State prediction method and device of automobile battery, computer equipment and storage medium

Abstract

The invention relates to the technical field of battery analysis, in particular to an automobile battery state prediction method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring vehicle battery parameters of a target vehicle in a preset period; predicting the battery state of the target vehicle according to the vehicle battery parameters through a pre-trained battery state prediction model to obtain a target battery state; the method is realized through the battery state prediction model, the battery state of the target vehicle is accurately analyzed according to the vehicle battery parameters of the vehicle battery parameters in the preset period and the change condition of the vehicle battery parameters in the preset period, the accuracy of battery state prediction of the target vehicle is ensured, and the user experience is improved. And the operation difficulty of predicting the battery state of the target vehicle is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of battery analysis, and particularly to a method, device, computer device, and storage medium for predicting the state of an automotive battery. Background Art

[0002] With the continuous increase in the social ownership of electric vehicles, there are more and more cases of spontaneous combustion, fire, and power loss of electric vehicles due to faults in power batteries. Among them, the main reason for the faults in power batteries is a series of problems caused by the aging of the battery state.

[0003] In the prior art, it is difficult to accurately predict the state of the power battery of an electric vehicle, which poses a great safety hazard to the driving safety of electric vehicles and is not conducive to the sustainable and stable development of the electric vehicle industry. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide a method, device, computer device, and storage medium for predicting the state of an automotive battery that can accurately predict the state of the power battery of an electric vehicle.

[0005] In a first aspect, the present application provides a method for predicting the state of an automotive battery. The method includes:

[0006] Obtain the vehicle battery parameters of a target vehicle within a preset period;

[0007] Predict the battery state of the target vehicle based on the vehicle battery parameters through a pre-trained battery state prediction model to obtain a target battery state; wherein, the battery state prediction model is trained based on the reference battery parameters of a reference vehicle within a preset period, the initial battery state of the reference vehicle when entering the preset period, and the real-time battery state of the reference vehicle within the preset period; the vehicle type of the reference vehicle is the same as that of the target vehicle; and the difference between the mileage of the reference vehicle and that of the target vehicle is less than a preset value.

[0008] In one embodiment, the training process of the battery state prediction model includes:

[0009] Collect data on the battery parameters of the reference vehicle within a preset period to obtain the reference battery parameters;

[0010] Obtain the initial battery state of the reference vehicle when entering the preset period and the real-time battery state of the reference vehicle within the preset period;

[0011] Based on the reference battery parameters, the initial battery state, the real-time battery state, the first mapping relationship between the reference battery parameters and the initial battery state, and the second mapping relationship between the reference battery parameters, the initial battery state, the real-time battery state, train the initial prediction model to obtain the trained battery state prediction model.

[0012] In one embodiment, the obtaining the initial battery state when the reference vehicle enters a preset period includes:

[0013] Conduct a physical analysis of the battery state based on the reference battery characteristics when the reference vehicle enters the preset period to obtain the initial battery state when the reference vehicle enters the preset period; and / or,

[0014] Perform a state prediction on the initial battery state based on the historical charge and discharge data when the reference vehicle enters the preset period to obtain the initial battery state when the reference vehicle enters the preset period.

[0015] In one embodiment, obtaining the real-time battery state of the reference vehicle within the preset period includes:

[0016] Use the Kalman filter algorithm to predict the battery state of the reference vehicle within the preset period to obtain the real-time battery state of the reference vehicle within the preset period.

[0017] In one embodiment, the method further includes:

[0018] Obtain the model performance parameters of the battery state prediction model under different working conditions;

[0019] Determine the robustness of the battery state prediction model according to the model performance parameters of the battery state prediction model under different working conditions;

[0020] In the case where the robustness of the battery state prediction model is unqualified, adjust the model parameters of the battery state prediction model.

[0021] In one embodiment, the obtaining the model performance parameters of the battery state prediction model under different working conditions includes:

[0022] Perform a performance test on the battery state prediction model under different working conditions to obtain performance test parameters;

[0023] Verify the performance test parameters of the battery state prediction model under different working conditions to obtain the model performance parameters of the battery state prediction model under different working conditions.

[0024] In one of the embodiments, the performance test parameters of the battery state prediction model under different working conditions are verified to obtain the model performance parameters of the battery state prediction model under different working conditions, including:

[0025] Perform cross-validation on the performance test parameters of the battery state prediction model under different working conditions to obtain the model performance parameters of the battery state prediction model under different working conditions.

[0026] In a second aspect, the present application also provides a device for predicting the state of an automotive battery. The device includes:

[0027] An acquisition module, configured to acquire vehicle battery parameters of a target vehicle within a preset period;

[0028] A prediction module, configured to predict the battery state of the target vehicle based on the vehicle battery parameters through a pre-trained battery state prediction model to obtain a target battery state; wherein, the battery state prediction model is trained according to the reference battery parameters of a reference vehicle within a preset period, the initial battery state of the reference vehicle when entering the preset period, and the real-time battery state of the reference vehicle within the preset period; the vehicle type of the reference vehicle is the same as that of the target vehicle; and the difference between the mileage of the reference vehicle and the mileage of the target vehicle is less than a preset value.

[0029] In a third aspect, the present application also provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0030] Acquire vehicle battery parameters of a target vehicle within a preset period;

[0031] Predict the battery state of the target vehicle based on the vehicle battery parameters through a pre-trained battery state prediction model to obtain a target battery state; wherein, the battery state prediction model is trained according to the reference battery parameters of a reference vehicle within a preset period, the initial battery state of the reference vehicle when entering the preset period, and the real-time battery state of the reference vehicle within the preset period; the vehicle type of the reference vehicle is the same as that of the target vehicle; and the difference between the mileage of the reference vehicle and the mileage of the target vehicle is less than a preset value.

