Model building method, mileage energy consumption determination method, equipment and storage medium

Abstract

The invention discloses a model building method, a mileage energy consumption determination method, equipment and a storage medium, and the model building method comprises the steps: obtaining at least one piece of mapping relation information, the mapping relation information represents a corresponding relation between sample driving condition information and unit mileage energy consumption, the sample driving condition information comprises a road condition type, and / or at least one driving condition characteristic under the road condition type; according to the at least one piece of mapping relation information, model building is carried out to obtain a unit energy consumption estimation model, and the unit energy consumption estimation model is used for outputting corresponding target unit mileage energy consumption according to the target driving condition information. Therefore, the technical scheme of the invention can support the estimation of the energy consumption per unit mileage, and enables the estimated energy consumption per unit mileage to be closer to the actual energy consumption per unit mileage. Furthermore, the trust degree of the user of the new energy automobile on the unit mileage energy consumption displayed in the automobile and other related energy consumption data can be improved, and the purpose of improving the user experience is achieved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a model building method, a method for determining mileage energy consumption, a computing device, and a computer-readable storage medium. Background Art

[0002] As the representative of new energy vehicles, electric vehicles have a growing demand for accurate estimation of electric vehicle energy consumption as they become more popular. Accurate energy consumption estimation can not only help users plan their trips, but also provide accurate predictions of driving range, optimize energy management strategies, charging strategies, and driving behaviors. Therefore, conducting research on the estimation of electric vehicle energy consumption per unit mileage is of great significance to promoting the development of the electric vehicle industry. Accurate estimation of energy consumption per unit mileage can help users better understand the performance of electric vehicles and alleviate their "mileage anxiety" problem.

[0003] Most of the existing methods for estimating the energy consumption per unit mileage of electric vehicles directly convert it based on the previous total energy consumption and the previous total mileage, without considering that the energy consumption of electric vehicles is affected by various factors (such as road traffic conditions and related driving conditions, etc.). As a result, there is a large error between the unit mileage energy consumption calculated by the existing method for estimating the energy consumption per unit mileage and the actual unit mileage energy consumption, which makes electric vehicle users have low trust in the unit mileage energy consumption displayed in the electric vehicle and other related energy consumption data, resulting in poor user experience. Summary of the invention

[0004] The purpose of this application is to provide a model building method, a method for determining mileage energy consumption, a computing device and a computer-readable storage medium, which can support the estimation of unit mileage energy consumption so that the estimated unit mileage energy consumption can be closer to the actual unit mileage energy consumption, and further achieve the purpose of improving user experience.

[0005] To achieve the above objectives: In a first aspect, an embodiment of the present application provides a model building method, including: obtaining at least one mapping relationship information, the mapping relationship information characterizing the correspondence between sample driving condition information and unit mileage energy consumption, the sample driving condition information including the road condition type, and / or at least one driving condition feature under the road condition type; building a model according to at least one mapping relationship information to obtain a unit energy consumption estimation model, the unit energy consumption estimation model being used to output the corresponding target unit mileage energy consumption according to the target driving condition information.

[0006] In one embodiment, the step of obtaining at least one mapping relationship information includes: determining at least one sample driving condition information based on the acquired historical driving data; calculating the unit energy consumption based on the sample driving condition information to obtain the corresponding unit mileage energy consumption; and forming at least one mapping relationship information based on the unit mileage energy consumption corresponding to the at least one sample driving condition information.

[0007] In one implementation, the historical driving data includes a vehicle speed-time correspondence and a road condition type.

[0008] In one embodiment, the step of determining at least one sample driving condition information according to the acquired historical driving data includes one of the following: Determine the vehicle speeds at multiple times according to the vehicle speed-time correspondence, and determine multiple sample driving condition information according to the vehicle speeds at multiple times and the corresponding road condition types, wherein the sample driving condition information includes the road condition type and the vehicle speed at the time; Determine the average vehicle speed according to the vehicle speed-time correspondence, and determine a sample driving condition information according to the average vehicle speed and the corresponding road condition type, the sample driving condition information including the road condition type and the average vehicle speed; The average vehicle speed is calculated according to the vehicle speed-time correspondence relationship and the calculation formula of the average vehicle speed, and the average acceleration is calculated according to the calculation formula of the average vehicle speed and acceleration, so as to determine a sample driving condition information according to the road condition type, the average acceleration and the average vehicle speed, and the sample driving condition information includes the road condition type, the average vehicle speed and the average acceleration; According to the calculation strategy of the vehicle speed-time correspondence and the average acceleration, the average acceleration is calculated, and the vehicle speeds at multiple moments are determined according to the vehicle speed-time correspondence. According to the road condition type, the average acceleration and the vehicle speeds at multiple moments, multiple sample driving condition information is determined, and the sample driving condition information includes the road condition type, the vehicle speed at the moment and the average acceleration.

[0009] In one embodiment, before the step of determining at least one sample driving condition information based on the acquired historical driving data, the step includes: collecting actual vehicle driving data; performing data preprocessing and condition classification processing on the actual vehicle driving data to obtain historical driving data of at least one road condition type; wherein the preprocessing strategy corresponding to the data preprocessing includes at least one of the following: deleting driving data segments that meet the exclusion conditions in the actual vehicle driving data; performing duplicate value deletion processing on the actual vehicle driving data; performing missing value supplement processing on the actual vehicle driving data; and performing outlier repair processing on the actual vehicle driving data.

[0010] In one embodiment, the driving data segments that meet the exclusion conditions include at least one of the following: The driving data segment corresponds to a driving condition in which the parking time is greater than or equal to the preset time; The driving data segment corresponds to a driving condition in which the maximum climbing gradient is greater than or equal to a preset gradient.

[0011] In one embodiment, the step of calculating unit energy consumption based on sample driving condition information to obtain corresponding unit mileage energy consumption includes: calculating unit energy consumption based on driving condition characteristics and vehicle performance information in the sample driving condition information to obtain corresponding unit mileage energy consumption.

[0012] In one embodiment, the driving condition characteristics include average acceleration, driving mileage and average vehicle speed / speed at a given moment, and the vehicle performance information includes vehicle mechanical parameters and energy conversion efficiency parameters.

[0013] In one embodiment, unit energy consumption is calculated based on driving condition characteristics and vehicle performance information in sample driving condition information to obtain the corresponding unit mileage energy consumption, including: calculating the driving force using a driving force calculation formula based on the average vehicle speed / momentary vehicle speed, average acceleration and vehicle mechanical parameters; calculating the driving energy consumption using a driving energy consumption calculation formula based on the driving force, average vehicle speed / momentary vehicle speed and energy conversion efficiency parameters; calculating the unit mileage energy consumption using a unit mileage energy consumption calculation formula based on the driving energy consumption and mileage.

