Vehicle energy consumption determination method and device, equipment and storage medium

Abstract

The invention relates to a vehicle energy consumption determination method and device, equipment and a storage medium, and relates to the technical field of vehicle data processing. The method comprises the steps that firstly, travel data of a current travel and travel data of at least one historical travel are obtained, the travel data of one travel comprises a travel route of the travel and travel starting time of the travel, and then the travel data of a target historical travel included in the at least one historical travel are obtained based on the travel data of the target historical travel; the method comprises the following steps: determining historical behavior characteristics which correspond to a target historical travel and are used for representing the driving state of a vehicle in the target historical travel, and finally determining the driving state of the vehicle in the target historical travel based on the travel data of the current travel, the travel data of the target historical travel and the historical behavior characteristics, wherein the similarity between the target historical travel and the current travel is greater than or equal to a similarity threshold value; and determining the vehicle energy consumption of the current travel. When the behavior characteristics are determined, the driving route and the starting time are considered at the same time, so that the accuracy of determining the behavior characteristics is improved, and the precision of determining the energy consumption of the vehicle in the current travel is further improved.

Description

Technical Field

[0001] This application relates to the field of vehicle data processing technology, and more particularly to the field of energy consumption determination technology for the future journey of electric vehicles, specifically to a method, apparatus, device and storage medium for determining vehicle energy consumption. Background Technology

[0002] The purpose of electric vehicle energy consumption (EVEC) estimation is to predict the total energy required for a given vehicle's journey before it begins. This is of great significance for vehicle kinetic management, journey planning, and transportation sustainability.

[0003] In related technologies, the energy consumption of a vehicle can be predicted based on the driving behavior of the driver.

[0004] However, due to the individualized driving behaviors of different drivers, that is, different drivers may have different driving behaviors, so relying solely on the driver's driving behavior may not be able to accurately predict the vehicle's energy consumption during a future trip, thus affecting the overall vehicle energy management. Summary of the Invention

[0005] This application provides a method, apparatus, device, and storage medium for determining vehicle energy consumption, to at least solve the technical problem in related technologies that cannot accurately predict vehicle energy consumption for a future trip. The technical solution of this application is as follows:

[0006] According to a first aspect of this application, a method for determining vehicle energy consumption is provided, comprising: acquiring trip data of multiple trips, wherein the trip data of one trip includes the travel route and the departure time of the trip, the multiple trips include the current trip and at least one historical trip, determining historical behavior features corresponding to the target historical trip based on the trip data of a target historical trip included in at least one historical trip, wherein the similarity between the target historical trip and the current trip is greater than or equal to a similarity threshold, the historical behavior features are used to characterize the driving state of the vehicle in the target historical trip, and determining the vehicle energy consumption of the current trip based on the trip data of the current trip, the trip data of the target historical trip, and the historical behavior features.

[0007] The departure time refers to the start time of each travel route.

[0008] According to the aforementioned technical means, since vehicle energy consumption may vary significantly even if the vehicle travels the same route at different times, this application, when determining the target historical route most similar to the current trip, not only considers the similarity between the current route and the historical route, but also incorporates the similarity between the departure time of the current trip and the departure time of the historical trip. This ensures that the determined target historical trip's route and departure time are as consistent as possible with the current trip's route and departure time, indirectly improving the accuracy of the behavioral characteristics corresponding to the target historical trip determined based on the trip data of the target historical trip. This, in turn, improves the accuracy of the vehicle energy consumption of the current trip determined based on the trip data of the current trip, the trip data of the target historical trip, and the behavioral characteristics.

[0009] In one possible implementation, the above-mentioned vehicle energy consumption determination method further includes: determining the similarity between each historical trip and the current trip based on the trip data of at least one historical trip and the trip data of the current trip, and determining the historical trips in at least one historical trip with a similarity greater than or equal to a similarity threshold as target historical trips.

[0010] Based on the above technical means, this application determines the target historical trip with a similarity threshold greater than or equal to the similarity threshold by calculating the similarity between each historical trip and the current trip. This ensures that the determined target historical trip has a high similarity to the current trip, meaning that the target historical trip can replace the current trip to a certain extent.

[0011] In one possible implementation, determining the similarity between each historical trip and the current trip based on trip data of at least one historical trip and trip data of the current trip includes: determining a first similarity and a second similarity, wherein the first similarity is the similarity between the driving route of the historical trip and the driving route of the current trip, and the second similarity is the similarity between the departure time of the historical trip and the departure time of the current trip, and determining the similarity between the historical trip and the current trip based on the first similarity and the second similarity.

[0012] Based on the aforementioned technical means, when determining the similarity between historical and current itineraries, this application, in addition to considering the similarity between the driving routes of historical and current itineraries, further combines the similarity between the departure time of historical and current itineraries to make the determined similarity between historical and current itineraries more consistent with reality.

[0013] In one possible implementation, the trip data of a trip also includes the driving parameters corresponding to the trip. Based on the trip data of the target historical trip included in the at least one historical trip, the historical behavior characteristics corresponding to the target historical trip are determined, including: identifying and processing the driving route and the driving parameters corresponding to the target historical trip respectively to obtain the route characteristics and driving characteristics corresponding to the target historical trip. The route characteristics are used to characterize the route state of the vehicle in the target historical trip, and the driving characteristics are used to characterize the change state of the driving parameters corresponding to the target historical trip. Based on the route characteristics and driving characteristics, the historical behavior characteristics are determined.

[0014] Based on the aforementioned technical means, this application improves the accuracy of the identified behavioral characteristics throughout the entire target historical journey by refining the identification of the driving routes and driving parameters in the target historical journey, and determining which driving parameters are more favored in each driving route.

