Furthermore, the system evaluates the specific impact of each target feature on the acceleration change through the above-mentioned association analysis. For example:

[0084] When the distance to the obstacle ahead is short and the relative speed is high, the system may conclude that the vehicle needs to decelerate sharply.

[0085] If the traffic light is about to change from green to red, the system combines the current vehicle speed with the countdown of the traffic light to determine whether to accelerate through the intersection or decelerate and wait.

[0086] Through the method of the above embodiments, the system can extract the features most relevant to the acceleration change from complex environmental information and vehicle state data, and perform association analysis with the parameters in the vehicle dynamic model. This method ensures the accuracy and real-time performance of the acceleration prediction, and helps to improve the automatic control ability of the vehicle in the changing traffic environment.

[0087] In some embodiments, based on the dynamic model after associating the target features, reverse reasoning is performed on the reasons for the vehicle acceleration change, including:

[0088] Using the association analysis between the target features and the parameters in the dynamic model to identify the reasons for the current acceleration change;

[0089] Based on the reasons for the current acceleration change, using a reverse reasoning algorithm to deduce the factors causing the current acceleration change, where the reverse reasoning algorithm is based on an optimization algorithm or machine learning technology;

[0090] Using the image data obtained by the binocular camera, calculate the velocity vector of surrounding objects through the binocular velocity measurement formula;

[0091] Associate the velocity vector with the physical characteristics and external forces in the vehicle dynamic model to analyze the influence of the velocity vector on the vehicle acceleration; Determine the ultimate cause of the current vehicle acceleration change based on the result of backward reasoning.

[0092] Specifically, based on environmental perception and the vehicle dynamic model, the system performs backward reasoning, that is, analyzes the reason for the current acceleration change. This usually uses machine learning or optimization algorithms to find the most likely factors causing the current acceleration change.

[0093] Backward reasoning derives the most reasonable explanation by tracing back various data inputs in the current state, thereby providing a basis for predicting future acceleration.

[0094] Furthermore, to calculate the velocity of surrounding vehicles or objects more precisely, this embodiment adopts binocular velocity measurement technology. The binocular camera captures the three-dimensional coordinates of an object at different times and calculates the velocity vector of the object.

[0095] By calculating the time difference based on the frame rate of the camera and then according to the displacement of the object, the system can obtain the moving speed of the object. This helps the system to more accurately predict the dynamics of the vehicle or obstacle ahead, thereby optimizing its own acceleration prediction.

[0096] The following combines a specific example to elaborate in detail on the backward reasoning process for the cause of vehicle acceleration change in this application, which may specifically include the following content:

[0097] Based on the current environmental perception and vehicle dynamic model, attempt to backward reason out the reason for the current acceleration change. This may require using machine learning or optimization algorithms to find the best match among possible factors.

[0098] The binocular velocity measurement formula calculates the velocity based on the displacement of the object in three-dimensional space and the time interval.

[0099] The specific implementation method is as follows: The three-dimensional coordinates of an object can be reconstructed from the images captured by two cameras. When the object moves, its three-dimensional coordinates at different time points will change, and thus the velocity of the object can be calculated.

[0100] The basic formula for binocular velocity measurement can be expressed as:

[0101]

[0102] Among them: is the velocity vector of the object, indicating the moving speed of the object in three-dimensional space. Δr is the displacement vector between different time points of an object, that is, the three-dimensional coordinate change of the object from one position to another. Δt is the time interval, representing the time difference between two observations.

[0103] In binocular velocity measurement, Δr is usually calculated by comparing the three-dimensional coordinates of an object at two different time points:

[0104]

[0105] where and are the three-dimensional coordinates of the object at two different time points respectively.

[0106] The time interval Δt can be calculated from the frame rate of the camera. If the frame rate of the camera is N frames per second (fps), and the two observations are made at the a-th frame and the b-th frame respectively, then the time interval is:

[0107] seconds

[0108] Substituting and Δt into the velocity formula, we get:

[0109]

[0110] The formula gives the velocity vector, which includes the moving direction and speed magnitude of the object in three-dimensional space.

