Vehicle energy consumption prediction method, device, equipment and medium

Abstract

The invention provides a vehicle energy consumption prediction method, apparatus and device, and a medium. The method comprises the steps of obtaining a first planned driving path of a first vehicle; determining a first energy consumption influence feature of the first planned driving path, the first energy consumption influence feature including a path length of the first planned driving path, and the first energy consumption influence feature further including at least one of a traffic control feature of the first planned driving path and a road altitude change feature of the first planned driving path; the first energy consumption influence feature is input into a first vehicle energy consumption prediction model, an energy consumption prediction result of the first vehicle is obtained, and the first vehicle energy consumption prediction model is a trained neural network model. In addition to the path length, the energy consumption influence feature of the vehicle also comprises at least one of the traffic control feature and the road altitude change feature, and by adopting the energy consumption influence feature to predict the vehicle energy consumption, the accuracy of vehicle energy consumption prediction can be improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of vehicle energy consumption management, and particularly relates to a vehicle energy consumption prediction method, device, equipment and medium. Background Art

[0002] Predicting vehicle energy consumption based on the driving route has various meanings and values. In the related art, after the driving route of a vehicle in the road network is determined, the driving energy consumption of the vehicle is usually predicted based on the driving distance. However, the driving distance is not the only factor affecting the driving energy consumption of the vehicle.

[0003] It can be seen that predicting vehicle energy consumption only based on the driving distance in the related art will result in poor accuracy of vehicle energy consumption prediction. Summary of the Invention

[0004] In view of the above-mentioned disadvantages of the prior art, the purpose of the present invention is to provide a vehicle energy consumption prediction method, device, equipment and medium for solving the above problems.

[0005] The vehicle energy consumption prediction method provided by the present invention includes:

[0006] Obtain the first planned driving route of the first vehicle;

[0007] Determine the first energy consumption influence feature of the first planned driving route, where the first energy consumption influence feature includes the path length of the first planned driving route, and the first energy consumption influence feature further includes at least one of the traffic control feature of the first planned driving route and the road altitude change feature of the first planned driving route;

[0008] Input the first energy consumption influence feature into the first vehicle energy consumption prediction model to obtain the energy consumption prediction result of the first vehicle, where the first vehicle energy consumption prediction model is a trained neural network model.

[0009] In an embodiment of the present invention, the first energy consumption influence feature includes the road altitude change feature of the first planned driving route. The determining the first energy consumption influence feature of the first planned driving route includes:

[0010] Determine multiple path nodes in the first planned driving route, where the multiple path nodes include the starting point, ending point and intermediate path nodes of the first planned driving route;

[0011] Based on the altitude corresponding to the multiple path nodes, determine the altitude sample variance of the multiple path nodes. The road altitude change feature of the first planned driving route includes the altitude sample variance.

[0012] In an embodiment of the present invention, the first energy consumption influence feature includes the road altitude change feature of the first planned driving path, and determining the first energy consumption influence feature of the first planned driving path includes:

[0013] Determine the altitude difference between the starting point and the ending point of the first planned driving path, and the road altitude change feature of the first planned driving path includes the altitude difference.

[0014] In an embodiment of the present invention, the first energy consumption influence feature includes the traffic control feature of the first planned driving path, and determining the first energy consumption influence feature of the first planned driving path includes:

[0015] Determine multiple path nodes in the first planned driving path, and the multiple path nodes include the starting point, the ending point, and intermediate path nodes of the first planned driving path;

[0016] Based on the multiple path nodes in the first planned driving path, divide the first planned driving path into multiple road segments;

[0017] Based on the speed limit values of each road segment in the multiple road segments, determine the speed limit feature, and the speed limit feature includes at least one of the average speed limit value of the multiple road segments, the sample variance of the speed limit values of the multiple road segments, and the lowest speed limit value of the multiple road segments. The traffic control feature of the first planned driving path includes the speed limit feature.

[0018] In an embodiment of the present invention, the first energy consumption influence feature includes the traffic control feature of the first planned driving path, and determining the first energy consumption influence feature of the first planned driving path includes:

[0019] Determine the number of signal lights in the first planned driving path, and the traffic control feature of the first planned driving path includes the number of signal lights.

[0020] In an embodiment of the present invention, the method further includes:

[0021] Obtain the second planned driving path of the second vehicle;

[0022] Determine the second energy consumption influence feature of the second planned driving path, and the second energy consumption influence feature includes the path length of the second planned driving path, and the second energy consumption influence feature further includes at least one of the traffic control feature of the second planned driving path and the road altitude change feature of the second planned driving path;

[0023] Input the second energy consumption impact feature into the second vehicle energy consumption prediction model to obtain the energy consumption prediction result of the second vehicle, where the second vehicle energy consumption prediction model is a trained neural network model;

[0024] Among them, the vehicle type of the first vehicle is the first power type, the vehicle type of the second vehicle is the second power type, the first vehicle energy consumption prediction model is a neural network model trained based on the energy consumption data of vehicles of the first power type, and the second vehicle energy consumption prediction model is a neural network model trained based on the energy consumption data of vehicles of the second power type.

[0025] In an embodiment of the present invention, the method further includes:

[0026] Obtain the third planned driving route of the third vehicle;

[0027] Determine the third energy consumption impact feature of the third planned driving route, where the third energy consumption impact feature includes the path length of the third planned driving route, and the third energy consumption impact feature further includes at least one of the traffic control feature of the third planned driving route and the road elevation change feature of the third planned driving route;

[0028] Input the third energy consumption impact feature into the third vehicle energy consumption prediction model to obtain the energy consumption prediction result of the third vehicle, where the third vehicle energy consumption prediction model is a trained neural network model;

[0029] Among them, the vehicle type of the third vehicle is the third power type, and the third vehicle energy consumption prediction model is a neural network model trained based on the energy consumption data of vehicles of the third power type.

