High energy consumption attribution method, device, equipment and readable storage medium

Abstract

The application discloses a high-energy-consumption attribution method, device and equipment and a readable storage medium, and relates to the technical field of computers. The high-energy-consumption attribution method comprises the following steps: obtaining specified running data of a target vehicle and a high-energy-consumption identification model, wherein the high-energy-consumption identification model is a model constructed based on historical driving data corresponding to the vehicle type of the target vehicle; inputting the specified running data into the high-energy-consumption identification model to obtain high-energy-consumption running data in the specified running data; obtaining a target high-energy-consumption scene, wherein the target high-energy-consumption scene comprises each preset high-energy-consumption reason corresponding to the vehicle type of the target vehicle; and matching the high-energy-consumption running data with high-energy-consumption indexes corresponding to each preset high-energy-consumption reason to obtain high-energy-consumption attribution of the target vehicle. The application improves the universality of high-energy-consumption attribution of vehicles.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer technology, and particularly relates to a high energy consumption attribution method, device, equipment and readable storage medium. BACKGROUND

[0002] Vehicle energy consumption is an important performance indicator of a vehicle, and manufacturers and users pay special attention to it. Vehicle energy consumption (fuel and electrical energy consumption) is not only an important optimization project of a vehicle, but also can directly feedback whether the use of the vehicle is abnormal when the vehicle energy consumption abnormally changes.

[0003] Compared with identifying a high energy consumption vehicle, manufacturers and users pay more attention to identifying the reason for high energy consumption. However, most of the energy consumption attribution currently adopts expert experience, and after identifying a high energy consumption vehicle, an experienced expert analyzes the vehicle operation and operating conditions to obtain the reason for high energy consumption. Therefore, the existing high energy consumption attribution method has the problem of poor universality. SUMMARY

[0004] The main purpose of the present application is to provide a high energy consumption attribution method, which aims to solve the technical problem of poor universality of the existing high energy consumption attribution method using the expert manual analysis method.

[0005] To achieve the above purpose, in a first aspect, the present application provides a high energy consumption attribution method, which comprises:

[0006] obtaining specified operation data of a target vehicle and a high energy consumption identification model, wherein the high energy consumption identification model is a model constructed based on historical driving data corresponding to the vehicle type of the target vehicle;

[0007] inputting the specified operation data into the high energy consumption identification model to obtain high energy consumption operation data in the specified operation data;

[0008] obtaining a target high energy consumption scene, wherein the target high energy consumption scene comprises each preset high energy consumption reason corresponding to the vehicle type of the target vehicle;

[0009] matching the high energy consumption operation data with high energy consumption indicators corresponding to each preset high energy consumption reason to obtain high energy consumption attribution of the target vehicle.

[0010] According to the first aspect, before the step of obtaining the target high energy consumption scene, it comprises:

[0011] obtaining historical driving data corresponding to each preset vehicle type, and according to each operating condition of the preset vehicle type, splitting the historical driving data into operating condition driving data of each operating condition;

[0012] The driving condition driving data of each of the operation conditions is aggregated according to a preset aggregation period to obtain driving condition driving features of each of the operation conditions;

[0013] The driving condition driving features are input into the high energy consumption identification model to obtain energy consumption state results of the driving condition driving features;

[0014] According to the driving condition driving features and the corresponding energy consumption state results, high energy consumption indexes of each of the preset high energy consumption reasons under each of the operation conditions are determined;

[0015] The high energy consumption indexes of each of the preset high energy consumption reasons under each of the operation conditions are used as target high energy consumption scenarios corresponding to the preset vehicle type.

[0016] According to the first aspect or any one of the implementation manners of the first aspect, the step of determining, according to the driving condition driving features and the corresponding energy consumption state results, the high energy consumption indexes of each of the preset high energy consumption reasons under each of the operation conditions comprises:

[0017] According to the driving condition driving features and the energy consumption state results, each high energy consumption driving feature in the driving condition driving features is screened out;

[0018] According to each of the high energy consumption driving features and each preset correlation feature function, a historical running feature value of a correlation running feature of each of the preset high energy consumption reasons is calculated;

[0019] According to the historical running feature value, a high energy consumption feature threshold of each of the correlation running features is determined, and the high energy consumption feature threshold of each of the correlation running features is used as the high energy consumption index of each of the preset high energy consumption reasons.

[0020] According to the first aspect or any one of the implementation manners of the first aspect, the step of matching the high energy consumption running data with the high energy consumption indexes corresponding to each of the preset high energy consumption reasons to obtain the high energy consumption attribution of the target vehicle comprises:

[0021] According to the high energy consumption running data and each preset correlation feature function, a specified correlation running feature of the high energy consumption running data is calculated;

[0022] The specified correlation running feature is matched with the high energy consumption indexes of each of the preset high energy consumption reasons to obtain a preset high energy consumption reason corresponding to a matched high energy consumption index as the high energy consumption attribution of the target vehicle.

[0023] According to the first aspect, or any one of the implementations of the first aspect, the specified associated running features include specified feature values of the associated running features, the high energy consumption indicators include high energy consumption feature thresholds of the associated running features, and the step of matching the specified associated running features with the high energy consumption indicators of each of the preset high energy consumption reasons to obtain a preset high energy consumption reason corresponding to a matched high energy consumption indicator as the high energy consumption attribution of the target vehicle includes:

[0024] sequentially judging whether each specified feature value in the specified associated running features exceeds a high energy consumption feature threshold in the corresponding high energy consumption indicator according to a preset attribution order;

[0025] if the specified feature value exceeds the high energy consumption feature threshold in the corresponding high energy consumption indicator, determining that the high energy consumption indicator is the matched associated indicator corresponding to the specified feature value;

[0026] if the specified feature value does not exceed the high energy consumption feature threshold, determining that the high energy consumption indicator is not the matched associated indicator corresponding to the specified feature value;

[0027] obtaining the preset high energy consumption reason corresponding to each matched associated indicator as the high energy consumption attribution of the target vehicle.

[0028] According to the first aspect, or any one of the implementations of the first aspect, after the step of matching the high energy consumption running data with the high energy consumption indicators corresponding to each of the preset high energy consumption reasons to obtain the high energy consumption attribution of the target vehicle, the method further includes:

[0029] obtaining actual energy consumption values and normal energy consumption reference values of each of the running conditions in the high energy consumption running data;

[0030] obtaining total energy consumption that can be saved of each of the running conditions in the high energy consumption running data according to the actual energy consumption values and the normal energy consumption reference values.

[0031] According to the first aspect, or any one of the implementations of the first aspect, after the step of matching the high energy consumption running data with the high energy consumption indicators corresponding to each of the preset high energy consumption reasons to obtain the high energy consumption attribution of the target vehicle, the method further includes:

[0032] obtaining high energy consumption running features and normal energy consumption running data corresponding to the high energy consumption attribution in the high energy consumption running data;

[0033] updating the normal energy consumption running data according to the high energy consumption running features to obtain differential running data of the high energy consumption attribution;

[0034] input the differential operation data into a preset energy consumption prediction model to obtain a predicted energy consumption value of the differential operation data;

[0035] According to the predicted energy consumption value of the differential operation data and the normal energy consumption reference value, a saveable energy value of the high energy consumption attribution is calculated.

