CN116278771A

CN116278771A - Vehicle energy consumption prediction method, system and equipment

Info

Publication number: CN116278771A
Application number: CN202310282623.1A
Authority: CN
Inventors: 曹宾; 邵晓伟; 胡兴航
Original assignee: Avatr Technology Chongqing Co Ltd
Current assignee: Avatr Technology Chongqing Co Ltd
Priority date: 2023-03-21
Filing date: 2023-03-21
Publication date: 2023-06-23

Abstract

The invention relates to the technical field of automobiles, and discloses a vehicle energy consumption prediction method, a vehicle energy consumption prediction system and vehicle energy consumption prediction equipment, wherein the method comprises the following steps: obtaining route information, vehicle position information and average energy consumption information of a vehicle, predicting and recording energy consumption of the vehicle on an energy consumption calibration road section according to the obtained information and an initial energy consumption prediction model, obtaining first energy consumption information and actual energy consumption information, if the difference value between the first energy consumption information and the actual energy consumption information is larger than a preset threshold value, iteratively updating parameters of the initial energy consumption prediction model according to the difference value until a target energy consumption prediction model meeting preset conditions is obtained, predicting energy consumption of the road section to be driven according to the target energy consumption prediction model, obtaining second energy consumption information, and generating energy consumption prompt information according to the second energy consumption information. By applying the technical scheme of the invention, the energy consumption of the pure electric vehicle can be predicted and updated, and the problem that the predicted energy consumption of the predicted vehicle is greatly different from the actual energy consumption is avoided.

Description

Vehicle energy consumption prediction method, system and equipment

Technical Field

The application relates to the technical field of automobiles, in particular to a vehicle energy consumption prediction method, a vehicle energy consumption prediction system and vehicle energy consumption prediction equipment.

Background

The electric vehicle, especially the pure electric vehicle, the power source is electric power, but is limited by the electric power storage capacity of the power battery, compared with an automobile using fossil energy, the pure electric vehicle is shorter in endurance mileage, and in order to avoid the vehicle anchoring, a user can continuously pay attention to the endurance mileage of the vehicle in the driving process. The range of the vehicle is calculated by comprehensively calculating the residual energy condition and the energy consumption condition of the vehicle, so that the prediction of the range of the vehicle can be also regarded as the prediction of the energy consumption of the vehicle.

In order to facilitate the user to obtain the energy consumption of the vehicle, most electric vehicles have corresponding functional modules set in the body for prediction, for example: the prediction of the vehicle energy consumption is carried out through the average energy consumption and the driving mileage in the previous time period; alternatively, the energy consumption of the vehicle in a route ahead is predicted by the navigation system.

However, there are many factors affecting the energy consumption of the vehicle, for example: driving behavior habits, road effects, weather effects, vehicle effects, etc., and some factors such as driving behavior habits, etc., may not be effectively analyzed by the vehicle, thereby affecting the result of energy consumption prediction. Therefore, the energy consumption is predicted only through the historical energy consumption or road conditions, so that great difference exists between the obtained predicted energy consumption and the actual energy consumption, and further the predicted endurance mileage obtained by the user is not accurate enough, and the driving experience of the user is affected.

Disclosure of Invention

The application provides a vehicle energy consumption prediction method, a vehicle energy consumption prediction system and vehicle energy consumption prediction equipment, and aims to solve the problem that the difference between predicted vehicle energy consumption and actual energy consumption is large.

According to a first aspect of an embodiment of the present invention, there is provided a vehicle energy consumption prediction method, including:

acquiring route information, vehicle position information and average energy consumption information of the vehicle; the route information comprises a road section to be driven and a plurality of energy consumption calibration road sections; predicting the energy consumption of the vehicle on the energy consumption calibration road section according to an initial energy consumption prediction model and the average energy consumption information to obtain first energy consumption information; determining actual energy consumption information of the vehicle when the vehicle runs in the energy consumption calibration road section according to the energy consumption calibration road section and the vehicle position information; if the difference value between the first energy consumption information and the actual energy consumption information is larger than a preset threshold value, iteratively updating parameters of the initial energy consumption prediction model according to the difference value until a target energy consumption prediction model meeting preset conditions is obtained; predicting the energy consumption of the road section to be driven in the route information according to the target energy consumption prediction model to obtain second energy consumption information; and generating energy consumption prompt information according to the second energy consumption information.

In an optional manner, the initial energy consumption prediction model includes at least one of a weather sub-model, a road condition sub-model, a vehicle weight sub-model, a gradient sub-model and a driving habit sub-model, and before the predicting the energy consumption of the vehicle in the energy consumption calibration section according to the initial energy consumption prediction model and the average energy consumption information, the method further includes at least one of:

determining weather information according to the vehicle position information and inputting the weather information into the weather sub-model; determining road condition information according to the route information and inputting the road condition information into the road condition sub-model; determining the vehicle weight information according to the identification information of the vehicle and inputting the vehicle weight information into the vehicle weight sub-model; determining gradient information according to gradient signals acquired by a sensor of the vehicle and inputting the gradient information into the gradient sub-model; and determining the driving habit type of the driver according to the change rate of the opening of the accelerator pedal and the change rate of the acceleration of the vehicle, and inputting the driving habit type into the driving habit sub-model.

In an alternative manner, the determining the driving habit type of the driver according to the change rate of the accelerator opening degree and the change rate of the acceleration of the vehicle includes: if the change rate of the opening of the accelerator pedal is larger than the preset opening change rate, or if the change rate of the acceleration of the vehicle within the preset time period is larger than the preset acceleration change rate, determining that the driving habit type of the driver is a first driving habit type; and if the change rate of the opening of the accelerator pedal is smaller than the preset opening change rate, or if the change rate of the acceleration of the vehicle within the preset time period is smaller than the preset acceleration change rate, determining that the driving habit type of the driver is a second driving habit type.

In an optional manner, predicting the energy consumption of the vehicle in the energy consumption calibration section according to the initial energy consumption prediction model and the average energy consumption information to obtain first energy consumption information, including:

determining a first additional energy consumption corresponding to the weather information according to the weather information and the weather sub-model; determining a second additional energy consumption corresponding to the road condition information according to the road condition information and the road condition sub-model; determining a third additional energy consumption corresponding to the vehicle weight information according to the vehicle weight information and the vehicle weight sub-model; determining fourth additional energy consumption corresponding to the gradient information according to the gradient information and the gradient sub-model; determining a fifth additional energy consumption corresponding to the driving habit type according to the driving habit type and the driving habit sub-model; and determining the first energy consumption information according to the average energy consumption information and at least one of the first additional energy consumption, the second additional energy consumption, the third additional energy consumption, the fourth additional energy consumption and the fifth additional energy consumption.