[0030] The vehicle energy consumption prediction device provided by the present invention includes:

[0031] The first acquisition module is used to acquire the first planned driving route of the first vehicle;

[0032] The first determination module is used to determine the first energy consumption impact feature of the first planned driving route, where the first energy consumption impact feature includes the path length of the first planned driving route, and the first energy consumption impact feature further includes at least one of the traffic control feature of the first planned driving route and the road elevation change feature of the first planned driving route;

[0033] The second determination module is used to input the first energy consumption impact feature into the first vehicle energy consumption prediction model to obtain the energy consumption prediction result of the first vehicle, where the first vehicle energy consumption prediction model is a trained neural network model.

[0034] In an embodiment of the present invention, the first energy consumption influencing feature includes the road elevation change feature of the first planned driving path, and the first determination module includes:

[0035] A first determination unit, configured to determine a plurality of path nodes in the first planned driving path, where the plurality of path nodes include the starting point, the ending point, and intermediate path nodes of the first planned driving path;

[0036] A second determination unit, configured to determine the sample variance of the elevation heights of the plurality of path nodes based on the elevation heights corresponding to the plurality of path nodes, and the road elevation change feature of the first planned driving path includes the sample variance of the elevation heights.

[0037] In an embodiment of the present invention, the first energy consumption influencing feature includes the road elevation change feature of the first planned driving path, and the first determination module includes:

[0038] A third determination unit, configured to determine the elevation difference between the starting point and the ending point of the first planned driving path, and the road elevation change feature of the first planned driving path includes the elevation difference.

[0039] In an embodiment of the present invention, the first energy consumption influencing feature includes the traffic control feature of the first planned driving path, and the first determination module includes:

[0040] A fourth determination unit, configured to determine a plurality of path nodes in the first planned driving path, where the plurality of path nodes include the starting point, the ending point, and intermediate path nodes of the first planned driving path;

[0041] A fifth determination unit, configured to divide the first planned driving path into a plurality of road segments based on the plurality of path nodes in the first planned driving path;

[0042] A sixth determination unit, configured to determine a speed limit feature based on the speed limit values of each road segment in the plurality of road segments, where the speed limit feature includes at least one of the average speed limit value of the plurality of road segments, the sample variance of the speed limit values of the plurality of road segments, and the lowest speed limit value in the plurality of road segments, and the traffic control feature of the first planned driving path includes the speed limit feature.

[0043] In an embodiment of the present invention, the first energy consumption influencing feature includes the traffic control feature of the first planned driving path, and the first determination module includes:

[0044] A seventh determination unit, configured to determine the number of signal lights in the first planned driving path, and the traffic control feature of the first planned driving path includes the number of signal lights.

[0045] In an embodiment of the present invention, the device further includes:

[0046] A second acquisition module, configured to acquire a second planned driving path of a second vehicle;

[0047] A second determination module, configured to determine a second energy consumption impact feature of the second planned driving path, where the second energy consumption impact feature includes a path length of the second planned driving path, and the second energy consumption impact feature further includes at least one of a traffic control feature of the second planned driving path and a road altitude change feature of the second planned driving path;

[0048] A third determination module, configured to input the second energy consumption impact feature into a second vehicle energy consumption prediction model to obtain an energy consumption prediction result of the second vehicle, where the second vehicle energy consumption prediction model is a trained neural network model;

[0049] Wherein, the vehicle type of the first vehicle is a first power type, the vehicle type of the second vehicle is a second power type, the first vehicle energy consumption prediction model is a neural network model trained based on energy consumption data of vehicles of the first power type, and the second vehicle energy consumption prediction model is a neural network model trained based on energy consumption data of vehicles of the second power type.

[0050] In an embodiment of the present invention, the method further includes:

[0051] A third acquisition module, configured to acquire a third planned driving path of a third vehicle;

[0052] A fourth determination module, configured to determine a third energy consumption impact feature of the third planned driving path, where the third energy consumption impact feature includes a path length of the third planned driving path, and the third energy consumption impact feature further includes at least one of a traffic control feature of the third planned driving path and a road altitude change feature of the third planned driving path;

[0053] A fifth determination module, configured to input the third energy consumption impact feature into a third vehicle energy consumption prediction model to obtain an energy consumption prediction result of the third vehicle, where the third vehicle energy consumption prediction model is a trained neural network model;

[0054] Wherein, the vehicle type of the third vehicle is a third power type, and the third vehicle energy consumption prediction model is a neural network model trained based on energy consumption data of vehicles of the third power type.

[0055] The electronic device provided by the present invention, the electronic device includes:

[0056] One or more processors;

[0057] A storage device for storing one or more programs, which, when executed by the one or more processors, cause the electronic device to implement the vehicle energy consumption prediction method described above.

[0058] The computer-readable storage medium provided by the present invention stores a computer program, which, when executed by a processor of a computer, causes the computer to execute the vehicle energy consumption prediction method described above.

[0059] Advantages of this technical solution: In this technical solution, the first planned driving route of the first vehicle is obtained, and the first energy consumption influence characteristics of the first planned driving route are determined, including the route length, and at least one of the traffic control characteristics and the road elevation change characteristics; by inputting the first energy consumption influence characteristics into the first vehicle energy consumption prediction model, the first vehicle energy consumption prediction model can analyze the first energy consumption influence characteristics to obtain an energy consumption prediction result. In this technical solution, the energy consumption influence characteristics of the vehicle include at least one of the traffic control characteristics and the road elevation change characteristics in addition to the route length. Compared with the related technology that predicts the vehicle energy consumption based on a single driving distance, using the energy consumption influence characteristics in this technical solution to predict the vehicle energy consumption can improve the accuracy of vehicle energy consumption prediction.