[0032] In a fourth aspect, the present application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, and when the computer program is executed by a processor, the following steps are implemented:

[0033] Acquire vehicle battery parameters of a target vehicle within a preset period;

[0034] Predict the battery state of the target vehicle based on the vehicle battery parameters through a pre-trained battery state prediction model to obtain the target battery state; wherein, the battery state prediction model is trained based on the reference battery parameters of the reference vehicle in a preset period, the initial battery state of the reference vehicle when entering the preset period, and the real-time battery state of the reference vehicle in the preset period; the vehicle type of the reference vehicle is the same as that of the target vehicle; and the difference between the mileage of the reference vehicle and the mileage of the target vehicle is less than a preset value.

[0035] In a fifth aspect, the present application also provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0036] Obtain the vehicle battery parameters of the target vehicle in a preset period;

[0037] Predict the battery state of the target vehicle based on the vehicle battery parameters through a pre-trained battery state prediction model to obtain the target battery state; wherein, the battery state prediction model is trained based on the reference battery parameters of the reference vehicle in a preset period, the initial battery state of the reference vehicle when entering the preset period, and the real-time battery state of the reference vehicle in the preset period; the vehicle type of the reference vehicle is the same as that of the target vehicle; and the difference between the mileage of the reference vehicle and the mileage of the target vehicle is less than a preset value.

[0038] For the above-mentioned method, device, computer device and storage medium for predicting the state of an automotive battery, by obtaining the vehicle battery parameters of the target vehicle in a preset period; furthermore, predicting the battery state of the target vehicle based on the vehicle battery parameters through a pre-trained battery state prediction model to obtain the target battery state; wherein, the battery state prediction model is trained based on the reference battery parameters of the reference vehicle in a preset period, the initial battery state of the reference vehicle when entering the preset period, and the real-time battery state of the reference vehicle in the preset period. According to the above content, it can be seen that in the process of predicting the battery state of the target vehicle in the present application, the vehicle battery parameters of the target vehicle in the preset period are combined to obtain the vehicle battery parameters of the target vehicle in the preset period, and through the vehicle battery parameters in the preset period and the change of the vehicle battery parameters in the preset period, the battery state of the target vehicle is accurately analyzed, ensuring the accuracy of the battery state prediction of the target vehicle and reducing the operation difficulty of predicting the battery state of the target vehicle. Description of the Drawings

[0039] Figure 1An application environment diagram of a method for predicting the state of an automotive battery provided by an embodiment of the present application;

[0040] Figure 2 A flowchart of a first method for predicting the state of an automotive battery provided by an embodiment of the present application;

[0041] Figure 3 A flowchart of a second method for predicting the state of an automotive battery provided by an embodiment of the present application;

[0042] Figure 4 A flowchart of a third method for predicting the state of an automotive battery provided by an embodiment of the present application;

[0043] Figure 5 A structural block diagram of a device for predicting the state of an automotive battery provided by an embodiment of the present application;

[0044] Figure 6 An internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0045] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to 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.

[0046] The method for predicting the state of an automotive battery provided by an embodiment of the present application can be applied to an application environment as shown in Figure 1 In the figure. Among them, the terminal 102 communicates with the server 104 through a network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or can be placed in the cloud or other network servers. By obtaining the vehicle battery parameters of the target vehicle within a preset period; furthermore, through a pre-trained battery state prediction model, the battery state of the target vehicle is predicted according to the vehicle battery parameters to obtain the target battery state; among them, the battery state prediction model is trained according to the reference battery parameters of the reference vehicle within a preset period, the initial battery state when the reference vehicle enters the preset period, and the real-time battery state of the reference vehicle within the preset period. Among them, the terminal 102 can be but is not limited to various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0047] In one embodiment, as shown in Figure 2As shown, a method for predicting the state of an automotive battery is provided. Taking the server 104 in Figure 1 as an example, the method includes the following steps:

[0048] S201, obtaining the vehicle battery parameters of the target vehicle within a preset period.

[0049] It should be noted that the vehicle battery parameters are used to characterize the relevant parameters of the vehicle battery of the target vehicle, and may include, but are not limited to: voltage information parameters, current information parameters, temperature information parameters, etc.

[0050] Among them, the voltage information parameter refers to the voltage value of the vehicle battery of the target vehicle, usually in volts (V). The current information parameter refers to the current value generated during the charging and discharging process of the vehicle battery, usually in amperes (A). The temperature information parameter refers to the temperature of the vehicle battery itself and the ambient temperature of its environment, usually in degrees Celsius (°C).

[0051] Furthermore, a battery management system for the vehicle battery of the target vehicle can be preset in advance, and the acquisition frequency (for example, once per second) and the acquisition time period (for example, the entire time period during which the target vehicle is driving) for the battery management system operator can be set; thereby, the operation of obtaining the vehicle battery parameters of the target vehicle within a preset period is realized according to the battery management system.

[0052] In an embodiment of the present application, to ensure the prediction accuracy of the subsequent prediction of the battery state of the target vehicle, the vehicle battery parameters can be data-cleaned to remove outliers and noise in the vehicle battery parameters, and ensure the parameter quality and parameter integrity of the vehicle battery parameters.

