Vehicle auxiliary driving method and device, electronic equipment, vehicle and program product

Abstract

The embodiment of the invention provides a vehicle auxiliary driving method and device, electronic equipment, a vehicle and a program product, and relates to the technical field of vehicle control. The method comprises the following steps: acquiring a vehicle driving data sample, wherein the vehicle driving data sample comprises vehicle driving data of a sample vehicle, road traffic data and a state mode identifier; inputting the vehicle driving data sample into a preset neural network model to iteratively evaluate model output error data of the vehicle driving data sample, and adjusting model parameters configured by the neural network model and the number of nodes of a hidden layer arranged by the neural network model based on the model output error data, obtaining a vehicle aided driving model until a preset iteration stop condition is met; obtaining vehicle driving data of the target vehicle; and analyzing the vehicle driving data through the vehicle auxiliary driving model to obtain a vehicle driving state result of the target vehicle. The application range of vehicle auxiliary driving can be widened.

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a method, device, electronic equipment, vehicle and program product for vehicle assisted driving. Background Art

[0002] Assisted driving means that during the process of driving, the car provides auxiliary support to the driver through various devices and systems, making driving easier and safer. It is usually achieved through sensors (such as cameras, radars, etc.) and computer systems on the vehicle, which can detect road conditions, traffic signals, pedestrians and other vehicles, and provide real-time information and suggestions to the driver.

[0003] At present, existing vehicle assisted driving technologies often face problems such as insufficient sensor accuracy and limited data processing capabilities, resulting in limited recognition and response capabilities in complex or changing road environments, thus limiting the scope of application of assisted driving. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a method, device, electronic equipment, vehicle and program product for vehicle assisted driving, aiming to increase the application scope of vehicle assisted driving.

[0005] In a first aspect, the present application provides a method for vehicle assisted driving, the method comprising:

[0006] Acquire a vehicle driving data sample, wherein the vehicle driving data sample includes vehicle driving data, road traffic data and a corresponding state mode identifier of a sample vehicle, wherein the state mode identifier is used to indicate whether the vehicle is driving normally;

[0007] Inputting the vehicle driving data sample into a preset neural network model to iteratively evaluate model output error data for the vehicle driving data sample, and adjusting model parameters configured by the neural network model and the number of nodes of the hidden layer arranged by the neural network model based on the model output error data until a preset iteration stop condition is reached, thereby obtaining a vehicle assisted driving model;

[0008] Acquiring vehicle driving data of a target vehicle;

[0009] The vehicle driving data is analyzed by the vehicle assisted driving model to obtain a vehicle driving state result of the target vehicle.

[0010] In a possible implementation, the neural network model includes a cascade-sorted feature extraction network and a classification network, and both the feature extraction network and the classification network include a plurality of hidden layers arranged in a cascade-sorted manner;

[0011] The following steps are performed by the feature extraction network and the classification network, including:

[0012] Performing feature dimension reduction on the vehicle driving data sample input into the neural network model through the feature extraction network to obtain vehicle feature information;

[0013] The vehicle characteristic information is classified through the classification network to obtain the vehicle driving state result of the sample vehicle and serve as the output of the neural network model.

[0014] In a possible implementation, the vehicle driving data sample is input into a preset neural network model to iteratively evaluate the model output error data for the vehicle driving data sample, and based on the model output error data, the model parameters configured by the neural network model and the number of nodes of the hidden layer arranged by the neural network model are adjusted until a preset iteration stop condition is reached to obtain a vehicle assisted driving model, including:

[0015] Initializing model parameters of the neural network model, wherein the model parameters include weights, biases, and learning rates;

[0016] For any iteration, based on the output of the neural network model in the previous iteration, the corresponding model output error data is determined, wherein the model output error data includes the model error and the error change amount of the previous iteration;

[0017] Based on the learning rate of the neural network model in the previous iteration and the error change in the previous iteration, the learning rate of this iteration is updated;

[0018] Based on the learning rate of this iteration, the weight of the neural network model in the previous iteration and the model error, the weight of this iteration is updated.

[0019] In a possible implementation, the initializing model parameters of the neural network model, the model parameters including weights, biases, and learning rates, includes:

[0020] The weights of the neural network model are initialized by the following formula (1), including:

[0021] W p，0 =μ p +σ p N(0, I) (1)

[0022] Among them, W p，0 is the initial value of the weight of the neural network model, μ p is the mean shift of the weights of the neural network model, σ pis the standard deviation of weight initialization, N(0, I) represents a normal distribution with a mean of 0 and a standard deviation of the identity matrix, and I is the identity matrix;

[0023] The updating of the learning rate of this iteration based on the learning rate of the neural network model in the previous iteration and the error change in the previous iteration includes:

[0024] The learning rate of this iteration is determined by the following formula (2), including:

[0025] η p，t =η p,t-1 ·exp(-γ p ΔE p，t-1 ) (2)

[0026] Among them, η p，t is the learning rate of the tth iteration, η p,t-1 is the learning rate of the neural network model in the t-1th iteration, ΔE p，t-1 is the error change of the t-1th iteration, γ p is the preset model adjustment factor;

[0027] The updating of the weight of this iteration based on the learning rate of this iteration, the weight of the neural network model in the previous iteration, and the model error includes:

[0028] The weight of this iteration is determined by the following formula (3), including:

[0029]

[0030] Among them, W p,t is the weight of the tth iteration, W p,t-1 is the weight of the neural network model in the t-1th iteration, E p is the model error.