[0060] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present invention, and are used together with the specification to explain the principles of the present invention. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts. In the drawings:

[0062] Figure 1 is one of the flowcharts of the vehicle energy consumption prediction method shown in an exemplary embodiment of the present invention;

[0063] Figure 2 is the structural schematic diagram of a BP neural network shown in an exemplary embodiment of the present invention;

[0064] Figure 3 is the schematic diagram of the planned driving route shown in an exemplary embodiment of the present invention;

[0065] Figure 4 is the second flowchart of the vehicle energy consumption prediction method shown in an exemplary embodiment of the present invention;

[0066] Figure 5It is a schematic diagram of the correlation of fuel vehicle training samples shown in an exemplary embodiment of the present invention;

[0067] Figure 6 It is a schematic diagram of the correlation of fuel vehicle verification samples shown in an exemplary embodiment of the present invention;

[0068] Figure 7 It is a schematic diagram of the correlation of fuel vehicle test samples shown in an exemplary embodiment of the present invention;

[0069] Figure 8 It is a schematic diagram of the correlation of all fuel vehicle samples shown in an exemplary embodiment of the present invention;

[0070] Figure 9 It is a mean square error verification convergence graph of a fuel vehicle shown in an exemplary embodiment of the present invention;

[0071] Figure 10 It is a schematic diagram of the correlation of pure electric vehicle training samples shown in an exemplary embodiment of the present invention;

[0072] Figure 11 It is a schematic diagram of the correlation of pure electric vehicle verification samples shown in an exemplary embodiment of the present invention;

[0073] Figure 12 It is a schematic diagram of the correlation of pure electric vehicle test samples shown in an exemplary embodiment of the present invention;

[0074] Figure 13 It is a schematic diagram of the correlation of all pure electric vehicle samples shown in an exemplary embodiment of the present invention;

[0075] Figure 14 It is a mean square error verification convergence graph of a pure electric vehicle shown in an exemplary embodiment of the present invention;

[0076] Figure 15 It is a schematic diagram of the correlation of hybrid vehicle training samples shown in an exemplary embodiment of the present invention;

[0077] Figure 16 It is a schematic diagram of the correlation of hybrid vehicle verification samples shown in an exemplary embodiment of the present invention;

[0078] Figure 17 It is a schematic diagram of the correlation of hybrid vehicle test samples shown in an exemplary embodiment of the present invention;

[0079] Figure 18 It is a schematic diagram of the correlation of all hybrid vehicle samples shown in an exemplary embodiment of the present invention;

[0080] Figure 19It is the mean square error verification convergence graph of a hybrid vehicle shown in an exemplary embodiment of the present invention;

[0081] Figure 20 It is a block diagram of a vehicle energy consumption prediction device shown in an exemplary embodiment of the present invention;

[0082] Figure 21 It shows a schematic structural diagram of a computer system of an electronic device suitable for implementing the embodiments of the present invention. Detailed implementation manners

[0083] The following will describe the implementation manners of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for explaining the present invention and not for limiting the protection scope of the present invention.

[0084] It should be noted that the drawings provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner. Therefore, only the components related to the present invention are shown in the drawings, rather than being drawn according to the number, shape, and size of the components in actual implementation. The type, quantity, and ratio of each component in actual implementation can be arbitrarily changed, and the component layout type may also be more complex.

[0085] In the following description, a large number of details are explored to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0086] Please refer to Figure 1 , Figure 1 It is a flowchart of a vehicle energy consumption prediction method shown in an exemplary embodiment of the present invention. As Figure 1 shown, in an exemplary embodiment, the vehicle energy consumption prediction method at least includes steps S110 to S130, which are introduced in detail as follows:

[0087] Step S110, obtain the first planned driving route of the first vehicle;

[0088] Step S120: Determine the first energy consumption impact feature of the first planned driving route. The first energy consumption impact feature includes the path length of the first planned driving route, and the first energy consumption impact feature further includes at least one of the traffic control feature of the first planned driving route and the road elevation change feature of the first planned driving route;

[0089] Step S130: Input the first energy consumption impact feature into the first vehicle energy consumption prediction model to obtain the energy consumption prediction result of the first vehicle. The first vehicle energy consumption prediction model is a trained neural network model.

[0090] In step S110, the above first planned driving route may be obtained after inputting the navigation information of the first vehicle.

[0091] In step S120, determine the first energy consumption impact feature of the first planned driving route. The first energy consumption impact feature includes the path length of the first planned driving route. The path length has an important impact on the energy consumption of the vehicle. Under the same other road conditions, theoretically, the longer the path, the higher the vehicle energy consumption. Based on this, the embodiment of the present invention incorporates the path length into the above energy consumption impact feature.

[0092] The above energy consumption impact feature further includes at least one of the traffic control feature and the road elevation change feature. Among them, the traffic control feature refers to a feature that has a certain impact on the driving speed and passing conditions of the vehicle, thereby having a certain impact on the vehicle energy consumption. The road elevation change feature can reflect the slope undulation of the road, and it can also have an impact on the energy consumption of the vehicle.

[0093] In step S130, by inputting the first energy consumption impact feature into the first vehicle energy consumption prediction model, the first vehicle energy consumption prediction model analyzes the input feature, and thus can output the energy consumption prediction result of the vehicle. The first vehicle energy consumption prediction model is a trained neural network model. Specifically, the selection or construction of the neural network can be determined according to requirements. For example, a BP neural network, an LSTM long short-term memory network, a convolutional neural network, an RNN recursive neural network, or an RBF neural network and various neural network variants can be selected. Among them, the BP neural network has good nonlinear fitting ability and approximation ability. The impact of road information on the energy consumption of the vehicle path is complex and nonlinear. Using a BP neural network to train the road information mapping network associated with the vehicle path energy consumption has certain advantages. The structure diagram of the BP neural network is as Figure 2 shown. After constructing the neural network model, corresponding sample data is constructed to train the neural network model to obtain the above first vehicle energy consumption prediction model. The input of the first vehicle energy consumption prediction model is the energy consumption impact feature, and the output is the energy consumption prediction result. The energy consumption prediction result can be a specific energy consumption prediction value.

[0094] In the embodiments of the present invention, the energy consumption influence characteristics of the vehicle include at least one of traffic control characteristics and road altitude change characteristics in addition to the path length. Compared with predicting the vehicle energy consumption based on a single driving distance in the related art, predicting the vehicle energy consumption using the energy consumption influence characteristics in the present invention can improve the accuracy of vehicle energy consumption prediction.