In an optional manner, the parameters of the initial energy consumption prediction model include at least one of a first energy consumption coefficient corresponding to the weather sub-model, a second energy consumption coefficient corresponding to the road condition sub-model, a third energy consumption coefficient corresponding to the vehicle weight sub-model, a fourth energy consumption coefficient corresponding to the gradient sub-model, and a fifth energy consumption coefficient corresponding to the driving habit sub-model, and the iteratively updating the parameters of the initial energy consumption prediction model according to the difference value includes at least one of:

Updating the first energy consumption coefficient according to the difference value and the weather sub-model; updating the second energy consumption coefficient according to the difference value and the road condition sub-model; updating the third energy consumption coefficient according to the difference value and the vehicle weight model; updating the fourth energy consumption coefficient according to the difference value and the gradient submodel; and updating the fifth energy consumption coefficient according to the difference value and the driving habit sub-model.

In an optional manner, the gradient information includes at least one of a gradient angle and a gradient length, and if the gradient angle indicates an upward gradient, the fourth additional energy consumption corresponding to the gradient information is a positive value; and if the gradient angle indicates a downhill slope, the fourth additional energy consumption corresponding to the gradient information is a negative value.

In an optional manner, before the predicting the energy consumption of the vehicle in the energy consumption calibration section according to the initial energy consumption prediction model and the average energy consumption information, to obtain the first energy consumption information, the method further includes: and sending an energy consumption prediction request to a server, wherein the energy consumption prediction request is used for requesting the server to predict the energy consumption of the vehicle.

According to a second aspect of an embodiment of the present invention, there is provided a vehicle energy consumption prediction system including:

the information acquisition unit is used for acquiring the route information, the vehicle position information and the average energy consumption information of the vehicle; determining actual energy consumption information of the vehicle when the vehicle runs in the energy consumption calibration road section according to the energy consumption calibration road section and the vehicle position information;

the energy consumption calculation unit is used for predicting the energy consumption of the vehicle on the energy consumption calibration road section according to an initial energy consumption prediction model to obtain first energy consumption information; predicting the energy consumption of the road section to be driven in the route information according to a target energy consumption prediction model to obtain second energy consumption information;

the energy consumption calibration unit is used for iteratively updating parameters of the initial energy consumption prediction model according to the difference value if the difference value between the first energy consumption information and the actual energy consumption information is larger than a preset threshold value until the target energy consumption prediction model meeting preset conditions is obtained;

and the energy consumption prompting unit is used for generating energy consumption prompting information according to the second energy consumption information.

According to a third aspect of the embodiment of the present invention, there is provided a vehicle energy consumption prediction apparatus including: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus; the memory is configured to store at least one executable instruction that causes the processor to perform the operations of the vehicle energy consumption prediction method as described in any one of the preceding.

According to a fourth aspect of embodiments of the present invention, there is provided a computer readable storage medium having stored therein at least one executable instruction which, when run on a vehicle energy consumption prediction system/device, causes the vehicle energy consumption prediction system/device to perform operations of a vehicle energy consumption prediction method as in any of the preceding.

The embodiment of the invention provides a vehicle energy consumption prediction method, a system and equipment, wherein the method comprises the following steps: firstly, acquiring route information, vehicle position information and average energy consumption information of a vehicle, predicting the energy consumption of the vehicle in an energy consumption calibration road section according to an initial energy consumption prediction model and the average energy consumption information according to the acquired information to obtain first energy consumption information, determining actual energy consumption information of the vehicle when the vehicle runs in the energy consumption calibration road section according to the energy consumption calibration road section and the vehicle position information, and if the difference value between the first energy consumption information and the actual energy consumption information is greater than a preset threshold value, iteratively updating parameters of the initial energy consumption prediction model according to the difference value until a target energy consumption prediction model meeting preset conditions is obtained, and finally predicting the energy consumption of the road section to be driven according to the target energy consumption prediction model to obtain second energy consumption information and generating energy consumption prompt information according to the second energy consumption information. By applying the technical scheme of the invention, the energy consumption of the pure electric vehicle can be predicted and updated, and the problem that the predicted energy consumption of the predicted vehicle is greatly different from the actual energy consumption is avoided.

The foregoing description is only an overview of the technical solutions of the embodiments of the present invention, and may be implemented according to the content of the specification, so that the technical means of the embodiments of the present invention can be more clearly understood, and the following specific embodiments of the present invention are given for clarity and understanding.

Drawings

In order to more clearly illustrate the technical solutions of the present application, the drawings that are needed in the embodiments will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.

FIG. 1 is a flowchart of a method for predicting vehicle energy consumption according to an embodiment of the present application;

FIG. 2 is a flow chart of another vehicle energy consumption prediction method according to an embodiment of the present application;

FIG. 3 is a flowchart of yet another vehicle energy consumption prediction method according to an embodiment of the present application;

FIG. 4 is a flowchart of yet another vehicle energy consumption prediction method according to an embodiment of the present application;

FIG. 5 is a timing diagram of a method for predicting vehicle energy consumption according to an embodiment of the present application;

fig. 6 is a schematic structural diagram of a vehicle energy consumption prediction system according to an embodiment of the present invention;

Fig. 7 is a schematic structural diagram of a vehicle energy consumption prediction apparatus according to an embodiment of the present invention.

Detailed Description

Reference will now be made in detail to the embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The embodiments described in the examples below do not represent all embodiments consistent with the present application. Merely as examples of systems and methods consistent with some aspects of the present application as detailed in the claims.

Because the power source of the pure electric vehicle is the electric power in the power battery, the electric power storage in the power battery is closely related to the cruising mileage of the pure electric vehicle, and the electric power storage is limited by the electric power storage of the power battery and the battery charging property.

When the endurance mileage is calculated, the energy consumption condition of the vehicle is predicted, and the endurance mileage is calculated through the residual energy and the energy consumption condition. Therefore, when calculating the endurance mileage, the energy consumption condition of the vehicle needs to be predicted. However, as the energy consumption condition of the electric vehicle is affected by various factors, such as weather, road conditions or driving behavior habit, when the energy consumption is predicted, the change of the factors can affect the accuracy of the energy consumption prediction, so that the cruising mileage presented to the user is inaccurate, and the driving experience of the user is affected.

In order to solve the problems, the application discloses a vehicle energy consumption prediction method, a system and equipment, which are used for obtaining predicted energy consumption by analyzing position information and driving route information of a vehicle, and correcting and updating the predicted energy consumption through real-time energy consumption, so that the vehicle can more accurately predict the subsequent energy consumption of the driving route, and the accuracy of a prediction result of the driving mileage of the vehicle is improved.

The file generation method disclosed in the embodiment of the present invention is exemplified below.

Fig. 1 shows a flowchart of a vehicle energy consumption prediction method in an embodiment of the present application. As shown in fig. 1, the prediction method includes:

s110: route information, vehicle position information, and average energy consumption information of the vehicle are acquired.