[0015] In one possible implementation, determining the vehicle energy consumption of the current trip based on the trip data of the current trip, the trip data of the target historical trip, and historical behavioral characteristics includes: determining the current behavioral characteristics of the current trip based on the trip data of the current trip, the trip data of the target historical trip, and historical behavioral characteristics, wherein the current behavioral characteristics are used to characterize the driving state of the vehicle in the current trip, and determining the vehicle energy consumption of the current trip based on the current behavioral characteristics and the trip data of the current trip.

[0016] Based on the aforementioned technical means, this application first combines the trip data of the current trip, the trip data of the historical trip closest to the current trip, and historical behavioral characteristics to improve the accuracy of determining the behavioral characteristics of the current trip, thereby improving the accuracy of determining the vehicle energy consumption of the current trip based on the behavioral characteristics of the current trip.

[0017] In one possible implementation, the current trip route includes multiple sub-routes. Based on the current trip's trip data, the target historical trip's trip data, and historical behavior characteristics, the current behavior characteristics of the current trip are determined, including: encoding the multiple sub-routes to obtain encoding information, the encoding information being used to characterize the energy consumption relationship between each sub-route and other sub-routes, and determining the current behavior characteristics based on the encoding information, the target historical trip's trip data, and historical behavior characteristics.

[0018] Based on the above technical means, when determining the driving behavior characteristics of the current trip, this application can also divide the current trip route into multiple shorter sub-routes and encode the energy consumption relationship between two sub-routes, thereby further combining the energy consumption relationship between the sub-routes to improve the accuracy of the determined behavior characteristics of the current trip.

[0019] According to a second aspect provided in this application, a vehicle energy consumption determination device is provided, comprising: an acquisition unit and a determination unit, wherein: the acquisition unit is configured to acquire trip data of multiple trips, wherein the trip data of one trip includes the travel route and the departure time of the trip, and the multiple trips include the current trip and at least one historical trip; the determination unit is configured to determine historical behavior features corresponding to the target historical trip based on the trip data of the target historical trip included in at least one historical trip, wherein the similarity between the target historical trip and the current trip is greater than or equal to a similarity threshold, and the historical behavior features are used to characterize the driving state of the vehicle in the target historical trip; the determination unit is further configured to determine the vehicle energy consumption of the current trip based on the trip data of the current trip, the trip data of the target historical trip, and the historical behavior features.

[0020] In one possible implementation, the determining unit is further configured to: determine the similarity between each historical trip and the current trip based on the trip data of at least one historical trip and the trip data of the current trip, and determine the historical trips in at least one historical trip with a similarity greater than or equal to a similarity threshold as target historical trips.

[0021] In one possible implementation, the determining unit is specifically used to: determine a first similarity and a second similarity, wherein the first similarity is the similarity between the driving route of the historical trip and the driving route of the current trip, and the second similarity is the similarity between the departure time of the historical trip and the departure time of the current trip, and determine the similarity between the historical trip and the current trip based on the first similarity and the second similarity.

[0022] In one possible implementation, the trip data of a trip also includes the driving parameters corresponding to the trip. The aforementioned determining unit is specifically used to: identify and process the driving route of the target historical trip and the driving parameters corresponding to the target historical trip respectively to obtain the route features and driving features corresponding to the target historical trip. The route features are used to characterize the route state of the vehicle in the target historical trip, and the driving features are used to characterize the change state of the driving parameters corresponding to the target historical trip. Based on the route features and driving features, the historical behavior features are determined.

[0023] In one possible implementation, the determining unit is specifically used to: determine the current behavior characteristics of the current trip based on the trip data of the current trip, the trip data of the target historical trip, and historical behavior characteristics, wherein the current behavior characteristics are used to characterize the driving state of the vehicle in the current trip, and determine the vehicle energy consumption of the current trip based on the current behavior characteristics and the trip data of the current trip.

[0024] In one possible implementation, the current travel route includes multiple sub-routes. The determining unit is specifically used to: encode the multiple sub-routes to obtain encoding information, the encoding information being used to characterize the energy consumption relationship between each sub-routes and other sub-routes, and to determine the current behavior characteristics based on the encoding information, the travel data of the target historical trip, and the historical behavior characteristics.

[0025] According to a third aspect provided in this application, an electronic device is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute instructions to implement the method of the first aspect described above and any possible implementation thereof.

[0026] According to a fourth aspect provided in this application, a computer-readable storage medium is provided that, when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, enables the electronic device to perform the methods described in the first aspect and any possible implementation thereof.

[0027] According to the fifth aspect provided in this application, a computer program product is provided, the computer program product including computer instructions, which, when executed on an electronic device, cause the electronic device to perform the method described in the first aspect and any possible implementation thereof.

[0028] Therefore, the above-mentioned technical features of this application have the following beneficial effects:

[0029] (1) Since the energy consumption of a vehicle may vary greatly even if the driving route is exactly the same at different times, this application considers not only the similarity between the current driving route and the historical driving route when determining the target historical driving route most similar to the current driving route, but also the similarity between the departure time of the current driving route and the departure time of the historical driving route. This ensures that the driving route and departure time of the determined target historical driving route are as consistent as possible with the driving route and departure time of the current driving route. This indirectly improves the accuracy of the behavioral characteristics corresponding to the target historical driving route determined based on the driving route data of the target historical driving route, thereby improving the accuracy of the vehicle energy consumption of the current driving route determined based on the driving route data of the current driving route, the driving route data of the target historical driving route, and the behavioral characteristics.