[0014] In one embodiment, the average vehicle speed is calculated as follows:

[0015] in, represents the average vehicle speed, represents the vehicle speed at a certain moment determined from the vehicle speed-time correspondence, Indicates the vehicle speed sampling duration; and / or, The acceleration is calculated as:

[0016] in, represents the average acceleration in the sample driving condition information, represents the vehicle speed at a certain moment determined from the vehicle speed-time correspondence, Indicates the vehicle speed sampling duration; and / or, The formula for calculating the driving force is:

[0017] in, Indicates driving force, Indicates average speed / speed at any given moment. Represents the average acceleration and vehicle mechanical parameters in the sample driving condition information: Indicates the vehicle's curb weight. is the rolling resistance coefficient, is the air resistance coefficient, represents the windward area, represents the rotational mass conversion factor; and / or, The calculation formula of driving energy consumption is:

[0018] in, Indicates the drive energy consumption, Indicates average vehicle speed / speed at any given moment, energy conversion efficiency parameters: represents the driving efficiency, represents the motor efficiency, represents the battery efficiency; and / or, The formula for calculating energy consumption per unit mileage is:

[0019] in, Indicates the energy consumption per unit mileage, Indicates the drive energy consumption, Indicates the mileage in the sample driving condition information.

[0020] In a second aspect, an embodiment of the present application provides a method for determining mileage energy consumption, including: obtaining target driving condition information of a future driving section, the target driving condition information including a road condition type, and / or at least one driving condition feature under the road condition type; determining a target unit mileage energy consumption corresponding to the future driving section according to the target driving condition information and a pre-built unit energy consumption estimation model, the unit energy consumption estimation model being obtained by modeling a mapping relationship information that characterizes the corresponding relationship between sample driving condition information and unit mileage energy consumption.

[0021] In a third aspect, an embodiment of the present application provides a computing device, comprising: a processor and a memory storing a computer program, and when the processor runs the computer program, the steps of the model building method described in any one of the above items are implemented.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the steps of the model building method described in any one of the above items are implemented.

[0023] In a fifth aspect, an embodiment of the present application provides a computing device, including: a processor and a memory storing a computer program, and when the processor runs the computer program, the steps of the method for determining mileage energy consumption described above are implemented.

[0024] In a sixth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method for determining mileage energy consumption described above.

[0025] An embodiment of the present application provides a model building method, a computing device and a computer-readable storage medium. The model building method includes: obtaining at least one mapping relationship information, the mapping relationship information characterizing the correspondence between sample driving condition information and unit mileage energy consumption, the sample driving condition information including the road condition type, and / or at least one driving condition feature under the road condition type; building a model according to at least one mapping relationship information to obtain a unit energy consumption estimation model, the unit energy consumption estimation model is used to output the corresponding target unit mileage energy consumption according to the target driving condition information. In this way, the technical solution of the present application can fully consider the impact of various driving condition information (such as road condition type and / or specific driving condition under the road condition type) on unit mileage energy consumption, and pre-associate accurate unit mileage energy consumption for various sample driving condition information to obtain one or more mapping relationship information, so that when building a model through one or more mapping relationship information, the unit mileage energy consumption law under different driving conditions is learned (for example, the unit mileage energy consumption law under specific driving conditions of different road condition types is learned, and / or the unit mileage energy consumption law under different specific driving conditions of the same road condition type is learned) to obtain a unit energy consumption estimation model, and then when determining the target driving condition information of the current driving section or the future driving section, the unit mileage energy consumption estimation model can be used to output a target unit mileage energy consumption that is close to the actual unit mileage energy consumption of the relevant real driving scenario for application. Therefore, the technical solution of the present application can support the estimation of energy consumption per unit mileage, so that the estimated energy consumption per unit mileage can be closer to the actual energy consumption per unit mileage, and further enable users of new energy vehicles to have increased trust in the energy consumption per unit mileage displayed in the vehicle and other related energy consumption data, thereby achieving the purpose of improving user experience.

[0026] The embodiment of the present application provides a method for determining mileage energy consumption, a computing device, and a computer-readable storage medium. The method for determining mileage energy consumption includes: obtaining target driving condition information of a future driving section, the target driving condition information includes a road condition type, and / or at least one driving condition feature under the road condition type; determining the target unit mileage energy consumption corresponding to the future driving section according to the target driving condition information and a pre-built unit energy consumption estimation model, the unit energy consumption estimation model is obtained by modeling the mapping relationship information representing the corresponding relationship between the driving condition information of the row sample and the unit mileage energy consumption. In this way, the technical solution of the present application can output a target unit mileage energy consumption close to the actual unit mileage energy consumption of the relevant real driving scene through the unit energy consumption estimation model when determining the target driving condition information of the future driving section, for application. Therefore, the technical solution of the present application can support the estimation of unit mileage energy consumption through the unit energy consumption estimation model, so that the estimated unit mileage energy consumption can be closer to the actual unit mileage energy consumption, and further can improve the trust of users of new energy vehicles in the unit mileage energy consumption displayed in the vehicle and other related energy consumption data, thereby achieving the purpose of improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application. In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor.

[0028] Figure 1 It is a flowchart of the model building method provided in the first embodiment of the present application.

[0029] Figure 2 It is a speed-time correspondence diagram for classifying driving state types according to an example of the present application.

[0030] Figure 3 It is a framework diagram of the construction process of the "speed-acceleration-energy consumption per unit mileage" MAP of the example of this application.

[0031] Figure 4 It is a flowchart of the method for determining mileage energy consumption provided in the second embodiment of the present application.

[0032] Figure 5 It is a schematic diagram of the structure of the computing device provided in an embodiment of the present application.

[0033] The realization of the purpose, functional features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. The above-mentioned drawings have shown clear embodiments of this application, which will be described in more detail later. These drawings and textual descriptions are not intended to limit the scope of the concept of this application in any way, but to illustrate the concept of this application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0034] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0035] It should be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context of the specific embodiment.

[0036] It should be understood that, although the terms first, second, third, etc. may be used to describe various information in this article, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this article, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein can be interpreted as "at the time of..." or "when..." or "in response to determination". Furthermore, as used in this article, the singular forms "one", "one" and "the" are intended to also include plural forms, unless there is an opposite indication in the context. It should be further understood that the terms "comprising", "including" indicate that there are described features, steps, operations, elements, components, projects, kinds, and / or groups, but do not exclude the existence, occurrence or addition of one or more other features, steps, operations, elements, components, projects, kinds, and / or groups. The terms "or" and "and / or" used herein are interpreted as inclusive, or mean any one or any combination. Thus, “A, B, or C” or “A, B and / or C” means “any of the following: A; B; C; A and B; A and C; B and C; A, B, and C.” An exception to this definition will occur only when a combination of elements, functions, steps, or operations are inherently mutually exclusive in some manner.

[0037] It should be understood that, although the various steps in the flowchart in the embodiment of the present application are displayed in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and it can be performed in other orders. Moreover, at least a portion of the steps in the figure may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and their execution order is not necessarily performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0038] It should be noted that, in this article, step codes such as S11, S12, etc. are used for the purpose of expressing the corresponding content more clearly and concisely, and do not constitute a substantial limitation on the sequence. When implementing it specifically, those skilled in the art may execute S12 first and then S11, etc., but these should all be within the scope of protection of this application.

[0039] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0040] In the subsequent description, the suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present application, and have no specific meanings. Therefore, "module", "component" or "unit" can be used in a mixed manner.

[0041] First embodiment See also Figure 1 , is a model building method provided in the first embodiment of the present application, which can be executed by a computing device provided in the embodiment of the present application, and the computing device can be implemented in software and / or hardware. Optionally, the computing device in this embodiment is, for example, a vehicle-mounted terminal or a server.