[0111] Given then

[0112] In some embodiments, based on the reverse reasoning result of the acceleration change reason, the acceleration of the vehicle in the future time period is predicted, including:

[0113] Based on the acceleration change reason obtained by reverse reasoning, determine the key factors affecting the current acceleration, and establish an acceleration prediction model based on the key factors;

[0114] Based on the current traffic flow, road conditions, dynamic behaviors of surrounding objects and historical driving data, determine the proportionality coefficient of the acceleration prediction model;

[0115] Based on the proportionality coefficient and the current acceleration, use a linear model to predict the acceleration of the vehicle in the future time period to obtain the predicted acceleration.

[0116] Specifically, this embodiment also provides a method for predicting the acceleration of a vehicle in a future time period based on the reverse reasoning result of the acceleration change reason. By analyzing the reason for the current acceleration change, an acceleration prediction model is established and a linear model is used for prediction, providing more accurate guidance for vehicle control and driving.

[0117] First, based on the result of backward reasoning, the system analyzes the specific reasons for the current acceleration change and determines the key factors affecting acceleration. These factors may include:

[0118] Distance to the obstacle ahead: such as deceleration of the vehicle ahead, pedestrians suddenly entering the lane, etc.

[0119] Traffic signal status: The countdown of traffic lights and signal switching may require the vehicle to accelerate through or decelerate and wait.

[0120] Road conditions: The wetness and slope of the road surface may affect the acceleration performance of the vehicle.

[0121] Physical characteristics of the vehicle: such as the mass of the vehicle, tire performance, etc.

[0122] By analyzing the above factors, the system can lock which external or internal conditions directly affect the current acceleration change, and thus provide reliable input for future acceleration prediction.

[0123] Furthermore, based on the determined key factors, the system establishes an acceleration prediction model. This model predicts the future acceleration change trend of the vehicle by integrating the current traffic flow, the dynamic behavior of surrounding objects (such as acceleration and deceleration of the vehicle ahead), and road conditions. At the same time, the model also considers historical driving data, such as the driving habits of the driver, previous acceleration patterns, etc., in order to more accurately reflect the acceleration or deceleration behavior of the vehicle in similar situations.

[0124] For example, in an urban road with high traffic flow, the system will predict that the vehicle may need to decelerate frequently based on past data, while on a relatively open highway, it may need to accelerate to maintain a high speed.

[0125] Furthermore, in the acceleration prediction model, the proportionality coefficient K is an important parameter determining the future acceleration change. The system dynamically determines this proportionality coefficient based on the current traffic conditions and environmental factors:

[0126] For example, if the road ahead is congested, the value of K will be small because the vehicle needs to decelerate or even stop. If the signal is about to turn red, the system will set K according to the countdown of the signal to make the vehicle decelerate gradually. If the road surface is wet and the friction is low, the system will reduce the value of K to avoid excessive acceleration. Based on historical data, if the driver has a relatively smooth driving style, the system may set a lower value of K to avoid excessive acceleration. The determination of K takes into account various dynamic factors to ensure that the acceleration prediction can accurately reflect the actual driving situation.

[0127] Furthermore, the system predicts acceleration using a linear model based on the current acceleration a and the proportionality coefficient K. The expression of the linear model is:

[0128] a1 = ka + b

[0129] Wherein, a1 represents the predicted acceleration of the vehicle in the future time period, a is the current acceleration, and b is a correction term used to adjust the impact of unforeseen environmental changes on the acceleration.

[0130] For example, when the system detects that the traffic signal ahead is about to turn red and the countdown is very short, and the current vehicle speed is relatively fast, the system may set a lower K value and further slow down the acceleration through the correction term b to ensure that the vehicle can stop safely.

[0131] Furthermore, during the process of acceleration prediction, the system will continuously make dynamic adjustments according to the vehicle operation data and environmental information collected by the sensors in real time. If the actual situation changes (such as the road ahead suddenly becomes clear), the system will update the proportionality coefficient K and the correction term b in real time and recalculate the future acceleration to ensure the accuracy and real-time nature of the prediction result.

[0132] Through the method of this embodiment above, the system can establish an accurate acceleration prediction model based on the reasons for the current acceleration change, and use the linear model combined with the proportionality coefficient and real-time data for dynamic adjustment, and finally obtain the predicted acceleration of the vehicle in the future time period. This method provides accurate and reliable acceleration prediction data for the vehicle control system and improves the response ability of the vehicle in complex traffic environments.