[0030] (2) This application determines the target historical trip with a similarity threshold greater than or equal to the similarity threshold by calculating the similarity between each historical trip and the current trip. This ensures that the determined target historical trip has a high similarity to the current trip, that is, the target historical trip can replace the current trip to a certain extent.

[0031] (3) When determining the similarity between the historical itinerary and the current itinerary, this application, in addition to considering the similarity between the driving route of the historical itinerary and the driving route of the current itinerary, further combines the similarity between the departure time of the historical itinerary and the departure time of the current itinerary, so that the determined similarity between the historical itinerary and the current itinerary is more in line with reality.

[0032] (4) This application improves the accuracy of the identified behavioral characteristics in the entire target historical journey by refining the identification of the driving routes in the target's historical journey and the behavioral characteristics corresponding to each driving route.

[0033] (5) This application first combines the trip data of the current trip, the trip data of the historical trip closest to the current trip, and historical behavioral characteristics to improve the accuracy of determining the behavioral characteristics of the current trip, thereby improving the accuracy of determining the vehicle energy consumption of the current trip based on the behavioral characteristics of the current trip.

[0034] (6) When determining the driving behavior characteristics of the current trip, this application can also divide the current trip route into multiple shorter sub-routes and encode the energy consumption relationship between the two sub-routes, thereby further combining the energy consumption relationship between the sub-routes to improve the accuracy of the determined behavior characteristics of the current trip.

[0035] It should be noted that the technical effects of any of the implementation methods in aspects two through five can be found in the technical effects of the corresponding implementation methods in aspect one, and will not be repeated here.

[0036] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0037] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application, and do not constitute an undue limitation of this application.

[0038] Figure 1 This is a flowchart illustrating a method for determining vehicle energy consumption according to an exemplary embodiment;

[0039] Figure 2 This is a flowchart illustrating yet another method for determining vehicle energy consumption according to an exemplary embodiment;

[0040] Figure 3 This is a flowchart illustrating yet another method for determining vehicle energy consumption according to an exemplary embodiment;

[0041] Figure 4This is a flowchart illustrating yet another method for determining vehicle energy consumption according to an exemplary embodiment;

[0042] Figure 5 This is a flowchart illustrating yet another method for determining vehicle energy consumption according to an exemplary embodiment;

[0043] Figure 6 This is a flowchart illustrating yet another method for determining vehicle energy consumption according to an exemplary embodiment;

[0044] Figure 7 This is a block diagram illustrating a vehicle energy consumption determination device according to an exemplary embodiment;

[0045] Figure 8 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Detailed Implementation

[0046] To enable those skilled in the art to better understand the technical solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0047] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0048] In the description of this application, unless otherwise stated, "multiple" means two or more. "At least one of the following or similar expressions" refers to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b and / or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0049] In the embodiments of this application, the words "exemplarily" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplarily" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of the words "exemplarily" or "for example" is intended to present the relevant concepts in a specific manner to facilitate understanding.

[0050] In addition, the use of “based on” implies openness and inclusivity, because processes, steps, calculations or other actions “based on” one or more of the stated conditions or values ​​may in practice be based on additional conditions or values ​​beyond those stated.

[0051] In recent years, the development of new energy vehicles has emerged irresistibly in the traditional fuel vehicle market. The purpose of EVEC estimation is to predict the total energy required for a given vehicle's journey before it begins. Accurate energy consumption determination allows for advance adjustments to the vehicle's powertrain, achieving overall energy reduction. It also helps users better understand future driving conditions, plan routes, and replenish vehicle energy in a timely manner.

[0052] Currently, the determination of energy consumption for new energy vehicles is based on data-driven methods, which involve mining and analyzing historical driving data and real-time driving data to estimate the vehicle's energy consumption in real-time driving data. For example, factors that can represent real-time driving data are extracted from historical driving data to accurately predict the vehicle's energy consumption for future trips. However, due to the individualized driving behaviors of different drivers, the energy consumption of each vehicle, even for the same model, may vary significantly.

[0053] Among related technologies, there are the following two methods for predicting vehicle energy consumption:

[0054] (i) By considering several driving styles (such as aggressive, standard, and steady), and combining them with various factors that influence driving style (weather, road conditions, etc.), the driving style and energy consumption obtained from the prediction model are continuously corrected when a driver uses a specific vehicle model to drive a specific route, resulting in a more accurate energy consumption reading. However, this method only considers a countable number of driving styles and cannot further differentiate driving styles for each driver, resulting in low accuracy in determining energy consumption at the single-vehicle level.

[0055] (ii) By extracting and training the relationships between energy consumption data and vehicle condition data, route condition data and driving behavior data, and combining this with the route condition data of the target route, the driver's driving behavior under the target route is predicted, thereby improving the accuracy of the trip energy consumption determination result. However, this method only extracts the relationship between driving behavior data and the route condition data, lacking the extraction and description of the driver's long-term intentions, which can easily lead to low accuracy of the driving behavior prediction model.

[0056] In summary, existing methods for determining vehicle energy consumption cannot flexibly adjust the predicted vehicle energy consumption when faced with different drivers and different driving time periods, resulting in the inability to accurately predict the vehicle energy consumption for a future trip.

[0057] To address the problem in existing technologies that cannot accurately predict vehicle energy consumption for a future trip, this application provides a vehicle energy consumption determination method. When determining the target historical trip most similar to the current trip, this method considers not only the similarity between the current and historical routes but also the similarity between the departure time of the current trip and the departure time of the historical trip. This ensures that the determined target historical trip's route and departure time are as consistent as possible with the current trip's route and departure time, indirectly improving the accuracy of determining the behavioral characteristics corresponding to the target historical trip based on the trip data. This, in turn, improves the accuracy of determining the vehicle energy consumption of the current trip based on the trip data of the current trip, the trip data of the target historical trip, and the behavioral characteristics.

