Remaining mileage estimation method, controller, electric vehicle and storage medium

Abstract

The embodiment of the invention provides a remaining mileage estimation method, a controller, an electric vehicle and a storage medium, and relates to the technical field of electric vehicles. The method comprises the following steps: acquiring target road state information of a vehicle driven by a target object; performing driving parameter prediction on the target road state information through a pre-trained target driving parameter prediction model to obtain predicted driving parameters of a target road section; wherein the target driving parameter prediction model is obtained by training sample road state information of a vehicle driven by the target object; determining target predicted total power consumption according to the target road segment predicted driving parameters; and performing residual mileage estimation according to the target predicted total power consumption to obtain a target residual mileage. According to the embodiment of the invention, the accuracy of remaining mileage estimation can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of electric vehicles, and in particular to a remaining mileage estimation method and controller, an electric vehicle, and a storage medium. Background Art

[0002] During the driving of an electric vehicle, it is very important to judge the remaining mileage, for example, you can plan your trip based on the remaining mileage. The current remaining mileage judgment method has low accuracy. For example, the remaining mileage is usually estimated based on the power consumption of the electric vehicle and the state of charge (SOC) of the battery. However, the error between the remaining mileage estimated by this method and the actual remaining mileage is large, and it is impossible to accurately judge the remaining mileage of the electric vehicle.

[0003] Therefore, how to improve the accuracy of remaining mileage estimation has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a remaining mileage estimation method and controller, an electric vehicle, and a storage medium, aiming to improve the accuracy of the remaining mileage estimation.

[0005] To achieve the above object, a first aspect of an embodiment of the present application provides a remaining mileage estimation method, the method comprising:

[0006] Step 101, obtaining target road state information of a vehicle driven by a target object; wherein the target road state information is used to characterize the condition of the road on which the vehicle driven by the target object is traveling;

[0007] Step 102, predicting driving parameters of the target road state information by using a pre-trained target driving parameter prediction model to obtain predicted driving parameters of a target road section; wherein the target driving parameter prediction model is trained by sample road state information of the vehicle driven by the target object, and the predicted driving parameters of the target road section are used to characterize the driving speed of the vehicle driven by the target object;

[0008] Step 103, determining a target predicted total power consumption according to the predicted driving parameters of the target road section; wherein the target predicted total power consumption is used to represent the power consumption predicted for the vehicle driven by the target object;

[0009] Step 104 , estimating the remaining mileage according to the target predicted total power consumption to obtain a target remaining mileage; wherein the target remaining mileage is used to represent the mileage that the vehicle driven by the target object can travel.

[0010] In some embodiments, the step 103 of determining the target predicted total power consumption according to the predicted driving parameters of the target road section includes:

[0011] Step 201, obtaining the in-vehicle load of the vehicle driven by the target object;

[0012] Step 202, obtaining a target in-vehicle accessory power consumption of the vehicle driven by the target object; wherein the target in-vehicle accessory power consumption is used to characterize the power consumption of the device inside the vehicle driven by the target object;

[0013] Step 203 , using a preset vehicle power consumption prediction model, power consumption prediction is performed on the vehicle load, the target vehicle accessory power consumption, and the target road section predicted driving parameters to obtain the target predicted total power consumption.

[0014] In some embodiments, in step 102, before predicting the driving parameters of the target road state information by using the pre-trained target driving parameter prediction model to obtain the predicted driving parameters of the target road section, the method further includes:

[0015] Step 301, obtaining the sample road state information of the vehicle driven by the target object; wherein the sample road state information includes road state information of at least two consecutive sub-segments, and the road state information of each sub-segment is used to represent the condition of the sub-segment;

[0016] Step 302, performing a first driving parameter prediction on the road state information of the first sub-segment by using a preset initial driving parameter prediction model to obtain a sub-segment predicted driving parameter of the first sub-segment; wherein the sub-segment predicted driving parameter is used to characterize the driving speed of the vehicle driven by the target object on the sub-segment;

[0017] Step 303, performing a second driving parameter prediction on the road state information of each of the sub-segments after the first one and the predicted driving parameters of the previous sub-segment of each of the sub-segments after the first one by using the initial driving parameter prediction model, to obtain the sub-segment predicted driving parameters of each of the sub-segments except the first sub-segment;

[0018] Step 304, calculating a loss value according to the sub-segment predicted driving parameters of each of the sub-segments to obtain a target loss value; wherein the target loss value is used to characterize a loss function value of the initial driving parameter prediction model;

[0019] Step 305: Adjust the parameters of the initial driving parameter prediction model according to the target loss value to obtain the target driving parameter prediction model.

[0020] In some embodiments, the step 102, performing driving parameter prediction on the target road state information by using a pre-trained target driving parameter prediction model to obtain predicted driving parameters of the target road section, includes:

[0021] Step 401, obtaining the current speed and current acceleration of the vehicle driven by the target object;

[0022] Step 402, fusing the current speed, the current acceleration and the target road state information to obtain target driving state information; wherein the target driving state information is used to characterize the driving state of the vehicle driven by the target object;

[0023] Step 403: Perform driving parameter prediction on the target driving state information using the target driving parameter prediction model to obtain predicted driving parameters of the target road section.

