A vehicle electric driving range prediction method, system, device and storage medium

Abstract

The application discloses a vehicle electric driving range prediction method, system and device and a storage medium, and comprises the following steps: acquiring navigation planning information of a target vehicle, acquiring three-dimensional map information of a corresponding planning path according to the navigation planning information, and determining spatial height information of each path point on the planning path according to the three-dimensional map information; dividing the planning path according to the spatial height information to obtain a plurality of three-dimensional path sections, and determining three-dimensional path information of each three-dimensional path section; inputting the three-dimensional path information into a pre-trained driving energy consumption prediction model to predict first driving energy consumption of each three-dimensional path section; acquiring current first residual electric energy of the target vehicle, and predicting a residual range of the target vehicle according to the first residual electric energy and the first driving energy consumption. The application improves the accuracy of vehicle electric driving residual range prediction, avoids the influence of inaccurate residual range on user travel, improves the user travel experience, and can be widely applied in the field of new energy vehicle technology.

Description

Technical Field

[0001] The present invention relates to the field of new energy vehicle technology, and in particular to a method, system, device and storage medium for predicting vehicle electric drive mileage. Background Art

[0002] With the rapid development of the automobile industry, new energy vehicles are increasingly being chosen by people due to their environmental protection and low travel costs. In the existing technology, the remaining mileage is usually estimated based on the state of charge (SOC) of the new energy vehicle battery, the calibrated mileage when fully charged, and the battery life. This method does not take into account the impact of the actual driving environment, resulting in inaccurate calculation of the remaining mileage. For example, when the vehicle is traveling on a climbing section, due to the need to overcome gravity, its energy consumption is often higher than the energy consumption calibrated at the time of leaving the factory. When the vehicle is traveling on a downhill section, due to the vehicle's energy regeneration mechanism, its actual energy consumption is often lower than the energy consumption calibrated at the time of leaving the factory.

[0003] As can be seen from the above, the calculation of the remaining mileage of the vehicle's electric drive in the existing technology is not accurate. There may be a large discrepancy between the actual drivable mileage and the displayed remaining mileage, which may cause the user to be unable to reach the destination and affect the user's travel experience. Summary of the Invention

[0004] The purpose of the present invention is to solve one of the technical problems existing in the prior art to at least a certain extent.

[0005] To this end, an object of an embodiment of the present invention is to provide a method for predicting the remaining electric drive range of a vehicle, which improves the accuracy of the prediction of the remaining electric drive range of the vehicle and the user's travel experience.

[0006] Another object of an embodiment of the present invention is to provide a vehicle electric drive mileage prediction system.

[0007] In order to achieve the above technical objectives, the technical solutions adopted by the embodiments of the present invention include:

[0008] In a first aspect, an embodiment of the present invention provides a method for predicting vehicle electric drive mileage, comprising the following steps:

[0009] Obtaining navigation planning information of the target vehicle, obtaining three-dimensional map information of the corresponding planned path based on the navigation planning information, and determining spatial height information of each path point on the planned path based on the three-dimensional map information;

[0010] Dividing the planned path into a plurality of three-dimensional road segments according to the spatial height information, and determining three-dimensional path information of each of the three-dimensional road segments;

[0011] Inputting the three-dimensional path information into a pre-trained driving energy consumption prediction model to predict a first driving energy consumption of each three-dimensional road segment;

[0012] The first current remaining electric energy of the target vehicle is obtained, and the remaining mileage of the target vehicle is predicted based on the first remaining electric energy and the first driving energy consumption.

[0013] Furthermore, in one embodiment of the present invention, the step of obtaining navigation planning information of the target vehicle, obtaining three-dimensional map information of the corresponding planned path based on the navigation planning information, and determining spatial height information of each path point on the planned path based on the three-dimensional map information specifically includes:

[0014] Obtaining a starting position and a target position of the target vehicle, and performing navigation planning according to the starting position and the target position to obtain the navigation planning information;

[0015] Determining a corresponding planned path according to the navigation planning information, and determining a first map area where the planned path is located;

[0016] Acquire a three-dimensional spatial map of the first map area, and determine three-dimensional map information of the planned path based on the three-dimensional spatial map;

[0017] The three-dimensional spatial coordinates of each path point on the planned path are determined according to the three-dimensional map information, and the spatial height information of each path point is determined according to the three-dimensional spatial coordinates.