[0058] For ease of understanding, the method for determining vehicle energy consumption provided in this application will be described in detail below with reference to the accompanying drawings.

[0059] Figure 1 This is a flowchart illustrating a method for determining vehicle energy consumption according to an exemplary embodiment, such as... Figure 1 As shown, the method for determining vehicle energy consumption includes the following steps:

[0060] S101. Obtain trip data for multiple trips.

[0061] The trip data for a single trip includes the route and departure time, while multiple trips include the current trip and at least one historical trip.

[0062] In this embodiment of the application, the aforementioned driving route refers to the route corresponding to the entire journey completed by the vehicle. For example, the driving route of the current journey refers to the vehicle's planned route for this journey; the driving route of the historical journey refers to the complete route of each journey recorded inside the vehicle.

[0063] In this embodiment of the application, the aforementioned departure time refers to the start time of the entire journey undertaken by the vehicle. For example, the departure time of the current journey refers to the planned start time of the current journey, while the departure time of historical journeys refers to the start time of each journey recorded within the vehicle.

[0064] For example, the departure time can be represented by time nodes, such as 10:00 or 15:00.

[0065] It should be noted that the departure times and routes of the aforementioned historical trips were already matched one-to-one when they were recorded. For example, if the set of historical routes includes Route 1, Route 2, and Route 3, and the historical departure times include 10:00, 15:00, and 20:00, then when recording the departure times and routes, Route 1 corresponding to 10:00, Route 2 corresponding to 15:00, and Route 3 corresponding to 20:00 will be divided accordingly.

[0066] In this embodiment of the application, the aforementioned trip data may further include various data contained by the vehicle during the trip. For example, trip data may include vehicle model information, vehicle operation data, trip navigation data, trip weather data, and trip road condition data.

[0067] In this application, vehicle model information may include vehicle type and vehicle identification number (VIN). The vehicle type may be a new energy vehicle (e.g., pure electric vehicle, hybrid electric vehicle), and the VIN is the vehicle identification number (VIN). Different vehicles have different VIN codes.

[0068] In this application, vehicle operating data may include power battery state of charge (SOC) signal, power battery state of health (SOH) signal, engine speed signal, engine torque signal, brake pedal signal, energy recovery intensity signal, energy recovery amount signal, etc.

[0069] Energy recovery refers to the ability of a vehicle to recover electricity by reversing the generator when it is going downhill or not using electricity.

[0070] In this application, the trip navigation data may include the trip route name, estimated trip time, estimated average trip speed, traffic congestion situation, number of traffic lights, etc.

[0071] In this application, the weather data for the trip may include temperature signals, humidity signals, visibility signals, and wind speed signals.

[0072] It should be noted that the trip navigation data can be retrieved using the existing map provider's open application programming interface (API); the trip weather data can be retrieved from weather websites.

[0073] In this application, the travel condition data may include road slope and road surface material. The road slope may include uphill and downhill slopes, and the road surface material may include asphalt, gravel, dirt, etc.

[0074] In this embodiment of the application, trip data of at least one historical trip stored in the vehicle's internal memory can be directly obtained, and trip data of the planned current trip can be obtained from the vehicle's internal processor.

[0075] S102. Based on the trip data of the target historical trip included in at least one historical trip, determine the historical behavioral characteristics corresponding to the target historical trip.

[0076] Among them, the similarity between the target historical trip and the current trip is greater than or equal to the similarity threshold.

[0077] In this embodiment of the application, the aforementioned similarity threshold can be a manually set value, which can be flexibly adjusted according to the actual scenario. For example, the similarity threshold can be 19.2.

[0078] In the embodiments of this application, similarity refers to the degree of closeness between the target historical itinerary and the current itinerary.

[0079] Optionally, in the embodiments of this application, such as Figure 2 As shown, the above-mentioned determination of the target historical trip from at least one historical trip can be achieved through the following S201 and S202:

[0080] S201. Based on the trip data of at least one historical trip and the trip data of the current trip, determine the similarity between each historical trip and the current trip in at least one historical trip.

[0081] In this embodiment of the application, the similarity between each historical trip and the current trip can be determined based on the travel route and departure time of at least one historical trip, as well as the travel route and departure time of the current trip.

[0082] For example, such as Figure 3 As shown, the above S201 can be implemented by the following S201a and S201b:

[0083] S201a, Determine the first similarity and the second similarity.

[0084] The first similarity is the similarity between the driving route of the historical trip and the driving route of the current trip, and the second similarity is the similarity between the departure time of the historical trip and the departure time of the current trip.

[0085] In this embodiment of the application, the similarity between the current trip's route and the routes of each historical trip can be calculated first.

[0086] For example, a specific algorithm can be used to calculate the first similarity. For instance, the dynamic time warping (DTW) algorithm can be introduced. Since there will be more or less difference in the length of each route, the DTW algorithm can provide a flexible alignment method between the two sequences. Therefore, the best alignment method between the current route sequence and the route sequence of each historical route can be found, and the similarity can be calculated based on this best alignment method to obtain the first similarity.

[0087] In this embodiment of the application, the similarity between the departure time of the current trip and the departure time of each historical trip can also be calculated.

[0088] For example, a specific algorithm can be used to calculate the second similarity. For instance, the Euclidean algorithm can be introduced. Since there is only one data point for the departure time of each trip, the Euclidean algorithm can be used to simply and intuitively calculate the greatest common divisor of the departure time of the current trip and the departure time of each historical trip until the remainder is zero, thus obtaining the second similarity.