[0053] Specifically, a reasonable value range of the vehicle battery parameters can be preset in advance, and then, it is determined whether the parameter value of each vehicle battery parameter is within the reasonable value range. If the parameter value of a certain vehicle battery parameter belongs to the reasonable value range, it is determined that the vehicle battery parameter is a normal parameter and does not need to be cleaned; if the parameter value of a certain vehicle battery parameter does not belong to the reasonable value range, it is determined that the vehicle battery parameter is an abnormal parameter and needs to be cleaned. Or, traditional anomaly detection methods (such as Z-score or IQR) can be used for outlier detection, and then, the abnormal parameters detected in the vehicle battery parameters are data-cleaned. Or, a filter can also be used to filter the fluctuating parameters in the vehicle battery parameters within a short time to complete the data-cleaning operation for the vehicle battery parameters.

[0054] In one embodiment of the present application, after obtaining the vehicle battery parameters, the vehicle battery parameters can be subjected to missing detection; if it is determined that there is missing data in the vehicle battery parameters, data supplementation can be performed in the form of data interpolation.

[0055] Specifically, after determining that there is missing data in the vehicle battery parameters, interpolation methods (such as linear interpolation or spline interpolation) can be used for data supplementation.

[0056] Furthermore, to further ensure that the operation and maintenance personnel can intuitively know the parameter situation of the vehicle battery parameters, a visualization tool can be preset to visually display the vehicle battery parameters, so as to enable the operation and maintenance personnel to detect the parameters of the vehicle battery through the visualization tool, and ensure the rationality and continuity of the vehicle battery parameters.

[0057] S202, through a pre-trained battery state prediction model, predict the battery state of the target vehicle according to the vehicle battery parameters to obtain the target battery state.

[0058] Among them, the battery state prediction model is trained according to the reference battery parameters of the reference vehicle in a preset period, the initial battery state of the reference vehicle when entering the preset period, and the real-time battery state of the reference vehicle in the preset period.

[0059] Among them, the vehicle type of the reference vehicle is the same as that of the target vehicle; and the difference between the mileage of the reference vehicle and the mileage of the target vehicle is less than the preset value.

[0060] It should be noted that when it is necessary to predict the battery state of the target vehicle, the vehicle battery parameters can be input into the pre-trained battery state prediction model, and the output result of the battery state prediction model can be obtained, and this output result is the target battery state.

[0061] In one embodiment of the present application, in order to improve the prediction efficiency while ensuring the accuracy of battery state prediction, key features can be extracted from the vehicle battery parameters, and the obtained and extracted key feature vectors can be used as new vehicle battery parameters.

[0062] Specifically, when key feature vectors need to be obtained, key features can be selected from the vehicle battery parameters. For example, the key features in the voltage feature parameters include: maximum voltage, minimum voltage, average voltage, standard deviation, etc.; the key features in the current feature parameters include: maximum current, minimum current, average current, charge and discharge cycle, etc.; the key features in the temperature feature parameters include: maximum temperature, minimum temperature, average temperature, temperature change rate, etc. The obtained key features are combined into a specific vector to form a multi-dimensional data structure; this multi-dimensional data structure is the key feature vector.

[0063] The above-mentioned method for predicting the state of a vehicle battery obtains the vehicle battery parameters of a target vehicle within a preset period; furthermore, through a pre-trained battery state prediction model, the battery state of the target vehicle is predicted based on the vehicle battery parameters to obtain the target battery state; wherein, the battery state prediction model is trained according to the reference battery parameters of a reference vehicle within a preset period, the initial battery state of the reference vehicle when entering the preset period, and the real-time battery state of the reference vehicle within the preset period. According to the above content, it can be known that in the process of predicting the battery state of the target vehicle in this application, the vehicle battery parameters of the target vehicle within the preset period are combined to obtain the vehicle battery parameters of the target vehicle within the preset period, and through the vehicle battery parameters within the preset period and the change of the vehicle battery parameters within the preset period, the battery state of the target vehicle is accurately analyzed, ensuring the accuracy of the battery state prediction of the target vehicle and reducing the operation difficulty of predicting the battery state of the target vehicle.

[0064] In one embodiment, as Figure 3 shown, the training process of the battery state prediction model may specifically include the following contents:

[0065] S301, Collect data on the battery parameters of the reference vehicle within a preset period to obtain reference battery parameters.

[0066] In one embodiment of this application, when it is necessary to collect data on the battery parameters within a preset period, the collected data parameters can be cleaned and noise-filtered to remove outliers and noise in the parameters; and, by extracting features from the parameters after data cleaning is completed, key feature vectors are obtained, and the key feature vectors are used as reference battery parameters.

[0067] S302, Obtain the initial battery state of the reference vehicle when entering the preset period and the real-time battery state of the reference vehicle within the preset period.

[0068] It should be noted that when it is necessary to obtain the initial battery state of the reference vehicle when entering the preset period, it may specifically include the following contents: Physically analyze the battery state according to the reference battery characteristics of the reference vehicle when entering the preset period to obtain the initial battery state of the reference vehicle when entering the preset period; and / or, predict the state of the initial battery state according to the historical charge and discharge data of the reference vehicle when entering the preset period to obtain the initial battery state of the reference vehicle when entering the preset period.

[0069] In an embodiment of the present application, when performing a physical analysis of the battery state based on the reference battery characteristics of the reference vehicle when entering a preset cycle, and when performing the physical analysis based on a physical model, specifically: obtain the physical characteristics of the vehicle battery, where the physical characteristics include different state of charge (SOC) corresponding to different reference battery parameters (for example, the physical characteristics may include the relationship between the open circuit voltage and the state of charge). Furthermore, based on the actually obtained reference battery parameters, determine the initial battery state of the reference vehicle when entering the preset cycle.