[0095] In some embodiments, the first energy consumption influence characteristic includes the road altitude change characteristic of the first planned driving path, and determining the first energy consumption influence characteristic of the first planned driving path includes:

[0096] Determine a plurality of path nodes in the first planned driving path, where the plurality of path nodes include the starting point, the end point (the end point of the first planned driving path), and the intermediate path nodes (the intermediate path nodes of the first planned driving path);

[0097] Based on the altitude heights corresponding to the plurality of path nodes, determine the sample variance of the altitude heights of the plurality of path nodes, and the road altitude change characteristic of the first planned driving path includes the sample variance of the altitude heights.

[0098] After the planned driving path of the vehicle is determined, each key path node in the overall driving path can be determined through an online map. Each key path node mainly includes the starting point, the end point in the planned driving path, and the key intermediate path nodes between the starting point and the end point. The intermediate path nodes between the starting point and the end point are mainly divided by the intersections of the main roads and the crossroads in the local road network.

[0099] To more clearly understand the determination of the above path nodes, the following is an exemplary description in conjunction with Figure 2 for it.

[0100] As Figure 2 shown, the planned driving path is the part marked by the red solid line, its starting point is 1, and the end point is 11. Based on the intersections of the main roads and the crossroads, determine the intermediate path nodes between the starting point and the end point, and then the intermediate path nodes in Figure 2 include path node 2, path node 5, path node 6, and path node 8. Based on this, the multiple path nodes included in the planned driving path in Figure 2 can be obtained as: path node 1, path node 2, path node 5, path node 6, path node 8, and path node 11.

[0101] In a pre-constructed road network model, each path node includes an altitude. Therefore, after determining the above-mentioned multiple path nodes, the altitudes corresponding to the above-mentioned multiple path nodes can be obtained. Based on the altitudes of the multiple path nodes, the sample variance of the altitude can be determined, and the sample variance of the altitude is used to evaluate the overall slope fluctuation of the road in the planned driving path. Specifically, the ramp is set based on the altitude difference between two adjacent path nodes. Therefore, the greater the sample variance of the altitude of the above-mentioned path nodes, the greater the ramp undulation of the road. For traditional fuel vehicles, frequent uphill and downhill on the whole path is not conducive to energy consumption economy. Even for pure electric vehicles, although a part of the gravitational potential energy can be recovered through the energy recovery mode when going downhill, this is far less than the additional energy consumption when the vehicle goes uphill. Based on this, determining the sample variance of the altitude of each path node in the planned driving path and predicting the energy consumption of the vehicle based on the sample variance of the altitude is beneficial to further improving the accuracy of energy consumption prediction. Among them, the sample variance of the altitude of the planned driving path can be determined based on the following formula:

[0102]

[0103] In the formula, A var is the sample variance of the altitude, A i represents the altitude (m) of the section node i, represents the average altitude (m) of N path nodes, and N is the total number of path nodes.

[0104] In the embodiments of the present invention, determining the energy consumption influence characteristics includes the road altitude change characteristics of the planned driving path; and quantifying the altitude change characteristics, and determining that it includes the sample variance of the altitude in each path node. The sample variance of the altitude can characterize the overall slope fluctuation of the road in the planned driving path, and the slope fluctuation has a certain impact on the vehicle energy consumption. Based on this, the embodiments of the present invention also predict the energy consumption of the vehicle based on the sample variance of the altitude, which is beneficial to further improving the accuracy of energy consumption prediction.

[0105] In some embodiments, determining the first energy consumption influence characteristic of the first planned driving path includes:

[0106] Determining the altitude difference between the starting point and the ending point of the first planned driving path, and the road altitude change characteristic of the first planned driving path includes the altitude difference.

[0107] During the planned driving route, the altitude difference between the starting point and the ending point is used to evaluate the overall altitude change trend of the route. When the altitude difference is positive, more energy consumption is required for the vehicle to overcome gravity during the entire driving section, and the larger the altitude difference, the more additional energy the vehicle consumes. The calculation formula for the altitude difference ΔA (m) between the starting point and the ending point is as follows:

[0108] ΔA = A e - A s (2)

[0109] In the formula, A e represents the altitude of the ending point (m), and A s represents the altitude of the starting point.

[0110] In the embodiments of the present invention, the altitude change characteristics are quantified, and it is determined that it also includes the altitude difference between the starting point and the ending point. By inputting the above altitude difference into the vehicle energy consumption prediction model, the prediction accuracy can be further improved.

[0111] In some embodiments, the first energy consumption influencing characteristic includes the traffic control characteristic of the first planned driving route. Determining the first energy consumption influencing characteristic of the first planned driving route includes:

[0112] Based on multiple path nodes in the first planned driving route, dividing the first planned driving route into multiple sections;

[0113] Based on the speed limit values of each section in the multiple sections, determining a speed limit characteristic, where the speed limit characteristic includes at least one of the average speed limit value of the multiple sections, the sample variance of the speed limit values of the multiple sections, and the lowest speed limit value in the multiple sections. The traffic control characteristic of the first planned driving route includes the speed limit characteristic.

[0114] In this implementation manner, based on multiple path nodes in the planned driving route, the planned driving route can be divided into multiple sections. For example Figure 2 in, based on path nodes 1, 2, 5, 6, 8, and 11, the planned route can be divided into 5 sections, namely 1 - 2, 2 - 5, 5 - 6, 6 - 8, and 8 - 11.

[0115] After dividing the planned route into the above - mentioned multiple sections, the speed limit values of each section can be obtained to determine the speed limit characteristic based on the speed limit values of each section. The speed limit characteristic includes at least one of the following: the average speed limit value of the multiple sections, the sample variance of the speed limit values of the multiple sections, and the lowest speed limit value in the multiple sections.

[0116] Below, the above - mentioned speed limit characteristics will be described separately.