[0031] In a possible implementation, the vehicle driving data sample is input into a preset neural network model to iteratively evaluate the model output error data for the vehicle driving data sample, and based on the model output error data, the model parameters configured by the neural network model and the number of nodes of the hidden layer arranged by the neural network model are adjusted until a preset iteration stop condition is reached to obtain a vehicle assisted driving model, further comprising:

[0032] Obtaining a node adjustment step size, wherein the node adjustment step size is associated with a hidden layer arranged in the neural network model;

[0033] For any iteration, based on the number of nodes in the hidden layer included in the neural network model in the previous iteration, the node adjustment step size and the error change of the previous iteration, the number of nodes in the hidden layer in this iteration is updated;

[0034] The number of nodes in the hidden layer in this iteration is determined by the following formula (4), including:

[0035] N p,t =N p,t-1 +sgn(ΔE p,t-1 )·β p (4)

[0036] Where N p,t is the number of nodes in the hidden layer in the tth iteration, N p,t-1 is the number of nodes in the hidden layer in the t-1th iteration, β p The step size is adjusted for the node, and sgn(*) represents the sign function of the error change.

[0037] In a possible implementation, obtaining the node adjustment step size includes:

[0038] The node adjustment step size is determined by the following formula (5), including:

[0039]

[0040] Among them, α p is the preset influence coefficient, d p is the model depth determined by the hidden layer arranged by the neural network model, Int cs (*) indicates a rounding operation.

[0041] In a second aspect, the present application provides a vehicle assisted driving device, the device comprising:

[0042] A first acquisition module is used to acquire a vehicle driving data sample, wherein the vehicle driving data sample includes vehicle driving data, road traffic data and a corresponding state mode identifier of a sample vehicle, wherein the state mode identifier is used to indicate whether the vehicle is driving normally;

[0043] A model training module, used to input the vehicle driving data sample into a preset neural network model to iteratively evaluate the model output error data for the vehicle driving data sample, and adjust the model parameters configured by the neural network model and the number of nodes of the hidden layer arranged by the neural network model based on the model output error data, until a preset iteration stop condition is reached, thereby obtaining a vehicle assisted driving model;

[0044] A second acquisition module is used to acquire vehicle driving data of the target vehicle;

[0045] The analysis module is used to analyze the vehicle driving data through the vehicle assisted driving model to obtain the vehicle driving state result of the target vehicle.

[0046] In a third aspect, the present application provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the vehicle assisted driving method as described in the first aspect or any possible implementation method of the first aspect is implemented.

[0047] In a fourth aspect, the present application provides a vehicle, comprising the vehicle assisted driving device described in the second aspect or the electronic device described in the third aspect.

[0048] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the vehicle assisted driving method described in the above-mentioned first aspect or any possible implementation method of the first aspect.

[0049] The vehicle assisted driving method, device, electronic device, vehicle and program product proposed in the present application trains a preset neural network model through a vehicle driving data sample containing vehicle driving data, road traffic data and state mode identification, that is, it iteratively evaluates the model output error data for the vehicle driving data sample, and adjusts the model parameters configured by the neural network model and the number of nodes of the hidden layer arranged by the neural network model based on the model output error data, so as to realize model adaptive adjustment, so as to obtain a vehicle assisted driving model, which can continuously adapt to new traffic environments and driving habits, and improve the accuracy and efficiency of model training. The vehicle assisted driving model is used to identify the vehicle driving state result of the vehicle, which can cope with complex or changeable driving environments, and realize rapid and timely identification of the vehicle driving state, thereby improving the efficiency and accuracy of vehicle assisted driving, thereby improving the safety of assisted driving and the application scope of vehicle assisted driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A schematic diagram of a process flow of a vehicle assisted driving method provided in an embodiment of the present application;

[0051] Figure 2 A structural diagram of a neural network model provided for an exemplary embodiment of the present application;

[0052] Figure 3 A schematic diagram of a process for adjusting model parameters of a neural network model provided in an embodiment of the present application;

[0053] Figure 4A schematic diagram of the structure of a vehicle assisted driving device provided in an embodiment of the present application;

[0054] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0056] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0058] First, some nouns involved in this application are analyzed:

[0059] Neural Networks (NN): A complex network system formed by a large number of simple processing units (called neurons) that are widely interconnected. It reflects many basic characteristics of human brain functions and is a highly complex nonlinear dynamic learning system. Neural networks have large-scale parallel, distributed storage and processing, self-organization, self-adaptation and self-learning capabilities, and are particularly suitable for processing imprecise and fuzzy information processing problems that require considering many factors and conditions at the same time.