[0070] As an example, calculate the initial battery state of the battery based on the charge and discharge history of the vehicle battery and the current voltage, current, and temperature data.

[0071] In an embodiment of the present application, when performing a physical analysis of the battery state based on the reference battery characteristics of the reference vehicle when entering a preset cycle, and when performing the physical analysis based on data-driven, specifically: use the historical data of the vehicle battery to perform data learning on a machine learning model (such as a random forest or a gradient boosting machine) to obtain an initial state prediction model. Furthermore, realize the relationship between the input features of the control model learning and the battery state, and analyze the reference battery parameters through the initial state prediction model to obtain the initial battery state of the reference vehicle when entering the preset cycle.

[0072] It should be noted that when it is necessary to obtain the real-time battery state of the reference vehicle within the preset cycle, it may specifically include the following content: use the Kalman filter algorithm to predict the battery state of the reference vehicle within the preset cycle to obtain the real-time battery state of the reference vehicle within the preset cycle.

[0073] Specifically, the Kalman filter algorithm includes a prediction step and an update step;

[0074] Among them, the prediction step is as follows:

[0075] ;

[0076] Among them, is the state estimate, P is the error covariance, A and B are the state transition matrices, Q is the process noise covariance, and k refers to the time.

[0077] The update step is as follows:

[0078] K k =P k|k-1 H T (HP k|k-1 H T +R) -1 = +K k (z k -H )P k|k =(I - K k H)P k|k-1 ;

[0079] Among them, K k represents the Kalman gain at time k, P k|k-1 represents the predicted value of the state covariance at time k, H represents the measurement matrix, R represents the covariance matrix of the measurement noise, represents the estimated value of the state at time k, represents the predicted estimated value of the state at time k, z k represents the measured value at time k, P k|k represents the estimated value of the state covariance at time k, and I is the identity matrix.

[0080] Further explanation, to improve the accuracy of state estimation, the parameters of the filtering algorithm can be calibrated and adjusted regularly to reduce error accumulation. Specifically: First, perform parameter identification to identify the key parameters in the filtering algorithm, such as process noise and observation noise covariance; then adjust the key parameters. Specifically: According to historical data and model prediction errors, adjust the parameters to minimize the prediction error, and / or use optimization algorithms (such as gradient descent or genetic algorithms) to adjust the parameters.

[0081] Further explanation, to further improve the long-term stability of state analysis, the model residuals can be analyzed to identify and correct possible systematic biases; specifically, calculate the residuals between the model predicted values and the actual observed values; among them, the residual e k = z k - H ; furthermore, use statistical tests (such as chi-square test) to evaluate the distribution of the residuals, and identify outliers and trends in the residuals.

[0082] S303. According to the reference battery parameters, the initial battery state, the real-time battery state, the first mapping relationship between the reference battery parameters and the initial battery state, and the second mapping relationship between the reference battery parameters, the initial battery state, the real-time battery state, and the reference battery parameters and the real-time battery state, train the initial prediction model to obtain the trained battery state prediction model.

[0083] It should be noted that after obtaining the reference battery parameters, the initial battery state, and the real-time battery state, the reference battery parameters can be labeled according to the initial battery state and the real-time battery state, so as to obtain the first mapping relationship between the reference battery parameters, the initial battery state, the real-time battery state, and the reference battery parameters and the initial battery state, and the second mapping relationship between the reference battery parameters, the initial battery state, the real-time battery state, and the reference battery parameters and the real-time battery state. Among them, different state labels are defined according to different battery states.

[0084] Among them, the labeling method can use expert knowledge or historical data for labeling to ensure the accuracy of labeling.

[0085] Furthermore, the first mapping relationship and the second mapping relationship can be stored in a preset database for subsequent model training and analysis.

[0086] Among them, the database can select a suitable database according to the actual situation. For example, the database can select an SQL database, a NoSQL database, etc. The selection of the database is not limited here. The data format can be set or adjusted according to the actual situation. For example, it can be stored in a structured format to ensure the queryability and scalability of the data. The data storage format is not limited here.

[0087] Among them, to further improve the storage security of data in the database, data encryption and access control can be implemented to ensure data security and privacy protection; and to prevent data loss or damage, the data in the database can be backed up regularly to ensure data persistence.

[0088] It should be noted that when model training is required for the initial prediction model, the reference battery parameters, the initial battery state, and the real-time battery state can be pre-augmented. Specifically, SMOTE (Synthetic Minority Over-sampling Technique) or generative adversarial networks (GANs) can be used to expand the training set and improve the generalization ability of the model for different battery states.

[0089] Among them, the SMOTE technique identifies minority class (abnormal battery state) samples and uses the SMOTE algorithm to synthesize new samples. Furthermore, the K-nearest neighbor (KNN) between each minority class sample and other samples is calculated, and new samples are generated based on the KNN. The generative adversarial networks (GANs) technique trains a generator network to generate new samples similar to real battery state data. At the same time, a discriminator network is trained to distinguish between real data and the data generated by the generator. Furthermore, through adversarial training, the generator learns to generate more real battery state samples to expand the training set.

[0090] Further, select an initial prediction model algorithm suitable for vehicle battery health monitoring, such as neural network, Kalman filter or its improved algorithms. The neural network may include but not limited to: such as multi-layer perceptron (MLP), convolutional neural network (CNN) or recurrent neural network (RNN). And determine neural network parameters such as the number of network layers, the number of neurons, activation functions, etc. The Kalman filter and its improved algorithms can select the traditional Kalman filter or its extensions such as extended Kalman filter (EKF) or unscented Kalman filter (UKF). Determine the state transition matrix, observation matrix, process noise covariance and observation noise covariance.