[0117] The average speed limit value is used to evaluate the overall speed limit level of the planned driving route. Theoretically, the average speed limit value of the route has a certain impact on the energy consumption of different types of vehicles. For example, for fuel vehicles, the higher the average speed limit value of the route, the more conducive it is for the vehicle to reach the economic cruising speed and thus reduce energy consumption; for pure electric vehicles, when the average speed limit value of the route increases, the energy consumption of the vehicle usually also increases. The average speed limit value v L (m / s) is calculated by the following formula:

[0118]

[0119] In the formula, v Li represents the speed limit condition (m / s) of the i-th section.

[0120] The sample variance of the speed limit value is used to evaluate the fluctuation of the speed limit conditions in the planned driving route. The larger the sample variance of the route speed limit value, the more frequently the vehicle needs to accelerate and decelerate to meet the speed limit conditions of different sections, which is not conducive to reducing the energy consumption of the entire route. The sample variance of the route speed limit v Lvar (m / s) is calculated by the following formula:

[0121]

[0122] The minimum speed limit value is used to evaluate the extreme traffic flow situation of the planned driving route. The energy consumption of the vehicle shows different degrees of sensitivity to low-speed traffic flow. Based on this, the embodiments of the present invention also use the minimum speed limit value as one of the indicators for predicting vehicle energy consumption.

[0123] The above speed limit features include at least one of the average speed limit value, the sample variance of the speed limit value, and the minimum speed limit value of the above-mentioned multiple sections. To improve the prediction accuracy, the speed limit features can be set to include the average speed limit value, the sample variance of the speed limit value, and the minimum speed limit value of the above-mentioned multiple sections.

[0124] In the embodiments of the present invention, the traffic control features are quantified. By setting the traffic control features to include, for example, the upper speed limit feature and using it as one of the evaluation indicators for predicting vehicle energy consumption, it is beneficial to further improve the accuracy of predicting vehicle energy consumption.

[0125] In some embodiments, the above energy consumption impact features further include the average speed of each section in the planned driving route. The average speed of each section is used to evaluate the overall speed situation of the vehicle during route driving, and it has a certain impact on the energy consumption of the vehicle. Among them, the average speed of each section can be determined based on the section length and the total passing time of the section. The total passing time of any section can be determined by the Intelligent Driver Model (IDM). The average speed of the section vehicle (m / s) is calculated by the following formula:

[0126]

[0127] Wherein, S f (m) represents the total length of the road segment, and t f represents the total travel time of the road segment (s).

[0128] In some embodiments, the determining of the first energy consumption influence feature of the first planned driving path includes:

[0129] Determining the number of signal lights in the first planned driving path, and the traffic control feature of the first planned driving path includes the number of signal lights.

[0130] The signal light can also be called a traffic light, and the number of signal lights can reflect the overall smoothness of the path. The more signal lights there are in the path, the more likely the vehicle is to encounter a red light interval during driving. Choosing a green light window to pass to avoid the red light will also cause fluctuations in vehicle speed, thereby affecting vehicle energy consumption.

[0131] In the embodiments of the present invention, the traffic control feature is quantified. By setting that the traffic control feature also includes the number of signal lights in the path and using it as one of the evaluation indicators for vehicle energy consumption prediction, it is beneficial to further improve the accuracy of vehicle energy consumption prediction.

[0132] Since the mapping relationship between the energy consumption of vehicles with different power types and the energy consumption influence features may be different, in order to improve the accuracy of energy consumption prediction, during the training process of the model, the model can be trained separately based on the energy consumption data of vehicles with different power types, so as to obtain different vehicle energy consumption prediction models. In the application stage of the vehicle energy consumption prediction model, based on the power type of the vehicle, its energy consumption influence features can be input into the corresponding type of vehicle energy consumption prediction model to obtain the energy consumption prediction result. The following is a specific description thereof.

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

[0134] Obtaining the second planned driving path of the second vehicle;

[0135] Determining the second energy consumption influence feature of the second planned driving path, where the second energy consumption influence feature includes the path length of the second planned driving path, and the second energy consumption influence feature further includes at least one of the traffic control feature of the second planned driving path and the road altitude change feature of the second planned driving path;

[0136] Inputting the second energy consumption influence feature into the second vehicle energy consumption prediction model to obtain the energy consumption prediction result of the second vehicle, where the second vehicle energy consumption prediction model is a trained neural network model;

[0137] Among them, the vehicle type of the first vehicle is the first power type, the vehicle type of the second vehicle is the second power type, the first vehicle energy consumption prediction model is a neural network model trained based on the energy consumption data of vehicles of the first power type, and the second vehicle energy consumption prediction model is a neural network model trained based on the energy consumption data of vehicles of the second power type.

[0138] The power types of vehicles include: fuel, pure electric, and hybrid. The above first power type and second power type are any two of the above three power types.

[0139] In the training stage of the neural network model, a large amount of energy consumption data of vehicles of the first power type is collected, including energy consumption impact features and corresponding energy consumption labels, to form a first sample set, and the above neural network model is trained based on the first sample set to obtain the above first vehicle energy consumption prediction model.

[0140] In the training stage of the neural network model, a large amount of energy consumption data of vehicles of the second power type is collected, including energy consumption impact features and corresponding energy consumption labels, to form a second sample set, and the above neural network model is trained based on the second sample set to obtain the above second vehicle energy consumption prediction model.

[0141] It should be noted that the determination methods of the energy consumption impact features in the sample set and the above second energy consumption impact features can both refer to the determination method of the above first energy consumption impact feature in the actual application of the model. To avoid repetition, it will not be elaborated here. To improve the prediction accuracy of the model, the energy consumption impact features include multiple quantified influencing factors. For example, it includes eight items: the altitude difference between the starting point and the ending point, the sample variance of the altitude of path nodes, the total path length, the average speed of each section of the path, the average speed limit value of the path, the sample variance of the speed limit value of the path, the minimum speed limit value of the path, and the number of traffic lights on the path.

[0142] It is also worth noting that the model construction embodiment of the second vehicle energy consumption prediction model can refer to the model construction embodiment of the above first vehicle energy consumption prediction model, that is, neural networks such as BP neural network, LSTM long short-term memory network, convolutional neural network, RNN recursive neural network, or RBF neural network and various neural network variants can be selected. To avoid repetition, it will not be elaborated here.