[0036] In a second aspect, the present application provides a high energy consumption attribution device, comprising:

[0037] A first obtaining module is configured to obtain specified operation data of a target vehicle and a high energy consumption identification model, wherein the high energy consumption identification model is a model constructed based on historical driving data corresponding to a vehicle type of the target vehicle;

[0038] An identification module is configured to input the specified operation data into the high energy consumption identification model to obtain high energy consumption operation data in the specified operation data;

[0039] A second obtaining module is configured to obtain a target high energy consumption scene, wherein the target high energy consumption scene comprises each preset high energy consumption reason corresponding to the vehicle type of the target vehicle;

[0040] A matching module is configured to match the high energy consumption operation data with high energy consumption indicators corresponding to each preset high energy consumption reason to obtain high energy consumption attribution of the target vehicle.

[0041] According to the second aspect, the high energy consumption attribution device further comprises a scene construction module configured to:

[0042] Obtain historical driving data corresponding to each preset vehicle type, and split the historical driving data into work condition driving data of each operation condition according to each operation condition of the preset vehicle type;

[0043] Aggregate the work condition driving data of each operation condition according to a preset aggregation period respectively to obtain work condition driving features of each operation condition;

[0044] Input each work condition driving feature into the high energy consumption identification model to obtain an energy consumption state result of each work condition driving feature;

[0045] Determine high energy consumption indicators of each preset high energy consumption reason under each operation condition according to each work condition driving feature and the corresponding energy consumption state result;

[0046] Take the high energy consumption indicators of each preset high energy consumption reason under each operation condition as a target high energy consumption scene corresponding to the preset vehicle type.

[0047] According to the second aspect, or any one of the implementation manners of the second aspect, the scene construction module is further configured to:

[0048] According to the driving characteristics and the energy consumption state results, high energy consumption driving characteristics are screened out from the driving characteristics;

[0049] According to the high energy consumption driving characteristics and preset correlation characteristic functions, historical running characteristic values of the correlation running characteristics of preset high energy consumption reasons are calculated;

[0050] According to the historical running characteristic values, high energy consumption characteristic thresholds of the correlation running characteristics are determined, and the high energy consumption characteristic thresholds of the correlation running characteristics are taken as high energy consumption indexes of the preset high energy consumption reasons.

[0051] According to the second aspect, or any one of the implementation manners of the second aspect, the matching module is further configured to:

[0052] According to the high energy consumption running data and the preset correlation characteristic functions, the specified correlation running characteristics of the high energy consumption running data are calculated;

[0053] The specified correlation running characteristics are matched with the high energy consumption indexes of the preset high energy consumption reasons, and a preset high energy consumption reason corresponding to a matched high energy consumption index is taken as the high energy consumption attribution of the target vehicle.

[0054] According to the second aspect, or any one of the implementation manners of the second aspect, the specified correlation running characteristics include specified characteristic values of the correlation running characteristics, and the high energy consumption indexes include high energy consumption characteristic thresholds of the correlation running characteristics, and the matching module is further configured to:

[0055] According to a preset attribution order, whether each specified characteristic value in the specified correlation running characteristics exceeds a high energy consumption characteristic threshold in a corresponding high energy consumption index is judged in sequence;

[0056] If the specified characteristic value exceeds the high energy consumption characteristic threshold in the corresponding high energy consumption index, the high energy consumption index is determined as a matching correlation index corresponding to the specified characteristic value;

[0057] If the specified characteristic value does not exceed the high energy consumption characteristic threshold, the high energy consumption index is determined as not being the matching correlation index corresponding to the specified characteristic value;

[0058] Preset high energy consumption reasons corresponding to each matching correlation index are taken as the high energy consumption attribution of the target vehicle.

[0059] According to the second aspect, or any one of the implementation manners of the second aspect, the high energy consumption attribution device further includes an energy consumption quantification module configured to:

[0060] obtain actual energy consumption values of each of the operation conditions in the high energy consumption operation data and normal energy consumption benchmark values;

[0061] obtain total energy saving values of each of the operation conditions in the high energy consumption operation data according to the actual energy consumption values and the normal energy consumption benchmark values.

[0062] According to the second aspect, or any one of the possible implementation manners of the second aspect, the energy consumption quantification module is further configured to:

[0063] obtain high energy consumption operation characteristics corresponding to the high energy consumption attribution in the high energy consumption operation data and normal energy consumption operation data;

[0064] update the normal energy consumption operation data according to the high energy consumption operation characteristics, and obtain differentiated operation data of the high energy consumption attribution;

[0065] input the differentiated operation data into a preset energy consumption prediction model, and obtain a predicted energy consumption value of the differentiated operation data;

[0066] calculate the energy saving value of the high energy consumption attribution according to the predicted energy consumption value of the differentiated operation data and the normal energy consumption benchmark values.

[0067] In a third aspect, the present application provides a high energy consumption attribution device, which comprises a memory and a processor, and the memory stores a computer program which can be run on the processor, and the computer program is configured to implement the steps of the high energy consumption attribution method.

[0068] The third aspect and any one of the possible implementation manners of the third aspect correspond to the first aspect and any one of the possible implementation manners of the first aspect respectively. For details, refer to the technical effects of the first aspect and any one of the possible implementation manners of the first aspect, which will not be described here again.

[0069] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the processor executes the high energy consumption attribution method according to the first aspect or any one of the possible implementation manners of the first aspect.

[0070] The fourth aspect and any one of the possible implementation manners of the fourth aspect correspond to the first aspect and any one of the possible implementation manners of the first aspect respectively. For details, refer to the technical effects of the first aspect and any one of the possible implementation manners of the first aspect, which will not be described here again.

[0071] In a fifth aspect, an embodiment of the present application provides a computer program, which comprises instructions for performing the high energy consumption attribution method in the first aspect and any possible implementation manner of the first aspect.

[0072] The fifth aspect and any possible implementation manner of the fifth aspect correspond to the first aspect and any possible implementation manner of the first aspect respectively. For details, refer to the technical effects of the first aspect and any possible implementation manner of the first aspect, which will not be repeated here.

[0073] The present application provides a high energy consumption attribution method, device, equipment and readable storage medium, by acquiring the specified running data of the target vehicle and the high energy consumption identification model, wherein the high energy consumption identification model is a model constructed based on the historical driving data corresponding to the vehicle type of the target vehicle. Since the high energy consumption identification model is a model corresponding to the vehicle type of the target vehicle, the influence of factors such as the design logic, operation law and attenuation law of different vehicle types can be avoided, and the accuracy of the output result of the high energy consumption identification model is further improved. The specified running data is input into the high energy consumption identification model to obtain high energy consumption running data in the specified running data. The target high energy consumption scene is acquired, wherein the target high energy consumption scene includes each preset high energy consumption reason corresponding to the vehicle type of the target vehicle. Therefore, by matching the high energy consumption running data with the high energy consumption indicators of each preset high energy consumption reason, the high energy consumption indicators that the high energy consumption running data meets can be determined, and the preset high energy consumption reason corresponding to the matched high energy consumption indicators can be used as the high energy consumption attribution of the target vehicle. The present application identifies the high energy consumption running data of the target vehicle with the high energy consumption identification model corresponding to the vehicle type of the target vehicle, and then matches the high energy consumption running data with the high energy consumption indicators of each preset high energy consumption reason, so that the high energy consumption of the target vehicle can be attributed, and the high energy consumption attribution of the target vehicle is obtained. Compared with the prior art, the present application reduces the dependence on expert experience to a certain extent, effectively improves the universality of high energy consumption attribution, and is more easily used in a large range and in batches. BRIEF DESCRIPTION OF DRAWINGS

[0074] Figure 1 The flowchart of the first embodiment of the high energy consumption attribution method of the present application is shown.