[0091] Further, use the reference battery parameters, initial battery state, real-time battery state after data augmentation, and the mapping relationships between the reference battery parameters and the initial battery state and the real-time battery state respectively to train the initial prediction model, and use the backpropagation algorithm and gradient descent method to optimize the model weights, and achieve parameter optimization by adjusting hyperparameters such as learning rate, batch size, number of iterations, etc. Furthermore, obtain the trained battery state prediction model.

[0092] Among them, the parameter optimization process may specifically include using methods such as grid search, random search or Bayesian optimization to find the optimal hyperparameters, and monitoring the loss function value and accuracy during the training process to ensure that the model is not overfitted.

[0093] In an embodiment of the present application, the accuracy and robustness of the model can be evaluated by methods such as cross-validation to ensure the effectiveness of the model in practical applications; specifically, obtain the model performance parameters of the battery state prediction model under different working conditions; determine the robustness of the battery state prediction model according to the model performance parameters of the battery state prediction model under different working conditions; in the case that the robustness of the battery state prediction model is unqualified, adjust the model parameters of the battery state prediction model.

[0094] Among them, the model performance parameters can be divided into a training set, a validation set and a test set; among them, the model performance parameters can be the same as the reference battery parameters, and the model performance parameters are not divided here.

[0095] Further, when obtaining the model performance parameters of the battery state prediction model under different working conditions, the following contents may be included: perform performance tests on the battery state prediction model under different working conditions to obtain performance test parameters; verify the performance test parameters of the battery state prediction model under different working conditions to obtain the model performance parameters of the battery state prediction model under different working conditions.

[0096] Specifically, the performance test parameters of the battery state prediction model under different working conditions can be obtained; by cross - validating the performance test parameters of the battery state prediction model under different working conditions, the model performance parameters of the battery state prediction model under different working conditions are obtained.

[0097] Among them, the methods for validating the performance test parameters can include but are not limited to: k - fold cross - validation, stratified cross - validation, time - series cross - validation, and Monte Carlo cross - validation.

[0098] In an embodiment of the present application, the model training of the initial prediction model mainly relies on two key processes: forward propagation and backward propagation. These two processes jointly act on the weight update of the battery state prediction model, enabling the battery state prediction model to gradually approach the optimal solution; among them, forward propagation requires passing the input data to the input layer of the model, and the neurons in each layer perform a linear transformation on the input data: taking each activation value as the input of the next layer, and repeating the above - mentioned linear transformation and non - linear activation steps until reaching the output layer.

[0099] The linear output can be expressed as:

[0100] ;

[0101] Among them, W refers to the weight, a refers to the input data of each layer, b refers to the bias, and l refers to the index of the neurons in each layer.

[0102] Furthermore, backward propagation is the process in which the model calculates the gradient according to the loss function and updates the weights. First, at the output layer, calculate the loss between the model prediction result and the actual label (for example, using mean square error, cross - entropy loss, etc.); output layer gradient: take the derivative of the activation value of the output layer according to the loss function to obtain the gradient δ(L) of the output layer. Propagate the gradient layer by layer in reverse: use the chain rule to calculate the gradient δ(l) of each layer layer by layer starting from the output layer; according to the gradient δ(l) of each layer and the input a(l−1), calculate the gradients of the weight W(l) and the bias b(l). Use an optimization algorithm (such as SGD, Adam, etc.) to update the weights and biases according to the calculated gradients;

[0103] The update formula is as follows:

[0104] ;

[0105] Among them, α is the learning rate; L is the loss function.

[0106] The above-mentioned method for predicting the state of a vehicle battery realizes model training for an initial prediction model by obtaining reference battery parameters, the initial battery state when a reference vehicle enters a preset period, and the real-time battery state of the reference vehicle within the preset period, thereby obtaining a trained battery state prediction model, providing a data basis for subsequent prediction of the battery state of a target vehicle through the battery state prediction model, and ensuring the accuracy of subsequent battery state prediction.

[0107] In one embodiment, as Figure 4 shown, the training process of the battery state prediction model may specifically include the following:

[0108] S401, Collect data on the battery parameters of the reference vehicle within the preset period to obtain reference battery parameters.

[0109] S402, Physically analyze the battery state based on the reference battery characteristics when the reference vehicle enters the preset period to obtain the initial battery state when the reference vehicle enters the preset period.

[0110] S403, Use the Kalman filter algorithm to predict the battery state of the reference vehicle within the preset period to obtain the real-time battery state of the reference vehicle within the preset period.

[0111] S404, Based on the reference battery parameters, the initial battery state, the real-time battery state, the first mapping relationship between the reference battery parameters and the initial battery state, and the second mapping relationship between the reference battery parameters, the initial battery state, the real-time battery state, and the reference battery parameters and the real-time battery state, perform model training on the initial prediction model to obtain a trained battery state prediction model.

[0112] S405, Perform performance tests on the battery state prediction model under different working conditions to obtain performance test parameters.

[0113] S406, Verify the performance test parameters of the battery state prediction model under different working conditions to obtain the model performance parameters of the battery state prediction model under different working conditions.

[0114] S407, Determine the robustness of the battery state prediction model based on the model performance parameters of the battery state prediction model under different working conditions.

[0115] S408, In the case where the robustness of the battery state prediction model is unqualified, adjust the model parameters of the battery state prediction model. Among them, the battery state prediction model can predict the battery state of the target vehicle based on the vehicle battery parameters to obtain the target battery state.