[0143] See Figure 4, during the model training stage, a large number of historical data samples are collected to train the model. After the model training is completed, the trained model can be used to predict the vehicle energy consumption. Specifically, after the first vehicle energy consumption prediction model is trained based on the energy consumption data of vehicles of the first power type, the first vehicle energy consumption prediction model can be used to predict the energy consumption of vehicles of the first power type; after the second vehicle energy consumption prediction model is trained based on the energy consumption data of vehicles of the second power type, the second vehicle energy consumption prediction model can be used to predict the energy consumption of vehicles of the second power type.

[0144] In the embodiment of the present invention, based on the energy consumption data of vehicles of the first power type and the energy consumption data of vehicles of the second power type, the neural network model is trained respectively, so that the first vehicle energy consumption prediction model and the second vehicle energy consumption prediction model can be obtained respectively. Predicting the energy consumption of vehicles of the corresponding power type based on different vehicle energy consumption prediction models is beneficial to improving the energy consumption prediction accuracy.

[0145] In some embodiments, the method further includes:

[0146] Obtain the third planned driving route of the third vehicle;

[0147] Determine the third energy consumption impact feature of the third planned driving route, where the third energy consumption impact feature includes the path length of the third planned driving route, and the third energy consumption impact feature also includes at least one of the traffic control feature of the third planned driving route and the road elevation change feature of the third planned driving route;

[0148] Input the third energy consumption impact feature into the third vehicle energy consumption prediction model to obtain the energy consumption prediction result of the third vehicle, where the third vehicle energy consumption prediction model is a trained neural network model;

[0149] Wherein, the vehicle type of the third vehicle is the third power type, and the third vehicle energy consumption prediction model is a neural network model trained based on the energy consumption data of vehicles of the third power type.

[0150] In this embodiment, the neural network model is also trained based on the energy consumption data of vehicles of the third power type to obtain the third vehicle energy consumption prediction model, and the third energy consumption prediction model is used to predict the energy consumption of vehicles of the third power type. The first power type, the second power type, and the third power type are fuel type, pure electric type, and hybrid type respectively.

[0151] During the training phase of the neural network model, a large amount of energy consumption data of vehicles of the third power type can be collected, including energy consumption impact features and corresponding energy consumption labels, to form a third sample set. Training the above neural network model based on the third sample set can obtain the above third vehicle energy consumption prediction model. Among them, the determination methods of the energy consumption impact features in the sample set and the above third energy consumption impact features can both refer to the determination method of the above first energy consumption impact feature in the actual application of the model. To avoid repetition, this will not be elaborated here. To improve the prediction accuracy of the model, the energy consumption impact features include multiple quantified influencing factors. For example, it includes the altitude difference between the starting point and the ending point, the sample variance of the altitude of path nodes, the total path length, the average speed of each section of the path, the average speed limit of the path, the sample variance of the speed limit of the path, the minimum speed limit of the path, and the number of traffic lights on the path, a total of eight items.

[0152] In the embodiment of the present invention, the neural network model is trained respectively with the energy consumption data of vehicles of different power types, and the above first vehicle energy consumption prediction model, second vehicle energy consumption prediction model, and third vehicle energy consumption prediction model can be obtained, that is, the energy consumption prediction model of fuel vehicles, the energy consumption prediction model of pure electric vehicles, and the energy consumption prediction model of hybrid vehicles can be obtained; since the mapping relationships between the energy consumption of vehicles of different power types and the energy consumption impact features may be different, predicting the energy consumption of fuel vehicles, pure electric vehicles, and hybrid vehicles respectively through the above three energy consumption prediction models is beneficial to further improve the prediction accuracy.

[0153] To more clearly illustrate the technical effects of the embodiments of the present invention, the embodiments of the present invention set the energy consumption impact features to include the altitude difference between the starting point and the ending point, the sample variance of the altitude of path nodes, the total path length, the average speed of each section of the path, the average speed limit of the path, the sample variance of the speed limit of the path, the minimum speed limit of the path, and the number of traffic lights on the path, a total of eight items. The historical energy consumption impact features of different power types and the corresponding energy consumption labels are collected to train, verify, and test the neural network respectively, and Figures 5 - 19 the corresponding model performance is shown. See Figures 5 to 9 , Figures 5 to 9 which shows the training results, verification results, and test results of the fuel vehicle energy consumption prediction model; see Figures 10 to 14 , Figures 10 to 14 which shows the training results, verification results, and test results of the pure electric vehicle energy consumption prediction model; see Figures 15 to 19 , Figures 15 to 19 which shows the training results, verification results, and test results of the hybrid vehicle energy consumption prediction model. Through Figures 5 - 19, it can be obtained that the correlation coefficients between the fitting network and the training samples, test samples, and validation samples all reach above 0.99, which indicates that the above eight road factors (i.e., the above energy consumption impact characteristics) in the present invention have a strong correlation with the energy consumption of the vehicle. Training the model based on the above energy consumption impact characteristics and using the energy consumption impact characteristics and the model for online prediction of vehicle energy consumption are beneficial to improving the accuracy of energy consumption prediction.

[0154] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0155] Figure 20 is a block diagram of a vehicle energy consumption prediction device shown in an exemplary embodiment of the present invention. As Figure 20 shown, the exemplary vehicle energy consumption prediction device includes:

[0156] A first acquisition module 2010, configured to acquire a first planned driving route of a first vehicle;

[0157] A first determination module 2020, configured to determine a first energy consumption impact characteristic of the first planned driving route, where the first energy consumption impact characteristic includes a path length of the first planned driving route, and the first energy consumption impact characteristic further includes at least one of a traffic control characteristic of the first planned driving route and a road altitude change characteristic of the first planned driving route;

[0158] A second determination module 2030, configured to input the first energy consumption impact characteristic into a first vehicle energy consumption prediction model to obtain an energy consumption prediction result of the first vehicle, where the first vehicle energy consumption prediction model is a trained neural network model.