[0133] In some embodiments, the method further includes:

[0134] Continuously update the key factors and the proportionality coefficient based on the environmental information and vehicle operation state data collected by the vehicle sensors in real time, so as to dynamically adjust the parameters in the acceleration prediction model;

[0135] Based on the actual acceleration collected by the vehicle sensors in real time, compare the actual acceleration with the predicted acceleration, and correct the parameters of the acceleration prediction model according to the comparison result.

[0136] Specifically, this embodiment also provides a method for dynamically adjusting and correcting the acceleration prediction model based on the data collected by the vehicle sensors in real time. This method continuously updates the key factors and the proportionality coefficient, and feeds back and compares the difference between the actual acceleration and the predicted acceleration to optimize the acceleration prediction model in real time to ensure the accuracy of the prediction.

[0137] Furthermore, this method relies on the environmental information and vehicle operation state data collected by the vehicle sensors in real time. The system continuously obtains the following data through sensors (such as acceleration sensors, vehicle speed sensors, cameras, etc.):

[0138] Environmental information: It includes road conditions (such as slope, road surface slipperiness), traffic signal status, dynamic behaviors of surrounding vehicles and pedestrians, etc. These data directly affect the key factors in the acceleration prediction model.

[0139] Vehicle operating status: It includes parameters such as the real-time speed, acceleration, and engine speed of the vehicle, reflecting the current motion situation of the vehicle.

[0140] Based on the data collected in real time, the system continuously updates the key factors (such as traffic flow, road surface conditions, dynamic behaviors of surrounding objects, etc.) and the proportionality coefficient K in the acceleration prediction model. For example, when the vehicle in front suddenly decelerates, the system will dynamically adjust the proportionality coefficient K to make the acceleration prediction of the vehicle more in line with the actual driving situation. The system updates the parameters of the model according to these real-time changing information to ensure that the acceleration prediction can adapt to the complex and changeable driving environment.

[0141] Furthermore, during the vehicle's driving process, the system real-time collects the actual acceleration of the vehicle through an acceleration sensor (such as an accelerometer). These actual acceleration data are used to verify the accuracy of the acceleration prediction model. Specifically, the system compares the actual acceleration with the predicted acceleration previously calculated by the acceleration prediction model:

[0142] If the actual acceleration is consistent with the predicted acceleration, it indicates that the parameter settings of the acceleration prediction model are relatively reasonable, and the vehicle control system can continue to use the current parameters for control.

[0143] If there is a large difference between the actual acceleration and the predicted acceleration, it indicates that some parameters of the acceleration prediction model may not fully reflect the current driving situation or environmental changes, and the system needs to correct the model.

[0144] Furthermore, after detecting the difference between the actual acceleration and the predicted acceleration, the system will correct the parameters of the acceleration prediction model based on the comparison result. The correction process includes:

[0145] Adjusting the proportionality coefficient K: According to the feedback data, the system will appropriately adjust the proportionality coefficient K to ensure that it can more accurately reflect the changes in the current environment and vehicle operating status. For example, if the vehicle accelerates too fast on a slippery road surface, the system will reduce the proportionality coefficient K, thereby reducing the predicted value of future acceleration to avoid vehicle out of control.

[0146] Updating of key factors: If the system detects changes in some key factors (such as traffic signal status, road surface friction coefficient), the system will dynamically adjust the influence weights of these factors on acceleration, thereby optimizing the acceleration prediction model.

[0147] Through these feedback and correction steps, the system can ensure that the acceleration prediction model is always in an optimal state to cope with the real-time changes in road conditions, traffic environment, and vehicle status.

[0148] For example, during vehicle driving, if the system detects through the camera that the countdown of the red light ahead is decreasing and the vehicle is accelerating too fast currently, the system will predict the acceleration required for future deceleration by reducing the proportionality coefficient K in the acceleration prediction model. At the same time, after the system monitors the deviation between the actual acceleration and the predicted acceleration through the acceleration sensor, it will further correct the model to ensure that the vehicle can decelerate in a timely and stable manner, avoiding sudden braking or loss of control caused by unexpected situations.

[0149] Through the method of the present embodiment described above, the system can realize continuous dynamic adjustment of the acceleration prediction model based on the real-time collected environmental information and vehicle operation status data. By comparing the actual acceleration with the predicted acceleration, the system timely performs feedback correction on the parameters of the prediction model to ensure the accuracy and adaptability of acceleration prediction. This method can significantly improve the automatic control and response capabilities of the vehicle under complex road conditions and traffic situations.