[0089] In this embodiment of the application, the aforementioned similarity can be a similarity score or a similarity percentage. For example, the similarity score between the current trip's route and the routes of each historical trip can include 8, 8.5, 8.7, 9, 9.3, or 9.6; the similarity score between the departure time of the current trip and the departure time of each historical trip can include 8.8, 8.9, 9.2, 9.5, 9.7, or 9.9.

[0090] It should be noted that, when the first similarity score is a perfect score of 10, the starting point of the current trip and the starting point of the historical trip completely coincide, the ending point of the current trip and the ending point of the historical trip completely coincide, and the path between the starting point and the ending point also completely coincides; when the second similarity score is a perfect score of 10, the departure time of the current trip is exactly the same as the departure time of the historical trip.

[0091] S201b: Based on the first similarity and the second similarity, determine the similarity between the historical itinerary and the current itinerary.

[0092] In this embodiment of the application, each first similarity between the current trip's route and the routes of each historical trip can be combined with each second similarity between the current trip's departure time and the departure time of each historical trip to determine the similarity between each historical trip and the current trip.

[0093] For example, each first similarity score and each second similarity score can be added together to obtain multiple similarity scores. For instance, adding the first similarity score 8 to the second similarity score 8.8 gives a similarity score of 16.8; adding the first similarity score 8.5 to the second similarity score 8.9 gives a similarity score of 17.4; adding the first similarity score 8.7 to the second similarity score 9.2 gives a similarity score of 17.9; and so on, until all the calculated first and second similarity scores are added together to obtain multiple similarity scores.

[0094] For example, as shown in Table 1, the result of adding a portion of the first similarity score and a portion of the second similarity score is displayed. In real-world scenarios, more first similarity scores and second similarity scores may be included, but not all of them are listed here.

[0095] Table 1

[0096]

[0097] Therefore, when determining the similarity between historical and current itineraries, this application considers not only the similarity between the routes of historical and current itineraries, but also the similarity between the departure time of historical and current itineraries, making the determined similarity between historical and current itineraries more consistent with reality.

[0098] S202. Identify at least one historical trip whose similarity to the current trip is greater than or equal to a similarity threshold as the target historical trip.

[0099] In this embodiment of the application, after obtaining multiple similarity scores, the similarity scores that are greater than or equal to the similarity threshold can be filtered out as the target similarity score, and then the historical trip corresponding to the target similarity score can be determined from at least one historical trip as the target historical trip.

[0100] For example, referring to Table 1 above, taking a target similarity threshold of 19.2 as an example. If at least one historical trip includes: trip 1 (19.5), trip 2 (19.1), trip 3 (19.3), trip 4 (19.2), trip 5 (19), and trip 6 (18.9), then the target similarity score can be determined to include 19.5, 19.3, and 19.2. Then, the target historical trip can be determined by trip 1 corresponding to 19.5; trip 3 corresponding to 19.3; and trip 4 corresponding to 19.2.

[0101] Thus, by calculating the similarity between each historical trip and the current trip, this application determines the target historical trip that is greater than or equal to the similarity threshold, which can ensure that the determined target historical trip has a high similarity to the current trip, that is, the target historical trip can replace the current trip to a certain extent.

[0102] In this embodiment of the application, the aforementioned historical behavior features are used to characterize the driving status of the vehicle during the target historical journey.

[0103] Optionally, the aforementioned trip data may also include driving parameters corresponding to the trip. These driving parameters may include average speed, acceleration, energy consumption per hour, energy consumption per kilometer, total power consumption during the trip, etc., and acceleration may include acceleration and deceleration.

[0104] Furthermore, such as Figure 4 As shown, the above S102 can be implemented by the following S102a and S102b:

[0105] S102a. The driving route and driving parameters corresponding to the target historical journey are identified and processed to obtain the route features and driving features corresponding to the target historical journey.

[0106] Among them, route features are used to characterize the route status of the vehicle in the target historical journey, and driving features are used to characterize the change status of driving parameters corresponding to the target historical journey.

[0107] In this application embodiment, route features may include route type, one-way indicator, number of lanes, maximum speed allowed on the route, and route length, etc.; driving features may include acceleration increase, acceleration decrease, etc.

[0108] In this embodiment of the application, in order to extract the form features hidden in the entire driving route, the driving route can be divided into multiple segments, the route features of each segment can be identified, and the driving features of the driving parameters corresponding to each segment can be identified.

[0109] For example, consider a driving route comprising five segments (Route 1, Route 2, Route 3, Route 4, and Route 5). If all five segments are uphill sections, then the acceleration corresponding to Route 1 is 2, the acceleration corresponding to Route 2 is 2, the acceleration corresponding to Route 3 is 2, the acceleration corresponding to Route 4 is 2, and the acceleration corresponding to Route 5 is 3.

[0110] S102b. Based on route characteristics and driving characteristics, determine historical behavior characteristics.

[0111] In this embodiment of the application, historical behavior features can be determined by a neural network model. For example, the route features of each route segment and the driving features of the driving parameters corresponding to each route segment can be input into a convolutional neural network (CNN) in chronological order. Since CNN has excellent feature extraction capabilities, through multi-layer convolution operations inside the CNN, the local structure of each route segment and the global features of the entire driving route can be learned, thereby capturing higher-level driving preference information. This driving preference feature information represents the historical behavior features corresponding to the target historical trip.