[0018] Furthermore, in one embodiment of the present invention, the step of dividing the planned path according to the spatial height information to obtain a plurality of three-dimensional road segments and determining the three-dimensional path information of each of the three-dimensional road segments specifically includes:

[0019] generating a spatial height variation curve of the planned path according to the spatial height information, and dividing the planned path into a plurality of three-dimensional sections with different slopes according to the spatial height variation curve;

[0020] A plurality of three-dimensional space vectors connected end to end are generated according to the three-dimensional space coordinates of each path point on the three-dimensional road segment, and the three-dimensional space vectors are sorted to generate the three-dimensional path information.

[0021] Furthermore, in one embodiment of the present invention, the vehicle electric driving mileage prediction method further includes the step of pre-training the driving energy consumption prediction model, which specifically includes:

[0022] Acquire a plurality of preset vehicle travel sample data, wherein the vehicle travel sample data includes a three-dimensional path sample of a traveled road section and corresponding driving energy consumption data;

[0023] Labeling the three-dimensional path samples according to the driving energy consumption data to obtain corresponding driving energy consumption labels, and constructing a training data set based on the three-dimensional path samples and the corresponding driving energy consumption labels;

[0024] The training data set is input into a pre-built convolutional neural network for training to obtain the trained driving energy consumption prediction model.

[0025] Furthermore, in one embodiment of the present invention, the step of inputting the training data set into a pre-built convolutional neural network for training to obtain the trained driving energy consumption prediction model specifically includes:

[0026] Inputting the training data set into the convolutional neural network to obtain a driving energy consumption prediction result;

[0027] Determining a loss value of the convolutional neural network according to the driving energy consumption prediction result and the driving energy consumption label;

[0028] Updating the model parameters of the convolutional neural network through a back-propagation algorithm according to the loss value, and returning to the step of inputting the training data set into the convolutional neural network;

[0029] When the loss value reaches a preset first threshold or the number of iterations reaches a preset second threshold, the training is stopped to obtain the trained driving energy consumption prediction model.

[0030] Furthermore, in one embodiment of the present invention, the step of predicting the remaining mileage of the target vehicle based on the first remaining electric energy and the first driving energy consumption specifically includes:

[0031] determining a first energy consumption sum value of the first driving energy consumption of each of the three-dimensional road sections, and comparing the first energy consumption sum value with the first remaining electric energy;

[0032] When the first energy consumption sum is equal to the first remaining electric energy, calculating a first mileage of the planned route, and using the first mileage as the remaining mileage of the target vehicle;

[0033] When the first energy consumption sum is less than the first remaining electric energy, calculating a first mileage of the planned route, and calculating a first energy consumption-mileage ratio of the planned route based on the first energy consumption sum and the first mileage, and then predicting the remaining mileage of the target vehicle based on the first energy consumption-mileage ratio and the first remaining electric energy;

[0034] When the first energy consumption sum is less than the first remaining electric energy, several first three-dimensional road sections and one second three-dimensional road section are selected in sequence according to the driving order of the three-dimensional road sections, so that the second energy consumption sum is less than or equal to the first remaining electric energy and the third energy consumption sum is greater than the first remaining electric energy, the second energy consumption sum is the sum of the first driving energy consumptions of the first three-dimensional road sections, and the third energy consumption sum is the sum of the second energy consumption sum and the first driving energy consumption of the second three-dimensional road section. The sum of the mileages of the first three-dimensional road sections is calculated as the second mileage, and the mileage of the second three-dimensional road section is determined as the third mileage. A second energy consumption-to-mileage ratio of the second three-dimensional road section is calculated based on the first driving energy consumption and the third mileage of the second three-dimensional road section, the second remaining electric energy is determined based on the difference between the first remaining electric energy and the second energy consumption sum, and a fourth mileage is calculated based on the second energy consumption-to-mileage ratio and the second remaining electric energy, and the sum of the second mileage and the fourth mileage is used as the remaining mileage of the target vehicle.

[0035] Furthermore, in one embodiment of the present invention, when the first energy consumption sum is less than the first remaining electric energy, the vehicle electric driving range prediction method further includes the following steps:

[0036] Determining a plurality of vehicle charging stations along the planned path, and determining a first distance between each of the vehicle charging stations and the current position of the target vehicle;

[0037] Selecting a number of vehicle charging stations whose first distance is less than the remaining mileage as candidate charging stations;

[0038] The charging pile queue status, charging charges and supported charging types of each of the alternative charging stations are obtained and pushed to the target vehicle for display.