[0024] In some embodiments, the step 104 of estimating the remaining mileage according to the target predicted total power consumption to obtain the target remaining mileage includes:

[0025] Step 501, obtaining the current remaining power of the vehicle driven by the target object;

[0026] Step 502, multiplying the first regression coefficient of the pre-trained target linear regression model by the current remaining power to obtain a first remaining mileage influence factor; wherein the first remaining mileage influence factor is used to characterize an influence factor of the remaining mileage of the vehicle driven by the target object;

[0027] Step 503, multiplying the second regression coefficient of the target linear regression model and the target predicted total power consumption to obtain a second remaining mileage influence factor; wherein the second remaining mileage influence factor is used to characterize an influence factor of the remaining mileage of the vehicle driven by the target object;

[0028] Step 504 , obtaining the target remaining mileage by summing the random error term of the target linear regression model, the first remaining mileage influencing factor, and the second remaining mileage influencing factor.

[0029] In some embodiments, the step 501 of obtaining the current remaining power of the vehicle driven by the target object includes:

[0030] Step 601, obtaining the battery voltage and battery temperature of the vehicle driven by the target object;

[0031] Step 602, performing battery charge calculation on the battery voltage to obtain a battery state of charge;

[0032] Step 603, calculating the battery power according to the battery voltage and the battery temperature to obtain the battery power state;

[0033] Step 604 , performing a remaining power analysis on the battery temperature, the battery state of charge, and the battery power state using a preset remaining power analysis model to obtain the current remaining power.

[0034] In some embodiments, before obtaining target road state information of the vehicle driven by the target object in step 101, the method further includes:

[0035] Step 701, obtaining a driver image through an in-vehicle camera device; wherein the driver image is an image of the driver in the vehicle driven by the target object;

[0036] Step 702, performing driver recognition on the driver image to obtain the target object;

[0037] Step 703, selecting a pre-trained candidate driving parameter prediction model according to the target object to obtain the target driving parameter prediction model corresponding to the target object; wherein the candidate driving parameter prediction model is used to predict the driving parameters of the vehicle.

[0038] To achieve the above-mentioned purpose, the second aspect of an embodiment of the present application proposes a controller, which includes a memory and a processor, the memory stores a computer program, and the processor implements the remaining mileage estimation method described in the first aspect when executing the computer program.

[0039] To achieve the above-mentioned purpose, a third aspect of an embodiment of the present application proposes an electric vehicle, which includes the controller described in the above-mentioned second aspect.

[0040] To achieve the above objectives, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the remaining mileage estimation method described in the first aspect above.

[0041] The remaining mileage estimation method and controller, electric vehicle, and storage medium proposed in the present application adopt a target driving parameter prediction model obtained by pre-training based on sample road state information of the vehicle driven by the target object, and use the target driving parameter prediction model to predict the driving parameters of the target road state information of the vehicle driven by the target object to obtain the predicted driving parameters of the target section, which can predict the driving parameters according to the driving habits of a specific driver, thereby improving the accuracy of the predicted driving parameters of the target section; then, the target predicted total power consumption is determined according to the predicted driving parameters of the target section, and the target remaining mileage is estimated according to the target predicted total power consumption, thereby adapting to the driving style of the specific driver to perform the remaining mileage estimation, providing a more personalized remaining mileage estimation method, avoiding the inconvenience of being unable to reach the destination due to insufficient power, etc., solving the problem of being unable to accurately estimate the remaining mileage, that is, the problem that the estimated remaining mileage is significantly different from the actual mileage of the vehicle, and improving the accuracy of the remaining mileage estimation. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is a flowchart of a remaining mileage estimation method provided in an embodiment of the present application;

[0043] Figure 2 yes Figure 1 Flow chart of step 103 in;

[0044] Figure 3 is a flowchart of a remaining mileage estimation method provided by another embodiment of the present application;

[0045] Figure 4 yes Figure 1 Flowchart of step 102 in FIG.

[0046] Figure 5 yes Figure 1 Flowchart of step 104 in;

[0047] Figure 6 yes Figure 5 Flow chart of step 501 in;

[0048] Figure 7 is a flowchart of a remaining mileage estimation method provided by another embodiment of the present application;

[0049] Figure 8 It is a schematic diagram of the hardware structure of the controller provided in the embodiment of the present application. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0051] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0052] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0053] First, some nouns involved in this application are analyzed:

[0054] Artificial Intelligence (AI): It is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. AI is a branch of computer science. AI attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Research in this field includes robots, language recognition, image recognition, natural language processing and expert systems. AI can simulate the information process of human consciousness and thinking. AI is also a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0055] Machine learning: is a branch of artificial intelligence that enables computer systems to automatically learn and improve their performance using data and algorithms. Machine learning aims to study how computers can simulate or implement the human learning process to improve intelligence and reorganize existing knowledge structures to continuously improve their performance.

[0056] SOC (State of Charge): refers to the ratio of the current charge of the battery to the rated charge, which can be used to reflect the remaining capacity of the battery. Specifically, when the battery is fully charged, the SOC is 100%, and when it is discharged to a complete empty state, the SOC is 0%.

[0057] SOP (State of Power): refers to the maximum power that a battery can output within a certain period of time. SOP involves the battery's charge and discharge power limits.

[0058] The remaining mileage estimation method and controller, electric vehicle, and storage medium provided in the embodiments of the present application are specifically illustrated through the following embodiments. First, the remaining mileage estimation method in the embodiments of the present application is described.