[0060] Hidden Layer: It is a key component in the neural network, located between the input layer and the output layer. The role and function of the hidden layer mainly include feature extraction and transformation, nonlinear modeling and reducing the number of parameters.

[0061] Weights: are the strength of the connections between neurons in a neural network. In a fully connected layer, each neuron is connected to all neurons in the previous layer, and each connection has a weight value. In a convolutional layer, weights exist in the form of convolution kernels (or filters), each of which contains a set of weight values ​​used to extract specific features of the input data. Weights are usually randomly generated at initialization and then updated through the back-propagation algorithm during training.

[0062] Biases: are additional parameters of each neuron that are used to adjust the output of the neuron.

[0063] Learning Rate: is a crucial hyperparameter that determines the magnitude of the model's parameter update in each iteration (or each training step). The choice of learning rate has a direct and significant impact on the training effect of the model.

[0064] At present, existing vehicle assisted driving technologies often face problems such as insufficient sensor accuracy and limited data processing capabilities, resulting in limited recognition and response capabilities in complex or changing road environments, thus limiting the scope of application of assisted driving.

[0065] Based on the above problems, the present application realizes dynamic adjustment of model parameters and the number of nodes in the hidden layer through model adaptive adjustment, so that the trained vehicle assisted driving model can continuously adapt to new traffic environments and driving habits. The vehicle assisted driving model is used to identify the vehicle driving status results of the vehicle, which can cope with complex or changeable driving environments, realize rapid and timely identification of vehicle driving status, improve the safety of assisted driving, and expand the application scope of vehicle assisted driving.

[0066] The vehicle assisted driving method, device, electronic device, vehicle and program product provided in the embodiments of the present application are specifically illustrated through the following embodiments. First, the vehicle assisted driving method in the embodiments of the present application is described.

[0067] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0068] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0069] The vehicle assisted driving method provided in the embodiment of the present application may relate to the field of artificial intelligence technology. The vehicle assisted driving method provided in the embodiment of the present application may be applied to a terminal, may be applied to a server side, or may be software running in a terminal or a server side. In some embodiments, the terminal may be a smart phone, a tablet computer, a laptop computer, a desktop computer, a vehicle-mounted terminal, etc.; the server side may be configured as an independent physical server, or may be configured as a server cluster or a distributed system consisting of multiple physical servers, or may be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software may be an application of a method for implementing vehicle assisted driving, etc., but is not limited to the above forms.

[0070] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0071] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0072] Figure 1 A schematic diagram of a vehicle assisted driving method provided in an embodiment of the present application, Figure 1 The method may include but is not limited to steps S101 to S104.

[0073] S101. Acquire a vehicle driving data sample, wherein the vehicle driving data sample includes vehicle driving data, road traffic data and a corresponding state mode identifier of a sample vehicle, wherein the state mode identifier is used to indicate whether the vehicle is driving normally.

[0074] In this application, vehicle driving data is used to describe the driving conditions of the vehicle and the vehicle's own conditions during driving. Vehicle driving data includes vehicle speed, vehicle position coordinates and vehicle internal state, but is not limited to this. Among them, the vehicle internal state includes engine state, gearbox state, brake system state, etc. For example, the vehicle speed V a =60km / h, vehicle position coordinates (X a ,Y a )=(34.05,-118.25), the internal state of the vehicle is normal, etc.

[0075] Road traffic data is used to describe relevant data such as road conditions, traffic signals, pedestrians and other vehicles during the driving process of the vehicle. Exemplarily, road traffic data includes traffic data and environmental data. The traffic data can be road conditions, congestion, traffic accidents, etc. Environmental data includes weather information such as temperature, humidity, rainfall, snowfall, etc., which has a certain impact on the safety of assisted driving. Specifically, traffic data includes lane type, traffic signals, the number of nearby vehicles and the number of nearby pedestrians. Environmental data includes ambient lighting, weather conditions and road conditions. For example, the lane type is highway, the traffic signal is green, the number of nearby vehicles is 5, the number of nearby pedestrians is 2, the ambient lighting is bright, the weather condition is sunny, and the road condition is dry.

[0076] The state mode identification is used to indicate whether the vehicle is driving normally, and the annotation is used to train the vehicle assisted driving model to correctly identify and respond to different driving environments and conditions. Exemplarily, the state mode identification includes a normal driving mode and an abnormal driving mode.

[0077] Optionally, the vehicle driving data samples are collected from various sensors of the vehicle, and the data is stored in a structured manner, specifically in JSON format.

[0078] S102. Input the vehicle driving data sample into a preset neural network model to iteratively evaluate the model output error data for the vehicle driving data sample, and adjust the model parameters configured by the neural network model and the number of nodes of the hidden layer arranged by the neural network model based on the model output error data, until a preset iteration stop condition is reached, thereby obtaining a vehicle assisted driving model.