[0116] The above-mentioned method for predicting the state of an automotive battery obtains the vehicle battery parameters of a target vehicle within a preset period. Further, through a pre-trained battery state prediction model, the battery state of the target vehicle is predicted based on the vehicle battery parameters to obtain the target battery state. The battery state prediction model is trained based on the reference battery parameters of a reference vehicle within a preset period, the initial battery state of the reference vehicle when it enters the preset period, and the real-time battery state of the reference vehicle within the preset period. According to the above content, it can be seen that in the process of predicting the battery state of the target vehicle in this application, the vehicle battery parameters of the target vehicle within the preset period are combined to obtain the vehicle battery parameters of the target vehicle within the preset period, and through the vehicle battery parameters within the preset period and the change of the vehicle battery parameters within the preset period, the battery state of the target vehicle is accurately analyzed, ensuring the accuracy of the battery state prediction of the target vehicle and reducing the operation difficulty of predicting the battery state of the target vehicle.

[0117] It should be understood that although the steps in the flowcharts involved in the above embodiments are sequentially shown according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0118] Based on the same inventive concept, an embodiment of this application also provides an automotive battery state prediction device for implementing the above-mentioned automotive battery state prediction method. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the automotive battery state prediction device provided below can refer to the limitations on the automotive battery state prediction method in the above text and will not be repeated here.

[0119] In one embodiment, as Figure 5 shown, an automotive battery state prediction device is provided, including: an acquisition module 10 and a prediction module 20, where:

[0120] The acquisition module 10 is configured to acquire the vehicle battery parameters of a target vehicle within a preset period.

[0121] A prediction module 20 is configured to predict the battery state of a target vehicle based on vehicle battery parameters through a pre-trained battery state prediction model, so as to obtain a target battery state. The battery state prediction model is trained according to the reference battery parameters of a reference vehicle in a preset period, the initial battery state of the reference vehicle when entering the preset period, and the real-time battery state of the reference vehicle in the preset period. The vehicle type of the reference vehicle is the same as that of the target vehicle, and the difference between the mileage of the reference vehicle and that of the target vehicle is less than a preset value.

[0122] In one embodiment, data collection is performed on the battery parameters of the reference vehicle in a preset period to obtain reference battery parameters.

[0123] Obtain the initial battery state of the reference vehicle when entering the preset period and the real-time battery state of the reference vehicle in the preset period.

[0124] According to the reference battery parameters, the initial battery state, the real-time battery state, the first mapping relationship between the reference battery parameters and the initial battery state, and the second mapping relationship between the reference battery parameters, the initial battery state, the real-time battery state, and the reference battery parameters and the real-time battery state, model training is performed on the initial prediction model to obtain a trained battery state prediction model.

[0125] In one embodiment, physical analysis is performed on the battery state according to the reference battery characteristics of the reference vehicle when entering the preset period to obtain the initial battery state of the reference vehicle when entering the preset period; and / or

[0126] According to the historical charge and discharge data of the reference vehicle when entering the preset period, state prediction is performed on the initial battery state to obtain the initial battery state of the reference vehicle when entering the preset period.

[0127] In one embodiment, the Kalman filtering algorithm is used to predict the battery state of the reference vehicle in a preset period to obtain the real-time battery state of the reference vehicle in the preset period.

[0128] In one embodiment, obtain the model performance parameters of the battery state prediction model under different working conditions.

[0129] Determine the robustness of the battery state prediction model according to the model performance parameters of the battery state prediction model under different working conditions.

[0130] In the case where the robustness of the battery state prediction model is unqualified, perform model parameter adjustment on the battery state prediction model.

[0131] In one embodiment, perform performance testing on the battery state prediction model under different working conditions to obtain performance test parameters.

[0132] Verify the performance test parameters of the battery state prediction model under different working conditions to obtain the model performance parameters of the battery state prediction model under different working conditions.

[0133] In one embodiment, cross-verify the performance test parameters of the battery state prediction model under different working conditions to obtain the model performance parameters of the battery state prediction model under different working conditions.

[0134] The above-mentioned state prediction device for vehicle batteries obtains the vehicle battery parameters of the target vehicle within a preset period; furthermore, through a pre-trained battery state prediction model, predicts the battery state of the target vehicle according to the vehicle battery parameters to obtain the target battery state; wherein, the battery state prediction model is trained according to the reference battery parameters of the reference vehicle within a preset period, the initial battery state of the reference vehicle when entering the preset period, and the real-time battery state of the reference vehicle within the preset period. According to the above content, it can be seen that in the process of predicting the battery state of the target vehicle in this application, the vehicle battery parameters of the target vehicle within the preset period are combined to obtain the vehicle battery parameters of the target vehicle within the preset period, and through the vehicle battery parameters within the preset period and the change of the vehicle battery parameters within the preset period, the battery state of the target vehicle is accurately analyzed, ensuring the accuracy of the battery state prediction of the target vehicle and reducing the operation difficulty of predicting the battery state of the target vehicle.

[0135] Each module in the above-mentioned state prediction device for vehicle batteries can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in the processor of the computer device in hardware form or be independent of it, or be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0136] In one embodiment, a computer device is provided. This computer device can be a terminal, and its internal structure diagram can be as Figure 6As shown in the figure. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. The computer program, when executed by the processor, implements a method for predicting the state of an automotive battery. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0137] Those skilled in the art can understand that Figure 6 the structure shown in the figure is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different component layout.