[0059] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0060] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0061] The remaining mileage estimation method provided in the embodiment of the present application can be applied to the terminal, can also be applied to the server side, and can also be software running in the terminal or the server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the remaining mileage estimation method, etc., but is not limited to the above forms.

[0062] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0063] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0064] Figure 1 is an optional flowchart of the remaining mileage estimation method provided in an embodiment of the present application. Figure 1 The method may include but is not limited to steps 101 to 104.

[0065] Step 101, obtaining target road state information of a vehicle driven by a target object; wherein the target road state information is used to characterize the condition of the road on which the vehicle driven by the target object is traveling;

[0066] Step 102, predicting driving parameters of the target road state information by using a pre-trained target driving parameter prediction model to obtain predicted driving parameters of the target road section; wherein the target driving parameter prediction model is trained by sample road state information of the vehicle driven by the target object, and the predicted driving parameters of the target road section are used to characterize the driving speed of the vehicle driven by the target object;

[0067] Step 103, determining a target predicted total power consumption according to the predicted driving parameters of the target road section; wherein the target predicted total power consumption is used to characterize the power consumption predicted for the vehicle driven by the target object;

[0068] Step 104 , estimating the remaining mileage according to the target predicted total power consumption to obtain a target remaining mileage; wherein the target remaining mileage is used to represent the mileage that the vehicle driven by the target object can travel.

[0069] The beneficial effects of the embodiments of the present application include but are not limited to: a target driving parameter prediction model obtained by pre-training based on sample road state information of the vehicle driven by the target object is adopted, and the driving parameter prediction model is used to predict the target road state information of the vehicle driven by the target object to obtain the predicted driving parameters of the target section, and the driving parameters can be predicted according to the driving habits of a specific driver, thereby improving the accuracy of the predicted driving parameters of the target section; then, the target predicted total power consumption is determined according to the predicted driving parameters of the target section, and the target remaining mileage is estimated according to the target predicted total power consumption, so as to adapt to the driving style of the specific driver for the remaining mileage estimation, provide a more personalized remaining mileage estimation method, avoid the inconvenience of being unable to reach the destination due to insufficient power, and solve the problem of being unable to accurately estimate the remaining mileage, that is, the estimated remaining mileage is significantly different from the actual mileage of the vehicle, and improve the accuracy of the remaining mileage estimation.

[0070] In step 101 of some embodiments, the target object refers to the driver. Before obtaining the target road state information, the identity of the target object can be determined first, that is, the identity of the driver in the vehicle can be determined. In some embodiments, the driver can be determined by the in-vehicle camera to obtain the target object. In another embodiment, the target object can be determined by referring to the in-vehicle seat memory position. Among them, the in-vehicle seat memory position information includes the front and rear position, height, and inclination of the seat backrest of the in-vehicle seat, etc. The control device inside the vehicle can store at least one in-vehicle seat memory position information, and each in-vehicle seat memory position information corresponds to a driver's driving preference. The identity of the driver can be reversely confirmed through different in-vehicle seat memory position information. When the driver enters the vehicle, the seat position of the driver's seat is obtained to obtain the current seat position information, and then the front seat position information is matched with the in-vehicle seat memory position stored in the control device. If the current seat position information matches the in-vehicle seat memory position information successfully, the driver corresponding to the in-vehicle seat memory position information is determined as the target object.

[0071] Specifically, the target road state information may include the current road condition (such as a straight road, a curve), traffic volume, speed limit, and the like. The target road state information may also include other conditions of the road on which the vehicle driven by the target object is traveling, which is not limited here. In one embodiment, the target road state information may be obtained through the map software of the vehicle driven by the target object. In another embodiment, the target road state information may also be obtained through a vehicle-mounted sensor. For example, the road image is collected in real time by a vehicle-mounted camera, and the road curvature is judged by a computer vision model to determine the current road condition as a straight road or a curve. Alternatively, the curvature information of the road is updated in real time by a vehicle-mounted radar, which is not limited here.

[0072] In step 102 of some embodiments, the target driving parameter prediction model may be a machine learning model. It is understandable that in current electric vehicles, it is difficult to apply complex algorithms to mileage calculations, for example, there is no operating environment that supports artificial intelligence algorithms. In response to this problem, in an embodiment of the present application, a high-computing-power controller, such as a vehicle domain controller (VDC), is used in the battery management system (Battery Management System, BMS) of the electric vehicle. The vehicle domain controller has powerful computing power, sufficient memory space, and efficient floating-point computing performance, which enables it to smoothly execute the machine learning model (i.e., the target driving parameter prediction model), making the judgment of the remaining mileage more accurate.

[0073] Specifically, the predicted driving parameters of the target road section include speed and acceleration.

[0074] In some embodiments, before step 102, the initial driving parameter prediction model may be trained using sample road state information to obtain a target driving parameter prediction model.

[0075] Specifically, the sample road state information is input into the loss function of the initial driving parameter prediction model to obtain the loss function value. The magnitude of the loss function value is used to reflect the prediction accuracy of the initial driving parameter prediction model. The smaller the loss function value, the closer the prediction result of the model is to the true value. The loss function value is minimized, and then the initial driving parameter prediction model corresponding to the minimized loss function value is determined as the target driving parameter prediction model.

[0076] It is understandable that the target driving parameter prediction model is trained by the initial driving parameter prediction model. The initial driving parameter prediction model is used to predict the driving parameters of the vehicle. For example, the initial driving parameter prediction model can be a machine learning model for predicting vehicle speed.