[0079] It should be noted that the neural network model in this application is used to extract feature data of input data and classify the input data accordingly. At present, neural networks are often used for feature extraction. In some neural network structures, problems such as gradient vanishing, gradient explosion, or falling into local optimal solutions may be encountered, affecting the stability of training and the performance of the model. Based on this, this application optimizes the model parameters and the number of hidden layer nodes of the neural network model based on a chaotic optimization algorithm to achieve model training. Specifically, the neural network model is trained in this application using a self-regulating mechanism, and the model parameters of the neural network model are dynamically adjusted according to the error of the previous training cycle (i.e., the previous iteration). The sensitivity in chaos theory is used to enhance the model's responsiveness to initial conditions and parameter changes.

[0080] In the present application, the model parameters of the neural network model include weights, biases and learning rates. Specifically, the vehicle driving data samples are input into the neural network model to obtain the model output results for the vehicle driving data samples in the previous iteration for any iteration, and the model output error data of the previous iteration is evaluated, and the current model parameters (i.e., the model parameters acting on the previous iteration) and the current number of hidden layer nodes (i.e., the number of hidden layer nodes acting on the previous iteration) of the neural network model are adjusted based on the model output error data to obtain the model parameters and the number of hidden layer nodes acting on this iteration, so as to extract features from the vehicle driving data samples and classify them according to the model parameters and the number of hidden layer nodes of this iteration, and output the model output results of this iteration. And so on, until the iteration stop condition is reached, the model training is completed, and the vehicle assisted driving model is obtained.

[0081] The iteration stop condition is used to characterize the stop condition of the neural network model iteration, which means that the model training is completed. Optionally, the iteration stop condition can be reaching a preset maximum number of iterations. For example, the maximum number of iterations is set to 1000 times.

[0082] Therefore, the present application obtains a vehicle assisted driving model by adaptively and dynamically adjusting the model parameters and the number of hidden layer nodes of the neural network model, which can continuously adapt to new traffic environments and driving habits, thereby improving the accuracy and efficiency of model training.

[0083] In some embodiments, Figure 2 A structural diagram of a neural network model provided for an exemplary embodiment of the present application, wherein the neural network model 200 includes a cascade-sorted feature extraction network 201 and a classification network 202, wherein both the feature extraction network 201 and the classification network 202 include multiple hidden layers arranged in a cascaded manner.

[0084] Specifically, the following steps are performed by the feature extraction network and the classification network, including:

[0085] Performing feature dimension reduction on the vehicle driving data sample input into the neural network model through the feature extraction network to obtain vehicle feature information;

[0086] The vehicle characteristic information is classified through the classification network to obtain the vehicle driving state result of the sample vehicle and serve as the output of the neural network model.

[0087] In this embodiment, the feature extraction network can be a 6-layer fully connected neural network. The feature extraction network is used to obtain vehicle feature information after performing feature dimensionality reduction on the input data. Among them, feature dimensionality reduction can reduce the number of features (i.e., dimensions) while retaining as much effective information as possible. Therefore, this embodiment achieves feature dimensionality reduction by setting a feature extraction network, which can reduce computational complexity, improve algorithm efficiency, and can be applied to electronic devices such as vehicle-mounted terminals with limited data processing capabilities, thereby increasing the application scope of assisted driving.

[0088] The reduced-dimensional data is input into a classification network connected to the feature extraction network for classification to identify the vehicle driving state (such as a state mode indicating whether the vehicle is driving normally). Optionally, the classification network can use a support vector machine classifier.

[0089] S103: Acquire vehicle driving data of the target vehicle.

[0090] S104: Analyze the vehicle driving data using the vehicle assisted driving model to obtain a vehicle driving state result of the target vehicle.

[0091] The vehicle driving data includes the vehicle travel data, road traffic data, etc. as described above. The vehicle assisted driving model includes a trained feature extraction network and a trained classification network. Then, the vehicle driving data is input into the vehicle assisted driving model, and the trained feature extraction network performs feature dimension reduction on the vehicle driving data to obtain vehicle feature information, and the trained classification network classifies the vehicle feature information and outputs a vehicle driving state result, which may include a state mode (i.e., whether the vehicle is driving normally).

[0092] Therefore, the present application utilizes the vehicle assisted driving model to identify the vehicle driving state result of the vehicle, which can cope with complex or changeable driving environments, and realize rapid and timely identification of the vehicle driving state, thereby improving the efficiency and accuracy of vehicle assisted driving, thereby improving the safety of assisted driving and the application scope of vehicle assisted driving. At the same time, with the help of the vehicle assisted driving model, a large amount of data processing is not required, which reduces the difficulty of hardware configuration.