[0075] Figure 2 The flowchart of the second embodiment of the high energy consumption attribution method of the present application is shown.

[0076] Figure 3 The distribution diagram of the associated running characteristics involved in the embodiment of the present application is shown.

[0077] Figure 4 Flowchart of the third embodiment of the high energy consumption attribution method of the present application;

[0078] Figure 5 Schematic diagram of the total energy consumption that can be saved under the normal driving condition involved in the embodiment of the present application;

[0079] Figure 6 First schematic diagram of the energy saving value of the high energy consumption attribution involved in the embodiment of the present application;

[0080] Figure 7 Second schematic diagram of the energy saving value of the high energy consumption attribution involved in the embodiment of the present application

[0081] Figure 8 Structural schematic diagram of the high energy consumption attribution device of the present application;

[0082] Figure 9 Device structural schematic diagram of the hardware running environment involved in the embodiment of the present application.

[0083] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0084] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.

[0085] The term “and / or” in the present application is only used to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can mean that there are three cases of A alone, A and B together, and B alone.

[0086] The terms “first” and “second” and the like in the specification and claims of the present application are used to distinguish different objects, and are not used to describe the specific order of the objects. For example, the first target object and the second target object are used to distinguish different target objects, and are not used to describe the specific order of the target objects.

[0087] In the embodiments of the present application, the words “exemplary” or “for example” are used to mean serving as an example, instance, or illustration. Any embodiment or design scheme described as “exemplary” or “for example” in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design schemes. Rather, the words “exemplary” or “for example” are used to present the relevant concept in a specific manner.

[0088] It is to be understood that the specific embodiments described herein are merely illustrative of the present application and should not be used to limit the present application in any manner.

[0089] Reference will now be made to the drawings, wherein Figure 1 , Figure 1 is a flowchart of a first embodiment of the high energy consumption attribution method of the present application. It should be noted that although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be performed in an order different from that shown herein.

[0090] The first embodiment of the present application provides a high energy consumption attribution method, which comprises the following steps:

[0091] Step S100, obtaining specified running data of a target vehicle and a high energy consumption identification model, wherein the high energy consumption identification model is a model constructed based on historical driving data corresponding to a vehicle type of the target vehicle;

[0092] In the present embodiment, it should be noted that the specified running data is driving data for which the target vehicle expects to be attributed to high energy consumption, which can be real-time driving data of the target vehicle or driving data within a specified time period. The specified running data can include vehicle speed, driving motor speed, driving motor torque, ambient temperature, driving motor controller temperature, driving motor temperature, state of charge, power battery current, power battery voltage, power battery temperature, altitude, and other detection values of vehicle running characteristics representing vehicle running state.

[0093] In addition, it should be noted that the vehicle type can be the power type of the vehicle, such as pure electric vehicles, range-extended vehicles, gasoline vehicles (vehicles using gasoline as fuel), diesel vehicles (vehicles using diesel as fuel), methanol vehicles (vehicles using methanol as fuel), and vehicles using different power. Further, the vehicle type can be further divided into small passenger cars, medium passenger cars, large passenger cars, light trucks, medium trucks, heavy trucks, and other vehicles with different purposes and sizes. For example, the vehicle type can be a range-extended vehicle or a range-extended small passenger car.

[0094] In addition, it also needs to be explained that the high energy consumption recognition model is a model constructed based on historical driving data corresponding to the vehicle type of the target vehicle. Since there are differences in the operating conditions possessed by vehicles of different vehicle types, the sub-recognition models corresponding to the operating conditions in the high energy consumption recognition models of different vehicle types are also different. For example, the high energy consumption recognition model can include a first sub-recognition model for high energy consumption recognition of normal driving data in normal driving conditions, a second sub-recognition model for high energy consumption recognition of energy recovery data in energy recovery conditions, and a third sub-recognition model for high energy consumption recognition of idle condition data in idle conditions. The high energy consumption recognition model can be a machine learning algorithm model or a neural network model. As an example, historical driving data corresponding to each preset vehicle type can be obtained; then according to each operating condition of the target vehicle, the historical driving data is divided into historical normal driving data, historical energy recovery data and historical idle condition data; the historical normal driving data, the historical energy recovery data and the historical idle condition data are aggregated according to a preset aggregation period, to obtain historical normal driving features, historical energy recovery features and historical idle condition features corresponding to each preset vehicle type; the historical normal driving features, the historical energy recovery features and the historical idle condition features are input into each preset initial model for training, to obtain high energy consumption recognition models corresponding to each preset vehicle type.

[0095] In step S200, the specified operating data is input into the high energy consumption recognition model to obtain high energy consumption operating data in the specified operating data.

[0096] As an example, the embodiment can obtain each specified operating feature corresponding to the specified operating data by feature extraction on the specified operating data. Then each specified operating feature is input into the high energy consumption recognition model to output the recognition result of each specified operating feature. The specified operating feature with the recognition result of high energy consumption state is taken as the high energy consumption operating data in the specified operating data. In addition, in order to ensure the accuracy of the output result of the high energy consumption recognition, the specified operating data can also be data cleaned before feature extraction. As an example, the data cleaning can include the following processes: eliminating abnormal data, such as eliminating abnormal data records with vehicle speed greater than 200km / h, negative vehicle speed, driving motor speed less than -500rpm or greater than 5000rpm, negative SOC, etc.; selecting data of vehicle driving process (i.e. data with vehicle state marker in driving state) from the specified driving data after eliminating abnormal data, to obtain the specified driving data after data cleaning. In addition, the data cleaning can also include deleting original data with less daily data amount or less mileage.

[0097] As another example, since the energy consumption of the vehicle is greatly different under different operating conditions, in order to further improve the identification accuracy of the high energy consumption operating data, the specified operating data can be split into normal driving data of a normal driving condition, energy recovery data of an energy recovery condition, and idling condition data of an idling condition according to each operating condition of the target vehicle. Then, the normal driving data, the energy recovery data and the idling condition data are respectively aggregated according to a preset aggregation period to obtain each normal driving feature of the normal driving condition, each energy recovery feature of the energy recovery condition, and each idling condition of the idling condition. The high energy consumption identification model can include a sub-identification model corresponding to each operating condition. Thus, each normal driving feature, each energy recovery feature and each idling condition feature can be input into the corresponding sub-identification model in the high energy consumption identification model to identify the high energy consumption data in the specified operating data under each operating condition, so as to take the high energy consumption data under each operating condition as the high energy consumption operating data.

[0098] In step S300, a target high energy consumption scenario is obtained, wherein the target high energy consumption scenario includes each preset high energy consumption reason corresponding to the vehicle type of the target vehicle.

[0099] In this embodiment, it should be noted that the target high energy consumption scenario can include each preset high energy consumption reason, each preset high energy consumption reason has a corresponding high energy consumption index, and the target high energy consumption scenario is determined according to the historical driving data of the vehicle type of the target vehicle. The preset high energy consumption reason is a reason that can cause high energy consumption of the vehicle. For example, the preset high energy consumption reason can include high energy consumption reasons such as sudden acceleration pedal, deep acceleration pedal, sudden brake pedal, deep brake pedal, large pedal stroke fluctuation under low speed condition, vehicle overload, energy recovery process pedal, frequent start-stop, and other bad driving behaviors, high energy consumption reasons such as climbing state and high-low temperature state, and high energy consumption reasons such as vehicle itself abnormality, such as motor high load work, motor controller continuous high current, poor air intake control, coolant temperature too high, cold start driving, engine fluctuation too large. It can be understood that the preset high energy consumption reason can only exist in part of the above high energy consumption reasons due to the difference in vehicle type. For example, a pure electric vehicle does not have an engine, so it will not have high energy consumption reasons such as poor air intake control, coolant temperature too high, and engine fluctuation too large. The fuel vehicle does not have a generator and an energy recovery mechanism, so it will not have high energy consumption reasons such as motor high load work, motor controller continuous high current, and energy recovery process pedal.