[0042] This embodiment provides a model building method, including (for example, the following steps S11 to S12): Step S11: obtaining at least one mapping relationship information, the mapping relationship information characterizing the correspondence between sample driving condition information and unit mileage energy consumption, the sample driving condition information including a road condition type, and / or at least one driving condition feature under the road condition type.

[0043] In one implementation, the sample driving condition information may correspond to sample driving data.

[0044] In one embodiment, the sample driving data may represent relevant data for achieving various analysis purposes related to the vehicle (eg, energy consumption analysis purpose, driving condition analysis purpose, etc.).

[0045] In one embodiment, the sample driving data may include at least one of virtual configuration driving data, historical driving data of the vehicle, historical driving data of other vehicles of the same model as the vehicle, etc. Optionally, the sample driving condition information in this embodiment may correspond to the historical driving data of the vehicle. In other words, the sample driving condition information in this embodiment may be obtained by analyzing the driving condition characteristics in the historical driving data of the vehicle, and the energy consumption per unit mileage corresponding to the sample driving condition information may be calculated based on the driving condition characteristics in the historical driving data corresponding to the sample driving condition information of the vehicle.

[0046] In one embodiment, the historical driving data of the vehicle is data obtained after actual operation of the vehicle based on the driving habits of the user of the vehicle and the explicit performance and / or implicit performance of the vehicle. Therefore, the technical solution of this embodiment is based on the sample driving condition information and its corresponding unit mileage energy consumption determined by the historical driving data of the vehicle, and a unit energy consumption estimation model is constructed to adapt to the driving habits of the user of the vehicle and the energy consumption rules of the explicit performance and / or implicit performance of the vehicle, so that the target unit mileage energy consumption estimated by the unit energy consumption estimation model is closer to the actual unit mileage energy consumption of the user of the vehicle when driving the vehicle in actual driving.

[0047] In one implementation, the sample driving condition information may be used to distinguish driving condition types corresponding to different sample driving data.

[0048] In one embodiment, the road condition type can be used to distinguish different road traffic conditions. Optionally, the road condition type can correspond to road traffic condition information, wherein the road traffic condition information includes at least one of road grade information, congestion grade information, and other information reflecting the road traffic condition. Optionally, the road traffic condition information can be included in the driving data (e.g., sample driving data). Optionally, the sample driving condition information of this embodiment can be determined based on the road grade information and congestion grade information in the corresponding sample driving data.

[0049] In one implementation, the road grade information in this embodiment can refer to the definition rules of road grades in the current mature navigation map platform, such as unnamed roads, general roads, main roads, expressways, urban expressways, national highways, expressways, etc.

[0050] In one implementation, the congestion level information in this embodiment may refer to the definition rules of congestion levels in currently mature navigation map platforms, such as unimpeded traffic, light congestion, moderate congestion, severe congestion, complete congestion, etc.

[0051] In one embodiment, according to actual research, the energy consumption per unit mileage of a vehicle under different road conditions may vary. Therefore, the technical solution of this embodiment can achieve model building based on the energy consumption per unit mileage corresponding to various detailed road conditions by dividing the road conditions into detailed types. This can enable the obtained model to grasp the changing rules of energy consumption per unit mileage that are more in line with the actual situation.

[0052] In one implementation, in order to facilitate understanding of the definition of the road condition type in this embodiment, this embodiment illustrates a method of classifying the road condition type according to the road grade and the congestion grade. The road condition type is exemplified in Table 1 below: Table 1:

[0053] In one embodiment, the driving condition characteristics under the road condition type can characterize various driving parameters of the vehicle on a road section of the road condition type. Optionally, the driving condition characteristics are, for example, average acceleration, average vehicle speed / momentary vehicle speed (instantaneous vehicle speed at a moment), mileage on a road section, driving time on a road section, average ambient temperature on a road section, etc.

[0054] In one embodiment, step S11: obtaining at least one mapping relationship information may include: determining at least one sample driving condition information according to the acquired historical driving data; calculating the unit energy consumption according to the sample driving condition information to obtain the corresponding unit mileage energy consumption; forming at least one mapping relationship information according to the unit mileage energy consumption corresponding to the at least one sample driving condition information. In this way, the technical solution of this embodiment can determine one or more sample driving condition information and the unit mileage energy consumption corresponding to each sample driving condition information through historical driving data, thereby obtaining one or more mapping relationship information for subsequent model building.

[0055] In one embodiment, before the step of determining at least one sample driving condition information based on the acquired historical driving data, it can include: collecting actual vehicle driving data; performing data preprocessing and condition classification processing on the actual vehicle driving data to obtain historical driving data of at least one road condition type.

[0056] In one implementation, the actual vehicle driving data may represent vehicle-related data and road traffic condition information during the actual driving process of the vehicle.

[0057] In one embodiment, the actual vehicle driving data may represent a set of driving data corresponding to road sections of various road condition types. Optionally, the driving condition characteristics (or driving condition parameters) in the actual vehicle driving data may include vehicle parameters and road parameters.

[0058] In one embodiment, the vehicle parameters may be various parameters corresponding to the vehicle when it is traveling, such as vehicle speed, time, battery voltage, motor torque, motor speed, mileage, etc. Optionally, the vehicle parameters may be recorded in association with a time axis, for example, the vehicle speed may be recorded in association with the time axis to obtain a vehicle speed-time correspondence relationship, and the mileage may be recorded in association with the time axis to obtain a mileage-time correspondence relationship.

[0059] In one embodiment, the road parameters may represent various parameters related to the driving environment of a road section, such as road grade information, congestion grade information, average road speed, altitude information, road section ambient temperature information, etc.

[0060] In one implementation, in order to facilitate understanding of actual vehicle driving data, the following driving condition characteristics collected at a sampling time are illustrated in Table 2: Table 2:

[0061] In one embodiment, the preprocessing strategy corresponding to the data preprocessing includes at least one of the following: Deleting driving data segments that meet the exclusion conditions in the actual vehicle driving data; Delete duplicate values ​​from real vehicle driving data; Supplement missing values ​​in real vehicle driving data; Perform outlier repair processing on real vehicle driving data.

[0062] In one embodiment, the driving data segments meeting the exclusion condition may represent driving data segments corresponding to unconventional driving conditions that may affect the calculation result of energy consumption per mileage.

[0063] In one embodiment, the driving data segments that meet the exclusion conditions include, but are not limited to, at least one of the following: The driving data segment corresponds to a driving condition in which the parking time is greater than or equal to the preset time; The driving data segment corresponds to a driving condition in which the maximum climbing gradient is greater than or equal to a preset gradient.

[0064] In one implementation, the preset duration may be an upper limit of the parking duration corresponding to a road section of a certain road condition type.

[0065] In one embodiment, the preset slope can be set to any slope value according to actual needs.

[0066] In one embodiment, the maximum climbing grade may be determined based on altitude information in the actual vehicle driving data. For example, the altitude information of the starting point of a road section of a road condition type in the actual vehicle driving data and the altitude information of the end point of the road section determine the altitude difference, thereby determining the maximum climbing grade based on the altitude difference.

[0067] In one embodiment, during the actual vehicle driving data collection process, data anomalies may occur due to driver misoperation and collection equipment communication, and therefore it is necessary to exclude driving data segments that meet the exclusion conditions in the actual vehicle driving data, and the collected actual vehicle driving data needs to delete duplicate values, process abnormal values, and supplement missing values, so that the historical driving data obtained based on the actual vehicle driving data can achieve more accurate calculation or prediction of energy consumption per unit mileage.