[0093] The vehicle assisted driving method, device, electronic device, vehicle and program product proposed in this embodiment trains a preset neural network model through a vehicle driving data sample containing vehicle driving data, road traffic data and state mode identification, that is, it iteratively evaluates the model output error data for the vehicle driving data sample, and adjusts the model parameters configured by the neural network model and the number of nodes of the hidden layer arranged by the neural network model based on the model output error data, so as to realize model adaptive adjustment, so that the vehicle assisted driving model is obtained, which can continuously adapt to new traffic environments and driving habits, and improve the accuracy and efficiency of model training. The vehicle driving state result of the vehicle is identified by the vehicle assisted driving model, which can cope with complex or changeable driving environments, and realize rapid and timely identification of the vehicle driving state, improve the efficiency and accuracy of vehicle assisted driving, thereby improving the safety of assisted driving and the application scope of vehicle assisted driving.

[0094] In some embodiments, Figure 3 A flow chart of adjusting the model parameters of a neural network model provided in an embodiment of the present application. This embodiment provides a method for adjusting the model parameters of a neural network model, that is, step S102 may include but is not limited to steps S301 to S304.

[0095] S301, initializing model parameters of the neural network model, wherein the model parameters include weight, bias and learning rate;

[0096] S302, for any iteration, based on the output of the neural network model in the previous iteration, determining corresponding model output error data, wherein the model output error data includes the model error and the error change amount of the previous iteration;

[0097] S303, updating the learning rate of this iteration based on the learning rate of the neural network model in the previous iteration and the error change in the previous iteration;

[0098] S304: based on the learning rate of this iteration, the weight of the neural network model in the previous iteration and the model error, update the weight of this iteration.

[0099] In this embodiment, the weights and biases of the neural network model are initialized, that is, the initial values ​​of the weights and the initial values ​​of the biases are obtained. Optionally, for step S301, the weights of the neural network model are initialized by the following formula (1), including:

[0100] W p，0 =μ p +σ p N(0, I) (1)

[0101] Among them, W p,0 is the initial value of the weight of the neural network model, μ p is the mean shift of the weights of the neural network model, σ p is the standard deviation of weight initialization, N(0, I) represents a normal distribution with mean 0 and standard deviation as the identity matrix, and I is the identity matrix.

[0102] The bias of the neural network model is initialized by the following formula, including:

[0103] b p,0 =v p N(0,I)

[0104] Among them, b p，0 is the initial value of the bias, v p is the mean shift of the bias of the neural network model.

[0105] For example, μ p Set to 0.01, v p Set to 0.05, σ p Set to 0.001.

[0106] Furthermore, for any iteration, the model output results for the vehicle driving data samples in the previous iteration are obtained, and the error change and model error of the previous iteration are evaluated. Based on the error change of the previous iteration, the current weights and learning rate of the neural network model are adjusted (i.e., the weights and learning rate of the previous iteration are used as the scope) to obtain the weights and learning rate of this iteration.

[0107] Optionally, a model error of the neural network model is obtained by calculating the output features of the last layer of the neural network using a preset Softmax function.

[0108] In some embodiments, the error change of the neural network model is evaluated, and the learning rate is adjusted through a chaotic feedback mechanism to avoid overfitting or underfitting and self-regulate the learning rate. Specifically, the learning rate of this iteration is determined by the following formula (2), including:

[0109] η p,t =η p，t-1 ·exp(-γ p ΔE p，t-1 ) (2)

[0110] Among them, η p，t is the learning rate of the tth iteration, η p,t-1 is the learning rate of the neural network model in the t-1th iteration, ΔE p，t-1 is the error change of the t-1th iteration, γ p It is a preset model adjustment factor that controls the sensitivity of learning rate changes.

[0111] Further, the weight is updated according to the updated learning rate. In some embodiments, the weight of this iteration is determined by the following formula (3), including:

[0112]

[0113] Among them, W p，t is the weight of the tth iteration, W p，t-1 is the weight of the neural network model in the t-1th iteration, E p is the model error. is the symbol of partial derivative.

[0114] Therefore, this embodiment evaluates the model output error data of the previous iteration, adjusts the learning rate of the neural network model, and adjusts the weight based on the adjusted learning rate to obtain the learning rate and weight for this iteration, thereby realizing model adaptive adjustment, being able to continuously adapt to new traffic environments and driving habits, improving the accuracy and efficiency of model training, and increasing the scope of application of the model.

[0115] In some embodiments, during the training process, a regularization strategy is used to prevent overfitting and ensure the generalization ability of the model. Specifically, regularization sparsification is performed by dynamically adjusting the number of nodes in the hidden layer of the neural network. Specifically, step S102 also includes:

[0116] Obtaining a node adjustment step size, wherein the node adjustment step size is associated with a hidden layer arranged in the neural network model;

[0117] For any iteration, the number of nodes in the hidden layer in this iteration is updated based on the number of nodes in the hidden layer included in the neural network model in the previous iteration, the node adjustment step size, and the error change in the previous iteration.

[0118] In this embodiment, the node adjustment step size of the hidden layer of the neural network model depends on the function of the network level. Optionally, the node adjustment step size is determined by the following formula (5), including:

[0119]

[0120] Among them, α p is the preset influence coefficient (i.e., the influence coefficient of adjusting the adjustment step), d p is the model depth determined by the hidden layer arranged by the neural network model (i.e., the depth of the current network layer); Int cs (*) indicates a rounding operation. For example, d p The value is 6, α p Set to 2.5.