[0100] Exemplarily, historical driving data corresponding to each preset vehicle type can be acquired, and the historical driving data is split into working condition driving data of each working condition according to each working condition of the preset vehicle type; the working condition driving data of each working condition is aggregated according to a preset aggregation period respectively to obtain working condition driving features of each working condition; and the working condition driving features are input into the high energy consumption identification model to obtain energy consumption state results of each working condition driving feature. Then, high energy consumption indexes of each preset high energy consumption reason under each working condition can be determined according to each working condition driving feature and the corresponding energy consumption state result. The high energy consumption indexes can include high energy consumption feature thresholds of each associated running feature. For example, the preset high energy consumption reason is rapid acceleration pedal, and the associated running feature in the corresponding high energy consumption index is the acceleration pedal change value. Then, the first acceleration pedal change value under the normal energy consumption state and the second acceleration pedal change value under the high energy consumption state are determined through the acceleration pedal change value in the working condition driving feature and the corresponding energy consumption state result, so as to generate the high energy consumption feature threshold corresponding to the acceleration pedal change value according to the first acceleration pedal change value and the second acceleration pedal change value, which is used to determine whether the acceleration pedal change value will cause the energy consumption state result to be in the high energy consumption state. Exemplarily, the high energy consumption feature threshold corresponding to the acceleration pedal change value can be the high quantile (such as 90 quantile, 95 quantile) of the first acceleration pedal change value, the low quantile (such as 10 quantile, 20 quantile) of the second acceleration pedal change value, or the average value between the maximum value of the first acceleration pedal change value and the minimum value of the second acceleration pedal change value. Further, the high energy consumption indexes of each preset high energy consumption reason under each working condition can be used as the target high energy consumption scene corresponding to the preset vehicle type.

[0101] In step S400, the high energy consumption running data is matched with the high energy consumption indexes corresponding to each preset high energy consumption reason to obtain the high energy consumption attribution of the target vehicle.

[0102] In this embodiment, it should be noted that the high energy consumption indexes of the preset high energy consumption reason include high energy consumption feature thresholds of each associated running feature. The associated running feature is a vehicle running feature associated with the preset high energy consumption reason, such as vehicle speed, acceleration pedal change value, acceleration pedal average value, brake pedal change value, brake pedal average value, vehicle load coefficient, vehicle climbing height, environmental temperature, motor temperature, motor controller temperature, number of start-stop times per unit time, air-fuel ratio, coolant temperature, engine speed, etc. The high energy consumption feature threshold is a value that can cause the associated running feature to be in a high energy consumption state.

[0103] The embodiment can determine the high energy consumption index matched with the high energy consumption running data, and the preset high energy consumption reason corresponding to the high energy consumption index matched with the high energy consumption running data is the reason causing the high energy consumption of the target vehicle. The preset high energy consumption reason corresponding to the high energy consumption index matched with the high energy consumption running data can be taken as the high energy consumption attribution of the target vehicle. It can be understood that the high energy consumption attribution can include at least one preset high energy consumption reason.

[0104] In the step S400, the high energy consumption running data is matched with the high energy consumption index corresponding to each preset high energy consumption reason to obtain the high energy consumption attribution of the target vehicle, and the step includes:

[0105] In the step S410, the specified correlation running feature of the high energy consumption running data is calculated according to the high energy consumption running data and each preset correlation feature function.

[0106] In the step S420, the specified correlation running feature is matched with the high energy consumption index of each preset high energy consumption reason to obtain the high energy consumption attribution of the target vehicle.

[0107] In the embodiment, it is necessary to note that the preset correlation feature function is a function for calculating the correlation running feature. Since the data recorded in the high energy consumption running data is usually original detection data, the specified correlation running feature corresponding to the high energy consumption running data can be calculated by the preset correlation feature function, and compared with the high energy consumption index of each preset high energy consumption reason. The specified correlation running feature is a specified feature value corresponding to each correlation running feature corresponding to the high energy consumption running data. It can be understood that the feature value can be the average value, extreme value, median, etc. of each correlation running feature.

[0108] The embodiment calculates the specified correlation running feature of the high energy consumption running data according to the high energy consumption running data and each preset correlation feature function. The specified correlation running feature can include the specified feature value of each correlation running feature. Then, the specified feature value in the specified correlation running feature is compared with the high energy consumption feature threshold in the high energy consumption index of each preset high energy consumption reason based on each correlation running feature, so that the preset high energy consumption reason corresponding to the specified feature value exceeding the corresponding high energy consumption feature threshold is taken as the high energy consumption attribution of the target vehicle.

[0109] The specified associated running features include specified feature values of the associated running features, the high energy consumption indicators include high energy consumption feature thresholds of the associated running features, and the step of matching the specified associated running features with the high energy consumption indicators of each of the preset high energy consumption reasons to obtain the high energy consumption attribution of the target vehicle includes:

[0110] In step S421, whether each specified feature value in the specified associated running features exceeds a high energy consumption feature threshold in the corresponding high energy consumption indicator is determined according to a preset attribution order.

[0111] In step S422, if the specified feature value exceeds the high energy consumption feature threshold in the corresponding high energy consumption indicator, the high energy consumption indicator is determined as the matching associated indicator corresponding to the specified feature value.

[0112] In step S423, if the specified feature value does not exceed the corresponding high energy consumption feature threshold, the high energy consumption indicator is determined as not being the matching associated indicator corresponding to the specified feature value.

[0113] In step S424, each preset high energy consumption reason corresponding to the matching associated indicator is taken as the high energy consumption attribution of the target vehicle.

[0114] In this embodiment, it should be noted that the preset attribution order is to pre-set the possibility of the impact of each of the preset high energy consumption reasons on energy consumption. For example, each of the preset high energy consumption reasons can be divided into three categories: bad driving behavior, bad driving environment, and vehicle abnormality. The bad driving behavior and the bad driving environment are common reasons for high energy consumption. The preset attribution order can be bad driving behavior, bad driving environment, and vehicle abnormality in turn, so as to quickly identify the cause of the high energy consumption of the target vehicle.

[0115] As an example, the specified feature value in the specified associated running feature can be sequentially judged according to a preset attribution order, whether the specified feature value exceeds a high energy consumption feature threshold in the corresponding high energy consumption indicator; if the specified feature value exceeds the high energy consumption feature threshold in the corresponding high energy consumption indicator, it indicates that the abnormal energy consumption driving data meets the high energy consumption feature threshold, and the preset high energy consumption reason corresponding to the high energy consumption indicator is one of the reasons for high energy consumption of the target vehicle, so it is determined that the high energy consumption indicator is the matching associated indicator corresponding to the specified feature value. If the specified feature value does not exceed the high energy consumption feature threshold corresponding to the high energy consumption indicator, it indicates that the abnormal energy consumption driving data does not meet the high energy consumption feature threshold, and the preset high energy consumption reason corresponding to the high energy consumption indicator is not the reason for high energy consumption of the target vehicle, so it is determined that the high energy consumption indicator is not the matching associated indicator corresponding to the specified feature value. The preset high energy consumption reason corresponding to each matching associated indicator is taken as the high energy consumption attribution of the target vehicle.