[0039] In a second aspect, an embodiment of the present invention provides a vehicle electric drive mileage prediction system, comprising:

[0040] A spatial height determination module is used to obtain navigation planning information of the target vehicle, obtain three-dimensional map information of the corresponding planned path based on the navigation planning information, and determine the spatial height information of each path point on the planned path based on the three-dimensional map information;

[0041] a three-dimensional road segment division module, configured to divide the planned path into a plurality of three-dimensional road segments according to the spatial height information, and determine the three-dimensional path information of each of the three-dimensional road segments;

[0042] a driving energy consumption prediction module, configured to input the three-dimensional path information into a pre-trained driving energy consumption prediction model to predict a first driving energy consumption of each three-dimensional road segment;

[0043] The remaining mileage prediction module is used to obtain the current first remaining electric energy of the target vehicle and predict the remaining mileage of the target vehicle based on the first remaining electric energy and the first driving energy consumption.

[0044] In a third aspect, an embodiment of the present invention provides a vehicle electric drive mileage prediction device, comprising:

[0045] at least one processor;

[0046] at least one memory for storing at least one program;

[0047] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned vehicle electric driving mileage prediction method.

[0048] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium storing a program executable by a processor, wherein the program executable by the processor is used to execute the above-mentioned vehicle electric drive mileage prediction method when executed by the processor.

[0049] The advantages and benefits of the present invention will be described in part in the following description and will become apparent from the following description or learned through practice of the present invention:

[0050] The embodiment of the present invention obtains navigation planning information of the target vehicle, obtains three-dimensional map information of the corresponding planned path based on the navigation planning information, and determines the spatial height information of each path point on the planned path based on the three-dimensional map information. The planned path is then divided into multiple three-dimensional road segments based on the spatial height information, and the three-dimensional path information of each three-dimensional road segment is determined. The three-dimensional path information is then input into a pre-trained driving energy consumption prediction model to predict the first driving energy consumption of each three-dimensional road segment. Finally, the current first remaining power of the target vehicle is obtained, so that the remaining range of the target vehicle can be predicted based on the first remaining power and the first driving energy consumption. The embodiment of the present invention fully considers the actual driving environment of the vehicle, divides the planned path into multiple different three-dimensional road segments, inputs them into the trained driving energy consumption prediction model, and obtains the actual driving energy consumption of each three-dimensional road segment. The remaining range can then be calculated in combination with the current remaining power of the vehicle, thereby improving the accuracy of the vehicle's electric drive remaining range prediction, avoiding the impact on user travel due to inaccurate remaining range, and improving the user's travel experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following introduction is made to the drawings required for use in the embodiments of the present invention. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative work.

[0052] Figure 1 A flowchart of the steps of a vehicle electric drive mileage prediction method provided by an embodiment of the present invention;

[0053] Figure 2 A structural block diagram of a vehicle electric drive mileage prediction system provided by an embodiment of the present invention;

[0054] Figure 3 This is a structural block diagram of a vehicle electric drive mileage prediction device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention and are not to be construed as limiting the present invention. The step numbers in the following embodiments are provided for ease of explanation only and do not limit the order of the steps. The order of execution of the steps in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0056] In the description of the present invention, "a plurality" means two or more. The terms "first" and "second" are used solely to distinguish technical features and are not to be construed as indicating or implying relative importance, or as implicitly indicating the number of the indicated technical features, or as implicitly indicating the order of the indicated technical features. Furthermore, unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art.

[0057] Reference Figure 1 The embodiment of the present invention provides a method for predicting vehicle electric driving range, which specifically includes the following steps:

[0058] S101. Obtain navigation planning information of a target vehicle, obtain three-dimensional map information of a corresponding planned path based on the navigation planning information, and determine spatial height information of each path point on the planned path based on the three-dimensional map information.

[0059] Specifically, the embodiment of the present invention takes into account the actual environment of the route the vehicle will travel, i.e., whether it is an uphill or downhill section, when predicting the remaining range. Therefore, after obtaining the planned route obtained by navigation planning, it is necessary to mark the spatial height (i.e., altitude) of each path point on the planned route. Step S101 specifically includes the following steps:

[0060] S1011. Obtaining a starting position and a target position of a target vehicle, and performing navigation planning based on the starting position and the target position to obtain navigation planning information;

[0061] S1012: Determine a corresponding planned path according to the navigation planning information, and determine a first map area where the planned path is located;

[0062] S1013: Acquire a three-dimensional spatial map of the first map area, and determine three-dimensional map information of the planned path based on the three-dimensional spatial map;

[0063] S1014: Determine the three-dimensional spatial coordinates of each path point on the planned path based on the three-dimensional map information, and determine the spatial height information of each path point based on the three-dimensional spatial coordinates.