Through the vehicle-mounted navigation system, after a user activates the vehicle, the navigation route set by the user and the current position information of the vehicle can be acquired. For example, when a user enters a driving position and activates a vehicle, the user is required to determine a destination, and an on-board system of the vehicle gives a navigation route through the current position and the destination position of the vehicle, and route information of the vehicle and position information of the vehicle can be obtained through the navigation route. In some embodiments, the vehicle location information may also be obtained directly by the navigation system through the location of the vehicle. The route information comprises a to-be-driven road section and a plurality of energy consumption calibration road sections, wherein the lengths of the plurality of energy consumption calibration road sections are the same, the length of the to-be-driven road section is larger than that of the energy consumption calibration road section, the starting point of the first energy consumption calibration road section is the starting position in the route information, and the ending point of the to-be-driven road section is the destination position in the route information.

The average energy consumption information of the vehicle can be obtained through recording the past driving process of the vehicle, for example, the average energy consumption information of the vehicle can be obtained through recording the energy consumption of the vehicle when driving in any route or road section and calculating the corresponding driving mileage.

For example, when recording the average energy consumption information, it is necessary to record the average energy consumption information while the vehicle is in a drivable state. In some embodiments, the average energy consumption is recorded only when the vehicle is in a drivable state and the vehicle speed reaches a certain threshold value, and the recording and updating of the average energy consumption information is stopped when the vehicle speed is less than the threshold value for a period of time. However, this case ignores the power consumption of the electronic devices in the vehicle when the vehicle is stopped for a long time and the vehicle is in a drivable state, so in another part of embodiments, the power consumption may be recorded when the vehicle is in a drivable state, so that the average power consumption condition in the historical driving time or the historical driving distance can be reflected more.

It should be understood that the recorded energy consumption information has a certain accuracy only when the travel time or travel distance of the vehicle reaches a certain threshold value, and the recorded energy consumption information may be stored as average energy consumption information when the travel time or travel distance of the vehicle meets the condition during the recording. For example, the threshold value of the travel time may be set to 1 hour, and the threshold value of the travel distance may be set to 10km, that is, when the travel time of the vehicle should be greater than or equal to 1 hour, or when the travel distance of the vehicle is greater than or equal to 10km, the recorded energy consumption information may be used as the average energy consumption information. The above threshold values are merely exemplary, and the threshold value of the driving time and the threshold value of the driving distance may be set by the user at his own discretion, and the specific size of the threshold values is not limited in this application.

In some embodiments, the average energy consumption information further includes driving information, where the driving information is information such as road conditions and weather of the vehicle during driving, so that a history driving record of the vehicle is more specific, and it is convenient to predict energy consumption through the average energy consumption information in a subsequent step.

It should be noted that after the user determines the destination, a plurality of navigation routes may be generated, and different navigation routes may be processed in the process of predicting the subsequent energy consumption. For example, respectively carrying out energy consumption prediction on all the generated navigation routes; for another example, by judging the distance difference between different navigation routes, selecting the navigation route with the nearest distance to carry out subsequent energy consumption prediction; and selecting any navigation route for subsequent energy consumption prediction processing by a user instruction.

S120: and predicting the energy consumption of the vehicle in the energy consumption calibration road section according to the initial energy consumption prediction model and the average energy consumption information to obtain first energy consumption information.

After the average energy consumption information is obtained, the average energy consumption information can be selected through an initial energy consumption prediction model, so that the predicted energy consumption condition of the vehicle on the energy consumption calibration road section, namely the first energy consumption information, is obtained. For example, the energy consumption condition of a road section with the same length as the energy consumption calibration road section and the relatively close running information in the average energy consumption information can be selected as the first energy consumption information. The obtained first energy consumption information is energy consumption prediction information of the vehicle driving in an energy consumption calibration road section.

S130: and determining actual energy consumption information of the vehicle when the vehicle runs on the energy consumption calibration road section according to the energy consumption calibration road section and the vehicle position information.

The actual energy consumption information can be obtained through the power consumption of the energy consumption calibration road section when the vehicle is in a driving state and the length of the energy consumption calibration road section. The power consumption of the vehicle during driving includes, for example, high-voltage module power consumption, low-voltage module power consumption, and heat loss power consumption of the vehicle, but the heat loss power consumption is small, so in some embodiments, the energy consumption due to heat loss is considered to be 0 or negligible. When the power consumption is calculated, the power battery providing high voltage and the storage battery providing low voltage in part of the vehicles are arranged separately, so that the power consumption of the high-voltage module and the power consumption of the low-voltage module of the vehicles can be calculated respectively to obtain the actual power consumption of the whole vehicle, and the power consumption can be calculated through the voltage and the current of the output ends of the power battery and the storage battery during specific calculation. In some embodiments, since low voltage power may also be provided by the power battery, the actual power consumption of the vehicle may also be calculated by directly measuring the current and voltage of the bus of the power battery.

It should be understood that in the present embodiment, the actual energy consumption information refers to the average energy consumption information of the vehicle in one energy consumption calibration section that has already been driven, and may be calculated by using the consumed power or the consumed percentage of the battery and the length of the energy consumption calibration section.

S140: if the difference value between the first energy consumption information and the actual energy consumption information is larger than a preset threshold value, the parameters of the initial energy consumption prediction model are iteratively updated according to the difference value until a target energy consumption prediction model meeting preset conditions is obtained.

The parameters of the initial energy consumption prediction model refer to the duty ratio of different influencing factors in the prediction result of the energy consumption prediction model, and the preset condition refers to that the difference value between the first energy consumption information and the actual energy consumption information is smaller than or equal to a preset threshold value.

After the first energy consumption information and the actual energy consumption information of a certain energy consumption calibration road section are obtained, the first energy consumption information and the actual energy consumption information are required to be compared, a difference value between the first energy consumption information and the actual energy consumption information is obtained, the difference value is compared with a preset threshold value, if the difference value is larger than the preset threshold value, the fact that a large difference exists between the predicted energy consumption and the actual energy consumption is indicated, and the energy consumption predicted value in the subsequent energy consumption calibration road section and even the road section to be driven is required to be adjusted, so that parameters of an initial energy consumption prediction model are required to be adjusted according to the difference value, the first energy consumption information obtained through subsequent prediction is enabled to be closer to the actual energy consumption information, and the difference value between the first energy consumption information and the actual energy consumption information is reduced until the difference value between the first energy consumption information and the actual energy consumption information is smaller than or equal to the preset threshold value.

And when the first energy consumption information acquired by the initial energy consumption prediction model meets the preset condition, the initial energy consumption prediction model is considered as a target energy consumption prediction model, and the energy consumption prediction is carried out on the section to be driven, which is subsequent to the energy consumption calibration section, through the target energy consumption prediction model.

S150: and predicting the energy consumption of the road section to be driven according to the target energy consumption prediction model to obtain second energy consumption information.

After the target energy consumption prediction model is obtained, the energy consumption of a subsequent road section in the route information, namely the road section to be driven, is required to be predicted, and second energy consumption information of the vehicle is obtained, wherein the second energy consumption information is used for representing the energy consumption required by the vehicle to drive from the current position to the destination.

S160: and generating energy consumption prompt information according to the second energy consumption information.