[0150] According to the technical solution provided by the embodiment of the present application, the technical solution of the present application has at least the following advantages:

[0151] I. Comprehensiveness of environmental perception

[0152] 1) Real-time performance: Visual sensors (such as cameras) can capture the environmental information around the vehicle in real time, including road conditions, traffic signs, the dynamics of other vehicles and pedestrians, etc. This real-time performance is crucial for timely predicting and responding to acceleration changes.

[0153] 2) Information richness: Visual information is more rich and intuitive than the information provided by a single sensor (such as radar or lidar). Through image processing technology, various features related to acceleration changes can be extracted from visual data.

[0154] II. Improvement in prediction accuracy

[0155] 1) Multi-source data fusion: By combining visual information with the data of other sensors (such as accelerometers, gyroscopes, etc.), multi-source data fusion can be achieved, thereby improving the accuracy and reliability of acceleration prediction.

[0156] 2) Coping with complex scenarios: In complex traffic scenarios, such as intersections, congested sections, etc., visual information can help the system better understand the dynamic changes in the surrounding environment, thereby more accurately predicting the acceleration of the vehicle.

[0157] III. Intelligence of decision-making

[0158] 1) Understanding-based prediction: Through visual information, the system can "understand" the semantic information of the surrounding environment, such as road type, traffic signal status, etc., and thus predict the acceleration change of the vehicle based on these understandings. This understanding-based prediction is more intelligent and flexible than pure physical model prediction.

[0159] 2) Adaptive adjustment: Visual information can also help the system adaptively adjust the prediction model according to the changes in the environment to meet the acceleration prediction requirements in different scenarios.

[0160] IV. Enhanced safety

[0161] 1) Early warning: Through visual reverse acceleration prediction, the system can perceive potential dangerous situations (such as sudden stops of vehicles ahead, pedestrians crossing the road, etc.) in advance and issue early warnings, thereby enhancing driving safety.

[0162] 2) Auxiliary decision-making: In an autonomous driving or driver assistance system, visual reverse acceleration prediction can be an important input to the decision-making system, helping the system make more reasonable and safer driving decisions.

[0163] V. Optimization of user experience

[0164] 1) Smooth driving: Through accurate acceleration prediction, the system can optimize the acceleration and deceleration processes of the vehicle, making the driving process smoother and more comfortable.

[0165] 2) Personalized settings: According to the driving habits and preferences of the driver, the system can also perform personalized settings on acceleration prediction to provide a driving experience that better meets the driver's expectations.

[0166] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0167] Figure 2 It is a schematic structural diagram of a vehicle acceleration prediction device provided by an embodiment of the present application. As Figure 2 shown, the vehicle acceleration prediction device includes:

[0168] An acquisition module 201, configured to collect in real time the environmental information around the vehicle and the vehicle operation state data;

[0169] A construction module 202, configured to construct a dynamic model of the vehicle based on the environmental information and the vehicle operation state data, and the dynamic model is used to simulate the dynamic response of the vehicle under different working conditions;

[0170] The association module 203 is configured to extract target features related to vehicle acceleration changes from environmental information and vehicle operation state data, and associate the target features with parameters in the dynamic model;

[0171] The prediction module 204 is configured to perform reverse reasoning on the reasons for vehicle acceleration changes based on the dynamic model after associating the target features, and predict the acceleration of the vehicle in a future time period based on the reverse reasoning results of the reasons for acceleration changes.

[0172] In some embodiments, Figure 2 The acquisition module 201 of uses a variety of sensors to collect environmental information around the vehicle and vehicle operation state data in real time. Among them, the sensors include image sensors, vehicle speed sensors, acceleration sensors, and engine speed sensors, and the environmental information includes road conditions, traffic signal states, and dynamic information of surrounding vehicles and pedestrians.

[0173] In some embodiments, Figure 2 The construction module 202 of establishes a physical property model based on vehicle operation state data, establishes an external environmental factor model based on environmental information, and establishes an external force model of the vehicle based on the external forces acting on the vehicle; integrates the physical property model, the external environmental factor model, and the external force model to construct a dynamic model of the vehicle.