[0077] It is understandable that the sample road state information is used to characterize the condition of the road on which the vehicle driven by the target object travels. The driver corresponding to the sample road state information and the target road state information is the same driver, and the sample road state information and the target road state information are different information. For example, driver A is determined as the target object, and the driving record of the vehicle driven by driver A three months ago is obtained. Since the driving record includes road state information such as road conditions, traffic flow, speed limit, etc., the road state information r1 can be directly selected from the driving record d1, and the road state information r1 is used as the sample road state information. Alternatively, the sample road state information can also be obtained in other ways, such as obtaining the sample road state information of the vehicle driven by driver A from the historical road state database, which is not limited here. After the target driving parameter prediction model is obtained through sample road state information training, the road state information r2 of the vehicle driven by driver A at the current time (such as the day) is obtained, and the road state information r2 is used as the target road state information.

[0078] In some embodiments, the number of sample road state information may be at least two, that is, the target driving parameter prediction model is trained by at least two sample road state information of the vehicle driven by the target object. It is understandable that, in this case, the vehicle corresponding to each sample road state information may be a different vehicle or the same vehicle, as long as the target object corresponding to the sample road state information is the same. For example, the target object drives vehicle C1 and obtains a sample road state information during this driving process. In addition, the target object also drives vehicle C2 and obtains another sample road state information during this driving process. Among them, vehicle C1 and vehicle C2 may be the same or different vehicles, which is not limited here. The above two sample road state information can be input into the same initial driving parameter prediction model for model training, and the model obtained after training is the target driving parameter prediction model.

[0079] It is understandable that different drivers have different driving habits, which have a greater impact on the remaining mileage estimation. In this regard, the embodiment of the present application uses the sample road state information of the same driver (target object) for model training to obtain a target driving parameter prediction model, which can learn the driver's driving habits under specific road conditions, for example, the driver's vehicle usually has what speed and acceleration for a specific road state (such as a curve). Then, the target road state information of the vehicle driven by the driver is input into the target driving parameter prediction model, so as to more accurately predict the target section predicted driving parameters that meet the driver's driving style, and estimate the remaining mileage based on the target section predicted driving parameters, so as to improve the pertinence and accuracy of the remaining mileage estimation method.

[0080] In some embodiments, different target driving parameter prediction models may be used to predict driving parameters for different drivers. For example, when a first object different from the target object is identified by an in-vehicle camera, a first driving parameter prediction model is used, and the first driving parameter prediction model is trained based on sample road state information of the vehicle driven by the first object.

[0081] In step 103 of some embodiments, it can be understood that the target road section predicted driving parameters include the speed and acceleration of the vehicle driven by the target object on the preset target road section, and the power consumption of the vehicle driven by the target object on the target road section can be calculated according to the target road section predicted driving parameters. For example, the target object enters the destination on the map software of the vehicle and selects the road section for reaching the destination. In some embodiments, the road section for reaching the destination can be obtained from the map software of the vehicle driven by the target object to obtain the target road section.

[0082] In step 104 of some embodiments, the target predicted total power consumption is used to characterize the power consumption generated by the vehicle driven by the target object traveling on the future road section. It is understandable that the vehicle may have traveled a portion of the road section along the target road section. In this case, the target road section includes the traveled road section and the future road section. The traveled road section is the road section that the vehicle driven by the target object has traveled, and the future road section is the road section that the vehicle driven by the target object has not traveled, that is, the part of the target road section between the current position of the vehicle and the destination. In some embodiments, the target remaining mileage estimated according to the target predicted total power consumption is the maximum mileage that the vehicle driven by the target object can travel. After obtaining the target remaining mileage, it can be judged whether the vehicle can reach the preset destination according to the target remaining mileage. For example, if the target remaining mileage is greater than or equal to the mileage of the future road section, it is judged that the vehicle can reach the destination, and the map software starts navigation. If the target remaining mileage is less than the mileage of the future road section, it is judged that the vehicle cannot reach the destination.

[0083] In some embodiments, after estimating the remaining mileage according to the target predicted total power consumption to obtain the target remaining mileage, the method further includes:

[0084] Compare the target remaining mileage with the distance of the preset future driving section;

[0085] If the target remaining mileage is less than the distance of the future driving section, obtain the charging pile information;

[0086] Path planning is performed based on the charging pile information and the target remaining mileage to obtain a target charging path so that the vehicle driven by the target object can reach the charging pile for charging along the target charging path.

[0087] The embodiment of the present application can ensure that, in the event that the vehicle driven by the target object is unable to complete the future driving section, a target charging path is planned to guide the vehicle driven by the target object to an accessible charging pile for charging along the target charging path, thereby preventing the electric vehicle from breaking down during driving due to insufficient power and improving driving safety.

[0088] It is understandable that the charging pile information can be obtained through the map software, specifically, the target distance range can be determined based on the range of a circle with a preset radius centered on the vehicle driven by the target object, and the location information of the charging pile within the target distance range can be obtained. In some embodiments, after obtaining the target charging path, a charging inquiry message can be displayed on the vehicle display screen, or the charging inquiry message can be broadcasted by voice to inquire whether the target object navigates to the charging pile.