After the second energy consumption information is obtained, comparing the second energy consumption information with the current residual electric quantity of the vehicle, and generating corresponding energy consumption prompt information according to a comparison result. For example, when the energy consumption in the second energy consumption information is smaller than the current residual electric quantity of the vehicle, generating information to prompt the user of the residual electric quantity of the vehicle after the vehicle runs at the moment; if the energy consumption in the second energy consumption information is greater than or equal to the current residual electric quantity of the vehicle, reminding the user that the electric quantity of the vehicle is insufficient to complete the current route, and providing a charging station which can be reached by the vehicle along the way for the user according to the route information so as to facilitate the subsequent charging of the user.

In some embodiments, in order to avoid that the second energy consumption information is too close to the current remaining power of the vehicle to cause the power failure of the vehicle, the content of the generated energy consumption prompt information may be determined according to the proportion of the energy consumption in the second energy consumption information to the current remaining power of the vehicle. For example, if the predicted second energy consumption information is more than 90% of the current residual electric quantity, providing a charging station for the user to reach the vehicle along the way according to the route information, and reminding the user to charge; if the proportion of the predicted second energy consumption information to the current residual electric quantity is smaller than or equal to 90%, the user is prompted to finish the running of the vehicle.

It should be noted that, in some embodiments of the present application, after the second energy consumption information is obtained, the current actual energy consumption information of the vehicle is further collected, and compared with a portion corresponding to the actual energy consumption information in the second energy consumption information to obtain a difference value, if the difference value is smaller than or equal to a preset threshold value, the second energy consumption information is considered to be still more accurate, and if the difference value is greater than the preset threshold value, the result of the second energy consumption information is inconsistent with the actual energy consumption, and the parameters of the target energy consumption prediction model need to be adjusted until the difference value between the obtained energy consumption information and the actual energy consumption information is smaller than or equal to the preset threshold value.

Through the technical scheme, the predicted energy consumption information is compared in real time, so that the parameters of the energy consumption prediction model are adjusted, the predicted energy consumption of the vehicle in the navigation route is more close to the actual energy consumption, the accuracy of energy consumption prediction is improved, the anxiety of a user is reduced, and the use experience of the user is improved.

Fig. 2 shows a flowchart of another vehicle energy consumption prediction method in an embodiment of the present application. In order to enable the initial energy consumption prediction model to more accurately predict the energy consumption of the vehicle, the energy consumption prediction model can be more accurately and reversely predicted by setting a sub-model for quantifying factors influencing the energy consumption in the model, and as shown in fig. 2, the prediction method comprises the following steps:

s210: route information, vehicle position information, and average energy consumption information of the vehicle are acquired.

S220: and predicting the energy consumption of the vehicle in the energy consumption calibration road section according to the initial energy consumption prediction model and the average energy consumption information to obtain first energy consumption information.

In order to quantify factors affecting the energy consumption of the vehicle, the initial energy consumption prediction model includes at least one of a weather sub-model, a road condition sub-model, a vehicle weight sub-model, a gradient sub-model and a driving habit sub-model, so that various information is acquired through devices such as sensors in the process of energy consumption prediction so as to facilitate calculation and adjustment. Illustratively, in making the energy consumption prediction, the method includes at least one of the following steps:

S221: and determining weather information according to the vehicle position information and inputting the weather information into the weather sub-model.

Wherein the weather information includes weather and air temperature. By way of example, according to the vehicle position information, the current city or area in which the vehicle is located can be obtained, and then the current air temperature and weather condition of the city or area in which the vehicle is located can be obtained through the network connection unit built in the vehicle.

In some embodiments, the external weather condition can also be obtained by loading a camera and a temperature sensor on the vehicle body. When the weather information is obtained, the weather information can be input into the weather sub-model, so that the weather factor is used as a parameter affecting the energy consumption information.

S222: and determining road condition information according to the route information and inputting the road condition information into the road condition sub-model.

The road condition information is obtained according to the congestion condition in the navigation information, so that the whole road condition information in the route is obtained, and the vehicle can input the road condition information into the road condition sub-model after obtaining the road condition information. For example, the vehicle may directly acquire the congestion status in the route through the on-board navigation unit.

It should be understood that the road condition information is continuously changed along with time, so that the road condition information acquired during the running process of the vehicle can be changed to a certain extent, and when the road condition information is changed to a large extent, for example, the congestion state is aggravated, the energy consumption prediction model is required to update the predicted energy consumption, so that the accuracy of energy consumption prediction is increased.

S223: and determining the weight information according to the identification information of the vehicle and inputting the weight information into the weight sub-model.

The identification information is information for reflecting real parameters of the vehicle, such as the weight, torque and the like, the identification information is related to the model of the vehicle, and when the number of passengers in the vehicle is small or the carrying amount of the passengers is small, the weight information can be obtained through the identification information in the vehicle identification information. After the weight information is determined, the weight information is input into a weight sub-model.

In some embodiments, pressure sensors may be disposed in the cabin and the trunk to obtain the weight of the passenger and the load in the vehicle, and the weight data of the vehicle may be obtained more accurately by combining the weight of the passenger and the load with the weight of the vehicle in the identification information.

S224: and determining gradient information according to gradient signals acquired by sensors of the vehicle and inputting the gradient information into a gradient sub-model.

The gradient information may include at least one of a gradient length and a gradient angle. For example, an inclination sensor may be disposed on a chassis of the vehicle to obtain an angle of passing through a ramp during running of the vehicle, and the positive and negative values of the inclination may be used to indicate whether the current vehicle is in an uphill state or a downhill state, for example, when the inclination is positive, the vehicle is in an uphill state, and when the inclination is negative, the vehicle is in a downhill state; and the ramp length may be determined by the time frame of the change in speed and inclination of the vehicle.

In some embodiments, when the gradient information is acquired, whether the ramp is included in the route or not can also be determined according to the route information in the navigation information, and if the ramp is included, the length and the angle of the ramp are respectively. The obtained gradient information needs to be input into the gradient sub-model to describe the prediction of the energy consumption more accurately.

S225: and determining the driving habit type of the driver according to the change rate of the opening of the accelerator pedal and the change rate of the acceleration of the vehicle, and inputting the driving habit type into the driving habit sub-model.

The change rate of the accelerator pedal opening is the change of the accelerator pedal opening in unit time, and the acceleration change rate is the change of the acceleration of the vehicle in unit time. And determining the driving habit type of the driver according to any one of the two values of the two change rates, and inputting the driving habit type into the driving habit sub-model after determining the compartment habit type.

For example, after the change rate of the opening degree of the accelerator pedal or the change rate of the acceleration of the vehicle is obtained, if the change rate of the opening degree of the accelerator pedal is greater than the preset opening degree change rate, or if the change rate of the acceleration of the vehicle within the preset time period is greater than the preset acceleration change rate, it is determined that the driving habit type of the driver is the first driving habit type.

If the change rate of the opening of the accelerator pedal is smaller than the preset opening change rate, or if the change rate of the acceleration of the vehicle in the preset time period is smaller than the preset acceleration change rate, determining that the driving habit type of the driver is the second driving habit type. Wherein the additional energy consumption corresponding to the first driving habit type is higher than the additional energy consumption corresponding to the second driving habit type.