[0068] In one embodiment, considering that the longest duration of traffic lights in urban roads is generally 120s, the preset duration can be appropriately extended to 150s based on this, so the driving data segments with continuous parking duration exceeding 150s are regarded as long-term parking segments (driving data segments that meet the exclusion conditions). Optionally, considering that the road slope has a direct impact on driving energy consumption, the present embodiment mainly considers the flat road surface when building the model, so that the target unit mileage energy consumption output by the built model can be corrected based on the slope in subsequent applications. Therefore, when determining historical driving data based on actual vehicle driving data, it is necessary to reduce the impact of the slope on energy consumption. Based on the road design specifications, for cars that often travel in cities and good roads, the maximum climbing gradient is about 10°. Because the driving data segments with a maximum climbing gradient greater than 10° (i.e., the preset slope) are regarded as excessively steep segments (driving data segments that meet the exclusion conditions). Optionally, in order to improve the validity of historical driving data, it is necessary to delete the aforementioned excessively steep segments and long-term parking segments.

[0069] In one embodiment, data preprocessing and working condition classification processing are performed on the actual vehicle driving data to obtain historical driving data of at least one road condition type. In one embodiment, the operating condition classification process may be to classify the actual vehicle driving data after data preprocessing according to a preset operating condition classification rule.

[0070] In one embodiment, the preset operating condition classification rules include but are not limited to at least one of the following: Extracting first driving data of a first trip segment that meets the road condition type requirement from the actual vehicle driving data; Extracting second driving data of a second trip segment that meets the driving state type requirement from the first driving data; The first driving data is used as the historical driving data, and / or the second driving data is used as the historical driving data.

[0071] In one implementation, the road condition type requirement may represent the types of road condition types required, such as the 30 road condition types in Table 1.

[0072] In one embodiment, the first driving data of the first trip segment can represent the driving data corresponding to a short trip of a road condition type. Optionally, when the first driving data is used as historical driving data and a model is built based on the mapping relationship information (the correspondence between road condition type and unit mileage energy consumption) determined based on the historical driving data, the influence of the road condition type on the unit mileage energy consumption can be learned, so that the subsequently obtained model can input the road condition type and output the corresponding target unit mileage energy consumption.

[0073] In one embodiment, the first driving data of the first trip segment is, for example, driving data corresponding to an interval from an idle stop state to a next idle stop state according to a time axis; or driving data corresponding to a preset mileage interval under a road condition type.

[0074] In one embodiment, the driving state type requirement represents at least one driving state type required. Optionally, the driving state type requirement may include at least one of an accelerating driving state, a constant speed driving state, a decelerating driving state, and the like.

[0075] In one embodiment, the second driving data of the second trip segment that meets the driving state type requirement is intercepted from the first driving data, including but not limited to at least one of the following: Extracting second driving data of a second travel segment representing an accelerated driving state from the first driving data; Extracting second driving data representing a second travel segment in a constant speed driving state from the first driving data; Second driving data representing a second journey segment in a deceleration driving state is extracted from the first driving data.

[0076] In one embodiment, see Figure 2 Taking the first driving data of the first trip segment under a road condition type as an example, through the speed-time correspondence included in the first driving data, it is exemplarily demonstrated that the first driving data is intercepted according to the driving state type into driving data of an accelerated driving state, driving data of a uniform speed driving state, and driving data of a decelerated driving state.

[0077] In one embodiment, the present embodiment can determine the driving state type that forms the segment characterization according to the average acceleration of the travel segment. Optionally, the driving state type is determined based on the average acceleration of the travel segment, for example:

[0078] in, Indicates the average acceleration of a travel segment.

[0079] It should be understood that The corresponding acceleration threshold can be, but is not limited to, , and can also be any other value set according to actual needs; The corresponding acceleration threshold can be, but is not limited to, , and can also be any other value set according to actual needs; The corresponding acceleration upper limit threshold can be but is not limited to , and can also be any other value set according to actual needs, and The corresponding lower acceleration threshold can be, but is not limited to, , and can also be any other value set according to actual needs.

[0080] In one embodiment, the second driving data of the second trip segment may represent driving data corresponding to a short trip of a specific driving state type under a road condition type. Optionally, when the second driving data is used as historical driving data and a model is built based on mapping relationship information (a corresponding relationship between a specific driving state type under a road condition type and energy consumption per unit mileage) determined by the historical driving data, the influence of the road condition type and the driving state type under the learned road condition type on the energy consumption per unit mileage can be learned, so that the model obtained subsequently can input the road condition type and the specific driving state type to output the corresponding target energy consumption per unit mileage.

[0081] In one embodiment, the technical solution of this embodiment divides the continuous real vehicle driving data or the first driving data into driving data representing independent travel segments, so as to better calculate or analyze the relationship between various driving conditions and energy consumption through the driving data representing independent travel segments, thereby facilitating the determination and association of sample unit mileage energy consumption that is closer to the actual unit mileage energy consumption for various driving conditions to obtain mapping relationship information, thereby facilitating the construction of a unit energy consumption estimation model that can estimate performance more accurately based on the obtained mapping relationship information.

[0082] In one embodiment, the historical driving data may represent vehicle-related data and road traffic condition information during the actual driving process of the vehicle on a road section of a road condition type, or represent vehicle-related data and road traffic condition information during the actual driving process when the vehicle is driven in a specific driving state on a road section of a road condition type.

[0083] In one embodiment, the historical driving data may include at least one of the vehicle speed-time correspondence, road parameters, vehicle speed sampling duration on a road segment, and mileage of a road segment. Optionally, the road parameters may include at least one of the road type, road grade information, congestion grade information, average road speed, altitude information, and road segment ambient temperature information.

[0084] In one embodiment, the step of determining at least one sample driving condition information based on the acquired historical driving data includes but is not limited to one of the following: Determine the vehicle speeds at multiple times according to the vehicle speed-time correspondence, and determine multiple sample driving condition information according to the vehicle speeds at multiple times and the corresponding road condition types, wherein the sample driving condition information includes the road condition type and the vehicle speed at the time; Determine the average vehicle speed according to the vehicle speed-time correspondence, and determine a sample driving condition information according to the average vehicle speed and the road condition type, the sample driving condition information including the road condition type and the average vehicle speed; The average vehicle speed is calculated according to the vehicle speed-time correspondence relationship and the calculation formula of the average vehicle speed, and the average acceleration is calculated according to the calculation formula of the average vehicle speed and acceleration, so as to determine a sample driving condition information according to the road condition type, the average acceleration and the average vehicle speed, and the sample driving condition information includes the road condition type, the average vehicle speed and the average acceleration; According to the vehicle speed-time correspondence relationship and the calculation strategy of the average acceleration, the average acceleration is calculated, and the vehicle speeds at multiple moments are determined according to the vehicle speed-time correspondence relationship, so as to determine multiple sample driving condition information according to the road condition type, the average acceleration and the vehicle speeds at multiple moments, wherein the sample driving condition information includes the road condition type, the vehicle speed at the moment and the average acceleration; The average acceleration is calculated according to the vehicle speed-time correspondence and the average acceleration calculation strategy, and the driving state type is determined according to the average acceleration, and the vehicle speeds at multiple moments are determined according to the vehicle speed-time correspondence, so as to determine multiple sample driving condition information according to the road condition type, the driving state type and the vehicle speeds at multiple moments, wherein the sample driving condition information includes the road condition type, the vehicle speed at the moment and the driving state type; The average vehicle speed is calculated according to the vehicle speed-time correspondence and the calculation formula of the average vehicle speed, and the average acceleration is calculated according to the calculation formula of the average vehicle speed and acceleration, and the driving state type is determined according to the average acceleration, so as to determine a sample driving condition information according to the road condition type, the driving state type and the average vehicle speed, and the sample driving condition information includes the road condition type, the average vehicle speed and the driving state type.