[0159] In an embodiment of the present invention, the first energy consumption impact characteristic includes a road altitude change characteristic of the first planned driving route. The first determination module 2020 includes:

[0160] A first determination unit, configured to determine a plurality of path nodes in the first planned driving route, where the plurality of path nodes include a starting point, an end point, and intermediate path nodes of the first planned driving route;

[0161] A second determination unit, configured to determine a sample variance of the altitude of the plurality of path nodes based on the altitude corresponding to the plurality of path nodes, and the road altitude change characteristic of the first planned driving route includes the sample variance of the altitude.

[0162] In an embodiment of the present invention, the first energy consumption influencing feature includes the road altitude change feature of the first planned driving path, and the first determination module 2020 includes:

[0163] A third determination unit, configured to determine the altitude difference between the starting point and the ending point of the first planned driving path, and the road altitude change feature of the first planned driving path includes the altitude difference.

[0164] In an embodiment of the present invention, the first energy consumption influencing feature includes the traffic control feature of the first planned driving path, and the first determination module 2020 includes:

[0165] A fourth determination unit, configured to determine a plurality of path nodes in the first planned driving path, and the plurality of path nodes include the starting point, the ending point, and intermediate path nodes of the first planned driving path;

[0166] A fifth determination unit, configured to divide the first planned driving path into a plurality of road segments based on the plurality of path nodes in the first planned driving path;

[0167] A sixth determination unit, configured to determine a speed limit feature based on the speed limit values of each road segment in the plurality of road segments, and the speed limit feature includes at least one of the average speed limit value of the plurality of road segments, the sample variance of the speed limit values of the plurality of road segments, and the minimum speed limit value of the plurality of road segments, and the traffic control feature of the first planned driving path includes the speed limit feature.

[0168] In an embodiment of the present invention, the first energy consumption influencing feature includes the traffic control feature of the first planned driving path, and the first determination module 2020 includes:

[0169] A seventh determination unit, configured to determine the number of signal lights in the first planned driving path, and the traffic control feature of the first planned driving path includes the number of signal lights.

[0170] In an embodiment of the present invention, the device further includes:

[0171] A second acquisition module, configured to acquire the second planned driving path of a second vehicle;

[0172] A second determination module, configured to determine the second energy consumption influencing feature of the second planned driving path, and the second energy consumption influencing feature includes the path length of the second planned driving path, and the second energy consumption influencing feature further includes at least one of the traffic control feature of the second planned driving path and the road altitude change feature of the second planned driving path;

[0173] A third determination module, configured to input the second energy consumption impact feature into a second vehicle energy consumption prediction model to obtain an energy consumption prediction result of the second vehicle, where the second vehicle energy consumption prediction model is a trained neural network model;

[0174] Wherein, the vehicle type of the first vehicle is a first power type, the vehicle type of the second vehicle is a second power type, the first vehicle energy consumption prediction model is a neural network model trained based on the energy consumption data of vehicles of the first power type, and the second vehicle energy consumption prediction model is a neural network model trained based on the energy consumption data of vehicles of the second power type.

[0175] In an embodiment of the present invention, the method further includes:

[0176] A third acquisition module, configured to acquire a third planned driving route of a third vehicle;

[0177] A fourth determination module, configured to determine a third energy consumption impact feature of the third planned driving route, where the third energy consumption impact feature includes the route length of the third planned driving route, and the third energy consumption impact feature further includes at least one of the traffic control feature of the third planned driving route and the road altitude change feature of the third planned driving route;

[0178] A fifth determination module, configured to input the third energy consumption impact feature into a third vehicle energy consumption prediction model to obtain an energy consumption prediction result of the third vehicle, where the third vehicle energy consumption prediction model is a trained neural network model;

[0179] Wherein, the vehicle type of the third vehicle is a third power type, and the third vehicle energy consumption prediction model is a neural network model trained based on the energy consumption data of vehicles of the third power type.

[0180] It should be noted that the vehicle energy consumption prediction device provided in the above embodiment and the vehicle energy consumption prediction method provided in the above embodiment belong to the same concept. The specific manners in which each module and unit perform operations have been described in detail in the method embodiment, and will not be repeated here. In practical applications, the vehicle energy consumption prediction device provided in the above embodiment may, according to needs, allocate the above functions to different functional modules, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above. This is not limited here either.

[0181] An embodiment of the present invention further provides an electronic device, including: one or more processors; a storage device, configured to store one or more programs, and when the one or more programs are executed by the one or more processors, enable the electronic device to implement the vehicle energy consumption prediction method provided in each of the above embodiments.

[0182] Figure 21 The structural schematic diagram of a computer system of an electronic device suitable for implementing the embodiments of the present invention is shown. It should be noted that Figure 21 The computer system 2100 of the shown electronic device is only an example, and should not impose any limitation on the functions and usage scope of the embodiments of the present invention.

[0183] As Figure 21 shown, the computer system 2100 includes a central processing unit (CPU) 2101, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 2102 or the program loaded from the storage section 2108 into the random access memory (RAM) 2103, such as executing the methods described in the above embodiments. In the RAM 2103, various programs and data required for system operation are also stored. The CPU 2101, ROM 2102, and RAM 2103 are connected to each other via a bus 2104. An input / output (I / O) interface 2105 is also connected to the bus 2104.

[0184] The following components are connected to the I / O interface 2105: an input section 2106 including a keyboard, a mouse, etc.; an output section 2107 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 2108 including a hard disk, etc.; and a communication section 2109 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 2109 performs communication processing via a network such as the Internet. A drive 2110 is also connected to the I / O interface 2105 as required. A removable medium 2111, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 2110 as required, so that the computer program read from it can be installed into the storage section 2108 as required.

[0185] In particular, according to an embodiment of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, an embodiment of the present invention includes a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 2109, and / or installed from the removable medium 2111. When the computer program is executed by the central processing unit (CPU) 2101, various functions defined in the system of the present invention are executed.

[0186] It should be noted that the computer-readable medium shown in the embodiments of the present invention can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program included on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0187] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. Among them, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the above-mentioned module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, as well as the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0188] The units involved in the embodiments of the present invention can be implemented in software or in hardware, and the described units can also be provided in a processor. Among them, the names of these units do not constitute a limitation to the unit itself in some cases.