In some embodiments, a third driving habit type may also be designed, where the additional energy consumption corresponding to the third driving habit type is lower than the additional energy consumption corresponding to the first driving habit type and higher than the additional energy consumption corresponding to the second driving habit type. Specifically, the preset opening degree change rate and the preset acceleration change rate are both a numerical range, and when the change rate of the opening degree of the accelerator pedal is larger than the preset opening degree change rate range or the acceleration change rate of the vehicle in a preset duration is larger than the preset acceleration change rate range, the driving habit type of the driver is determined to be a first driving habit type; when the change rate of the opening of the accelerator pedal is smaller than the preset opening change rate range or the acceleration change rate of the vehicle in the preset duration is smaller than the preset acceleration change rate range, determining that the driving habit type of the driver is a second driving habit type; and when the change rate of the opening of the accelerator pedal is in a preset opening change rate range or the acceleration change rate of the vehicle in a preset duration is in a preset acceleration change rate range, determining that the driving habit type of the driver is a third driving habit type.

If the driving habit type is determined, the acceleration change rate of the vehicle is used as the main criterion of the driving habit type when the opening change rate and the acceleration change rate of the accelerator pedal are both collected.

S230: and determining actual energy consumption information of the vehicle when the vehicle runs on the energy consumption calibration road section according to the energy consumption calibration road section and the vehicle position information.

Through the information obtained in the steps S221 to S225, the factors that affect the energy consumption of the vehicle can be determined and obtained, and then the parameters in the initial energy consumption prediction model are set through the factors, so that the influence of different factors is quantified, and the model can be updated later.

S240: if the difference value between the first energy consumption information and the actual energy consumption information is larger than a preset threshold value, the parameters of the initial energy consumption prediction model are iteratively updated according to the difference value until a target energy consumption prediction model meeting preset conditions is obtained.

And adjusting parameters of at least one sub-model in the initial energy consumption prediction model through a difference value between the actual energy consumption information and the first energy consumption information, so as to update the initial energy consumption prediction model until a target energy consumption prediction model capable of accurately predicting energy consumption is finally obtained.

S250: and predicting the energy consumption of the road section to be driven in the route information according to the target energy consumption prediction model to obtain second energy consumption information.

S260: and generating energy consumption prompt information according to the second energy consumption information.

In the method, the execution process of steps S210 to S220 is the same as the execution process of steps S110 to S120, so steps S210 to S220 are not described in detail in the present application; in the method, the execution process of steps S250 to S260 is the same as the execution process of steps S150 to S160, so that steps S250 to S260 are not described in detail in the present application.

Through the technical scheme, the energy consumption influence caused by weather, road conditions, vehicle weight, gradient and driving habit types is quantized into the model, so that the energy consumption prediction model can more accurately predict the energy consumption condition of the vehicle.

Fig. 3 shows a flowchart of yet another vehicle energy consumption prediction method in an embodiment of the present application. The external environmental influence or the influence of the user is quantified through the sub-model in the energy consumption prediction model, so that the energy consumption prediction is more accurate, and as shown in fig. 3, the prediction method further comprises:

s310: route information, vehicle position information, and average energy consumption information of the vehicle are acquired.

S321: and determining the first additional energy consumption corresponding to the weather information according to the weather information and the weather sub-model.

According to the weather conditions obtained in the above method S221, the first additional energy consumption corresponding to the weather information can be determined. Specifically, under the condition that other influencing factors are the same, when the weather is sunny or the temperature is higher, the value of the first additional energy consumption is reduced to a certain extent, so that the ratio of the first additional energy consumption in the first energy consumption information is reduced; when the weather is rainy or the air temperature is low, the value of the first additional energy consumption is increased to a certain extent, so that the duty ratio of the first additional energy consumption in the first energy consumption information is increased.

In some embodiments, the weather sub-model corresponds to the first energy consumption coefficient, and the first energy consumption coefficient in the weather sub-model can be directly adjusted to increase or decrease the duty ratio of the first additional energy consumption in the first energy consumption information, so as to achieve the calculation of the energy consumption affecting the weather factors.

S322: and determining second additional energy consumption corresponding to the road condition information according to the road condition information and the road condition sub-model.

According to the road condition information obtained in the above method S222, the second additional energy consumption corresponding to the road condition information may be calculated through the road condition sub-model. For example, since frequent acceleration and deceleration are required during traffic jam and the vehicle is in a drivable state for a longer period of time, the more congested the road is shown in the road condition information, the larger the value of the second additional energy consumption is, and the higher the duty ratio of the second additional energy consumption in the first energy consumption information is under the condition that other influencing factors are the same.

In some embodiments, the road condition sub-model corresponds to a second energy consumption coefficient, and the magnitude of the second additional energy consumption can be adjusted by adjusting the second energy consumption coefficient, so that the influence of the road condition can be calculated.

S323: and determining third additional energy consumption corresponding to the vehicle weight information according to the vehicle weight information and the vehicle weight sub-model.

According to the vehicle weight information and the vehicle weight model obtained in the above method S223, the influence of the vehicle weight information on the predicted energy consumption can be reflected, and under the condition that other influence factors are the same, the heavier the vehicle is, the higher the energy consumption is, and the higher the duty ratio in the first energy consumption information is. Meanwhile, in some embodiments, the third energy consumption coefficient corresponding to the vehicle weight sub-model is used for reflecting the influence duty ratio of the vehicle weight to the energy consumption.

S324: and determining fourth additional energy consumption corresponding to the gradient information according to the gradient information and the gradient sub-model.

The gradient information includes at least one of a gradient angle and a gradient length, as described in the above step S224. For example, the vehicle may be indicated as ascending or descending by the positive or negative gradient angle, if the gradient angle is positive, the vehicle is in the ascending state, and if the gradient angle is negative, the vehicle is in the descending state.

Since the thrust required for the vehicle to ascend is higher than that on the flat ground and the thrust required for the vehicle to descend is lower than that on the flat ground while maintaining a vehicle speed, the fourth additional energy consumption is a positive value when the vehicle ascends and a negative value when the vehicle descends. If the gradient angle indicates an ascending slope, the fourth additional energy consumption corresponding to the gradient information is a positive value; and if the gradient angle indicates a downhill slope, the fourth additional energy consumption corresponding to the gradient information is a negative value.

In some embodiments, the gradient sub-model corresponds to a fourth energy consumption coefficient, and is used to evaluate an overall effect of the gradient information on the first energy consumption information, that is, a duty ratio of the gradient information in the first energy consumption information.

S325: and determining fifth additional energy consumption corresponding to the driving habit type according to the driving habit type and the driving habit sub-model.

After the driving habit type of the user is obtained in the step S225, according to different driving habit types of the user, the fifth additional energy consumption corresponding to the driving habit can be determined, so as to obtain the influence of the driving habit type on the first energy consumption information.

In some embodiments, the driving habit sub-model further corresponds to a fifth energy consumption coefficient, and an influence of the driving habit type on the energy consumption of the vehicle can be reflected through the fifth energy consumption coefficient.