[0116] In the first embodiment of the present application, the specified running data of the target vehicle and the high energy consumption identification model are obtained, wherein the high energy consumption identification model is a model constructed based on the historical driving data corresponding to the vehicle type of the target vehicle. Since the high energy consumption identification model is a model corresponding to the vehicle type of the target vehicle, the influence of factors such as design logic, running law, and attenuation law of different vehicle types can be avoided, and the accuracy of the output result of the high energy consumption identification model is further improved. The specified running data is input into the high energy consumption identification model to obtain high energy consumption running data in the specified running data. The target high energy consumption scene is obtained, wherein the target high energy consumption scene includes each preset high energy consumption reason corresponding to the vehicle type of the target vehicle. Thus, by matching the high energy consumption running data with the high energy consumption indicators of each preset high energy consumption reason, the high energy consumption indicators that the high energy consumption running data meets can be determined, and the preset high energy consumption reason corresponding to the matching high energy consumption indicator can be taken as the high energy consumption attribution of the target vehicle. In this embodiment, the high energy consumption running data of the target vehicle in the high energy consumption condition is identified by the high energy consumption identification model corresponding to the vehicle type of the target vehicle, and then the high energy consumption running data is matched with the high energy consumption indicators of each preset high energy consumption reason, so that the high energy consumption condition of the target vehicle can be attributed, and the high energy consumption attribution of the target vehicle is obtained. Compared with the prior art, the present application reduces the dependence on expert experience to some extent, effectively improves the universality of high energy consumption attribution, and is more easily used in a large range and in batches.

[0117] Reference Figure 2 , Figure 2 The flowchart of the second embodiment of the high energy consumption attribution method of the present application is shown.

[0118] The second embodiment of the present application provides a high energy consumption attribution method, before the step of obtaining a target high energy consumption scene in step S300, comprising:

[0119] Step A10, obtaining historical driving data corresponding to each preset vehicle type, and splitting the historical driving data into operating condition driving data of each operating condition according to each operating condition of the preset vehicle type;

[0120] Step A20, aggregating the operating condition driving data of each operating condition according to a preset aggregation period respectively to obtain operating condition driving features of each operating condition;

[0121] Step A30, inputting each operating condition driving feature into the high energy consumption identification model to obtain a power consumption state result of each operating condition driving feature;

[0122] Step A40, determining high energy consumption indexes of each preset high energy consumption reason under each operating condition according to each operating condition driving feature and the corresponding power consumption state result;

[0123] Step A50, taking the high energy consumption indexes of each preset high energy consumption reason under each operating condition as the target high energy consumption scene corresponding to the preset vehicle type.

[0124] It should be noted that the operating conditions of the target vehicle can include normal driving condition, energy recovery condition and idle condition. In the case of the target vehicle being a vehicle with normal driving condition, energy recovery condition and idle condition (such as a pure electric vehicle, a range extended vehicle, etc.), the specified operating data can be divided into normal driving data of normal driving condition, energy recovery data of energy recovery condition and idle condition data of idle condition according to the operating conditions of the target vehicle. For example, the splitting rule for splitting the specified operating data is as follows: a. the data in the specified operating data with vehicle speed equal to 0 and total current greater than 0 is divided into idle condition data; b. the data in the specified operating data with vehicle speed greater than 0 and motor current greater than 0 is divided into normal driving data; c. the data in the specified operating data with vehicle speed greater than 0 and motor current less than 0 is divided into energy recovery data. In order to meet the user's demand for data granularity, reduce the error caused by instantaneous sampling or avoid data interruption, the original data in the specified operating data can be aggregated. By aggregating the normal driving data, the energy recovery data and the idle condition data according to the preset aggregation period, the normal driving features of the normal driving condition, the energy recovery features of the energy recovery condition and the idle condition features of the idle condition are obtained; each normal driving feature, each energy recovery feature and each idle condition feature are used as the vehicle condition feature of each operating condition of the target vehicle. The preset aggregation period can be selected according to the user's demand for data granularity, such as 30 seconds, 1 minute, 5 minutes, etc.

[0125] Further, the driving characteristics of each of the working conditions can be input into the high energy consumption identification model to obtain the power consumption state results of the driving characteristics of each of the working conditions. According to the driving characteristics of each of the working conditions and the corresponding power consumption state results, the power consumption state results are determined as the first historical operating characteristic values of each of the associated operating characteristics in the normal energy consumption state, and the power consumption state results are determined as the second historical operating characteristic values of each of the associated operating characteristics in the high energy consumption state. Then, according to the first historical operating characteristic values and the second historical operating characteristic values, the high energy consumption characteristic thresholds corresponding to each of the associated operating characteristics are generated. Exemplarily, the high energy consumption characteristic threshold corresponding to the associated operating characteristic can adopt a high quantile (such as a 90th quantile, a 95th quantile) of the first historical operating characteristic value, a low quantile (such as a 10th quantile, a 20th quantile) of the second historical operating characteristic value, or an average value between a maximum value of the first historical operating characteristic value and a minimum value of the second historical operating characteristic value. Thus, the high energy consumption characteristic thresholds corresponding to each of the associated operating characteristics serve as high energy consumption indicators to obtain the high energy consumption indicators of each of the preset high energy consumption reasons in each of the operating conditions. The high energy consumption indicators of each of the preset high energy consumption reasons in each of the operating conditions serve as the target high energy consumption scenarios corresponding to the preset vehicle type.

[0126] In step A40, the step of determining the high energy consumption indicators of each of the preset high energy consumption reasons in each of the operating conditions according to the driving characteristics of each of the working conditions and the corresponding power consumption state results comprises:

[0127] In step B10, according to the driving characteristics of each of the working conditions and the power consumption state results, each high power consumption driving characteristic in the driving characteristics of each of the working conditions is screened out.

[0128] In step B20, according to each of the high power consumption driving characteristics and each of the preset associated characteristic functions, the historical operating characteristic values of the associated operating characteristics of each of the preset high energy consumption reasons are calculated.

[0129] In step B30, according to the historical operating characteristic values, the high energy consumption characteristic thresholds of each of the associated operating characteristics are determined, and the high energy consumption characteristic thresholds of each of the associated operating characteristics serve as the high energy consumption indicators of each of the preset high energy consumption reasons.

[0130] According to the driving characteristics of each working condition and the power consumption state result, each high-power consumption driving characteristic (i.e., the working condition driving characteristic with the high-energy consumption state result) in the driving characteristics of each working condition can be screened out. According to each high-power consumption driving characteristic and each preset correlation characteristic function, the historical running characteristic value of each preset high-energy consumption reason correlation running characteristic is calculated. The historical running characteristic value is the characteristic value corresponding to the high-power consumption driving characteristic, i.e., the historical characteristic value of the correlation running characteristic in the high-energy consumption state. Then, according to the historical running characteristic value, the high-energy consumption characteristic threshold of each correlation running characteristic is determined, and the high-energy consumption characteristic threshold of each correlation running characteristic is taken as the high-energy consumption index of each preset high-energy consumption reason. The high-energy consumption characteristic threshold can be a minimum value, a low quantile (such as a 10th quantile or a 20th quantile), or the like.