[0085] In one embodiment, multiple vehicle speeds at different times are determined based on the vehicle speed-time correspondence, and multiple sample driving condition information is determined based on the multiple vehicle speeds at different times and the corresponding road condition types, so that multiple different sample driving condition information can be determined based on a historical driving data, so as to facilitate the subsequent determination of the unit mileage energy consumption corresponding to each sample driving condition information, thereby determining multiple different mapping relationship information based on a historical driving data, so as to quickly obtain a large amount of mapping relationship information to build a unit energy consumption estimation model, and improve the unit mileage energy consumption estimation capability of the unit energy consumption estimation model. In addition, the sample driving condition information obtained in this way mainly includes the road condition type and the vehicle speed at different times. Therefore, the mapping relationship information obtained based on the sample driving condition information is the corresponding relationship between the road condition type-the vehicle speed at different times-the unit mileage energy consumption. The unit energy consumption estimation model built according to the mapping relationship information can output the target unit mileage energy consumption according to the input target road condition type and target vehicle speed.

[0086] In one embodiment, according to the calculation strategy of the vehicle speed-time correspondence and the average acceleration, the average acceleration is calculated, and the vehicle speeds at multiple times are determined according to the vehicle speed-time correspondence, so as to determine multiple sample driving condition information according to the road condition type, the average acceleration and the vehicle speeds at multiple times, so as to achieve the determination of multiple different sample driving condition information according to a historical driving data, so as to facilitate the subsequent determination of the unit mileage energy consumption corresponding to each sample driving condition information, thereby achieving the determination of multiple different mapping relationship information according to a historical driving data, so as to achieve the rapid acquisition of a large amount of mapping relationship information to build a unit energy consumption estimation model, and improve the estimation ability of the unit mileage energy consumption of the unit energy consumption estimation model. In addition, the sample driving condition information obtained in this way mainly includes the road condition type, the vehicle speed at the time and the average acceleration. Therefore, the mapping relationship information obtained based on the sample driving condition information is the corresponding relationship of the road condition type-the vehicle speed at the time-the average acceleration-the unit mileage energy consumption. The unit energy consumption estimation model built according to the mapping relationship information can output the target unit mileage energy consumption according to the input target road condition type, vehicle speed and average acceleration.

[0087] In one embodiment, the average acceleration is calculated according to the speed-time correspondence and the calculation strategy of the average acceleration, and the driving state type is determined according to the average acceleration, and the vehicle speeds at multiple times are determined according to the speed-time correspondence, so as to determine multiple sample driving condition information according to the road condition type, the driving state type and the vehicle speeds at multiple times, so as to achieve the determination of multiple different sample driving condition information according to a historical driving data, so as to facilitate the subsequent determination of the unit mileage energy consumption corresponding to each sample driving condition information, thereby achieving the determination of multiple different mapping relationship information according to a historical driving data, so as to achieve the rapid acquisition of a large amount of mapping relationship information to build a unit energy consumption estimation model, and improve the estimation ability of the unit mileage energy consumption of the unit energy consumption estimation model. In addition, the sample driving condition information obtained in this way mainly includes the road condition type, the vehicle speed at the time and the driving state type, so that the mapping relationship information obtained based on the sample driving condition information is the corresponding relationship of the road condition type-the vehicle speed at the time-the driving state type-the unit mileage energy consumption, and the unit energy consumption estimation model built according to the mapping relationship information can output the target unit mileage energy consumption according to the input target road condition type, vehicle speed and driving state type.

[0088] In one embodiment, the average vehicle speed is determined based on the vehicle speed-time correspondence, and a sample driving condition information is determined based on the average vehicle speed and the road condition type, so that the most representative sample driving condition information can be determined based on historical driving data, so that the unit mileage energy consumption corresponding to the most representative sample driving condition information can be quickly determined with less computing power to obtain the most representative mapping relationship information. The unit energy consumption estimation model is built based on the most representative mapping relationship information under various road condition types, which has the advantages of high efficiency and low computing power consumption. The unit energy consumption estimation model built according to the mapping relationship information can output the target unit mileage energy consumption according to the input target road condition type and vehicle speed (such as average vehicle speed).

[0089] In one embodiment, the average vehicle speed is calculated according to the vehicle speed-time correspondence and the calculation formula of the average vehicle speed, and the average acceleration is calculated according to the calculation formula of the average vehicle speed and acceleration, so as to determine a sample driving condition information according to the road condition type, the average acceleration, and the average vehicle speed, so as to achieve the most representative sample driving condition information according to the historical driving data, so as to quickly determine the unit mileage energy consumption corresponding to the most representative sample driving condition information with less computing power, so as to obtain the most representative mapping relationship information. The unit energy consumption estimation model is constructed based on the most representative mapping relationship information under various road condition types, which has the advantages of high efficiency and low computing power occupation. The unit energy consumption estimation model constructed according to the mapping relationship information can output the target unit mileage energy consumption according to the input target road condition type, vehicle speed (such as average vehicle speed), and average acceleration.

[0090] In one embodiment, the average vehicle speed is calculated according to the vehicle speed-time correspondence and the calculation formula of the average vehicle speed, and the average acceleration is calculated according to the calculation formula of the average vehicle speed and acceleration, and the driving state type is determined according to the average acceleration, so as to determine a sample driving condition information according to the road condition type, the driving state type, and the average vehicle speed, so as to achieve the most representative sample driving condition information according to a historical driving data, so as to quickly determine the unit mileage energy consumption corresponding to the most representative sample driving condition information with less computing power, so as to obtain the most representative mapping relationship information. The unit energy consumption estimation model is constructed based on the most representative mapping relationship information under various road condition types, which has the advantages of high efficiency and low computing power occupation. The unit energy consumption estimation model constructed according to the mapping relationship information can output the target unit mileage energy consumption according to the input target road condition type, vehicle speed (such as average vehicle speed), and driving state type.

[0091] In one embodiment, the step of calculating the unit energy consumption according to the sample driving condition information to obtain the corresponding unit mileage energy consumption includes: calculating the unit energy consumption according to the driving condition characteristics and vehicle performance information in the sample driving condition information to obtain the corresponding unit mileage energy consumption. In this way, when determining the unit mileage energy consumption, the technical solution of this embodiment can not only fully consider the influence of driving behavior (such as acceleration), traffic road conditions and environmental conditions (such as road condition type, road slope) based on historical driving data, but also fully combine the performance of the vehicle itself. Therefore, the unit mileage energy consumption determined by the technical solution of this embodiment can be closer to the actual unit mileage energy consumption, and then the technical solution of this embodiment can improve the trust of users of new energy vehicles in the unit mileage energy consumption displayed in the vehicle and other related energy consumption data, thereby achieving the purpose of improving user experience.