[0138] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented:

[0139] Obtain the vehicle battery parameters of the target vehicle within a preset period;

[0140] Predict the battery state of the target vehicle based on the vehicle battery parameters through a pre-trained battery state prediction model to obtain the target battery state; wherein, the battery state prediction model is trained based on the reference battery parameters of the reference vehicle within a preset period, the initial battery state of the reference vehicle when entering the preset period, and the real-time battery state of the reference vehicle within the preset period; the vehicle type of the reference vehicle is the same as that of the target vehicle; and the difference between the mileage of the reference vehicle and the mileage of the target vehicle is less than a preset value.

[0141] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0142] Collect data on the battery parameters of the reference vehicle within a preset period to obtain reference battery parameters;

[0143] Obtain the initial battery state when the reference vehicle enters the preset period and the real-time battery state of the reference vehicle within the preset period;

[0144] According to the reference battery parameters, the initial battery state, the real-time battery state, the first mapping relationship between the reference battery parameters and the initial battery state, and the second mapping relationship between the reference battery parameters, the initial battery state, the real-time battery state, and the reference battery parameters and the real-time battery state, train the initial prediction model to obtain a trained battery state prediction model.

[0145] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0146] Perform a physical analysis of the battery state based on the reference battery characteristics when the reference vehicle enters the preset period to obtain the initial battery state when the reference vehicle enters the preset period; and / or,

[0147] Predict the state of the initial battery state based on the historical charge and discharge data when the reference vehicle enters the preset period to obtain the initial battery state when the reference vehicle enters the preset period.

[0148] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0149] Use the Kalman filter algorithm to predict the battery state of the reference vehicle within the preset period to obtain the real-time battery state of the reference vehicle within the preset period.

[0150] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0151] Obtain the model performance parameters of the battery state prediction model under different working conditions;

[0152] Determine the robustness of the battery state prediction model according to the model performance parameters of the battery state prediction model under different working conditions;

[0153] In the case where the robustness of the battery state prediction model is unqualified, adjust the model parameters of the battery state prediction model.

[0154] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0155] Perform a performance test on the battery state prediction model under different working conditions to obtain performance test parameters;

[0156] Verify the performance test parameters of the battery state prediction model under different working conditions, and obtain the model performance parameters of the battery state prediction model under different working conditions.

[0157] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0158] Perform cross-validation on the performance test parameters of the battery state prediction model under different working conditions, and obtain the model performance parameters of the battery state prediction model under different working conditions.

[0159] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0160] Obtain the vehicle battery parameters of the target vehicle within a preset period;

[0161] Predict the battery state of the target vehicle based on the vehicle battery parameters through a pre-trained battery state prediction model to obtain the target battery state; wherein, the battery state prediction model is trained according to the reference battery parameters of the reference vehicle within a preset period, the initial battery state of the reference vehicle when entering the preset period, and the real-time battery state of the reference vehicle within the preset period; the vehicle type of the reference vehicle is the same as that of the target vehicle; and the difference between the mileage of the reference vehicle and the mileage of the target vehicle is less than a preset value.

[0162] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0163] Collect data on the battery parameters of the reference vehicle within a preset period to obtain reference battery parameters;

[0164] Obtain the initial battery state of the reference vehicle when entering the preset period and the real-time battery state of the reference vehicle within the preset period;

[0165] Train the initial prediction model according to the reference battery parameters, the initial battery state, the real-time battery state, the first mapping relationship between the reference battery parameters and the initial battery state, and the second mapping relationship between the reference battery parameters, the initial battery state, the real-time battery state, and the reference battery parameters and the real-time battery state to obtain the trained battery state prediction model.

[0166] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0167] Perform physical analysis on the battery state according to the reference battery characteristics of the reference vehicle when entering the preset period to obtain the initial battery state of the reference vehicle when entering the preset period; and / or,

[0168] Predict the initial battery state based on the historical charge and discharge data of the reference vehicle when it enters the preset cycle, and obtain the initial battery state of the reference vehicle when it enters the preset cycle.

[0169] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0170] Use the Kalman filter algorithm to predict the battery state of the reference vehicle within the preset cycle, and obtain the real-time battery state of the reference vehicle within the preset cycle.

[0171] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0172] Obtain the model performance parameters of the battery state prediction model under different working conditions;

[0173] Determine the robustness of the battery state prediction model according to the model performance parameters of the battery state prediction model under different working conditions;

[0174] In the case that the robustness of the battery state prediction model is unqualified, adjust the model parameters of the battery state prediction model.

[0175] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0176] Perform performance tests on the battery state prediction model under different working conditions to obtain performance test parameters;

[0177] Verify the performance test parameters of the battery state prediction model under different working conditions to obtain the model performance parameters of the battery state prediction model under different working conditions.

[0178] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0179] Perform cross-validation on the performance test parameters of the battery state prediction model under different working conditions to obtain the model performance parameters of the battery state prediction model under different working conditions.

[0180] In one embodiment, a computer program product is provided, including a computer program, which when executed by the processor implements the following steps:

[0181] Obtain the vehicle battery parameters of the target vehicle within the preset cycle;

[0182] Predict the battery state of the target vehicle based on the vehicle battery parameters through a pre-trained battery state prediction model to obtain the target battery state; wherein, the battery state prediction model is trained based on the reference battery parameters of the reference vehicle in a preset period, the initial battery state of the reference vehicle when entering the preset period, and the real-time battery state of the reference vehicle in the preset period; the vehicle type of the reference vehicle is the same as that of the target vehicle; and the difference between the mileage of the reference vehicle and that of the target vehicle is less than the preset value.