[0174] In some embodiments, Figure 2 The association module 203 of uses image processing technology to analyze environmental information in order to extract first raw features related to vehicle acceleration changes from the visual data of environmental information; extracts second raw features related to vehicle acceleration from vehicle operation state data; based on association analysis or feature selection algorithms, screens target features related to vehicle acceleration changes from the first raw features and the second raw features; performs corresponding matching between the target features and the physical parameters of the dynamic model, and evaluates the influence of the target features on vehicle acceleration changes.

[0175] In some embodiments, Figure 2 The prediction module 204 of performs association analysis using the target features and the parameters in the dynamic model to identify the reasons for the current acceleration changes; based on the reasons for the current acceleration changes, uses reverse reasoning algorithms to deduce the factors causing the current acceleration changes, where the reverse reasoning algorithms are based on optimization algorithms or machine learning techniques; uses the image data obtained by the binocular camera to calculate the velocity vectors of surrounding objects through the binocular velocity measurement formula; associates the velocity vectors with the physical properties and external forces in the vehicle dynamic model to analyze the influence of the velocity vectors on vehicle acceleration; determines the ultimate reasons for the current acceleration changes of the vehicle based on the reverse reasoning results.

[0176] In some embodiments,Figure 2 The prediction module 204 determines the key factors affecting the current acceleration based on the reasons for the acceleration change obtained by reverse reasoning, establishes an acceleration prediction model based on the key factors; determines the proportionality coefficient of the acceleration prediction model based on the current traffic flow, road conditions, dynamic behavior of surrounding objects, and historical driving data; and predicts the acceleration of the vehicle in a future time period using a linear model based on the proportionality coefficient and the current acceleration to obtain the predicted acceleration.

[0177] In some embodiments, Figure 2 The update module 205 continuously updates the key factors and the proportionality coefficient based on the environmental information and vehicle operation state data collected in real time by the vehicle sensors, so as to dynamically adjust the parameters in the acceleration prediction model; compares the actual acceleration with the predicted acceleration based on the actual acceleration collected in real time by the vehicle sensors, and corrects the parameters of the acceleration prediction model according to the comparison result.

[0178] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0179] Figure 3 is a schematic structural diagram of the electronic device 3 provided by the embodiment of the present application. As Figure 3 shown, the electronic device 3 of this embodiment includes: a processor 301, a memory 302, and a computer program 303 stored in the memory 302 and executable on the processor 301. When the processor 301 executes the computer program 303, the steps in the above-mentioned various method embodiments are implemented. Alternatively, when the processor 301 executes the computer program 303, the functions of each module / unit in the above-mentioned various device embodiments are implemented.

[0180] Exemplarily, the computer program 303 can be divided into one or more modules / units. The one or more modules / units are stored in the memory 302 and executed by the processor 301 to complete the present application. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 303 in the electronic device 3.

[0181] The electronic device 3 can be a desktop computer, a notebook, a palm computer, a cloud server, and other electronic devices. The electronic device 3 may include, but is not limited to, the processor 301 and the memory 302. Those skilled in the art can understand, Figure 3This is only an example of the electronic device 3, which does not constitute a limitation on the electronic device 3. It may include more or fewer components than those shown in the figure, or combine certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, etc.

[0182] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor may also be any conventional processor, etc.

[0183] The memory 302 may be an internal storage unit of the electronic device 3. For example, the hard disk or memory of the electronic device 3. The memory 302 may also be an external storage device of the electronic device 3. For example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 3. Further, the memory 302 may also include both an internal storage unit and an external storage device of the electronic device 3. The memory 302 is used to store computer programs and other programs and data required by the electronic device. The memory 302 may also be used to temporarily store data that has been output or will be output.

[0184] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment may be integrated into a processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0185] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For parts not detailed or recorded in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0186] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0187] In the embodiments provided in this application, it should be understood that the disclosed device / computer device and method can be implemented in other ways. For example, the device / computer device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. Multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0188] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0189] In addition, the functional units in the various embodiments of this application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0190] When the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiment methods of this application, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in the computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method embodiments can be implemented. The computer program can include computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0191] The above embodiments are only used to illustrate the technical solutions of this application, rather than to limit it; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A vehicle acceleration prediction method, characterized in that, Including: Real-time collecting environmental information around the vehicle and vehicle operation state data; Based on the environmental information and vehicle operation state data, constructing a dynamic model of the vehicle, where the dynamic model is used to simulate the dynamic response of the vehicle under different working conditions; Extracting target features related to vehicle acceleration change from the environmental information and the vehicle operation state data, and associating the target features with parameters in the dynamic model; Based on the dynamic model associated with the target features, inversely reasoning the reasons for vehicle acceleration change, and predicting the acceleration of the vehicle in a future time period based on the inverse reasoning result of the acceleration change reason.