[0092] In one embodiment, the driving condition characteristics include but are not limited to average acceleration, mileage and average vehicle speed / speed at any given moment, and the vehicle performance information includes but is not limited to vehicle mechanical parameters and energy conversion efficiency parameters.

[0093] In one embodiment, the step of calculating unit energy consumption according to the driving condition characteristics and vehicle performance information in the sample driving condition information to obtain the corresponding unit mileage energy consumption includes: calculating the driving force using the driving force calculation formula according to the average vehicle speed / momentary vehicle speed, the average acceleration and the vehicle mechanical parameters; calculating the driving energy consumption using the driving energy consumption calculation formula according to the driving force, the average vehicle speed / momentary vehicle speed and the energy conversion efficiency parameters; calculating the unit mileage energy consumption using the unit mileage energy consumption calculation formula according to the driving energy consumption and the mileage. In this way, when determining the unit mileage energy consumption, the technical solution of this embodiment can not only fully consider the influence of driving behavior (such as acceleration), traffic road environment conditions (such as road condition type, road slope) and the like according to historical driving data, but also can fully combine the vehicle mechanical parameters and energy conversion efficiency parameters. Therefore, the unit mileage energy consumption determined by the technical solution of this embodiment can be closer to the actual unit mileage energy consumption.

[0094] In one embodiment, the average vehicle speed is calculated as follows:

[0095] in, represents the average vehicle speed, represents the vehicle speed at a certain moment determined from the vehicle speed-time correspondence, Indicates the vehicle speed sampling duration; and / or, The acceleration is calculated as:

[0096] in, represents the average acceleration in the sample driving condition information, represents the vehicle speed at a certain moment determined from the vehicle speed-time correspondence, Indicates the vehicle speed sampling duration; and / or, The formula for calculating the driving force is:

[0097] in, Indicates driving force, Indicates average speed / speed at any given moment. Represents the average acceleration and vehicle mechanical parameters in the sample driving condition information: Indicates the vehicle's curb weight. is the rolling resistance coefficient, represents the air resistance coefficient, represents the windward area, represents the rotational mass conversion factor; and / or, The calculation formula of driving energy consumption is:

[0098] in, Indicates the drive energy consumption, Indicates average vehicle speed / speed at any given moment, energy conversion efficiency parameters: represents the driving efficiency, represents the motor efficiency, represents the battery efficiency; and / or, The formula for calculating energy consumption per unit mileage is:

[0099] in, Indicates the energy consumption per unit mileage, Indicates the drive energy consumption, Indicates the mileage in the sample driving condition information.

[0100] In one embodiment, the speed and acceleration of the vehicle will have a direct impact on the vehicle's energy consumption. Therefore, the technical solution of this embodiment enables the unit energy consumption estimation model to fully learn the change law of unit mileage energy consumption under different vehicle speeds and different acceleration conditions under various road conditions.

[0101] Step S12: constructing a model according to at least one mapping relationship information to obtain a unit energy consumption estimation model, where the unit energy consumption estimation model is used to output a corresponding target unit mileage energy consumption according to the target driving condition information.

[0102] In one embodiment, the unit energy consumption estimation model can be obtained by building a model based on a machine learning prediction model and at least one mapping relationship information. Optionally, the machine learning prediction model includes but is not limited to: decision tree: a tree diagram is used to represent data features and decision rules for classification and regression problems; support vector machine regression (SVR): a supervised learning technique for regression analysis that can predict continuous values; random forest: integrating multiple decision trees to improve prediction accuracy; neural network: simulating the way the human brain processes information, suitable for the prediction of complex data sets; ensemble learning: combining multiple learners to improve prediction performance, such as XGBoost, LightGBM, CatBoost, etc.

[0103] In one implementation, the unit energy consumption estimation model of this embodiment may also be a mapping diagram (MAP for short).

[0104] In one embodiment, step S12: constructing a model according to at least one mapping relationship information to obtain a unit energy consumption estimation model may include: constructing a model according to multiple mapping relationship information corresponding to the road condition type to obtain a mapping diagram associated with the road condition type. Through the technical solution of this embodiment, it is possible to obtain mapping diagrams associated with multiple road condition types.

[0105] A model building method provided in this embodiment includes: step S11: obtaining at least one mapping relationship information, the mapping relationship information characterizing the correspondence between sample driving condition information and unit mileage energy consumption, the sample driving condition information including the road condition type, and / or at least one driving condition feature under the road condition type; step S12: building a model according to at least one mapping relationship information to obtain a unit energy consumption estimation model, the unit energy consumption estimation model is used to output the corresponding target unit mileage energy consumption according to the target driving condition information. In this way, the technical solution of this embodiment can fully consider the impact of various driving condition information (such as road condition type and / or specific driving condition under the road condition type) on unit mileage energy consumption, and pre-associate accurate unit mileage energy consumption for various sample driving condition information to obtain one or more mapping relationship information, so that when building a model through one or more mapping relationship information, the unit mileage energy consumption law under different driving conditions is learned (for example, the unit mileage energy consumption law under specific driving conditions of different road condition types is learned, and / or the unit mileage energy consumption law under different specific driving conditions of the same road condition type is learned) to obtain a unit energy consumption estimation model, and then when determining the target driving condition information of the current driving section or the future driving section, the unit mileage energy consumption estimation model can be used to output a target unit mileage energy consumption that is close to the actual unit mileage energy consumption of the relevant real driving scenario for application. Therefore, the technical solution of this embodiment can support the estimation of energy consumption per unit mileage, so that the estimated energy consumption per unit mileage can be closer to the actual energy consumption per unit mileage, and further can enhance the trust of users of new energy vehicles in the energy consumption per unit mileage displayed in the vehicle and other related energy consumption data, thereby achieving the purpose of improving user experience.

[0106] In addition, the technical solution of this embodiment can be based on the vehicle's actual driving data and the road traffic condition information provided by the navigation map platform (online map), consider the different energy consumption performance of the vehicle under different road conditions or the energy consumption performance of different driving conditions under different road conditions, and establish a unit energy consumption estimation model that comprehensively considers multiple energy consumption influencing factors such as road grade and congestion level. By establishing a unit energy consumption estimation model, the unit mileage energy consumption can be estimated and output based on the input road condition type and / or the driving condition characteristics under a road condition type, so as to support the provision of more accurate and reliable energy consumption prediction services.

[0107] Based on the same inventive concept as the above technical solution, see Figure 3 The following example shows the construction scenario of the "speed-acceleration-energy consumption per unit mileage" MAP (i.e. the aforementioned unit energy consumption estimation model) associated with the road condition type: 1. Collect original data (i.e. the actual vehicle driving data mentioned above).

[0108] 2. Data preprocessing to deal with invalid fragments and outliers in the original data.

[0109] Optionally, driving data segments corresponding to driving conditions with a parking time greater than or equal to 150 seconds and driving data segments corresponding to driving conditions with a maximum climbing gradient greater than or equal to 10° in the original data are both determined to be invalid segments.

[0110] 3. The original data after data preprocessing is intercepted according to the road condition type requirements to obtain the first driving data of n types of road conditions.

[0111] Optionally, the road condition type can be determined based on road grade information and congestion grade information in the original data.