[0112] For example, if the above routes 1, 2, 3, 4, and 5, as well as the acceleration 2 corresponding to route 1, the acceleration 2 corresponding to route 2, the acceleration 2 corresponding to route 3, the acceleration 2 corresponding to route 4, and the acceleration 3 corresponding to route 5 are input into a CNN network, the CNN network can combine these five routes to determine that the acceleration of the uphill section is 2, and thus determine the historical behavioral characteristics of the target's historical journey.

[0113] Thus, by refining the identification of driving routes in the target's historical journey and the corresponding behavioral characteristics of each driving route, this application determines which behavioral characteristics are more prevalent in each driving route, thereby improving the accuracy of the identified behavioral characteristics in the entire target's historical journey.

[0114] S103. Based on the current trip's trip data, the target historical trip's trip data, and historical behavioral characteristics, determine the vehicle's energy consumption for the current trip.

[0115] In this embodiment of the application, vehicle energy consumption refers to the amount of electricity consumed during vehicle operation.

[0116] In this embodiment of the application, since the vehicle energy consumption of the current trip is more directly determined by the behavioral characteristics and trip data of the current trip, it is necessary to first determine the behavioral characteristics of the current trip.

[0117] Optionally, in the embodiments of this application, such as Figure 5 As shown, the above S103 can be implemented by the following S103a and S103b:

[0118] S103a. Based on the current trip's trip data, the target historical trip's trip data, and historical behavioral characteristics, determine the current behavioral characteristics of the current trip.

[0119] Among them, the current behavior feature is used to characterize the vehicle's driving status during the current journey.

[0120] In this embodiment of the application, after determining the target historical trip most similar to the current trip through similarity, the current behavioral characteristics of the current trip can be determined by combining the historical behavioral characteristics of each target historical trip.

[0121] For example, taking the target historical journey as an example, if the historical behavior characteristics of each of the three historical journeys include 10 deceleration accelerations and 20 acceleration accelerations, it can be determined that the current behavior characteristics of the current journey will also include 10 deceleration accelerations and 20 acceleration accelerations.

[0122] For example, consider a target historical journey that includes three historical journeys. If the historical behavior characteristics of each of the three historical journeys include 8 decelerations and 20 accelerations, 9 decelerations and 22 accelerations, and 10 decelerations and 24 accelerations respectively, the average of the historical behavior characteristics of the three historical journeys can be calculated. Therefore, the current behavior characteristics of the current journey will be determined to include 10 decelerations and 20 accelerations.

[0123] Further, optionally, to improve the accuracy of the current behavioral characteristics of the determined current itinerary, such as Figure 6 As shown, when the current journey includes multiple sub-routes, step S103a may include the following steps:

[0124] S103a1. Encode multiple sub-routes to obtain encoded information.

[0125] The encoded information is used to characterize the energy consumption relationship between each sub-route and other sub-routes in multiple sub-routes.

[0126] In this embodiment of the application, the energy consumption relationship can be the change in energy consumption caused by the change in the behavioral characteristics of a vehicle when it travels from one sub-route to another.

[0127] In this embodiment of the application, in order to more accurately determine the behavioral characteristics in the current journey, the current journey route can be divided into more granular multiple trajectories (such as multiple sub-routes), and then each trajectory segment is input into a specific neural network for encoding to infer the changes in behavioral characteristics such as acceleration and speed between every two trajectories, so as to further obtain the energy consumption change.

[0128] For example, each trajectory segment can be input into a variant gated recurrent unit (GRU) network of a recurrent network. Since the GRU network can effectively solve the sequence problem, when processing road segment sequence data, it can control the updating and transmission of information through a gating mechanism, so that the network can focus on important information in the road segment sequence and suppress the propagation of useless information. Therefore, it can encode multiple sub-routes in the current driving route and infer detailed driving behavior characteristics such as acceleration and speed on each sub-routes.

[0129] It should be noted that GRU networks have fewer parameters and a simpler structure than classic long short-term memory (LSTM) networks, and they run faster, thus improving data processing efficiency.

[0130] S103a2. Based on the coding information, the trip data of the target historical trip, and the historical behavioral characteristics, determine the current behavioral characteristics.

[0131] In this embodiment of the application, since it is necessary to determine the current driving behavior characteristics from multiple perspectives, the encoded information, the trip data of the target historical trip, and the historical behavior characteristics can be input into a neural network with a multi-head attention mechanism for processing.

[0132] For example, taking the above-mentioned target historical trip as an example, the encoded information, the trip data of the three selected historical trips, and the behavioral features corresponding to each trip data can be divided into multiple heads through a multi-head attention network to form multiple sub-semantic spaces, so as to focus on two-dimensional semantic space information of different dimensions. Then, the two-dimensional semantic space information of different dimensions is input into a fully connected layer to be transformed into one-dimensional behavioral features, that is, to obtain the current behavioral features of the current trip.

[0133] Thus, when determining the driving behavior characteristics of the current trip, this application can also break down the current trip route into multiple shorter sub-routes and encode the energy consumption relationship between two sub-routes, thereby further combining the energy consumption relationship between the sub-routes to improve the accuracy of the determined behavior characteristics of the current trip.

[0134] S103b. Based on current behavioral characteristics and current trip data, determine the vehicle energy consumption for the current trip.

[0135] In this embodiment of the application, the current behavior characteristics of the current trip, as well as the trip data including road condition data, weather data and navigation data, can be input into a specific neural network. After processing by the neural network, the vehicle energy consumption of the current trip can be obtained.

[0136] For example, current behavioral characteristics (such as average speed and acceleration), current road condition data (such as road surface material and road slope), current weather data (such as temperature signal, humidity signal, visibility signal, and wind speed signal), and current navigation data (such as current departure time, current route, current road name, current estimated time, current estimated average speed, current traffic situation, and current number of traffic lights) can be input into a multi-layer perceptron (MLP) to output the vehicle energy consumption for this trip.