[0064] Specifically, after obtaining a planned path, the navigation planner determines the map area within which the planned path lies. A 3D spatial map of that map area is then retrieved. Within this 3D spatial map, the 3D coordinates of each path point on the planned path can be determined, thereby obtaining the spatial height information for each path point. It should be noted that path points can be selected at preset intervals, for example, every 10 meters.

[0065] S102 : Divide the planned path into multiple three-dimensional road sections according to the spatial height information, and determine the three-dimensional path information of each three-dimensional road section.

[0066] Specifically, the spatial height variation of the planned path can be obtained based on the spatial height information of each path point on the planned path. The planned path is then divided into horizontal sections, climbing sections, and downhill sections. The climbing sections and downhill sections can be further divided according to the different slopes, thereby increasing the accuracy of the driving energy consumption prediction and thus the accuracy of the remaining mileage prediction. Step S102 specifically includes the following steps:

[0067] S1021, generating a spatial height change curve of the planned path according to the spatial height information, and dividing the planned path into a plurality of three-dimensional sections with different slopes according to the spatial height change curve;

[0068] S1022. Generate a plurality of three-dimensional space vectors connected end to end according to the three-dimensional space coordinates of each path point on the three-dimensional road segment, and sort the three-dimensional space vectors to generate three-dimensional path information.

[0069] Specifically, in an embodiment of the present invention, a continuous path area with a slope in the same interval is divided into the same three-dimensional road section, obtaining several horizontal sections, several climbing sections, and several downhill sections. For each three-dimensional road section, three-dimensional space vectors connected in sequence are formed according to the order of the path points. These three-dimensional space vectors can represent the spatial height change and path length and other characteristics of the corresponding three-dimensional path. The three-dimensional path information can be obtained by sorting the three-dimensional space vectors. The three-dimensional path information can be represented by a vector sequence, which is convenient for subsequent input into the driving energy consumption prediction model for prediction.

[0070] S103: Input the three-dimensional path information into a pre-trained driving energy consumption prediction model to predict a first driving energy consumption of each three-dimensional road section.

[0071] Specifically, the driving energy consumption prediction model of the embodiment of the present invention is obtained through convolutional neural network training. The three-dimensional path information to be identified is input into the driving energy consumption prediction model to obtain the driving energy consumption information of the target vehicle in the corresponding three-dimensional road section.

[0072] As an optional embodiment, the vehicle electric drive mileage prediction method further includes the step of pre-training a driving energy consumption prediction model, which specifically includes:

[0073] A1. Acquire a plurality of preset vehicle travel sample data, where the vehicle travel sample data includes three-dimensional path samples of traveled sections and corresponding driving energy consumption data;

[0074] A2. Label the three-dimensional path samples according to the driving energy consumption data to obtain corresponding driving energy consumption labels, and construct a training dataset based on the three-dimensional path samples and the corresponding driving energy consumption labels;

[0075] A3. Input the training data set into the pre-built convolutional neural network for training to obtain a trained driving energy consumption prediction model.

[0076] Specifically, when constructing the training dataset, we collected sample data for vehicle trips at different slopes and lengths, and determined the labels for each 3D path sample based on the actual driving energy consumption data. 3D path samples can also be represented as an ordered set of multiple 3D space vectors.

[0077] As a further optional implementation, step A3 of inputting the training data set into a pre-built convolutional neural network for training to obtain a trained driving energy consumption prediction model specifically includes:

[0078] A31. Input the training data set into the convolutional neural network to obtain the driving energy consumption prediction result;

[0079] A32. Determine a loss value of the convolutional neural network based on the driving energy consumption prediction result and the driving energy consumption label;

[0080] A33. Update the model parameters of the convolutional neural network through the back propagation algorithm according to the loss value, and return to the step of inputting the training data set into the convolutional neural network;

[0081] A34. When the loss value reaches a preset first threshold or the number of iterations reaches a preset second threshold, the training is stopped to obtain a trained driving energy consumption prediction model.