S326: and determining the first energy consumption information according to the average energy consumption information and at least one of the first additional energy consumption, the second additional energy consumption, the third additional energy consumption, the fourth additional energy consumption and the fifth additional energy consumption.

After the average energy consumption information, the first additional energy consumption, the second additional energy consumption, the third additional energy consumption, the fourth additional energy consumption and the fifth additional energy consumption are obtained through the steps, the additional energy consumption and the energy consumption value in the average energy consumption information are correspondingly calculated, and then the first energy consumption information can be determined.

S330: and determining actual energy consumption information of the vehicle when the vehicle runs on the energy consumption calibration road section according to the energy consumption calibration road section and the vehicle position information.

S340: if the difference value between the first energy consumption information and the actual energy consumption information is larger than a preset threshold value, the parameters of the initial energy consumption prediction model are iteratively updated according to the difference value until a target energy consumption prediction model meeting preset conditions is obtained.

For example, the initial energy consumption prediction model includes at least one of a weather sub-model, a road condition sub-model, a vehicle weight sub-model, a gradient sub-model, and a driving habit sub-model, and the parameter of the initial energy consumption prediction model includes at least one of a first energy consumption coefficient, a second energy consumption coefficient, a third energy consumption coefficient, a fourth energy consumption coefficient, and a fifth energy consumption coefficient. When the parameters of the initial energy consumption prediction model are iteratively updated, the energy consumption coefficients are mainly adjusted and updated, so that the parameters of the initial energy consumption prediction model are updated, namely the energy consumption influenced by different factors is adjusted in the proportion of the energy consumption in the first energy consumption information.

For example, updating the parameters of the initial energy consumption prediction model may include at least one of: updating the first energy consumption coefficient according to the difference value and the weather sub-model; updating a second energy consumption coefficient according to the difference value and the road condition sub-model; updating a third energy consumption coefficient according to the difference value and the vehicle weight model; updating a fourth energy consumption coefficient according to the difference value and the gradient sub-model; and updating the fifth energy consumption coefficient according to the difference value and the driving habit sub-model.

S350: and predicting the energy consumption of the road section to be driven in the route information according to the target energy consumption prediction model to obtain second energy consumption information.

S360: and generating energy consumption prompt information according to the second energy consumption information.

In the method, the execution process of steps S310 to S320 is the same as the execution process of steps S110 to S120, so steps S310 to S320 are not described in detail in the present application; in the method, the execution process of steps S350 to S360 is the same as the execution process of steps S150 to S160, so that the steps S350 to S360 are not described in detail in the present application.

According to the technical scheme, the additional energy consumption caused by different factors influencing the energy consumption is added into the predicted energy consumption information, and the initial energy consumption prediction model is adjusted in a mode of adjusting the duty ratio or the coefficient of different factors after comparison, so that the energy consumption prediction result is more accurate.

FIG. 4 illustrates a flow chart of yet another vehicle energy consumption prediction method in an embodiment of the present application; fig. 5 shows a timing chart of a vehicle energy consumption prediction method in an embodiment of the present application. Because the vehicle end performs the energy consumption prediction, which has the problems of large data volume and slower processing speed, and simultaneously, a large number of parameters need to be imported to the vehicle end for the vehicle end to perform the prediction alone, so that the efficiency of the energy consumption prediction is lower, as shown in fig. 4 and 5, the prediction method in the application may further include:

s410: route information and vehicle position information of a vehicle are acquired.

S420: and sending an energy consumption prediction request to a server.

The energy consumption prediction request is used for requesting the server to predict the energy consumption of the vehicle. Specifically, when the energy consumption prediction request is sent to the request server, the route information of the vehicle and the vehicle position information are sent to the server side together, so that the subsequent process is calculated and processed by the server side, the calculation pressure of the vehicle side is reduced, and the energy consumption can be predicted more quickly. For example, when gradient information is acquired, the gradient information can be acquired through navigation information, and the current running state of the vehicle is calculated and acquired to be an ascending slope or a descending slope in a cloud computing mode, so that the influence of the gradient information on the energy consumption of the vehicle is acquired.

It should be understood that, in order for the server side to be able to predict the vehicle energy consumption, the initial energy consumption prediction model needs to be set in the server side, so as to achieve the purpose of rapid iterative update to obtain the target energy consumption prediction model.

S430: and predicting the energy consumption of the vehicle in the energy consumption calibration road section according to the initial energy consumption prediction model and the average energy consumption information to obtain first energy consumption information.

S440: and determining actual energy consumption information of the vehicle when the vehicle runs in the energy consumption calibration road section according to the energy consumption calibration road section and the vehicle position information.

S450: if the difference value between the first energy consumption information and the actual energy consumption information is larger than a preset threshold value, the parameters of the initial energy consumption prediction model are iteratively updated according to the difference value until a target energy consumption prediction model meeting preset conditions is obtained.

S460: and predicting the energy consumption of the road section to be driven in the route information according to the target energy consumption prediction model to obtain second energy consumption information.

S470: and generating energy consumption prompt information according to the second energy consumption information.

In the method, the execution process of steps S410 and S430 to S470 is the same as the execution process of steps S110 to S160, and only the data calculation in steps S430 to S470 is transferred to the server for execution, so that the steps S410 and S430 to S470 are not described in detail in the present application.

According to the technical scheme, the information to be processed and the energy consumption prediction request are sent to the server side, so that the energy consumption prediction and model update are realized through the server side, the consumption of the vehicle side is reduced, and the operation efficiency is improved.

Based on the above method for predicting vehicle energy consumption, the present application further provides a system 600 for predicting vehicle energy consumption, as shown in fig. 6, including:

an information acquisition unit 610 for acquiring route information, vehicle position information, and average energy consumption information of the vehicle; and determining actual energy consumption information of the vehicle when the vehicle runs in the energy consumption calibration road section according to the energy consumption calibration road section and the vehicle position information.

The energy consumption calculating unit 620 is configured to predict energy consumption of the vehicle in the energy consumption calibration section according to the initial energy consumption prediction model, so as to obtain first energy consumption information; and predicting the energy consumption of the road section to be driven in the route information according to the target energy consumption prediction model to obtain second energy consumption information.

And the energy consumption calibration unit 630 is configured to iteratively update parameters of the initial energy consumption prediction model according to the difference value if the difference value between the first energy consumption information and the actual energy consumption information is greater than a preset threshold value, until a target energy consumption prediction model satisfying a preset condition is obtained.

And the energy consumption prompting unit 640 is configured to generate energy consumption prompting information according to the second energy consumption information.