[0089] See also Figure 2 In some embodiments, step 103 may include but is not limited to steps 201 to 203:

[0090] Step 201, obtaining the in-vehicle load of the vehicle driven by the target object;

[0091] Step 202, obtaining the target in-vehicle accessory power consumption of the vehicle driven by the target object; wherein the target in-vehicle accessory power consumption is used to characterize the power consumption of the equipment inside the vehicle driven by the target object;

[0092] Step 203 , using a preset vehicle power consumption prediction model, power consumption prediction is performed on the vehicle load, target vehicle accessory power consumption, and target road section predicted driving parameters to obtain a target predicted total power consumption.

[0093] The advantage of this embodiment is that when making power consumption predictions, not only the predicted driving parameters (speed and acceleration) of the target road section are taken into account, but also the load inside the vehicle and the power consumption of the internal equipment of the vehicle are taken into account. Specifically, a preset vehicle power consumption prediction model is used to predict the load inside the vehicle, the power consumption of the target accessories inside the vehicle, and the predicted driving parameters of the target road section to obtain the target predicted total power consumption, thereby making a more comprehensive power consumption prediction, improving the accuracy and reliability of the target predicted total power consumption, and further improving the accuracy and reliability of the target remaining mileage estimated based on the target predicted total power consumption.

[0094] In step 201 of some embodiments, the in-vehicle load may be the total weight of objects inside the vehicle driven by the target object, such as the sum of the weights of the driver, passengers, items, etc. The in-vehicle load may be obtained through an in-vehicle weight sensor or other methods, which are not limited here.

[0095] In step 202 of some embodiments, it can be understood that the equipment inside the vehicle includes but is not limited to a vehicle air conditioner, a vehicle charger, etc. The target in-vehicle accessory power consumption can be the sum of the power consumption of the equipment inside the above-mentioned equipment vehicle. The electrical parameters of the equipment inside the vehicle driven by the target object, such as current and voltage, can be obtained, and the target in-vehicle accessory power consumption is calculated according to the electrical parameters. In some embodiments, the target in-vehicle accessory power consumption is the average power consumption of the equipment inside the above-mentioned equipment vehicle within a preset time period threshold. For example, the time period threshold is 5 minutes, the target object starts the vehicle at time t0, and the power consumption of the equipment inside the vehicle is continuously recorded from the time t0 when the vehicle driven by the target object starts, and the target in-vehicle accessory power consumption is obtained at time t1 (also referred to as the current time). If the time period from time t0 to time t1 (such as 14 minutes) is greater than or equal to the time period threshold (such as 5 minutes), the average power consumption generated in the first 5 minutes of time t1 is calculated, that is, the average power consumption generated within the time period threshold before the current time is calculated, and the average power consumption is determined as the target in-vehicle accessory power consumption. If the time period from t0 to t1 (such as 1 minute) is less than the time period threshold, the average power consumption generated in the time period from the time the vehicle is started to the current time is calculated, that is, the average power consumption generated in the time period from t0 to t1.

[0096] In step 203 of some embodiments, a first power consumption prediction may be performed based on the vehicle load and the target road section predicted driving parameters to obtain a first predicted power consumption, and then the first predicted power consumption and the target vehicle accessory power consumption are summed to obtain a target predicted total power consumption. In some embodiments, the vehicle power consumption prediction model may be a machine learning model.

[0097] See also Figure 3 In some embodiments, before step 102, the remaining mileage estimation method may also include but is not limited to steps 301 to 305:

[0098] Step 301, obtaining sample road state information of a vehicle driven by a target object; wherein the sample road state information includes road state information of at least two consecutive sub-segments, and the road state information of each sub-segment is used to represent the condition of the sub-segment;

[0099] Step 302, performing a first driving parameter prediction on the road state information of the first sub-segment by using a preset initial driving parameter prediction model to obtain a sub-segment predicted driving parameter of the first sub-segment; wherein the sub-segment predicted driving parameter is used to characterize the driving speed of the vehicle driven by the target object on the sub-segment;

[0100] Step 303, performing a second driving parameter prediction on the road state information of each sub-segment after the first one and the predicted driving parameter of the previous sub-segment of each sub-segment after the first one by using the initial driving parameter prediction model, to obtain the sub-segment predicted driving parameter of each sub-segment except the first sub-segment;

[0101] Step 304, calculating the loss value according to the sub-section predicted driving parameters of each sub-section to obtain a target loss value; wherein the target loss value is used to characterize the loss function value of the initial driving parameter prediction model;

[0102] Step 305: Adjust the parameters of the initial driving parameter prediction model according to the target loss value to obtain a target driving parameter prediction model.

[0103] The advantage of this embodiment is that, in order to more accurately perform model training to obtain the target driving parameter prediction model, after obtaining the sample road state information, since the road section corresponding to the sample road state information includes at least two sub-sections, the driving parameter prediction is performed for each sub-section respectively, so that the model training is performed for different road state information existing in different sub-sections (that is, the first or second driving parameter prediction is performed), thereby improving the accuracy of the target driving parameter prediction model. In addition, since each sub-section is continuous, after calculating the sub-section predicted driving parameters of the first sub-section, when calculating the sub-section predicted driving parameters (such as speed, acceleration) of each sub-section after the first sub-section, the sub-section predicted driving parameters of the previous sub-section of the above sub-section will be taken into account, thereby comprehensively considering the impact of the vehicle speed in the previous section on the vehicle speed in the next section, so as to improve the reliability of the target driving parameter prediction model, and then improve the reliability and accuracy of the remaining mileage estimation.