[0082] Specifically, after inputting the data in the training dataset into the initialized convolutional neural network model, the model output recognition results, namely the driving energy consumption prediction results, can be obtained. The driving energy consumption prediction results and the aforementioned label information can be used to evaluate the accuracy of the model prediction, thereby updating the model parameters. For the driving energy consumption prediction model, the accuracy of the model prediction results can be measured using a loss function. The loss function is defined on a single training data point and is used to measure the prediction error of a training data point. Specifically, the loss value of the training data point is determined by the label of the single training data point and the model's prediction result for the training data point. In actual training, a training dataset contains a lot of training data, so a cost function is generally used to measure the overall error of the training dataset. The cost function is defined on the entire training dataset and is used to calculate the average prediction error of all training data points, which can better measure the model's prediction effect. For general machine learning models, the aforementioned cost function, plus a regularization term to measure the complexity of the model, can be used as the training objective function. Based on this objective function, the loss value of the entire training dataset can be calculated. There are many types of commonly used loss functions, such as 0-1 loss function, square loss function, absolute loss function, logarithmic loss function, cross entropy loss function, etc., which can all be used as loss functions of machine learning models, which will not be elaborated here one by one. In an embodiment of the present invention, any one of the loss functions can be selected to determine the loss value of training. Based on the loss value of training, the back propagation algorithm is used to update the parameters of the model, and a trained drive energy consumption prediction model can be obtained by iterating several rounds. The specific number of iterations can be pre-set, or the training is considered to be completed when the test set meets the accuracy requirements.

[0083] S104: Obtain a current first remaining electric energy of the target vehicle, and predict a remaining mileage of the target vehicle based on the first remaining electric energy and the first driving energy consumption.

[0084] Specifically, after determining the actual driving energy consumption of each three-dimensional road section, combined with the driving order of each three-dimensional road section and the current remaining power of the target vehicle, it is possible to determine whether the remaining power of the target vehicle can complete the entire planned route, and to accurately predict the remaining mileage of the target vehicle.

[0085] As a further optional implementation, the step of predicting the remaining mileage of the target vehicle based on the first remaining electric energy and the first driving energy consumption specifically includes:

[0086] S1041, determining a first energy consumption sum value of a first driving energy consumption of each three-dimensional road segment, and comparing the first energy consumption sum value with a first remaining electric energy;

[0087] S1042: When the first energy consumption sum equals the first remaining electric energy, calculate the first mileage of the planned route and use the first mileage as the remaining mileage of the target vehicle;

[0088] S1043: When the first energy consumption sum is less than the first remaining electric energy, calculating a first mileage of the planned route, and calculating a first energy consumption-to-mileage ratio of the planned route based on the first energy consumption sum and the first mileage, and then predicting the remaining mileage of the target vehicle based on the first energy consumption-to-mileage ratio and the first remaining electric energy;

[0089] S1044. When the first energy consumption sum is less than the first remaining electric energy, select several first three-dimensional road sections and one second three-dimensional road section in sequence according to the driving order of the three-dimensional road sections, so that the second energy consumption sum is less than or equal to the first remaining electric energy, and the third energy consumption sum is greater than the first remaining electric energy, the second energy consumption sum is the sum of the first driving energy consumption of the first three-dimensional road sections, and the third energy consumption sum is the sum of the second energy consumption sum and the first driving energy consumption of the second three-dimensional road section, calculate the sum of the mileage of each first three-dimensional road section as the second mileage, determine the mileage of the second three-dimensional road section as the third mileage, calculate the second energy consumption-to-mileage ratio of the second three-dimensional road section based on the first driving energy consumption and the third mileage, determine the second remaining electric energy based on the difference between the first remaining electric energy and the second energy consumption sum, and calculate the fourth mileage based on the second energy consumption-to-mileage ratio and the second remaining electric energy, and then use the sum of the second mileage and the fourth mileage as the remaining mileage of the target vehicle.