2. The method according to claim 1, wherein The real-time collecting of environmental information around the vehicle and vehicle operation state data includes: Using a variety of sensors to real-time collect environmental information around the vehicle and vehicle operation state data, where the sensors include an image sensor, a vehicle speed sensor, an acceleration sensor, and an engine speed sensor, and the environmental information includes road conditions, traffic signal states, and dynamic information of surrounding vehicles and pedestrians.

3. The method according to claim 1, wherein The constructing of a dynamic model of the vehicle based on the environmental information and vehicle operation state data includes: Establishing a physical property model based on the vehicle operation state data, establishing an external environmental factor model based on the environmental information, and establishing an external force model of the vehicle based on the external forces acting on the vehicle; Integrating the physical property model, the external environmental factor model, and the external force model to construct the dynamic model of the vehicle.

4. The method according to claim 1, wherein The extracting of target features related to vehicle acceleration change from the environmental information and the vehicle operation state data, and associating the target features with parameters in the dynamic model includes: Using image processing technology to analyze the environmental information so as to extract first original features related to vehicle acceleration change from the visual data of the environmental information; Extracting second original features related to vehicle acceleration from the vehicle operation state data; Based on an association analysis or feature selection algorithm, screening target features related to vehicle acceleration change from the first original features and the second original features; Performing corresponding matching of the target features with the physical parameters of the dynamic model, and evaluating the influence of the target features on vehicle acceleration change.

5. The method according to claim 1, wherein The inversely reasoning of the reasons for vehicle acceleration change based on the dynamic model associated with the target features includes: Using the association analysis of the target features and the parameters in the dynamic model to identify the reasons for the current acceleration change; Based on the reasons for the current acceleration change, using an inverse reasoning algorithm to deduce the factors causing the current acceleration change, where the inverse reasoning algorithm is based on an optimization algorithm or machine learning technology; Using the image data obtained by a binocular camera to calculate the velocity vector of surrounding objects through a binocular speed measurement formula; Associating the velocity vector with the physical properties and external forces in the vehicle dynamic model to analyze the influence of the velocity vector on vehicle acceleration; determining the ultimate reason for the current acceleration change of the vehicle based on the inverse reasoning result.

6. The method according to claim 1, characterized in that, Predicting the acceleration of the vehicle in a future time period based on the reverse inference result of the cause of acceleration change includes: Determining the key factors affecting the current acceleration based on the cause of acceleration change obtained by reverse inference, and establishing an acceleration prediction model based on the key factors; Determining the proportionality coefficient of the acceleration prediction model based on the current traffic flow, road conditions, dynamic behavior of surrounding objects, and historical driving data; Predicting the acceleration of the vehicle in a future time period using a linear model based on the proportionality coefficient and the current acceleration to obtain a predicted acceleration.

7. The method according to claim 6, characterized in that, The method further includes: Continuously updating the key factors and the proportionality coefficient based on the environmental information and vehicle operation state data collected in real time by the vehicle sensor, so as to dynamically adjust the parameters in the acceleration prediction model; Comparing the actual acceleration with the predicted acceleration based on the actual acceleration collected in real time by the vehicle sensor, and correcting the parameters of the acceleration prediction model according to the comparison result.

8. A vehicle acceleration prediction device, characterized in that, Including: An acquisition module configured to collect in real time the environmental information around the vehicle and the vehicle operation state data; A construction module configured to construct a dynamic model of the vehicle based on the environmental information and the vehicle operation state data, and the dynamic model is used to simulate the dynamic response of the vehicle under different working conditions; An association module configured to extract target features related to the vehicle acceleration change from the environmental information and the vehicle operation state data, and associate the target features with the parameters in the dynamic model; A prediction module configured to perform reverse inference on the cause of the vehicle acceleration change based on the dynamic model after associating the target features, and predict the acceleration of the vehicle in a future time period based on the reverse inference result of the cause of acceleration change.

9. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 7.

Images