In an alternative manner, the initial energy consumption prediction model includes at least one of a weather sub-model, a road condition sub-model, an automobile weight sub-model, a gradient sub-model, and a driving habit sub-model, and the energy consumption calculation unit 620 is further configured to perform at least one of: determining weather information according to the vehicle position information and inputting the weather information into a weather sub-model; determining road condition information according to the route information and inputting the road condition information into the road condition sub-model; determining vehicle weight information according to the identification information of the vehicle and inputting the vehicle weight information into a vehicle weight sub-model; according to gradient signals acquired by a sensor of the vehicle, gradient information is determined and input into a gradient sub-model; and determining the driving habit type of the driver according to the change rate of the opening of the accelerator pedal and the change rate of the acceleration of the vehicle, and inputting the driving habit type into the driving habit sub-model.

In an alternative way, the energy consumption calculation unit 620 is further configured to: if the change rate of the opening of the accelerator pedal is larger than the change rate of the preset opening, or if the change rate of the acceleration of the vehicle in the preset time period is larger than the change rate of the preset acceleration, determining that the driving habit type of the driver is a first driving habit type; if the change rate of the opening of the accelerator pedal is smaller than the preset opening change rate, or if the change rate of the acceleration of the vehicle in the preset time period is smaller than the preset acceleration change rate, determining that the driving habit type of the driver is a second driving habit type; wherein the additional energy consumption corresponding to the first driving habit type is higher than the additional energy consumption corresponding to the second driving habit type.

In an alternative way, the energy consumption calculation unit 620 is further configured to: determining a first additional energy consumption corresponding to the weather information according to the weather information and the weather sub-model; determining a second additional energy consumption corresponding to the road condition information according to the road condition information and the road condition sub-model; determining third additional energy consumption corresponding to the vehicle weight information according to the vehicle weight information and the vehicle weight sub-model; determining fourth additional energy consumption corresponding to the gradient information according to the gradient information and the gradient sub-model; determining a fifth additional energy consumption corresponding to the driving habit type according to the driving habit type and the driving habit sub-model; and determining the first energy consumption information according to the average energy consumption information and at least one of the first additional energy consumption, the second additional energy consumption, the third additional energy consumption, the fourth additional energy consumption and the fifth additional energy consumption.

In an optional manner, the parameters of the initial energy consumption prediction model include at least one of a first energy consumption coefficient corresponding to the weather sub-model, a second energy consumption coefficient corresponding to the road condition sub-model, a third energy consumption coefficient corresponding to the vehicle weight sub-model, a fourth energy consumption coefficient corresponding to the gradient sub-model, and a fifth energy consumption coefficient corresponding to the driving habit sub-model, and the energy consumption calibration unit 630 is further configured to execute at least one of: updating the first energy consumption coefficient according to the difference value and the weather sub-model; updating a second energy consumption coefficient according to the difference value and the road condition sub-model; updating a third energy consumption coefficient according to the difference value and the vehicle weight model; updating a fourth energy consumption coefficient according to the difference value and the gradient sub-model; and updating the fifth energy consumption coefficient according to the difference value and the driving habit sub-model.

In an optional manner, the gradient information includes at least one of a gradient angle and a gradient length, and if the gradient angle indicates an uphill slope, the fourth additional energy consumption corresponding to the gradient information is a positive value; and if the gradient angle indicates a downhill slope, the fourth additional energy consumption corresponding to the gradient information is a negative value.

In an alternative way, the information acquisition unit 610 is further configured to: and sending an energy consumption prediction request to the server, wherein the energy consumption prediction request is used for requesting the server to predict the energy consumption of the vehicle.

Fig. 7 is a schematic structural diagram of a vehicle energy consumption prediction device according to an embodiment of the present invention, and the specific embodiment of the present invention is not limited to the specific implementation of the electronic device.

Based on the vehicle energy consumption prediction method, the application further provides a vehicle energy consumption prediction device, as shown in fig. 7, where the electronic device may include: a processor 702, a communication interface (Communications Interface), a memory 706, and a communication bus 708.

Wherein: processor 702, communication interface 704, and memory 706 perform communication with each other via a communication bus 708. A communication interface 704 for communicating with network elements of other devices, such as clients or other servers. The processor 702 is configured to execute the program 710, and may specifically perform relevant steps in the above-described vehicle energy consumption prediction method embodiment.

In particular, program 710 may include program code including computer-executable instructions.

The processor 702 may be a Central Processing Unit (CPU), or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included in the electronic device may be the same type of processor, such as one or more CPUs; but may also be different types of processors such as one or more CPUs and one or more ASICs.

Memory 706 for storing programs 710. The memory 706 may comprise high-speed RAM memory or may further comprise non-volatile memory (non-volatile memory), such as at least one disk memory.

The program 710 may be specifically invoked by the processor 702 to cause the electronic device to:

route information, vehicle position information, and average energy consumption information of the vehicle are acquired.

And predicting the energy consumption of the vehicle in the energy consumption calibration road section according to the initial energy consumption prediction model and the average energy consumption information to obtain first energy consumption information.

And determining actual energy consumption information of the vehicle when the vehicle runs in the energy consumption calibration road section according to the energy consumption calibration road section and the vehicle position information.

If the difference value between the first energy consumption information and the actual energy consumption information is larger than a preset threshold value, the parameters of the initial energy consumption prediction model are iteratively updated according to the difference value until a target energy consumption prediction model meeting preset conditions is obtained.

And predicting the energy consumption of the road section to be driven in the route information according to the target energy consumption prediction model to obtain second energy consumption information.

And generating energy consumption prompt information according to the second energy consumption information.

In an optional manner, the initial energy consumption prediction model includes at least one of a weather sub-model, a road condition sub-model, a vehicle weight sub-model, a gradient sub-model and a driving habit sub-model, and before predicting the energy consumption of the vehicle in the energy consumption calibration section according to the initial energy consumption prediction model and the average energy consumption information, the method further includes at least one of:

determining weather information according to the vehicle position information and inputting the weather information into a weather sub-model;

determining road condition information according to the route information and inputting the road condition information into the road condition sub-model;

determining vehicle weight information according to the identification information of the vehicle and inputting the vehicle weight information into a vehicle weight sub-model;

according to gradient signals acquired by a sensor of the vehicle, gradient information is determined and input into a gradient sub-model;

And determining the driving habit type of the driver according to the change rate of the opening of the accelerator pedal and the change rate of the acceleration of the vehicle, and inputting the driving habit type into the driving habit sub-model.

In an alternative manner, determining the driving habit type of the driver from the change rate of the accelerator opening degree and the acceleration change rate of the vehicle includes:

if the change rate of the opening of the accelerator pedal is larger than the change rate of the preset opening, or if the change rate of the acceleration of the vehicle in the preset time period is larger than the change rate of the preset acceleration, determining that the driving habit type of the driver is a first driving habit type; if the change rate of the opening of the accelerator pedal is smaller than the preset opening change rate, or if the change rate of the acceleration of the vehicle in the preset time period is smaller than the preset acceleration change rate, determining that the driving habit type of the driver is a second driving habit type; wherein the additional energy consumption corresponding to the first driving habit type is higher than the additional energy consumption corresponding to the second driving habit type.

determining a first additional energy consumption corresponding to the weather information according to the weather information and the weather sub-model;

Determining a second additional energy consumption corresponding to the road condition information according to the road condition information and the road condition sub-model;

determining third additional energy consumption corresponding to the vehicle weight information according to the vehicle weight information and the vehicle weight sub-model;

determining fourth additional energy consumption corresponding to the gradient information according to the gradient information and the gradient sub-model;

determining a fifth additional energy consumption corresponding to the driving habit type according to the driving habit type and the driving habit sub-model;

and determining the first energy consumption information according to the average energy consumption information, the first additional energy consumption, the second additional energy consumption, the third additional energy consumption, the fourth additional energy consumption and the fifth additional energy consumption.