[0090] Specifically, when the sum of the driving energy consumption of all three-dimensional road sections is equal to the current remaining electrical energy of the target vehicle, the target vehicle can just complete the entire planned path, and the first mileage of the planned path is the remaining mileage of the target vehicle; when the sum of the driving energy consumption of all three-dimensional road sections is less than the current remaining electrical energy of the target vehicle, the target vehicle still has remaining electrical energy after completing the entire planned path. At this time, the remaining mileage of the target vehicle can be calculated based on the energy consumption-mileage ratio on the planned path; when the sum of the driving energy consumption of all three-dimensional road sections is greater than the current remaining electrical energy of the target vehicle, the target vehicle cannot complete the entire planned path. At this time, it is necessary to determine which three-dimensional road section the target vehicle's current remaining electrical energy is sufficient to complete. This three-dimensional road section and the previous three-dimensional road section are the first three-dimensional road section, and the three-dimensional road section after this three-dimensional road section is the second three-dimensional road section. The mileage that the target vehicle can travel on the second three-dimensional road section with the remaining electrical energy after completing all first three-dimensional road sections is calculated, and then added to the sum of the mileage of all first three-dimensional road sections to obtain the remaining mileage of the target vehicle.

[0091] It should be noted that in the process of calculating mileage, only the horizontal distance of the planned path is considered, and the altitude change is not considered.

[0092] As a further optional embodiment, when the first energy consumption sum is less than the first remaining electric energy, the vehicle electric driving mileage prediction method further includes the following steps:

[0093] Determining a plurality of vehicle charging stations along the planned route, and determining a first distance between each vehicle charging station and the current position of the target vehicle;

[0094] Selecting a number of vehicle charging stations whose first distance is less than the remaining mileage as candidate charging stations;

[0095] Obtain the charging pile queue status, charging rates and supported charging types of each alternative charging station, and push them to the target vehicle for display.

[0096] Specifically, when it is determined that the remaining power of the target vehicle is insufficient to complete the entire planned route, multiple car charging stations along the planned route are obtained, and the first distance between them and the current position of the target vehicle (i.e., the starting position) is determined, so that alternative charging stations that the target vehicle can reach for charging while traveling on the planned route can be screened out. Then, information such as the queue status, charges, and whether fast charging is supported at these alternative charging stations is obtained and pushed to the target vehicle for display, making it easier for users to choose a suitable charging station for charging, further improving the user's travel experience.

[0097] The above describes the method steps of an embodiment of the present invention. It can be appreciated that this embodiment fully considers the actual driving environment of the vehicle, dividing the planned route into multiple different three-dimensional road segments and inputting them into a trained driving energy consumption prediction model to obtain the actual driving energy consumption of each three-dimensional road segment. This allows the remaining range to be calculated based on the vehicle's current remaining power, improving the accuracy of the vehicle's remaining electric range prediction, avoiding travel delays caused by inaccurate remaining range, and enhancing the user's travel experience.

[0098] Reference Figure 2 , an embodiment of the present invention provides a vehicle electric drive mileage prediction system, comprising:

[0099] A spatial height determination module is used to obtain navigation planning information of the target vehicle, obtain three-dimensional map information of the corresponding planned path based on the navigation planning information, and determine the spatial height information of each path point on the planned path based on the three-dimensional map information;

[0100] A 3D road segment division module is used to divide the planned path into multiple 3D road segments according to the spatial height information, and determine the 3D path information of each 3D road segment;

[0101] A driving energy consumption prediction module is used to input the three-dimensional path information into a pre-trained driving energy consumption prediction model to predict the first driving energy consumption of each three-dimensional road section;

[0102] The remaining mileage prediction module is used to obtain the current first remaining electric energy of the target vehicle and predict the remaining mileage of the target vehicle based on the first remaining electric energy and the first driving energy consumption.

[0103] The contents of the above method embodiments are all applicable to the present system embodiments. The functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0104] Reference Figure 3 An embodiment of the present invention provides a vehicle electric drive mileage prediction device, comprising:

[0105] at least one processor;

[0106] at least one memory for storing at least one program;

[0107] When the at least one program is executed by the at least one processor, the at least one processor implements the vehicle electric drive mileage prediction method.

[0108] The contents of the above method embodiments are all applicable to the present device embodiments. The functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0109] An embodiment of the present invention further provides a computer-readable storage medium storing a program executable by a processor. When the program is executed by the processor, it is used to execute the above-mentioned vehicle electric drive mileage prediction method.

[0110] A computer-readable storage medium according to an embodiment of the present invention can execute a vehicle electric drive mileage prediction method provided by an embodiment of the present invention, can execute any combination of implementation steps of the embodiment of the method, and has the corresponding functions and beneficial effects of the method.

[0111] The embodiment of the present invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs Figure 1 The method shown.