[0104] It is understandable that different sub-segments may have different road state information. For example, sub-segment 1 is a straight road, and the next sub-segment 2 of sub-segment 1 is a curve. Among them, there are significant differences in the road condition characteristics of straight roads and curves, which will have different effects on the speed and acceleration of the vehicle. Through the initial driving parameter prediction model, different road state information is trained separately, so that the initial driving parameter prediction model can better capture and learn these specific road state information, thereby improving the prediction ability of the target driving parameter prediction model.

[0105] In step 301 of some embodiments, the sample road state information includes road conditions (straight road, curve), traffic flow, speed limit, etc. The sample road state information can be obtained from a sample road state database. The driver corresponding to the sample road state information and the target road state information is the same driver, that is, the target object, so as to ensure that the target driving parameter prediction model trained according to the sample road state information is applicable to the target road state information.

[0106] In step 302 of some embodiments, the sub-segment predicted driving parameters include speed and acceleration. The first sub-segment refers to the sub-segment connected to the starting point of the segment corresponding to the sample road state information. For example, the segment corresponding to the sample road state information includes sub-segment 1, sub-segment 2, and sub-segment 3. The vehicle can pass through sub-segment 1, sub-segment 2, and sub-segment 3 from the starting point to reach the destination. Among them, sub-segment 1 is connected to the starting point, that is, sub-segment 1 is the first sub-segment.

[0107] In step 303 of some embodiments, it is understood that the predicted driving parameters of the previous sub-segment of each sub-segment will affect the predicted driving parameters of the sub-segment. For example, the predicted driving parameters include speed and acceleration, and the road state information includes the speed limit. The previous sub-segment of sub-segment 2 is sub-segment 1, and the speed corresponding to sub-segment 1 (such as 90km / h) is greater than the speed limit of sub-segment 2 (such as 60km / h). The greater the speed corresponding to sub-segment 1, the greater the absolute value of the acceleration corresponding to sub-segment 2.

[0108] In step 304 of some embodiments, the initial driving parameter prediction model has a loss function, and the loss value of the sub-segment predicted driving parameters of each sub-segment is calculated using the loss function to obtain a target loss value.

[0109] In step 305 of some embodiments, the parameters of the initial driving parameter prediction model are adjusted according to the target loss value to reduce the target loss value, and the initial driving parameter prediction model with the smallest target loss value is determined as the target driving parameter prediction model.

[0110] See also Figure 4 In some embodiments, step 102 may include but is not limited to steps 401 to 403:

[0111] Step 401, obtaining the current speed and current acceleration of the vehicle driven by the target object;

[0112] Step 402, fusing the current speed, the current acceleration and the target road state information to obtain target driving state information; wherein the target driving state information is used to characterize the driving state of the vehicle driven by the target object;

[0113] Step 403: predicting driving parameters of the target driving state information using a target driving parameter prediction model to obtain predicted driving parameters of the target road section.

[0114] The advantage of this embodiment is that it not only obtains the target road state information, but also obtains the current speed and current acceleration of the vehicle driven by the target object, and then fuses the current speed, current acceleration and target road state information and inputs them into the target driving parameter prediction model to obtain the predicted driving parameters of the target road section. When predicting the driving parameters of the target object, the embodiment of the present application also considers the current speed and current acceleration of the target object in addition to the target road state information, thereby improving the accuracy of the predicted driving parameters of the target road section and realizing the learning of the driving style of the target object.

[0115] It is understandable that the current speed can be obtained through a vehicle speed sensor, and the current acceleration can be obtained through an acceleration sensor. The current speed and current acceleration can also be obtained through other methods, which are not limited here.

[0116] In some embodiments, specifically, the target driving state information includes current speed, current acceleration and target road state information.

[0117] See also Figure 5 In some embodiments, step 104 may include but is not limited to steps 501 to 504:

[0118] Step 501, obtaining the current remaining power of the vehicle driven by the target object;

[0119] Step 502, multiplying the first regression coefficient of the pre-trained target linear regression model by the current remaining power to obtain a first remaining mileage influence factor; wherein the first remaining mileage influence factor is used to characterize the influence factor of the remaining mileage of the vehicle driven by the target object;

[0120] Step 503, multiplying the second regression coefficient of the target linear regression model and the target predicted total power consumption to obtain a second remaining mileage influence factor; wherein the second remaining mileage influence factor is used to characterize the influence factor of the remaining mileage of the vehicle driven by the target object;

[0121] Step 504 , summing up the random error term of the target linear regression model, the first remaining mileage influencing factor, and the second remaining mileage influencing factor to obtain the target remaining mileage.

[0122] The advantage of this embodiment is that the remaining mileage is estimated by using a target linear regression model to estimate the current remaining power and the target predicted total power consumption to obtain the target remaining mileage. After estimating the target predicted total power consumption based on the driving habits of the target object, the target remaining mileage can be estimated based on the target predicted total power consumption, thereby improving the accuracy and pertinence of the remaining mileage estimation.

[0123] In step 501 of some embodiments, the current remaining power can be obtained through the vehicle system of the vehicle driven by the target object, such as the BMS system. The current remaining power can be expressed in the form of percentage or in the form of value.