[0183] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0184] Collect data on the battery parameters of the reference vehicle in a preset period to obtain the reference battery parameters;

[0185] Obtain the initial battery state of the reference vehicle when entering the preset period and the real-time battery state of the reference vehicle in the preset period;

[0186] Train the initial prediction model based on the reference battery parameters, the initial battery state, the real-time battery state, the first mapping relationship between the reference battery parameters and the initial battery state, and the second mapping relationship between the reference battery parameters, the initial battery state, the real-time battery state, and the reference battery parameters and the real-time battery state to obtain the trained battery state prediction model.

[0187] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0188] Conduct a physical analysis of the battery state based on the reference battery characteristics of the reference vehicle when entering the preset period to obtain the initial battery state of the reference vehicle when entering the preset period.

[0189] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0190] Predict the state of the initial battery state based on the historical charge and discharge data of the reference vehicle when entering the preset period to obtain the initial battery state of the reference vehicle when entering the preset period; and / or,

[0191] Use the Kalman filter algorithm to predict the battery state of the reference vehicle in a preset period to obtain the real-time battery state of the reference vehicle in the preset period.

[0192] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0193] Obtain the model performance parameters of the battery state prediction model under different working conditions;

[0194] Determine the robustness of the battery state prediction model according to the model performance parameters of the battery state prediction model under different working conditions;

[0195] In the case where the robustness of the battery state prediction model is unqualified, adjust the model parameters of the battery state prediction model.

[0196] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0197] Perform performance tests on the battery state prediction model under different working conditions to obtain performance test parameters;

[0198] Verify the performance test parameters of the battery state prediction model under different working conditions to obtain the model performance parameters of the battery state prediction model under different working conditions.

[0199] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0200] Perform cross-validation on the performance test parameters of the battery state prediction model under different working conditions to obtain the model performance parameters of the battery state prediction model under different working conditions.

[0201] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions.

[0202] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above various methods. Among them, any reference to a memory, database, or other medium used in the various embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the various embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the various embodiments provided in the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0203] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as falling within the scope described in this specification.

[0204] The above embodiments only represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for predicting the state of an automotive battery, characterized in that, The method includes: Obtaining vehicle battery parameters of a target vehicle within a preset period; Predicting the battery state of the target vehicle based on the vehicle battery parameters through a pre-trained battery state prediction model to obtain a target battery state; wherein, the battery state prediction model is trained based on reference battery parameters of a reference vehicle within a preset period, an initial battery state of the reference vehicle when entering the preset period, and a real-time battery state of the reference vehicle within the preset period; the vehicle type of the reference vehicle is the same as that of the target vehicle; and the difference between the mileage of the reference vehicle and that of the target vehicle is less than a preset value.

2. The method according to claim 1, wherein The training process of the battery state prediction model includes: Collecting data on the battery parameters of the reference vehicle within a preset period to obtain the reference battery parameters; Obtaining the initial battery state of the reference vehicle when entering the preset period and the real-time battery state of the reference vehicle within the preset period; Training an initial prediction model based on the reference battery parameters, the initial battery state, the real-time battery state, a first mapping relationship between the reference battery parameters and the initial battery state, and a second mapping relationship between the reference battery parameters, the initial battery state, the real-time battery state, and the reference battery parameters and the real-time battery state to obtain the trained battery state prediction model.

3. The method according to claim 2, characterized in that, The obtaining of the initial battery state of the reference vehicle when entering the preset period includes: Analyzing the battery state based on the reference battery characteristics of the reference vehicle when entering the preset period to obtain the initial battery state of the reference vehicle when entering the preset period; and / or, Predicting the state of the initial battery state based on the historical charge and discharge data of the reference vehicle when entering the preset period to obtain the initial battery state of the reference vehicle when entering the preset period.

4. The method according to claim 2, wherein Obtaining the real-time battery state of the reference vehicle within the preset period includes: Predicting the battery state of the reference vehicle within a preset period using the Kalman filter algorithm to obtain the real-time battery state of the reference vehicle within the preset period.

5. The method according to claim 2, wherein The method further includes: Obtaining model performance parameters of the battery state prediction model under different working conditions; Determining the robustness of the battery state prediction model based on the model performance parameters of the battery state prediction model under different working conditions; Adjusting the model parameters of the battery state prediction model when the robustness of the battery state prediction model is unqualified.

6. The method according to claim 5, characterized in that, The obtaining of the model performance parameters of the battery state prediction model under different working conditions includes: Performing a performance test on the battery state prediction model under different working conditions to obtain performance test parameters; Verifying the performance test parameters of the battery state prediction model under different working conditions to obtain the model performance parameters of the battery state prediction model under different working conditions.

7. The method according to claim 6, wherein Verify the performance test parameters of the battery state prediction model under different working conditions to obtain the model performance parameters of the battery state prediction model under different working conditions, including: Perform cross-validation on the performance test parameters of the battery state prediction model under different working conditions to obtain the model performance parameters of the battery state prediction model under different working conditions.

8. A state prediction device for an automotive battery, characterized in that, The device includes: An acquisition module, configured to acquire vehicle battery parameters of a target vehicle within a preset period; A prediction module, configured to predict the battery state of the target vehicle based on the vehicle battery parameters through a pre-trained battery state prediction model to obtain a target battery state; wherein, the battery state prediction model is trained according to the reference battery parameters of a reference vehicle within a preset period, the initial battery state of the reference vehicle when entering the preset period, and the real-time battery state of the reference vehicle within the preset period; the vehicle type of the reference vehicle is the same as that of the target vehicle; and the difference between the mileage of the reference vehicle and the mileage of the target vehicle is less than a preset value.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images