[0112] In some optional embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the above-mentioned boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided in an exemplary manner for the purpose of providing a more comprehensive understanding of the technology. The disclosed method is not limited to the operation and logic flow presented herein. Optional embodiments are contemplated in which the order of the various operations is changed and the sub-operations described as a part of a larger operation are performed independently.

[0113] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the above-mentioned functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in separate physical devices or software modules. It is also understood that a detailed discussion of the actual implementation of each module is not necessary for understanding the present invention. More specifically, given the properties, functions, and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the module will be understood within the routine skills of an engineer. Therefore, a person skilled in the art can implement the present invention set forth in the claims using ordinary skills without undue experimentation. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0114] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the above methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0115] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0116] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable media on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0117] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0118] In the above description of this specification, reference to the terms "one embodiment / example," "another embodiment / example," or "certain embodiments / examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0119] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

[0120] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A method for predicting vehicle electric drive mileage, characterized in that: The following steps are involved: Obtaining navigation planning information of the target vehicle, obtaining three-dimensional map information of the corresponding planned path based on the navigation planning information, and determining spatial height information of each path point on the planned path based on the three-dimensional map information; Dividing the planned path into a plurality of three-dimensional road segments according to the spatial height information, and determining three-dimensional path information of each of the three-dimensional road segments; Inputting the three-dimensional path information into a pre-trained driving energy consumption prediction model to predict a first driving energy consumption of each three-dimensional road segment; Obtaining a current first remaining electric energy of the target vehicle, and predicting a remaining mileage of the target vehicle based on the first remaining electric energy and the first driving energy consumption; The step of dividing the planned path into a plurality of three-dimensional road segments according to the spatial height information and determining the three-dimensional path information of each three-dimensional road segment specifically includes: generating a spatial height variation curve of the planned path according to the spatial height information, and dividing the planned path into a plurality of three-dimensional sections with different slopes according to the spatial height variation curve; generating a plurality of three-dimensional space vectors connected end to end according to the three-dimensional space coordinates of each path point on the three-dimensional road segment, and sorting the three-dimensional space vectors to generate the three-dimensional path information; The vehicle electric drive mileage prediction method further includes the step of pre-training the driving energy consumption prediction model, which specifically includes: Acquire a plurality of preset vehicle travel sample data, wherein the vehicle travel sample data includes a three-dimensional path sample of a traveled road section and corresponding driving energy consumption data; Labeling the three-dimensional path samples according to the driving energy consumption data to obtain corresponding driving energy consumption labels, and constructing a training data set based on the three-dimensional path samples and the corresponding driving energy consumption labels; The training data set is input into a pre-built convolutional neural network for training to obtain the trained driving energy consumption prediction model.

2. The method for predicting vehicle electric driving mileage according to claim 1, characterized in that: The step of obtaining navigation planning information of the target vehicle, obtaining three-dimensional map information of the corresponding planned path according to the navigation planning information, and determining spatial height information of each path point on the planned path according to the three-dimensional map information specifically includes: Obtaining a starting position and a target position of the target vehicle, and performing navigation planning according to the starting position and the target position to obtain the navigation planning information; Determining a corresponding planned path according to the navigation planning information, and determining a first map area where the planned path is located; Acquire a three-dimensional spatial map of the first map area, and determine three-dimensional map information of the planned path based on the three-dimensional spatial map; The three-dimensional spatial coordinates of each path point on the planned path are determined according to the three-dimensional map information, and the spatial height information of each path point is determined according to the three-dimensional spatial coordinates.

3. The method for predicting vehicle electric driving mileage according to claim 1, characterized in that: The step of inputting the training data set into a pre-built convolutional neural network for training to obtain the trained driving energy consumption prediction model specifically includes: Inputting the training data set into the convolutional neural network to obtain a driving energy consumption prediction result; Determining a loss value of the convolutional neural network according to the driving energy consumption prediction result and the driving energy consumption label; Updating the model parameters of the convolutional neural network through a back-propagation algorithm according to the loss value, and returning to the step of inputting the training data set into the convolutional neural network; When the loss value reaches a preset first threshold or the number of iterations reaches a preset second threshold, the training is stopped to obtain the trained driving energy consumption prediction model.