[0124] In step 502 of some embodiments, the target linear regression model is trained using sample remaining power and sample predicted total power consumption of the vehicle driven by the target object.

[0125] In step 503 of some embodiments, the first regression coefficient and the second regression system are both preset parameters of the target linear regression model. The first regression coefficient and the second regression system can be the same or different, without limitation.

[0126] In step 504 of some embodiments, the random error term is a preset parameter of the target linear regression model.

[0127] See also Figure 6 In some embodiments, step 501 may include but is not limited to steps 601 to 604:

[0128] Step 601, obtaining the battery voltage and battery temperature of the vehicle driven by the target object;

[0129] Step 602, performing battery charge calculation on the battery voltage to obtain the battery charge state;

[0130] Step 603, calculating the battery power according to the battery voltage and the battery temperature to obtain the battery power state;

[0131] Step 604 , performing a remaining power analysis on the battery temperature, the battery state of charge and the battery power state using a preset remaining power analysis model to obtain the current remaining power.

[0132] The advantage of this embodiment is that the battery state of charge is calculated based on the battery voltage of the vehicle driven by the target object, and the battery power state is calculated based on the battery voltage and battery temperature. The battery temperature, battery state of charge and battery power state are then input into a remaining power analysis model to calculate the current remaining power, thereby being able to estimate the remaining mileage based on the current remaining power.

[0133] In step 601 of some embodiments, the battery voltage and battery temperature may be obtained through the BMS system, or may be obtained through other methods, which are not limited here.

[0134] In step 602 of some embodiments, the battery voltage is the voltage of the battery of the vehicle driven by the target object. The battery charge calculation method can be used to calculate the battery charge of the battery voltage to obtain the battery charge state. For example, the battery charge calculation method includes but is not limited to the real-time integration method, the open circuit voltage method, and the Kalman filter method. The battery charge calculation of the battery voltage can also be performed using a machine learning model without limitation.

[0135] In step 603 of some embodiments, the battery power state may be calculated using a preset battery power algorithm, such as an Extended Kalman Filter (EKF) algorithm.

[0136] In step 604 of some embodiments, the remaining power analysis model is a machine learning model.

[0137] See also Figure 7 In some embodiments, before step 101, the remaining mileage estimation method may also include but is not limited to steps 701 to 703:

[0138] Step 701, obtaining a driver image through an in-vehicle camera device; wherein the driver image is an image of the driver in the vehicle driven by the target object;

[0139] Step 702, performing driver recognition on the driver image to obtain a target object;

[0140] Step 703, select a pre-trained candidate driving parameter prediction model according to the target object to obtain a target driving parameter prediction model corresponding to the target object; wherein the candidate driving parameter prediction model is used to predict the driving parameters of the vehicle.

[0141] The advantage of this embodiment is that, in the case of different drivers, the driver's image can be acquired through the in-vehicle camera device, the target object can be identified based on the driver's image, and then the target driving parameter prediction model corresponding to the target object can be selected from the pre-trained candidate driving parameter prediction models, so as to obtain a model corresponding to the specific driver, that is, the target driving parameter prediction model corresponding to the target object, so that the driving parameters predicted by the target driving parameter prediction model can reflect the driving habits of the specific driver (that is, the target object).

[0142] Specifically, different candidate driving parameter prediction models are models trained based on data of different drivers.

[0143] The embodiment of the present application also provides a controller, the controller includes a memory and a processor, the memory stores a computer program, and the processor implements the above remaining mileage estimation method when executing the computer program. The controller can include any intelligent terminal such as a tablet computer and a car computer.

[0144] See also Figure 8 , Figure 8 The hardware structure of a controller of another embodiment is illustrated, and the controller includes:

[0145] The processor 801 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0146] The memory 802 may be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 802 may store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 802, and the processor 801 calls and executes the remaining mileage estimation method of the embodiment of this application;

[0147] Input / output interface 803, used to implement information input and output;

[0148] The communication interface 804 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.);

[0149] A bus 805 that transmits information between the various components of the device (e.g., the processor 801, the memory 802, the input / output interface 803, and the communication interface 804);

[0150] The processor 801 , the memory 802 , the input / output interface 803 and the communication interface 804 are connected to each other in communication within the device via a bus 805 .

[0151] An embodiment of the present application also provides an electric vehicle, which includes the above-mentioned controller.

[0152] The specific implementation of the electric vehicle is substantially the same as the specific implementation of the remaining mileage estimation method described above, and will not be described in detail herein.

[0153] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned remaining mileage estimation method is implemented.

[0154] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0155] It should be noted that the non-Company's software tools or components that appear in the embodiments of the present application are merely examples and do not represent actual use.

[0156] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0157] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0158] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0159] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0160] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0161] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0162] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. The mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0163] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0164] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0165] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0166] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for estimating remaining mileage, characterized in that: The method comprises: Step 101, obtaining target road state information of a vehicle driven by a target object; wherein the target road state information is used to characterize the condition of the road on which the vehicle driven by the target object is traveling; Step 102, predicting driving parameters of the target road state information by using a pre-trained target driving parameter prediction model to obtain predicted driving parameters of a target road section; wherein the target driving parameter prediction model is trained by sample road state information of the vehicle driven by the target object, and the predicted driving parameters of the target road section are used to characterize the driving speed of the vehicle driven by the target object; Step 103, determining a target predicted total power consumption according to the predicted driving parameters of the target road section; wherein the target predicted total power consumption is used to represent the power consumption predicted for the vehicle driven by the target object; Step 104 , estimating the remaining mileage according to the target predicted total power consumption to obtain a target remaining mileage; wherein the target remaining mileage is used to represent the mileage that the vehicle driven by the target object can travel.