[0112] Optionally, the road grade information and congestion grade information in the original data may be provided in real time by the online map function of the navigation map platform during previous vehicle use.

[0113] 4. The first driving data of each road condition type is divided into short-trip types according to the driving state type requirements, so as to extract the second driving data corresponding to the accelerated driving state under one road condition type, the second driving data corresponding to the uniform speed driving state under one road condition type, and the second driving data corresponding to the decelerated driving state under one road condition type from each first driving data.

[0114] 5. According to each second driving data under each road condition type, a plurality of mapping relationship information is respectively obtained, and the mapping relationship information includes a corresponding relationship of road condition type-acceleration-speed-energy consumption per unit mileage.

[0115] Optionally, the energy consumption per mile in the mapping relationship information can fully consider the influence of driving behavior (such as acceleration), traffic environment conditions (such as road type, road slope), etc. when calculating, and can fully combine vehicle mechanical parameters and energy conversion efficiency parameters. Therefore, the error between the energy consumption per mile in the mapping relationship information and the energy consumption per mile is small.

[0116] 6. Based on the acquired mapping relationship information, sort and interpolate to associate a speed-acceleration-energy consumption per unit mileage MAP with each road condition type.

[0117] The method for constructing a "speed-acceleration-energy consumption per unit mileage" MAP associated with the road condition type exemplified in this embodiment can consider the energy consumption performance of the vehicle under different driving conditions under different road conditions based on the vehicle's actual driving data and the road traffic condition information provided by the navigation map platform (online map), and establish a "speed-acceleration-energy consumption per unit mileage" MAP that comprehensively considers multiple energy consumption influencing factors such as road grade and congestion level. The established "speed-acceleration-energy consumption per unit mileage" MAP can subsequently estimate and output the corresponding energy consumption per unit mileage based on the speed and acceleration under an input road condition type, so as to support the provision of more accurate and reliable energy consumption prediction services.

[0118] Second embodiment See also Figure 4 The second embodiment of the present application provides a method for determining mileage energy consumption, which can be executed by a computing device provided in the embodiment of the present application, and the computing device can be implemented in software and / or hardware. Optionally, the computing device in this embodiment is, for example, a vehicle-mounted terminal or a server.

[0119] This embodiment provides a method for determining mileage energy consumption, including (the following steps S21 to S22): Step S21: obtaining target driving condition information of a future driving section, wherein the target driving condition information includes a road condition type and / or at least one driving condition feature under the road condition type.

[0120] In one embodiment, the future driving section may represent a section of a road that the vehicle will travel on. Alternatively, the future driving section may be determined by an online map function of a navigation map platform.

[0121] In one embodiment, step S21: obtaining target driving condition information of a future driving section may include: determining navigation section data of at least one future driving section based on navigation route data of a navigation route fed back by a navigation map platform; determining target driving condition information of the future driving section based on the navigation section data of the future driving section.

[0122] In one embodiment, the navigation section data may represent vehicle-related data and road traffic condition information estimated by the navigation map platform when traveling on a section. In this way, the technical solution of this embodiment may determine the road condition type of the future driving section and / or at least one driving condition feature under the road condition type based on the navigation section data to obtain the target driving condition information of the future driving section.

[0123] Step S22: Determine the target unit mileage energy consumption corresponding to the future driving section according to the target driving condition information and a pre-built unit energy consumption estimation model, wherein the unit energy consumption estimation model is obtained by building a model based on mapping relationship information that characterizes the corresponding relationship between the sample driving condition information and the unit mileage energy consumption.

[0124] In one implementation, the specific method for building the unit energy consumption estimation model can refer to the model building method provided in the first implementation, which will not be repeated here.

[0125] In one implementation, after the step of determining the target energy consumption per unit mileage corresponding to the future driving section, the step may include: performing an application operation on the target energy consumption per unit mileage.

[0126] In one implementation, the application operation may represent various specific application methods for the target unit mileage energy consumption corresponding to the future driving section.

[0127] In one embodiment, the application operation includes but is not limited to at least one of the following: Display the target unit mileage energy consumption of the future driving section on the instrument panel; The cruising range is calculated based on the target unit mileage energy consumption of the future driving section to determine the cruising range, etc.

[0128] The technical solution of this embodiment can output a target unit mileage energy consumption close to the actual unit mileage energy consumption of the relevant real driving scene through the unit energy consumption estimation model when determining the target driving condition information of the future driving section for application. Therefore, the technical solution of this embodiment can support the estimation of unit mileage energy consumption through the unit energy consumption estimation model, so that the estimated unit mileage energy consumption can be closer to the actual unit mileage energy consumption, and further can enhance the trust of users of new energy vehicles in the unit mileage energy consumption displayed in the vehicle and other related energy consumption data, thereby achieving the purpose of improving user experience.

[0129] The technical solution of this embodiment obtains the target unit mileage energy consumption based on the target driving condition information and the unit energy consumption estimation model, and the error between the target unit mileage energy consumption and the actual unit mileage energy consumption is small. Therefore, the subsequent call of the target unit mileage energy consumption can achieve accurate prediction of the driving range and alleviate the user's "range anxiety". The technical solution of this embodiment obtains the target driving condition information of the future driving section through the data fed back by the online map function, so as to achieve the prediction of the unit mileage energy consumption of the vehicle's future working conditions, which is closer to the user's actual driving conditions, can help users plan their trips, and can also provide accurate prediction of the driving range, optimize energy management strategies, charging strategies and driving behaviors, etc. Based on the same inventive concept as the above embodiments, the present application embodiment provides a computing device, such as Figure 5As shown, the device includes: a processor 310 and a memory 311 storing a computer program; wherein, Figure 5 The processor 310 shown in the figure is not used to indicate that the number of the processor 310 is one, but is only used to indicate the positional relationship of the processor 310 relative to other devices. In actual applications, the number of the processor 310 may be one or more; similarly, Figure 5 The memory 311 shown in the figure has the same meaning, that is, it is only used to refer to the position relationship of the memory 311 relative to other devices. In practical applications, the number of memories 311 can be one or more. When the processor 310 runs the computer program, the model building method and / or the mileage energy consumption determination method applied to the above device are implemented.

[0130] The device may also include: at least one network interface 312. The various components in the device are coupled together via a bus system 313. It is understood that the bus system 313 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 313 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, Figure 5 Various buses are labeled as bus system 313.

[0131] The memory 311 may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. The non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); the magnetic surface memory may be a disk memory or a tape memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM, SyncLink Dynamic Random Access Memory), and direct RAMbus random access memory (DRRAM, Direct Rambus Random Access Memory).The memory 311 described in the embodiments of the present application is intended to include but is not limited to these and any other suitable types of memories.

[0132] The memory 311 in the embodiment of the present application is used to store various types of data to support the operation of the device. Examples of these data include: any computer program used to operate on the device, such as an operating system and an application program. Among them, the operating system includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and handle hardware-based tasks. The application program may include various applications, such as a media player (MediaPlayer), a browser (Browser), etc., for implementing various application services. Here, a program that implements the model building method and / or the method for determining mileage energy consumption of the embodiment of the present application may be included in the application.