4. A vehicle electric drive mileage prediction method according to any one of claims 1 to 3, characterized in that: The step of predicting the remaining mileage of the target vehicle based on the first remaining electric energy and the first driving energy consumption specifically includes: determining a first energy consumption sum value of the first driving energy consumption of each of the three-dimensional road sections, and comparing the first energy consumption sum value with the first remaining electric energy; When the first energy consumption sum is equal to the first remaining electric energy, calculating a first mileage of the planned route, and using the first mileage as the remaining mileage of the target vehicle; When the first energy consumption sum is less than the first remaining electric energy, calculating a first mileage of the planned route, and calculating a first energy consumption-mileage ratio of the planned route based on the first energy consumption sum and the first mileage, and then predicting the remaining mileage of the target vehicle based on the first energy consumption-mileage ratio and the first remaining electric energy; When the first energy consumption sum is less than the first remaining electric energy, several first three-dimensional road sections and one second three-dimensional road section are selected in sequence according to the driving order of the three-dimensional road sections, so that the second energy consumption sum is less than or equal to the first remaining electric energy and the third energy consumption sum is greater than the first remaining electric energy, the second energy consumption sum is the sum of the first driving energy consumptions of the first three-dimensional road sections, and the third energy consumption sum is the sum of the second energy consumption sum and the first driving energy consumption of the second three-dimensional road section. The sum of the mileages of the first three-dimensional road sections is calculated as the second mileage, and the mileage of the second three-dimensional road section is determined as the third mileage. A second energy consumption-to-mileage ratio of the second three-dimensional road section is calculated based on the first driving energy consumption and the third mileage of the second three-dimensional road section, the second remaining electric energy is determined based on the difference between the first remaining electric energy and the second energy consumption sum, and a fourth mileage is calculated based on the second energy consumption-to-mileage ratio and the second remaining electric energy, and the sum of the second mileage and the fourth mileage is used as the remaining mileage of the target vehicle.

5. The method for predicting vehicle electric driving mileage according to claim 4, characterized in that: When the first energy consumption sum is less than the first remaining electric energy, the vehicle electric driving mileage prediction method further includes the following steps: Determining a plurality of vehicle charging stations along the planned path, and determining a first distance between each of the vehicle charging stations and the current position of the target vehicle; Selecting a number of vehicle charging stations whose first distance is less than the remaining mileage as candidate charging stations; The charging pile queue status, charging charges and supported charging types of each of the alternative charging stations are obtained and pushed to the target vehicle for display.

6. A vehicle electric drive mileage prediction system, characterized in that: include: A spatial height determination module is used to obtain navigation planning information of the target vehicle, obtain three-dimensional map information of the corresponding planned path based on the navigation planning information, and determine the spatial height information of each path point on the planned path based on the three-dimensional map information; a three-dimensional road segment division module, configured to divide the planned path into a plurality of three-dimensional road segments according to the spatial height information, and determine the three-dimensional path information of each of the three-dimensional road segments; a driving energy consumption prediction module, configured to input the three-dimensional path information into a pre-trained driving energy consumption prediction model to predict a first driving energy consumption of each three-dimensional road segment; a remaining mileage prediction module, configured to obtain a current first remaining electrical energy of the target vehicle and predict a remaining mileage of the target vehicle based on the first remaining electrical energy and the first driving energy consumption; The three-dimensional road segment division module is specifically used for: generating a spatial height variation curve of the planned path according to the spatial height information, and dividing the planned path into a plurality of three-dimensional sections with different slopes according to the spatial height variation curve; generating a plurality of three-dimensional space vectors connected end to end according to the three-dimensional space coordinates of each path point on the three-dimensional road segment, and sorting the three-dimensional space vectors to generate the three-dimensional path information; The driving energy consumption prediction model is trained by the following steps: Acquire a plurality of preset vehicle travel sample data, wherein the vehicle travel sample data includes a three-dimensional path sample of a traveled road section and corresponding driving energy consumption data; Labeling the three-dimensional path samples according to the driving energy consumption data to obtain corresponding driving energy consumption labels, and constructing a training data set based on the three-dimensional path samples and the corresponding driving energy consumption labels; The training data set is input into a pre-built convolutional neural network for training to obtain the trained driving energy consumption prediction model.

7. A vehicle electric drive mileage prediction device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the vehicle electric driving mileage prediction method according to any one of claims 1 to 5.

8. A computer-readable storage medium storing a program executable by a processor, characterized in that: The program executable by the processor is used to execute a vehicle electric driving range prediction method according to any one of claims 1 to 5 when executed by the processor.

Images