[0137] It should be noted that since behavioral characteristics, travel road condition data, travel weather data, and travel navigation data are all non-linear data (i.e., the data uncertainty is relatively large), MLP with strong generalization ability can effectively process these data.

[0138] Thus, this application first combines the trip data of the current trip, the trip data of the historical trip closest to the current trip, and historical behavioral characteristics to improve the accuracy of determining the behavioral characteristics of the current trip, thereby improving the accuracy of determining the vehicle energy consumption of the current trip based on the behavioral characteristics of the current trip.

[0139] The foregoing mainly describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the above functions, the vehicle energy consumption determination device or electronic device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0140] This application embodiment can, based on the above method, exemplarily divide a vehicle energy consumption determination device or electronic device into functional modules. For example, the vehicle energy consumption determination device or electronic device may include functional modules corresponding to each functional division, or two or more functions may be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this application embodiment is illustrative and only represents one logical functional division; in actual implementation, there may be other division methods.

[0141] Figure 7 This is a block diagram illustrating a vehicle energy consumption determination device according to an exemplary embodiment. (Refer to...) Figure 7 The vehicle energy consumption determination device 700 includes: an acquisition unit 701 and a determination unit 702.

[0142] The acquisition unit 701 is used to acquire trip data for multiple trips, wherein the trip data for one trip includes the travel route and the departure time of the trip, and the multiple trips include the current trip and at least one historical trip. The determination unit 702 is used to determine the historical behavior features corresponding to the target historical trip based on the trip data of the target historical trip included in at least one historical trip. The similarity between the target historical trip and the current trip is greater than or equal to a similarity threshold. The historical behavior features are used to characterize the driving state of the vehicle in the target historical trip. The determination unit 702 is also used to determine the vehicle energy consumption of the current trip based on the trip data of the current trip, the trip data of the target historical trip, and the historical behavior features.

[0143] In some embodiments, the determining unit 702 is further configured to: determine the similarity between each historical trip and the current trip based on the trip data of at least one historical trip and the trip data of the current trip, and determine the historical trips in at least one historical trip with a similarity greater than or equal to a similarity threshold as target historical trips.

[0144] In some embodiments, the determining unit 702 is specifically used to: determine a first similarity and a second similarity, wherein the first similarity is the similarity between the driving route of the historical trip and the driving route of the current trip, and the second similarity is the similarity between the departure time of the historical trip and the departure time of the current trip, and determine the similarity between the historical trip and the current trip based on the first similarity and the second similarity.

[0145] In some embodiments, the trip data of a trip also includes the driving parameters corresponding to the trip. The determining unit 702 is specifically used to: identify and process the driving route of the target historical trip and the driving parameters corresponding to the target historical trip respectively to obtain the route features and driving features corresponding to the target historical trip. The route features are used to characterize the route state of the vehicle in the target historical trip, and the driving features are used to characterize the change state of the driving parameters corresponding to the target historical trip. Based on the route features and driving features, the historical behavior features are determined.

[0146] In some embodiments, the determining unit 702 is specifically used to: determine the current behavior characteristics of the current trip based on the trip data of the current trip, the trip data of the target historical trip, and historical behavior characteristics, wherein the current behavior characteristics are used to characterize the driving state of the vehicle in the current trip, and determine the vehicle's capability in the current trip based on the current behavior characteristics and the trip data of the current trip.

[0147] In some embodiments, the current travel route includes multiple sub-routes. The determining unit 702 is specifically used to: encode the multiple sub-routes to obtain encoding information, the encoding information being used to characterize the energy consumption relationship between each sub-routes and other sub-routes, and to determine the current behavior characteristics based on the encoding information, the travel data of the target historical trip, and the historical behavior characteristics.

[0148] In the vehicle energy consumption determination device provided in this application embodiment, since the vehicle energy consumption may vary greatly even if the vehicle travels the same route at different times, this application, when determining the target historical route most similar to the current trip, not only considers the similarity between the current route and the historical route, but also incorporates the similarity between the departure time of the current trip and the departure time of the historical trip. This ensures that the determined target historical trip route and departure time are as consistent as possible with the current trip route and departure time, indirectly improving the accuracy of the behavioral characteristics corresponding to the target historical trip determined based on the trip data of the target historical trip. This, in turn, improves the accuracy of the vehicle energy consumption of the current trip determined based on the trip data of the current trip, the trip data of the target historical trip, and the behavioral characteristics.

[0149] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0150] Figure 8 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Figure 8 As shown, the electronic device 800 includes, but is not limited to, a processor 801 and a memory 802.

[0151] The memory 802 described above is used to store the executable instructions of the processor 801. It is understood that the processor 801 is configured to execute instructions to implement the vehicle energy consumption determination method in the above embodiments.

[0152] It should be noted that those skilled in the art will understand that Figure 8 The electronic device structure shown does not constitute a limitation on the electronic device; the electronic device may include, but is not limited to, other electronic devices. Figure 8 This may indicate more or fewer components, or a combination of certain components, or a different arrangement of components.

[0153] The processor 801 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 802, and by calling data stored in the memory 802, it performs various functions and processes data, thereby providing overall monitoring of the electronic device. The processor 801 may include one or more processing units. Optionally, the processor 801 may integrate an application processor and a modem processor. The application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 801.