[0121] Further, based on the number of nodes in the hidden layer in the previous iteration, the node adjustment step size, and the error change in the previous iteration, the number of nodes in the hidden layer in this iteration is updated. Optionally, the number of nodes in the hidden layer in this iteration is determined by the following formula (4), including:

[0122] N p，t =N p,t-1 +sgn(ΔE p，t-1 )·β p (4)

[0123] Where N p，t is the number of nodes in the hidden layer in the tth iteration, N p，t-1 is the number of nodes in the hidden layer in the t-1th iteration, β p Adjust the step size for the node. Where sgn(*) represents the sign function of the error change, which is used to decide whether to increase or decrease the number of nodes, that is, for sgn(ΔE p，t-1 ), when ΔE p，t-1 When sgn(ΔE p，t-1 ) is 1, when ΔE p,t-1 When sgn(ΔE p,t-1 ) is -1.

[0124] Therefore, this embodiment prevents overfitting through a regularization strategy and dynamically adjusts the number of hidden layer nodes, thereby improving the accuracy of model training.

[0125] Furthermore, the vehicle driving data samples are input into the neural network model, so that for any iteration, the feature extraction network and the classification network are updated according to the adjusted model parameters and the number of hidden layer nodes, so as to extract features from the vehicle driving data samples and classify them, and output the model output result of this iteration. And so on, until the iteration stop condition is reached, the model training is completed, and the vehicle assisted driving model is obtained. Thus, the vehicle driving data is input into the vehicle assisted driving model, so that the trained feature extraction network performs feature dimension reduction on the vehicle driving data to obtain vehicle feature information, and the trained classification network classifies the vehicle feature information and outputs the vehicle driving state result.

[0126] Therefore, the present application utilizes the vehicle assisted driving model to identify the vehicle driving state result of the vehicle, which can cope with complex or changeable driving environments, and realize rapid and timely identification of the vehicle driving state, thereby improving the efficiency and accuracy of vehicle assisted driving, thereby improving the safety of assisted driving and the application scope of vehicle assisted driving. At the same time, with the help of the vehicle assisted driving model, a large amount of data processing is not required, which reduces the difficulty of hardware configuration.

[0127] Figure 4 A schematic diagram of the structure of a vehicle assisted driving device provided in an embodiment of the present application, wherein the vehicle assisted driving device 400 comprises:

[0128] A first acquisition module 401 is used to acquire a vehicle driving data sample, wherein the vehicle driving data sample includes vehicle driving data, road traffic data and a corresponding state mode identifier of a sample vehicle, wherein the state mode identifier is used to indicate whether the vehicle is driving normally;

[0129] A model training module 402 is used to input the vehicle driving data sample into a preset neural network model to iteratively evaluate the model output error data for the vehicle driving data sample, and adjust the model parameters configured by the neural network model and the number of nodes of the hidden layer arranged by the neural network model based on the model output error data, until a preset iteration stop condition is reached, thereby obtaining a vehicle assisted driving model;

[0130] The second acquisition module 403 is used to acquire vehicle driving data of the target vehicle;

[0131] The analysis module 404 is used to analyze the vehicle driving data through the vehicle assisted driving model to obtain the vehicle driving state result of the target vehicle.

[0132] In some embodiments, the neural network model includes a cascade-sorted feature extraction network and a classification network, and the feature extraction network and the classification network both include a plurality of hidden layers arranged in a cascade-sorted manner;

[0133] The model training module 402 includes:

[0134] A feature extraction unit, configured to perform feature dimension reduction on a vehicle driving data sample input into the neural network model through the feature extraction network to obtain vehicle feature information;

[0135] The classification unit is used to classify the vehicle feature information through the classification network to obtain the vehicle driving state result of the sample vehicle as the output of the neural network model.

[0136] In some embodiments, the model training module 402 includes:

[0137] An initialization unit, used to initialize model parameters of the neural network model, wherein the model parameters include weights, biases, and learning rates;

[0138] An error calculation unit, for determining corresponding model output error data for any iteration based on the output of the neural network model in the previous iteration, wherein the model output error data includes the model error and the error change amount of the previous iteration;

[0139] A learning rate updating unit, used to update the learning rate of this iteration based on the learning rate of the neural network model in the previous iteration and the error change of the previous iteration;

[0140] The weight updating unit is used to update the weight of this iteration based on the learning rate of this iteration, the weight of the neural network model in the previous iteration and the model error.

[0141] In some embodiments, the initialization unit includes:

[0142] The weight initialization unit is used to initialize the weight of the neural network model by the following formula (1), including:

[0143] W p，0 =μ p +σ p N(0, I) (1)

[0144] Among them, W p,0 is the initial value of the weight of the neural network model, μ p is the mean shift of the weights of the neural network model, σ p is the standard deviation of weight initialization, N(0, I) represents a normal distribution with mean 0 and standard deviation as the identity matrix, and I is the identity matrix.