2. The remaining mileage estimation method according to claim 1, characterized in that: The step 103, determining a target predicted total power consumption according to the predicted driving parameters of the target road section, includes: Step 201, obtaining the in-vehicle load of the vehicle driven by the target object; Step 202, obtaining target in-vehicle accessory power consumption of the vehicle driven by the target object; wherein the target in-vehicle accessory power consumption is used to characterize the power consumption of the equipment inside the vehicle driven by the target object; Step 203 , using a preset vehicle power consumption prediction model, power consumption prediction is performed on the vehicle load, the target vehicle accessory power consumption, and the target road section predicted driving parameters to obtain the target predicted total power consumption.

3. The remaining mileage estimation method according to claim 1, characterized in that: In step 102, before predicting the driving parameters of the target road state information by using the pre-trained target driving parameter prediction model to obtain the predicted driving parameters of the target road section, the method further includes: Step 301, obtaining the sample road state information of the vehicle driven by the target object; wherein the sample road state information includes road state information of at least two consecutive sub-segments, and the road state information of each sub-segment is used to represent the condition of the sub-segment; Step 302, performing a first driving parameter prediction on the road state information of the first sub-segment by using a preset initial driving parameter prediction model to obtain a sub-segment predicted driving parameter of the first sub-segment; wherein the sub-segment predicted driving parameter is used to characterize the driving speed of the vehicle driven by the target object on the sub-segment; Step 303, performing a second driving parameter prediction on the road state information of each of the sub-segments after the first one and the predicted driving parameters of the previous sub-segment of each of the sub-segments after the first one by using the initial driving parameter prediction model, to obtain the sub-segment predicted driving parameters of each of the sub-segments except the first sub-segment; Step 304, calculating a loss value according to the sub-segment predicted driving parameters of each of the sub-segments to obtain a target loss value; wherein the target loss value is used to characterize a loss function value of the initial driving parameter prediction model; Step 305: Adjust the parameters of the initial driving parameter prediction model according to the target loss value to obtain the target driving parameter prediction model.

4. The remaining mileage estimation method according to claim 1, characterized in that: The step 102, predicting the driving parameters of the target road state information by using a pre-trained target driving parameter prediction model to obtain the predicted driving parameters of the target road section, includes: Step 401, obtaining the current speed and current acceleration of the vehicle driven by the target object; Step 402, fusing the current speed, the current acceleration and the target road state information to obtain target driving state information; wherein the target driving state information is used to characterize the driving state of the vehicle driven by the target object; Step 403: Perform driving parameter prediction on the target driving state information using the target driving parameter prediction model to obtain predicted driving parameters of the target road section.

5. The remaining mileage estimation method according to claim 1, characterized in that: The step 104, estimating the remaining mileage according to the target predicted total power consumption to obtain the target remaining mileage, includes: Step 501, obtaining the current remaining power of the vehicle driven by the target object; Step 502, multiplying the first regression coefficient of the pre-trained target linear regression model by the current remaining power to obtain a first remaining mileage influence factor; wherein the first remaining mileage influence factor is used to characterize an influence factor of the remaining mileage of the vehicle driven by the target object; Step 503, multiplying the second regression coefficient of the target linear regression model and the target predicted total power consumption to obtain a second remaining mileage influence factor; wherein the second remaining mileage influence factor is used to characterize an influence factor of the remaining mileage of the vehicle driven by the target object; Step 504 , obtaining the target remaining mileage by summing the random error term of the target linear regression model, the first remaining mileage influencing factor, and the second remaining mileage influencing factor.

6. The remaining mileage estimation method according to claim 5, characterized in that: The step 501, obtaining the current remaining power of the vehicle driven by the target object, includes: Step 601, obtaining the battery voltage and battery temperature of the vehicle driven by the target object; Step 602, performing battery charge calculation on the battery voltage to obtain a battery state of charge; Step 603, calculating the battery power according to the battery voltage and the battery temperature to obtain the battery power state; Step 604 , performing a remaining power analysis on the battery temperature, the battery state of charge, and the battery power state using a preset remaining power analysis model to obtain the current remaining power.

7. The remaining mileage estimation method according to any one of claims 1 to 5, characterized in that: Before obtaining the target road state information of the vehicle driven by the target object in step 101, the method further includes: Step 701, obtaining a driver image through an in-vehicle camera device; wherein the driver image is an image of the driver in the vehicle driven by the target object; Step 702, performing driver recognition on the driver image to obtain the target object; Step 703, selecting a pre-trained candidate driving parameter prediction model according to the target object to obtain the target driving parameter prediction model corresponding to the target object; wherein the candidate driving parameter prediction model is used to predict the driving parameters of the vehicle.

8. A controller, characterized in that: The controller includes a memory and a processor, the memory stores a computer program, and the processor implements the remaining mileage estimation method according to any one of claims 1 to 7 when executing the computer program.

9. An electric vehicle, characterized in that: The electric vehicle comprises the controller according to claim 8.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the remaining mileage estimation method according to any one of claims 1 to 7 is implemented.

Images