[0189] Another aspect of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer is caused to execute the vehicle energy consumption prediction method as described above. The computer-readable storage medium can be included in the electronic device described in the above embodiments, or can exist separately without being assembled into the electronic device.

[0190] Another aspect of the present invention also provides a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the vehicle energy consumption prediction method provided in the above various embodiments.

[0191] The above embodiments are only used to exemplarily illustrate the principles and effects of the present invention, rather than to limit the present invention. Any person familiar with this technology can make modifications or changes to the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or changes completed by those with ordinary knowledge in the technical field without departing from the spirit and technical ideas disclosed by the present invention should still be covered by the claims of the present invention.

Claims

1. A vehicle energy consumption prediction method, characterized in that, Including: Obtain the first planned driving route of the first vehicle; Determine the first energy consumption impact characteristics of the first planned driving route, where the first energy consumption impact characteristics include the path length of the first planned driving route, and the first energy consumption impact characteristics further include at least one of the traffic control characteristics of the first planned driving route and the road elevation change characteristics of the first planned driving route; Input the first energy consumption impact characteristics into the first vehicle energy consumption prediction model to obtain the energy consumption prediction result of the first vehicle, where the first vehicle energy consumption prediction model is a trained neural network model.

2. The vehicle energy consumption prediction method according to claim 1, characterized in that The first energy consumption impact characteristics include the road elevation change characteristics of the first planned driving route. Determining the first energy consumption impact characteristics of the first planned driving route includes: Determine multiple path nodes in the first planned driving route, where the multiple path nodes include the starting point, the ending point, and intermediate path nodes of the first planned driving route; Based on the elevation heights corresponding to the multiple path nodes, determine the sample variance of the elevation heights of the multiple path nodes, and the road elevation change characteristics of the first planned driving route include the sample variance of the elevation heights.

3. The vehicle energy consumption prediction method according to claim 1 or 2, characterized in that The first energy consumption impact characteristics include the road elevation change characteristics of the first planned driving route. Determining the first energy consumption impact characteristics of the first planned driving route includes: Determine the elevation difference between the starting point and the ending point of the first planned driving route, and the road elevation change characteristics of the first planned driving route include the elevation difference.

4. The vehicle energy consumption prediction method according to claim 1, wherein, The first energy consumption impact characteristics include the traffic control characteristics of the first planned driving route. Determining the first energy consumption impact characteristics of the first planned driving route includes: Determine multiple path nodes in the first planned driving route, where the multiple path nodes include the starting point, the ending point, and intermediate path nodes of the first planned driving route; Based on the multiple path nodes in the first planned driving route, divide the first planned driving route into multiple road segments; Based on the speed limit values of each road segment in the multiple road segments, determine the speed limit characteristics, where the speed limit characteristics include at least one of the average speed limit value of the multiple road segments, the sample variance of the speed limit values of the multiple road segments, and the lowest speed limit value of the multiple road segments, and the traffic control characteristics of the first planned driving route include the speed limit characteristics.

5. The vehicle energy consumption prediction method according to claim 1, wherein, The first energy consumption impact characteristics include the traffic control characteristics of the first planned driving route. Determining the first energy consumption impact characteristics of the first planned driving route includes: Determine the number of traffic lights in the first planned driving route, and the traffic control characteristics of the first planned driving route include the number of traffic lights.

6. The vehicle energy consumption prediction method according to claim 1, wherein The method further includes: Obtain the second planned driving route of the second vehicle; Determine the second energy consumption impact characteristics of the second planned driving route, where the second energy consumption impact characteristics include the path length of the second planned driving route, and the second energy consumption impact characteristics further include at least one of the traffic control characteristics of the second planned driving route and the road elevation change characteristics of the second planned driving route; Input the second energy consumption impact feature into the second vehicle energy consumption prediction model to obtain the energy consumption prediction result of the second vehicle, where the second vehicle energy consumption prediction model is a trained neural network model; Among them, the vehicle type of the first vehicle is the first power type, the vehicle type of the second vehicle is the second power type, the first vehicle energy consumption prediction model is a neural network model trained based on the energy consumption data of vehicles of the first power type, and the second vehicle energy consumption prediction model is a neural network model trained based on the energy consumption data of vehicles of the second power type.

7. The vehicle energy consumption prediction method according to claim 6, wherein The method further includes: Obtain the third planned driving route of the third vehicle; Determine the third energy consumption impact feature of the third planned driving route, where the third energy consumption impact feature includes the path length of the third planned driving route, and the third energy consumption impact feature further includes at least one of the traffic control feature of the third planned driving route and the road elevation change feature of the third planned driving route; Input the third energy consumption impact feature into the third vehicle energy consumption prediction model to obtain the energy consumption prediction result of the third vehicle, where the third vehicle energy consumption prediction model is a trained neural network model; Among them, the vehicle type of the third vehicle is the third power type, and the third vehicle energy consumption prediction model is a neural network model trained based on the energy consumption data of vehicles of the third power type.

8. A vehicle energy consumption prediction device, characterized in that, Includes: A first acquisition module for acquiring the first planned driving route of the first vehicle; A first determination module for determining the first energy consumption impact feature of the first planned driving route, where the first energy consumption impact feature includes the path length of the first planned driving route, and the first energy consumption impact feature further includes at least one of the traffic control feature of the first planned driving route and the road elevation change feature of the first planned driving route; A second determination module for inputting the first energy consumption impact feature into the first vehicle energy consumption prediction model to obtain the energy consumption prediction result of the first vehicle, where the first vehicle energy consumption prediction model is a trained neural network model.

9. A device, characterized in that, Includes: One or more processors and a memory, The memory stores a computer program, and when the one or more processors execute the computer program, the device executes the vehicle energy consumption prediction method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, A computer program is stored thereon, and when executed by one or more processors, the device executes the vehicle energy consumption prediction method according to any one of claims 1-7.

Images