[0145] In some embodiments, the learning rate updating unit includes:

[0146] The learning rate calculation unit is used to determine the learning rate of this iteration through the following formula (2), including:

[0147] η p,t =η p,t-1 ·exp(-γ p ΔE p，t-1 ) (2)

[0148] Among them, η p，t is the learning rate of the tth iteration, η p,t-1 is the learning rate of the neural network model in the t-1th iteration, ΔE p，t-1 is the error change of the t-1th iteration, γ p is the preset model adjustment factor.

[0149] In some embodiments, the weight updating unit includes:

[0150] The weight calculation unit is used to determine the weight of this iteration through the following formula (3), including:

[0151]

[0152] Among them, W p，t is the weight of the tth iteration, W p，t-1 is the weight of the neural network model in the t-1th iteration, E p is the model error.

[0153] In some embodiments, the model training module 402 further includes:

[0154] A node adjustment step length acquisition unit, used to acquire a node adjustment step length, wherein the node adjustment step length is associated with a hidden layer arranged in the neural network model;

[0155] A node quantity updating unit, for any iteration, based on the number of nodes in the hidden layer included in the neural network model in the previous iteration, the node adjustment step size and the error change in the previous iteration, updates the number of nodes in the hidden layer in this iteration;

[0156] The number of nodes in the hidden layer in this iteration is determined by the following formula (4), including:

[0157] N p，t =N p，t-1 +sgn(ΔE p，t-1 )·β p (4)

[0158] Where N p，t is the number of nodes in the hidden layer in the tth iteration, N p，t-1is the number of nodes in the hidden layer in the t-1th iteration, β p The step size is adjusted for the node, and sgn(*) represents the sign function of the error change.

[0159] In some embodiments, the node adjustment step acquisition unit:

[0160] The node adjustment step length calculation unit is used to determine the node adjustment step length by the following formula (5), including:

[0161]

[0162] Among them, α p is the preset influence coefficient, d p is the model depth determined by the hidden layer arranged by the neural network model, Int cs (*) indicates a rounding operation.

[0163] The device of the embodiments of the present application can execute the method provided by the embodiments of the present application, and the implementation principles are similar. The actions performed by each module in the device of each embodiment of the present application correspond to the steps in the method of each embodiment of the present application. For the detailed functional description of each module of the device, please refer to the description in the corresponding method shown in the previous text, which will not be repeated here.

[0164] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned vehicle assisted driving method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0165] See also Figure 5 , Figure 5 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0166] The processor 501 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0167] The memory 502 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 502 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 502, and the processor 501 calls and executes a vehicle assisted driving method in the embodiment of this application;

[0168] Input / output interface 503, used to implement information input and output;

[0169] Communication interface 504, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0170] A bus 505 that transmits information between the various components of the device (e.g., the processor 501, the memory 502, the input / output interface 503, and the communication interface 504);

[0171] The processor 501 , the memory 502 , the input / output interface 503 and the communication interface 504 are connected to each other in communication within the device via the bus 505 .

[0172] An embodiment of the present application also provides a vehicle, which includes the above-mentioned vehicle assisted driving device or the above-mentioned electronic device.

[0173] An embodiment of the present application also provides a computer program product, including a computer program, which implements the above-mentioned vehicle assisted driving method when executed by a processor.

[0174] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0175] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0176] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0177] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0178] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application 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 interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising 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, products or devices.

[0179] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0180] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may 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 is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0181] The units described above 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 on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0182] In addition, each functional unit in each embodiment of the present application 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.

[0183] If the integrated 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, the technical solution of the present application, 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 product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0184] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A vehicle assisted driving method, characterized in that: The method comprises: Acquire a vehicle driving data sample, wherein the vehicle driving data sample includes vehicle driving data, road traffic data and a corresponding state mode identifier of a sample vehicle, wherein the state mode identifier is used to indicate whether the vehicle is driving normally; Inputting the vehicle driving data sample into a preset neural network model to iteratively evaluate model output error data for the vehicle driving data sample, and adjusting model parameters configured by the neural network model and the number of nodes of the hidden layer arranged by the neural network model based on the model output error data until a preset iteration stop condition is reached, thereby obtaining a vehicle assisted driving model; Acquiring vehicle driving data of a target vehicle; The vehicle driving data is analyzed by the vehicle assisted driving model to obtain a vehicle driving state result of the target vehicle.

2. The vehicle assisted driving method according to claim 1, characterized in that: The neural network model includes a cascade-sorted feature extraction network and a classification network, and the feature extraction network and the classification network both include a plurality of hidden layers arranged in a cascade-sorted manner; The following steps are performed by the feature extraction network and the classification network, including: Performing feature dimension reduction on the vehicle driving data sample input into the neural network model through the feature extraction network to obtain vehicle feature information; The vehicle feature information is classified through the classification network to obtain the vehicle driving state result of the sample vehicle and serve as the output of the neural network model.