[0131] With reference to Figure 3 , Figure 3 is a distribution diagram of a correlation running characteristic involved in the embodiment of the application. In the diagram, the correlation running characteristic is an accelerator pedal mean value, the dark gray points represent accelerator pedal mean values less than the corresponding high-energy consumption characteristic threshold (such as 70 mm), and the light gray points represent accelerator pedal mean values greater than the corresponding high-energy consumption characteristic threshold (such as 70 mm), i.e., the high-energy consumption index is deep accelerator pedal pressing. In the diagram, the horizontal axis is the vehicle speed, and the vertical axis is the energy consumption value. As can be seen from the diagram, the light gray points (deep accelerator pedal pressing) generate more energy consumption.

[0132] In the second embodiment of the application, the historical driving data corresponding to each preset vehicle type is obtained, and the historical driving data is split into working condition driving data of each running working condition according to each running working condition of the preset vehicle type; the working condition driving data of each running working condition is aggregated according to a preset aggregation period to obtain working condition driving characteristics of each running working condition; each working condition driving characteristic is input into the high-energy consumption identification model to obtain a power consumption state result of each working condition driving characteristic; the high-energy consumption index of each preset high-energy consumption reason in each running working condition is determined according to each working condition driving characteristic and the corresponding power consumption state result; and the high-energy consumption index of each preset high-energy consumption reason in each running working condition is taken as the target high-energy consumption scene corresponding to the preset vehicle type. Thus, in the embodiment, the high-energy consumption scene in different vehicle types and different running working conditions is constructed based on the historical driving data corresponding to each preset vehicle type, thereby improving the matching accuracy between the high-energy consumption scene and the high-energy consumption running data, more accurately identifying the preset high-energy consumption reason in the high-energy consumption running data, and further improving the accuracy of high-energy consumption attribution of the target vehicle.

[0133] With reference to Figure 4 , Figure 4A flowchart of a third embodiment of the high energy consumption attribution method.

[0134] The third embodiment of the present application provides a high energy consumption attribution method, after the step of matching the high energy consumption operation data with the high energy consumption indicators corresponding to each of the preset high energy consumption reasons in step S400, obtaining the high energy consumption attribution of the target vehicle, the method further comprises:

[0135] Step C10, obtaining the actual energy consumption value under each of the operation conditions in the high energy consumption operation data and the normal energy consumption reference value.

[0136] Step C20, obtaining the total energy saving of the high energy consumption operation data under each of the operation conditions according to the actual energy consumption value and the normal energy consumption reference value.

[0137] In this embodiment, it should be noted that the normal energy consumption reference value can be the average energy consumption value of the corresponding vehicle type of the target vehicle under the same operating state (such as the same vehicle speed) as the high energy consumption operation data, or a theoretical energy consumption value obtained based on the high energy consumption operation data through a preset normal energy consumption prediction model.

[0138] In this embodiment, the actual energy consumption value under each of the operation conditions in the high energy consumption operation data and the normal energy consumption reference value are obtained. Thus, the energy consumption difference between the actual energy consumption value under each of the operation conditions and the corresponding normal energy consumption reference value can be used as the total energy saving under each of the operation conditions. Of course, the energy consumption difference can also be based on a preset correction coefficient (such as 0.9, 1.1, etc.) to obtain a corrected energy consumption difference as the total energy saving. For reference Figure 5 , Figure 5 A schematic diagram of the total energy saving under normal driving conditions involved in the embodiment of the present application.

[0139] In this embodiment, the actual energy consumption value under each of the operation conditions in the high energy consumption operation data and the normal energy consumption reference value are obtained, and then the total energy saving of the high energy consumption operation data under each of the operation conditions is obtained according to the actual energy consumption value and the normal energy consumption reference value. In this embodiment, each of the operation conditions is distinguished, so that the total energy saving of the high energy consumption operation data of the target vehicle under different operation conditions is identified, which helps the user to understand the impact of the high energy consumption attribution on energy consumption of the target vehicle under different conditions.

[0140] After the step of matching the high energy consumption operation data with the high energy consumption indicators corresponding to each of the preset high energy consumption reasons in step S400, obtaining the high energy consumption attribution of the target vehicle, the method further comprises:

[0141] Step D10, obtaining high energy consumption running features corresponding to the high energy consumption attribution in the high energy consumption running data and normal energy consumption running data;

[0142] Step D20, updating the normal energy consumption running data according to the high energy consumption running features to obtain differentiated running data of the high energy consumption attribution;

[0143] Step D30, inputting the differentiated running data into a preset energy consumption prediction model to obtain a predicted energy consumption value of the differentiated running data;

[0144] Step D40, calculating a savable energy value of the high energy consumption attribution according to the predicted energy consumption value of the differentiated running data and the normal energy consumption benchmark value.

[0145] In this embodiment, it should be noted that the preset energy consumption prediction model is a model for predicting an energy consumption value corresponding to vehicle running data, and the preset energy consumption prediction model can be a machine learning algorithm model or a neural network model. The normal energy consumption running data can be vehicle driving data of a vehicle of the same vehicle type as the target vehicle under the same running state (such as the same vehicle speed) and with a normal energy consumption state as the result of the energy consumption state.

[0146] In this embodiment, the high energy consumption running features corresponding to the high energy consumption attribution in the high energy consumption running data and the normal energy consumption running data are obtained. The high energy consumption running features include associated running features corresponding to each preset high energy consumption reason in the high energy consumption attribution. Then, the vehicle running features corresponding to the high energy consumption running features in the normal energy consumption running data are replaced, so that the normal energy consumption running data is updated according to the high energy consumption running features to obtain differentiated running data of the high energy consumption attribution. It can be understood that the differentiated running data is data in which the vehicle running features corresponding to the high energy consumption running features in the normal energy consumption running data are replaced. The differentiated running data is input into a preset energy consumption prediction model to obtain a predicted energy consumption value of the differentiated running data. Thus, the high energy consumption running features corresponding to each preset high energy consumption reason in the high energy consumption attribution are taken as variables to predict energy consumption. Thus, the predicted energy consumption value in the case where the high energy consumption running features corresponding to each preset high energy consumption reason exist is obtained. Then, the savable energy value of each preset high energy consumption reason in the high energy consumption attribution is calculated according to the difference between the predicted energy consumption value of the differentiated running data and the normal energy consumption benchmark value. Thus, this embodiment more accurately quantifies the influence of each preset high energy consumption reason in the high energy consumption attribution on energy consumption, which helps users understand the influence degree of each preset high energy consumption reason in the high energy consumption attribution on energy consumption. See Figure 6 and Figure 7 , Figure 6A first schematic diagram of the energy-saving values of the high energy consumption attributions involved in the embodiment of the present application, Figure 7 A second schematic diagram of the energy-saving values of the high energy consumption attributions involved in the embodiment of the present application. The energy-saving values of different high energy consumption attributions can be represented in the form of tables or images.

[0147] In the third embodiment of the present application, the actual energy consumption values of each operating condition in the high energy consumption operation data are obtained, and the normal energy consumption reference values are obtained, and then the total energy-saving values of the high energy consumption operation data in each operating condition are obtained according to the actual energy consumption values and the normal energy consumption reference values. In this embodiment, the total energy-saving values of the high energy consumption operation data of the target vehicle in different operating conditions are identified by distinguishing each operating condition, which helps the user to understand the influence of the high energy consumption attributions on the energy consumption of the target vehicle in different operating conditions. Furthermore, the energy-saving values of each preset high energy consumption reason in the high energy consumption attributions can be further subdivided and quantified.