In an alternative manner, the weather sub-model corresponds to a first energy consumption coefficient, the road condition sub-model corresponds to a second energy consumption coefficient, the vehicle weight sub-model corresponds to a third energy consumption coefficient, the gradient sub-model corresponds to a fourth energy consumption coefficient, and the driving habit sub-model corresponds to a fifth energy consumption coefficient; the parameters of the initial energy consumption prediction model include at least one of a first energy consumption coefficient, a second energy consumption coefficient, a third energy consumption coefficient, a fourth energy consumption coefficient, and a fifth energy consumption coefficient.

In an optional manner, before predicting the energy consumption of the vehicle in the energy consumption calibration section according to the initial energy consumption prediction model and the average energy consumption information to obtain the first energy consumption information, the method further includes: and sending an energy consumption prediction request to the server, wherein the energy consumption prediction request is used for requesting the server to predict the energy consumption of the vehicle.

The embodiment of the invention also provides a computer readable storage medium, wherein at least one executable instruction is stored in the storage medium, and when the executable instruction runs on the vehicle energy consumption prediction system/device, the vehicle energy consumption prediction system/device executes the operation of the vehicle energy consumption prediction method according to any one of the above.

In the description provided herein, numerous specific details are set forth. It will be appreciated, however, that embodiments of the invention may be practiced without such specific details. Similarly, in the above description of exemplary embodiments of the invention, various features of embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. Wherein the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Except that at least some of such features and/or processes or elements are mutually exclusive.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specifically stated.

Claims

1. A vehicle energy consumption prediction method, characterized by comprising:

acquiring route information, vehicle position information and average energy consumption information of a vehicle; the route information comprises a road section to be driven and a plurality of energy consumption calibration road sections;

predicting the energy consumption of the vehicle on the energy consumption calibration road section according to an initial energy consumption prediction model and the average energy consumption information to obtain first energy consumption information;

determining actual energy consumption information of the vehicle when the vehicle runs in the energy consumption calibration road section according to the energy consumption calibration road section and the vehicle position information;

if the difference value between the first energy consumption information and the actual energy consumption information is larger than a preset threshold value, iteratively updating parameters of the initial energy consumption prediction model according to the difference value until a target energy consumption prediction model meeting preset conditions is obtained;

predicting the energy consumption of the road section to be driven according to the target energy consumption prediction model to obtain second energy consumption information;

2. The vehicle energy consumption prediction method according to claim 1, wherein the initial energy consumption prediction model includes at least one of a weather sub-model, a road condition sub-model, a vehicle weight sub-model, a gradient sub-model, and a driving habit sub-model, and wherein before the predicting the energy consumption of the vehicle in the energy consumption calibration section according to the initial energy consumption prediction model and the average energy consumption information, the method further includes at least one of:

Determining weather information according to the vehicle position information and inputting the weather information into the weather sub-model;

determining the vehicle weight information according to the identification information of the vehicle and inputting the vehicle weight information into the vehicle weight sub-model;

determining gradient information according to gradient signals acquired by a sensor of the vehicle and inputting the gradient information into the gradient sub-model;

3. The vehicle energy consumption prediction method according to claim 2, characterized in that the determining the driving habit type of the driver based on the rate of change of the accelerator pedal opening and the rate of change of the acceleration of the vehicle includes:

if the change rate of the opening of the accelerator pedal is larger than the preset opening change rate, or if the change rate of the acceleration of the vehicle within the preset time period is larger than the preset acceleration change rate, determining that the driving habit type of the driver is a first driving habit type;

and if the change rate of the opening of the accelerator pedal is smaller than the preset opening change rate, or if the change rate of the acceleration of the vehicle within the preset time period is smaller than the preset acceleration change rate, determining that the driving habit type of the driver is a second driving habit type.

4. The vehicle energy consumption prediction method according to claim 2, wherein predicting the energy consumption of the vehicle in the energy consumption calibration section according to an initial energy consumption prediction model and the average energy consumption information to obtain first energy consumption information includes:

determining a third additional energy consumption corresponding to the vehicle weight information according to the vehicle weight information and the vehicle weight sub-model;

and determining the first energy consumption information according to the average energy consumption information and at least one of the first additional energy consumption, the second additional energy consumption, the third additional energy consumption, the fourth additional energy consumption and the fifth additional energy consumption.

5. The vehicle energy consumption prediction method according to claim 4, wherein the parameters of the initial energy consumption prediction model include at least one of a first energy consumption coefficient corresponding to the weather sub-model, a second energy consumption coefficient corresponding to the road condition sub-model, a third energy consumption coefficient corresponding to the vehicle weight sub-model, a fourth energy consumption coefficient corresponding to the gradient sub-model, and a fifth energy consumption coefficient corresponding to the driving habit sub-model, and the iteratively updating the parameters of the initial energy consumption prediction model according to the difference value includes at least one of:

Updating the first energy consumption coefficient according to the difference value and the weather sub-model;

updating the second energy consumption coefficient according to the difference value and the road condition sub-model;

updating the third energy consumption coefficient according to the difference value and the vehicle weight model;

updating the fourth energy consumption coefficient according to the difference value and the gradient submodel;

and updating the fifth energy consumption coefficient according to the difference value and the driving habit sub-model.

6. The vehicle energy consumption prediction method according to claim 4, wherein the gradient information includes at least one of a gradient angle and a gradient length, and if the gradient angle indicates an upward gradient, the fourth additional energy consumption corresponding to the gradient information is a positive value; and if the gradient angle indicates a downhill slope, the fourth additional energy consumption corresponding to the gradient information is a negative value.

7. The vehicle energy consumption prediction method according to claim 1, wherein before predicting the energy consumption of the vehicle in the energy consumption calibration section according to the initial energy consumption prediction model and the average energy consumption information, the method further comprises:

and sending an energy consumption prediction request to a server, wherein the energy consumption prediction request is used for requesting the server to predict the energy consumption of the vehicle.

8. A vehicle energy consumption prediction system, comprising:

9. A vehicle energy consumption prediction apparatus, characterized by comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus; the memory is configured to store at least one executable instruction that causes the processor to perform the operations of a vehicle energy consumption prediction method according to any one of claims 1-7.

10. A computer readable storage medium, characterized in that at least one executable instruction is stored in the storage medium, which executable instruction, when run on a vehicle energy consumption prediction system/device, causes the vehicle energy consumption prediction system/device to perform the operations of the vehicle energy consumption prediction method according to any one of claims 1-7.