3. The vehicle assisted driving method according to claim 2, characterized in that: The step of inputting the vehicle driving data sample into a preset neural network model to iteratively evaluate the model output error data for the vehicle driving data sample, and adjusting the model parameters configured by the neural network model and the number of nodes of the hidden layer arranged by the neural network model based on the model output error data until a preset iteration stop condition is reached to obtain a vehicle assisted driving model, comprising: Initializing model parameters of the neural network model, wherein the model parameters include weights, biases, and learning rates; For any iteration, based on the output of the neural network model in the previous iteration, the corresponding model output error data is determined, wherein the model output error data includes the model error and the error change amount of the previous iteration; Based on the learning rate of the neural network model in the previous iteration and the error change in the previous iteration, the learning rate of this iteration is updated; Based on the learning rate of this iteration, the weight of the neural network model in the previous iteration and the model error, the weight of this iteration is updated.

4. The vehicle assisted driving method according to claim 3, characterized in that: The initialization of the model parameters of the neural network model, the model parameters including weights, biases and learning rates, includes: The weights of the neural network model are initialized by the following formula (1), including: W p，0 =μ p +s p ·N(0, I) (1) Among them, W p，0 is the initial value of the weight of the neural network model, μ p is the mean shift of the weights of the neural network model, σ p is the standard deviation of weight initialization, N(0, I) represents a normal distribution with a mean of 0 and a standard deviation of the identity matrix, and I is the identity matrix; The updating of the learning rate of this iteration based on the learning rate of the neural network model in the previous iteration and the error change in the previous iteration includes: The learning rate of this iteration is determined by the following formula (2), including: or p，t =the p，t-1 ·exp(-γ p ·D.E p，t-1 ) (2) Among them, η p，t is the learning rate of the tth iteration, η p，t-1 is the learning rate of the neural network model in the t-1th iteration, ΔE p，t-1 is the error change of the t-1th iteration, γ p is the preset model adjustment factor; The updating of the weight of this iteration based on the learning rate of this iteration, the weight of the neural network model in the previous iteration, and the model error includes: The weight of this iteration is determined by the following formula (3), including: Among them, W p，t is the weight of the tth iteration, W p，t-1 is the weight of the neural network model in the t-1th iteration, E p is the model error.

5. The vehicle assisted driving method according to claim 4, characterized in that: The step of inputting the vehicle driving data sample into a preset neural network model to iteratively evaluate the model output error data for the vehicle driving data sample, and adjusting the model parameters configured by the neural network model and the number of nodes of the hidden layer arranged by the neural network model based on the model output error data until a preset iteration stop condition is reached to obtain a vehicle assisted driving model, further comprising: Obtaining a node adjustment step size, wherein the node adjustment step size is associated with a hidden layer arranged in the neural network model; For any iteration, based on the number of nodes in the hidden layer included in the neural network model in the previous iteration, the node adjustment step size and the error change of the previous iteration, the number of nodes in the hidden layer in this iteration is updated; The number of nodes in the hidden layer in this iteration is determined by the following formula (4), including: N p，t =N p，t-1 +sgn(ΔE p，t-1 )·b p (4) Where N p，t is the number of nodes in the hidden layer in the tth iteration, N p，t-1 is the number of nodes in the hidden layer in the t-1th iteration, β p The step size is adjusted for the node, and sgn(*) represents the sign function of the error change.

6. The vehicle assisted driving method according to claim 5, characterized in that: The obtaining of the node adjustment step size comprises: The node adjustment step size is determined by the following formula (5), including: Among them, α p is the preset influence coefficient, d p is the model depth determined by the hidden layer arranged by the neural network model, Int cs (*) indicates a rounding operation.

7. A vehicle assisted driving device, characterized in that: The device comprises: A first acquisition module is used to acquire a vehicle driving data sample, wherein the vehicle driving data sample includes vehicle driving data, road traffic data and a corresponding state mode identifier of a sample vehicle, wherein the state mode identifier is used to indicate whether the vehicle is driving normally; A model training module, used to input the vehicle driving data sample into a preset neural network model to iteratively evaluate the model output error data for the vehicle driving data sample, and adjust the model parameters configured by the neural network model and the number of nodes of the hidden layer arranged by the neural network model based on the model output error data, until a preset iteration stop condition is reached, thereby obtaining a vehicle assisted driving model; A second acquisition module is used to acquire vehicle driving data of the target vehicle; The analysis module is used to analyze the vehicle driving data through the vehicle assisted driving model to obtain the vehicle driving state result of the target vehicle.

8. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the vehicle assisted driving method according to any one of claims 1 to 6 when executing the computer program.

9. A vehicle, characterized in that: The vehicle includes the vehicle assisted driving device as claimed in claim 7 or the electronic device as claimed in claim 8.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the vehicle assisted driving method according to any one of claims 1 to 6 is implemented.

Images