[0148] Referring to Figure 8 , Figure 8 A structural schematic diagram of the high energy consumption attribution device of the present application.

[0149] The present application also provides a high energy consumption attribution device, which comprises:

[0150] A first obtaining module 10 is configured to obtain specified operation data of a target vehicle and a high energy consumption identification model, wherein the high energy consumption identification model is a model constructed based on historical driving data corresponding to the vehicle type of the target vehicle;

[0151] An identification module 20 is configured to input the specified operation data into the high energy consumption identification model to obtain high energy consumption operation data in the specified operation data.

[0152] A second obtaining module 30 is configured to obtain a target high energy consumption scene, wherein the target high energy consumption scene comprises each preset high energy consumption reason corresponding to the vehicle type of the target vehicle.

[0153] A matching module 40 is configured to match the high energy consumption operation data with high energy consumption indicators corresponding to each preset high energy consumption reason to obtain high energy consumption attributions of the target vehicle.

[0154] Optionally, the high energy consumption attribution device further comprises a scene construction module configured to:

[0155] Obtain historical driving data corresponding to each preset vehicle type, and split the historical driving data into operating condition driving data of each operating condition according to the operating conditions of the preset vehicle type.

[0156] aggregating the driving data of each of the driving conditions according to a preset aggregation period to obtain driving condition characteristics of each of the driving conditions;

[0157] inputting the driving condition characteristics into the high energy consumption identification model to obtain energy consumption state results of the driving condition characteristics;

[0158] determining high energy consumption indexes of each of the preset high energy consumption reasons under each of the driving conditions according to the driving condition characteristics and the corresponding energy consumption state results;

[0159] taking the high energy consumption indexes of each of the preset high energy consumption reasons under each of the driving conditions as target high energy consumption scenarios corresponding to the preset vehicle type.

[0160] Optionally, the scenario construction module is further configured to:

[0161] screening each high energy consumption driving characteristic from the driving condition characteristics according to the driving condition characteristics and the energy consumption state results;

[0162] calculating historical running characteristic values of the associated running characteristics of each of the preset high energy consumption reasons according to each of the high energy consumption driving characteristics and each of the preset associated characteristic functions;

[0163] determining high energy consumption characteristic thresholds of each of the associated running characteristics according to the historical running characteristic values, and taking the high energy consumption characteristic thresholds of each of the associated running characteristics as the high energy consumption indexes of each of the preset high energy consumption reasons.

[0164] Optionally, the matching module 40 is further configured to:

[0165] calculating specified associated running characteristics of the high energy consumption running data according to the high energy consumption running data and each of the preset associated characteristic functions;

[0166] matching the specified associated running characteristics with the high energy consumption indexes of each of the preset high energy consumption reasons to obtain a preset high energy consumption reason corresponding to a matched high energy consumption index as the high energy consumption attribution of the target vehicle.

[0167] Optionally, the specified associated running characteristics include specified characteristic values of each of the associated running characteristics, and the high energy consumption indexes include high energy consumption characteristic thresholds of each of the associated running characteristics, and the matching module 40 is further configured to:

[0168] judging whether each of the specified characteristic values in the specified associated running characteristics exceeds a high energy consumption characteristic threshold in the corresponding high energy consumption index in a preset attribution order;

[0169] if the specified characteristic value exceeds the high energy consumption characteristic threshold in the corresponding high energy consumption index, determining that the high energy consumption index is a matching associated index corresponding to the specified characteristic value.

[0170] if the specified feature value does not exceed the corresponding high-energy-consumption feature threshold, determining that the high-energy-consumption indicator is not the matching correlation indicator corresponding to the specified feature value;

[0171] taking the preset high-energy-consumption reason corresponding to each matching correlation indicator as the high-energy-consumption attribution of the target vehicle.

[0172] Optionally, the high-energy-consumption attribution device further comprises an energy consumption quantification module, configured to:

[0173] obtain actual energy consumption values and normal energy consumption reference values in each running condition in the high-energy-consumption running data;

[0174] obtain total energy saving values of the high-energy-consumption running data in each running condition according to the actual energy consumption values and the normal energy consumption reference values.

[0175] Optionally, the energy consumption quantification module is further configured to:

[0176] obtain high-energy-consumption running features corresponding to the high-energy-consumption attribution and normal energy consumption running data in the high-energy-consumption running data;

[0177] update the normal energy consumption running data according to the high-energy-consumption running features, and obtain differentiated running data of the high-energy-consumption attribution;

[0178] input the differentiated running data into a preset energy consumption prediction model, and obtain a predicted energy consumption value of the differentiated running data;

[0179] calculate the energy saving value of the high-energy-consumption attribution according to the predicted energy consumption value of the differentiated running data and the normal energy consumption reference value.

[0180] As shown in FIG. 1, Figure 9 FIG. 1 is a device structure schematic diagram of a hardware running environment involved in an embodiment of the present application. Figure 9

[0181] Specifically, the high-energy-consumption attribution device can be a VCU (Vehicle Control Unit, vehicle controller), a PC (Personal Computer, personal computer), a tablet computer, a portable computer, a server or the like.

[0182] As shown in FIG. 2, Figure 9 ​As shown, the high energy consumption attribution device can include a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize the connection communication between these components. The user interface 1003 can include a display, an input unit such as a keyboard, and can also include a standard wired interface, a wireless interface. The network interface 1004 can optionally include a standard wired interface, a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 1005 can be a high-speed random access memory (RAM) memory, or a stable non-volatile memory (NVM) such as a disk memory. The memory 1005 can also be a storage device independent of the aforementioned processor 1001.

[0183] Those skilled in the art can understand that Figure 9 The device structure shown in the foregoing embodiments does not constitute a limitation on the high energy consumption attribution device, and can include more or fewer components than those shown, or combine certain components, or different component arrangements.

[0184] As Figure 9 As shown, the memory 1005 as a computer storage medium can include an operating system, a network communication module, a user interface module, and a high energy consumption attribution application.

[0185] In Figure 9 In the device shown, the network interface 1004 is mainly used to connect to a background server and communicate data with the background server; the user interface 1003 is mainly used to connect to a client and communicate data with the client; and the processor 1001 can be used to call the high energy consumption attribution program stored in the memory 1005 to realize the operations in the high energy consumption attribution method provided in the foregoing embodiments.

[0186] In addition, the embodiment of the present application also proposes a vehicle, and the vehicle includes the high energy consumption attribution device described above. Of course, it can be understood that the vehicle also includes an energy storage device, a driving device, and other devices that ensure the normal operation of the vehicle.

[0187] In addition, the embodiment of the present application also proposes a computer storage medium, and the computer storage medium stores a computer program. When the processor executes the computer program, the operations in the high energy consumption attribution method provided in the foregoing embodiments are realized, and the specific steps will not be described here.

[0188] It should be noted that, in the present document, the terms such as first and second, etc. are used only to distinguish one entity / operation / element from another entity / operation / element, and do not necessarily require or imply any such actual relationship or order between such entities / operations / elements; the terms "comprising", "containing" or any other variant thereof are intended to cover a non-exclusive inclusion, such that a process, method, article or system including a list of elements does not necessarily include only those elements recited, but can include other elements not expressly listed or inherent to such process, method, article or system. Without more limitations, an element defined by the phrase "comprising a" does not exclude the presence of additional identical elements in the process, method, article or system including the element.