[0133] Based on the same inventive concept as the above-mentioned embodiment, this embodiment further provides a computer-readable storage medium, in which a computer program is stored. The computer-readable storage medium may be a ferromagnetic random access memory (FRAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); it may also be various devices including one or any combination of the above memories, such as a mobile phone, a computer, a tablet device, a personal digital assistant, etc. When the computer program stored in the computer-readable storage medium is executed by the processor, the above-mentioned model building method and / or the method for determining the mileage energy consumption is implemented. The specific steps and processes implemented when the computer program is executed by the processor can be referred to. Figure 1 Description of the illustrated embodiments or references Figure 4 The description of the illustrated embodiment will not be repeated here.

[0134] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0135] In this document, the terms "comprises," "comprising," or any other variations thereof, are intended to cover a non-exclusive inclusion of elements other than those listed and may also include additional elements not expressly listed.

[0136] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A model building method, characterized in that: include: Acquire at least one mapping relationship information, wherein the mapping relationship information represents a corresponding relationship between sample driving condition information and unit mileage energy consumption, wherein the sample driving condition information includes a road condition type and / or at least one driving condition feature under the road condition type; A model is constructed according to at least one of the mapping relationship information to obtain a unit energy consumption estimation model, wherein the unit energy consumption estimation model is used to output a corresponding target unit mileage energy consumption according to the target driving condition information.

2. The method according to claim 1, characterized in that The step of obtaining at least one mapping relationship information includes: Determining at least one of the sample driving condition information according to the acquired historical driving data; Calculating unit energy consumption according to the sample driving condition information to obtain corresponding unit mileage energy consumption; At least one mapping relationship information is formed according to the energy consumption per unit mileage corresponding to at least one of the sample driving condition information.

3. The method according to claim 2, characterized in that The historical driving data includes the vehicle speed-time correspondence and the road condition type; The step of determining at least one of the sample driving condition information based on the acquired historical driving data comprises one of the following: Determine a plurality of vehicle speeds at a time according to the vehicle speed-time correspondence, and determine a plurality of sample driving condition information according to the plurality of vehicle speeds at a time and the corresponding road condition types, wherein the sample driving condition information includes the road condition type and the vehicle speed at a time; Determine an average vehicle speed according to the vehicle speed-time correspondence, and determine a sample driving condition information according to the average vehicle speed and the corresponding road condition type, wherein the sample driving condition information includes the road condition type and the average vehicle speed; Calculating the average vehicle speed according to the vehicle speed-time correspondence relationship and the calculation formula of the average vehicle speed, and calculating the average acceleration according to the calculation formula of the average vehicle speed and acceleration, so as to determine the sample driving condition information according to the road condition type, the average acceleration and the average vehicle speed, wherein the sample driving condition information includes the road condition type, the average vehicle speed and the average acceleration; According to the calculation strategy of the vehicle speed-time correspondence and the average acceleration, the average acceleration is calculated, and the vehicle speeds at multiple moments are determined according to the vehicle speed-time correspondence, so as to determine multiple sample driving condition information according to the road condition type, the average acceleration and the vehicle speeds at multiple moments, and the sample driving condition information includes the road condition type, the vehicle speed at the moment and the average acceleration.

4. The method according to claim 2, characterized in that: Before the step of determining at least one of the sample driving condition information according to the acquired historical driving data, the method includes: Collect real vehicle driving data; Performing data preprocessing and working condition classification processing on the actual vehicle driving data to obtain the historical driving data of at least one road condition type; The preprocessing strategy corresponding to the data preprocessing includes at least one of the following: Deleting driving data segments that meet the exclusion conditions in the actual vehicle driving data; Deleting duplicate values ​​from the actual vehicle driving data; Performing missing value supplementation processing on the actual vehicle driving data; Perform outlier repair processing on the actual vehicle driving data.

5. The method according to claim 4, characterized in that The driving data segments meeting the exclusion conditions include at least one of the following: The driving data segment corresponds to a driving condition in which the parking time is greater than or equal to the preset time; The driving data segment corresponds to a driving condition in which the maximum climbing gradient is greater than or equal to a preset gradient.

6. The method according to claim 2 or 3, characterized in that: The step of calculating the unit energy consumption according to the sample driving condition information to obtain the corresponding unit mileage energy consumption includes: The unit energy consumption is calculated according to the driving condition characteristics and vehicle performance information in the sample driving condition information to obtain the corresponding unit mileage energy consumption.

7. The method according to claim 6, characterized in that The driving condition characteristics include the average acceleration, mileage and the average vehicle speed / the vehicle speed at the moment, and the vehicle performance information includes vehicle mechanical parameters and energy conversion efficiency parameters; The step of calculating unit energy consumption according to the driving condition characteristics and vehicle performance information in the sample driving condition information to obtain the corresponding unit mileage energy consumption includes: Calculating the driving force using a driving force calculation formula according to the average vehicle speed / the vehicle speed at the moment, the average acceleration and the vehicle mechanical parameters; Calculating the driving energy consumption using a driving energy consumption calculation formula according to the driving force, the average vehicle speed / the vehicle speed at the moment and the energy conversion efficiency parameter; The energy consumption per unit mileage is calculated according to the driving energy consumption and the driving mileage using the calculation formula of the energy consumption per unit mileage.

8. The method according to claim 7, characterized in that The calculation formula of the average vehicle speed is: in, represents the average vehicle speed, represents the vehicle speed at a moment determined from the vehicle speed-time correspondence, Indicates the vehicle speed sampling duration; and / or, The calculation formula of the acceleration is: in, represents the average acceleration in the sample driving condition information, represents the vehicle speed at a moment determined from the vehicle speed-time correspondence, Indicates the vehicle speed sampling duration; and / or, The driving force is calculated as follows: in, represents the driving force, represents the average vehicle speed / the vehicle speed at the moment, represents the average acceleration in the sample driving condition information, and the vehicle mechanical parameters: Indicates the vehicle's curb weight. is the rolling resistance coefficient, represents the air resistance coefficient, represents the windward area, represents the rotational mass conversion factor; and / or, The calculation formula of the driving energy consumption is: in, represents the driving energy consumption, Represents the average vehicle speed / the vehicle speed at the moment, the energy conversion efficiency parameter: represents the driving efficiency, represents the motor efficiency, represents the battery efficiency; and / or, The calculation formula of the energy consumption per unit mileage is: in, represents the energy consumption per unit mileage, represents the driving energy consumption, Indicates the mileage in the sample driving condition information.

9. A method for determining mileage energy consumption, characterized in that: include: Acquiring target driving condition information of a future driving section, wherein the target driving condition information includes a road condition type and / or at least one driving condition feature under the road condition type; According to the target driving condition information and a pre-built unit energy consumption estimation model, the target unit mileage energy consumption corresponding to the future driving section is determined. The unit energy consumption estimation model is obtained by building a model based on mapping relationship information that characterizes the corresponding relationship between sample driving condition information and unit mileage energy consumption.

10. A computing device, characterized in that include: A processor and a memory storing a computer program, when the processor runs the computer program, the steps of the model building method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a processor, the steps of the model building method according to any one of claims 1 to 8 are implemented.

12. A computing device, characterized in that: include: A processor and a memory storing a computer program, when the processor runs the computer program, the steps of the method for determining the mileage energy consumption described in claim 9 are implemented.

13. A computer-readable storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a processor, the steps of the method for determining mileage energy consumption according to claim 9 are implemented.

Images