[0154] The memory 802 can be used to store software programs and various data. The memory 802 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, application programs required by at least one functional module (such as a determination unit, processing unit, etc.), etc. Furthermore, the memory 802 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0155] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 802 including instructions, which can be executed by a processor 801 of an electronic device 800 to implement the vehicle energy consumption determination method in the above embodiments.

[0156] In actual implementation, Figure 7 The functions of the acquisition unit 701 and the determination unit 702 can both be provided by Figure 8 The processor 801 calls the computer program stored in the memory 802 to implement the process. The specific execution process can be found in the method section of the previous embodiment, and will not be repeated here.

[0157] Optionally, the computer-readable storage medium may be a non-transitory computer-readable storage medium, such as a read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device.

[0158] In an exemplary embodiment, this application also provides a computer program product including one or more instructions, which can be executed by a processor 801 of an electronic device to complete the vehicle energy consumption determination method in the above embodiments.

[0159] It should be noted that when one or more instructions in the computer-readable storage medium or computer program product are executed by the processor of an electronic device, they implement the various processes of the above method embodiments and achieve the same technical effect as the above method. To avoid repetition, they will not be described again here.

[0160] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0161] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another apparatus, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0162] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the classified units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0163] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0164] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, essentially, or the part that contributes to the prior art, or a complete or partial classification of the technical solution, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0165] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for determining vehicle energy consumption, characterized in that, include: Acquire trip data for multiple trips, wherein the trip data for one trip includes the route of the trip and the departure time of the trip, and the multiple trips include the current trip and at least one historical trip; Based on the trip data of the target historical trip included in the at least one historical trip, the historical behavior features corresponding to the target historical trip are determined. The similarity between the target historical trip and the current trip is greater than or equal to a similarity threshold. The historical behavior features are used to characterize the driving status of the vehicle in the target historical trip. Based on the trip data of the current trip, the trip data of the target historical trip, and the historical behavioral characteristics, the vehicle energy consumption of the current trip is determined.

2. The method according to claim 1, characterized in that, The method further includes: Based on the trip data of the at least one historical trip and the trip data of the current trip, determine the similarity between each historical trip and the current trip in the at least one historical trip; The historical trips in at least one historical trip whose similarity to the current trip is greater than or equal to the similarity threshold are identified as the target historical trips.

3. The method according to claim 2, characterized in that, Determining the similarity between each historical trip and the current trip based on the trip data of the at least one historical trip and the trip data of the current trip includes: A first similarity and a second similarity are determined, wherein the first similarity is the similarity between the driving route of the historical trip and the driving route of the current trip, and the second similarity is the similarity between the departure time of the historical trip and the departure time of the current trip; Based on the first similarity and the second similarity, the similarity between the historical trip and the current trip is determined.

4. The method according to claim 1, characterized in that, Trip data for a trip also includes driving parameters corresponding to the trip. Determining the historical behavioral characteristics corresponding to the target historical trip based on the trip data of the target historical trip included in the at least one historical trip includes: The driving route and driving parameters corresponding to the target historical journey are identified and processed respectively to obtain the route features and driving features corresponding to the target historical journey. The route features are used to characterize the route state of the vehicle in the target historical journey, and the driving features are used to characterize the change state of the driving parameters corresponding to the target historical journey. Based on the route characteristics and the driving characteristics, the historical behavior characteristics are determined.

5. The method according to any one of claims 1-4, characterized in that, Determining the vehicle energy consumption for the current trip based on the trip data of the current trip, the trip data of the target historical trip, and the historical behavioral characteristics includes: Based on the trip data of the current trip, the trip data of the target historical trip, and the historical behavior characteristics, the current behavior characteristics of the current trip are determined, and the current behavior characteristics are used to characterize the driving status of the vehicle in the current trip; Based on the current behavioral characteristics and the trip data of the current trip, the vehicle energy consumption of the current trip is determined.

6. The method according to claim 5, characterized in that, The current trip's route includes multiple sub-routes. Determining the current behavioral characteristics of the current trip based on the current trip's trip data, the target historical trip's trip data, and the historical behavioral characteristics includes: The plurality of sub-routes are encoded to obtain encoded information, which is used to characterize the energy consumption relationship between each sub-routes and other sub-routes. The current behavioral characteristics are determined based on the encoded information, the travel data of the target historical itinerary, and the historical behavioral characteristics.

7. A vehicle energy consumption determination device, characterized in that, The device includes: an acquisition unit and a determination unit, wherein: The acquisition unit is used to acquire trip data for multiple trips, wherein the trip data for one trip includes the travel route and the departure time of the trip, and the multiple trips include the current trip and at least one historical trip; The determining unit is used to determine the historical behavior features corresponding to the target historical trip based on the trip data of the target historical trip included in the at least one historical trip, wherein the similarity between the target historical trip and the current trip is greater than or equal to a similarity threshold, and the historical behavior features are used to characterize the driving state of the vehicle in the target historical trip; The determining unit is further configured to determine the vehicle energy consumption of the current trip based on the trip data of the current trip, the trip data of the target historical trip, and the historical behavior characteristics.

8. The apparatus according to claim 7, characterized in that, The determining unit is further configured to: Based on the trip data of the at least one historical trip and the trip data of the current trip, determine the similarity between each historical trip and the current trip in the at least one historical trip; The historical trips in at least one historical trip whose similarity to the current trip is greater than or equal to the similarity threshold are identified as the target historical trips.

9. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the method as described in any one of claims 1 to 6.

10. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the method as described in any one of claims 1 to 6.

11. A computer-readable storage medium, characterized in that, When the computer-executable instructions stored in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is capable of performing the method as described in any one of claims 1 to 6.

12. A computer program product, characterized in that, The computer program product includes instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1 to 6.

Images