[0189] For the device embodiments, since they are basically similar to the method embodiments, they are described more simply, and the relevant parts are referred to the part of the description of the method embodiments. The above-described device embodiments are only illustrative, and the units described as separate components can or can not be physically separated. Part or all of the modules can be selected according to actual needs to achieve the purpose of the present application scheme. Those skilled in the art can understand and implement without creative labor.

[0190] The above-mentioned serial numbers of the embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0191] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be realized by means of software and the necessary general hardware platform, of course, they can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a plurality of instructions for making a terminal device (which can be a mobile phone, computer, server, vehicle, or network device, etc.) execute the methods described in various embodiments of the present application.

[0192] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent flow transformation made by using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A high energy consumption attribution method, characterized in that, The high energy consumption attribution method comprises the following steps: obtaining specified running data of a target vehicle and a high energy consumption identification model, wherein the high energy consumption identification model is a model constructed based on historical driving data corresponding to a vehicle type of the target vehicle; inputting the specified running data into the high energy consumption identification model to obtain high energy consumption running data in the specified running data; obtaining a target high energy consumption scene, wherein the target high energy consumption scene comprises each preset high energy consumption reason corresponding to the vehicle type of the target vehicle; matching the high energy consumption running data with high energy consumption indicators corresponding to each preset high energy consumption reason to obtain high energy consumption attribution of the target vehicle; before the step of obtaining the target high energy consumption scene, comprising: obtaining historical driving data corresponding to each preset vehicle type, and splitting the historical driving data into work condition driving data of each running condition according to each running condition of the preset vehicle type; aggregating the work condition driving data of each running condition according to a preset aggregation period to obtain work condition driving features of each running condition; inputting each work condition driving feature into the high energy consumption identification model to obtain energy consumption state results of each work condition driving feature; screening each high energy consumption driving feature in each work condition driving feature according to each work condition driving feature and the energy consumption state results; calculating historical running feature values of associated running features of each preset high energy consumption reason according to each high energy consumption driving feature and each preset associated feature function; determining high energy consumption feature thresholds of each associated running feature according to the historical running feature values, and taking the high energy consumption feature thresholds of each associated running feature as high energy consumption indicators of each preset high energy consumption reason; taking the high energy consumption indicators of each preset high energy consumption reason under each running condition as a target high energy consumption scene corresponding to the preset vehicle type.

2. The high energy expenditure attribution method of claim 1, wherein, The step of matching the high energy consumption running data with high energy consumption indicators corresponding to each preset high energy consumption reason to obtain high energy consumption attribution of the target vehicle comprises: calculating specified associated running features of the high energy consumption running data according to the high energy consumption running data and each preset associated feature function; matching the specified associated running features with high energy consumption indicators of each preset high energy consumption reason to obtain a preset high energy consumption reason corresponding to a matched high energy consumption indicator as the high energy consumption attribution of the target vehicle.

3. The high energy expenditure attribution method of claim 2, wherein, The specified associated running features comprise specified feature values of each associated running feature, the high energy consumption indicators comprise high energy consumption feature thresholds of each associated running feature, and the step of matching the specified associated running features with high energy consumption indicators of each preset high energy consumption reason to obtain a preset high energy consumption reason corresponding to a matched high energy consumption indicator as the high energy consumption attribution of the target vehicle comprises: sequentially judging whether each specified feature value in the specified associated running features exceeds a high energy consumption feature threshold in a corresponding high energy consumption indicator according to a preset attribution order; if the specified feature value exceeds the high energy consumption feature threshold in the corresponding high energy consumption indicator, determining that the high energy consumption indicator is a matched associated indicator corresponding to the specified feature value. if the specified feature value does not exceed the corresponding high-energy-consumption feature threshold, determining that the high-energy-consumption indicator is not the matching correlation indicator corresponding to the specified feature value; taking the preset high-energy-consumption reasons corresponding to the matching correlation indicators as the high-energy-consumption attribution of the target vehicle.

4. The high energy consumption attribution method of any one of claims 1 to 3, wherein, After the step of matching the high-energy-consumption running data with the high-energy-consumption indicators corresponding to the preset high-energy-consumption reasons to obtain the high-energy-consumption attribution of the target vehicle, the method further comprises: obtaining actual energy consumption values and normal energy consumption reference values in each running condition in the high-energy-consumption running data; obtaining total energy saving values of the high-energy-consumption running data in each running condition according to the actual energy consumption values and the normal energy consumption reference values.

5. The high energy consumption attribution method of claim 4, wherein, After the step of matching the high-energy-consumption running data with the high-energy-consumption indicators corresponding to the preset high-energy-consumption reasons to obtain the high-energy-consumption attribution of the target vehicle, the method further comprises: obtaining high-energy-consumption running features and normal energy consumption running data corresponding to the high-energy-consumption attribution in the high-energy-consumption running data; updating the normal energy consumption running data according to the high-energy-consumption running features to obtain differential running data of the high-energy-consumption attribution; inputting the differential running data into a preset energy consumption prediction model to obtain a predicted energy consumption value of the differential running data; calculating a savable energy value of the high-energy-consumption attribution according to the predicted energy consumption value of the differential running data and the normal energy consumption reference value.

6. A high energy consumption attribution apparatus characterized by, The high-energy-consumption attribution device comprises: a first obtaining module configured to obtain specified running data of a target vehicle and a high-energy-consumption identification model, wherein the high-energy-consumption identification model is a model constructed based on historical driving data corresponding to a vehicle type of the target vehicle; an identification module configured to input the specified running data into the high-energy-consumption identification model to obtain high-energy-consumption running data in the specified running data; a second obtaining module configured to obtain a target high-energy-consumption scenario, wherein the target high-energy-consumption scenario comprises preset high-energy-consumption reasons corresponding to the vehicle type of the target vehicle; a matching module configured to match the high-energy-consumption running data with high-energy-consumption indicators corresponding to the preset high-energy-consumption reasons to obtain a high-energy-consumption attribution of the target vehicle. The scene construction module is configured to obtain historical driving data corresponding to each preset vehicle type, split the historical driving data into working condition driving data of each working condition according to each working condition of the preset vehicle type, aggregate the working condition driving data of each working condition according to a preset aggregation period to obtain working condition driving features of each working condition, input the working condition driving features into the high-energy consumption identification model to obtain energy consumption state results of the working condition driving features, screen out each high-energy consumption driving feature in the working condition driving features according to the working condition driving features and the energy consumption state results, calculate historical running feature values of associated running features of each preset high-energy consumption reason according to each high-energy consumption driving feature and each preset associated feature function, determine high-energy consumption feature thresholds of each associated running feature according to the historical running feature values, and take the high-energy consumption feature thresholds of each associated running feature as high-energy consumption indexes of each preset high-energy consumption reason, and take the high-energy consumption indexes of each preset high-energy consumption reason in each working condition as target high-energy consumption scenes corresponding to the preset vehicle type.

7. A high energy consumption attribution device, characterized by, The high-energy consumption attribution device comprises a memory and a processor, the memory stores a computer program capable of running on the processor, and the computer program implements the steps of the high-energy consumption attribution method according to any one of claims 1 to 5 when executed by the processor.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a high-energy consumption attribution program, and the high-energy consumption attribution program implements the steps of the high-energy consumption attribution method according to any one of claims 1 to 5 when executed by the processor.

Images