Method and device for predicting endurance mileage of vehicle and electronic equipment
By using prediction models in cloud servers combined with driver information and historical information, considering road conditions and environmental parameters, the problem of low prediction accuracy in vehicle range in the prior art is solved, and higher prediction accuracy and vehicle intelligence are achieved Management in a comprehensive way.
Patent Information
- Application Number
- CN202411116232.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-14
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
Smart Images

Figure CN118906826A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the field of vehicle technology, and specifically to a method, device and electronic device for predicting vehicle range. Background Art
[0002] When a user is driving a vehicle, the remaining cruising range of the vehicle affects the user's travel plan. Therefore, it is necessary to predict the remaining cruising range of the vehicle.
[0003] In some technologies, the remaining cruising range of a vehicle is calculated by the historical average energy consumption of the vehicle and the current remaining power of the vehicle. The above solution does not take into account factors such as the current road conditions and environmental changes of the vehicle, and the prediction accuracy of the remaining cruising range is low. Summary of the invention
[0004] In view of the above problems, the embodiments of the present application provide a method, device and electronic device for predicting the remaining cruising range of a vehicle, which are used to improve the prediction accuracy of the remaining cruising range of the vehicle.
[0005] In a first aspect, an embodiment of the present application provides a method for predicting vehicle range, which is applied to a cloud server, and the method includes:
[0006] receiving a first request from a vehicle end, the first request including driver information of the vehicle end and vehicle history information related to the driver information;
[0007] The driver information and vehicle history information are input into the prediction model to predict the remaining energy storage information on the vehicle side and the average energy consumption information of the driver driving the vehicle;
[0008] Determine a first remaining cruising range of the vehicle at the current moment according to the remaining energy storage information and the average energy consumption information;
[0009] A first response is sent to the vehicle end, where the first response includes a first remaining cruising range.
[0010] In a second aspect, an embodiment of the present application provides a method for predicting vehicle range, which is applied to a vehicle side, and the method includes:
[0011] After the vehicle is unlocked or started, obtaining the driver information of the vehicle and the vehicle history information related to the driver information;
[0012] Sending a first request to a cloud server, the first request including driver information and vehicle history information;
[0013] Receiving a first response from the cloud server, the first response including a first remaining cruising range, the first remaining cruising range being determined by the cloud server based on the driver information and the vehicle history information;
[0014] A second remaining cruising range is displayed on the display device, where the second remaining cruising range is the first remaining cruising range or the third remaining cruising range, and the third remaining cruising range is determined based on the first remaining cruising range.
[0015] In a third aspect, an embodiment of the present application provides a vehicle range prediction device, comprising:
[0016] A processing module, configured to receive a first request from a vehicle end, wherein the first request includes driver information of the vehicle end and vehicle history information related to the driver information;
[0017] The processing module is also used to input the driver information and the vehicle history information into the prediction model to predict the remaining energy storage information of the vehicle and the average energy consumption information of the driver driving the vehicle;
[0018] The processing module is further used to determine a first remaining cruising range of the vehicle at a current moment according to the remaining energy storage information and the average energy consumption information;
[0019] The sending module is used to send a first response to the vehicle end, and the first response includes a first remaining cruising range.
[0020] In a fourth aspect, an embodiment of the present application provides a vehicle range prediction device, comprising:
[0021] An acquisition module, used to acquire the driver information of the vehicle and the vehicle history information related to the driver information after the vehicle is unlocked or started;
[0022] A sending module, used for sending a first request to a cloud server, wherein the first request includes driver information and vehicle history information;
[0023] a processing module, configured to receive a first response from a cloud server, the first response including a first remaining cruising range, the first remaining cruising range being determined by the cloud server according to driver information and vehicle history information;
[0024] The display module is also used to display a second remaining cruising range on the display device, where the second remaining cruising range is the first remaining cruising range or the third remaining cruising range, and the third remaining cruising range is determined based on the first remaining cruising range.
[0025] In a fifth aspect, an embodiment of the present application provides an electronic device, including:
[0026] A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus;
[0027] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute the method provided by the first aspect above, or execute the method provided by the second aspect above.
[0028] In a sixth aspect, an embodiment of the present application provides a computer-readable storage medium, in which at least one executable instruction is stored. When the executable instruction is executed on an electronic device, the electronic device executes the method provided in the first aspect above, or executes the method provided in the second aspect above.
[0029] In a seventh aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method provided in the first aspect or the method provided in the second aspect.
[0030] The embodiment of the present application provides a method, device and electronic device for predicting vehicle cruising range, which deploys a prediction model on a cloud server and obtains driver information and vehicle history information related to the driver information on the vehicle side. The vehicle side sends a request to the cloud server, which responds and predicts and calculates the remaining cruising range of the vehicle, returns it to the vehicle side, and is displayed by the display device on the vehicle side. This is used to achieve the effect of improving the prediction accuracy of the vehicle's remaining cruising range.
[0031] The above description is only an overview of the technical solution of the embodiment of the present application. In order to more clearly understand the technical means of the embodiment of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiment of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] The accompanying drawings are only used to illustrate the embodiments and are not to be considered as limiting the present application. In addition, the same reference symbols are used to represent the same components throughout the accompanying drawings. In the accompanying drawings:
[0033] Figure 1 Schematic diagram of the process of predicting vehicle cruising range provided in this application Figure 1 ;
[0034] Figure 2 is a schematic diagram of an exemplary interactive interface;
[0035] Figure 3 A schematic diagram of obtaining prompts for an exemplary driver's face image;
[0036] Figure 4 Schematic diagram of the process of predicting vehicle cruising range provided in this application Figure 2 ;
[0037] Figure 5 is a schematic diagram of the structure of an exemplary prediction model;
[0038] Figure 6 Schematic diagram of the process of predicting vehicle cruising range provided in this application Figure 3 ;
[0039] Figure 7 Schematic diagram of the linear relationship between the exemplary remaining energy storage information M2 and the temperature T in the environmental parameters;
[0040] Figure 8 is a schematic diagram of the linear relationship between exemplary average energy consumption information M3 and temperature T in environmental parameters;
[0041] Fig. 9 A schematic diagram of the structure of the vehicle range prediction device provided in this application Figure 1 ;
[0042] Fig.10 A schematic diagram of the structure of the vehicle range prediction device provided in this application Figure 2 ;
[0043] Fig.11 A schematic diagram of the structure of the electronic device provided in this application.
[0044] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION
[0045] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein.
[0046] First, the terms involved in this application are explained.
[0047] Vehicle: refers to automobiles, including but not limited to traditional internal combustion engine vehicles and new energy vehicles. New energy vehicles include but are not limited to pure electric vehicles and hybrid vehicles.
[0048] Remaining cruising range: refers to the maximum distance the vehicle can travel continuously with the current stored energy until the energy is exhausted.
[0049] With the rapid development of vehicle technology, cars have become a common means of transportation. As a means of transportation, the remaining range of a vehicle affects the user's travel planning. Users can understand the current operating status of the vehicle based on the remaining range and decide whether to refuel or charge. Therefore, it is necessary to predict the remaining range of the vehicle.
[0050] In some embodiments, the remaining cruising range of the vehicle is calculated based on the announced energy consumption standards and the energy currently stored in the vehicle. Among them, the announced energy consumption standards include but are not limited to the Worldwide Harmonized Light Vehicles Test Cycle (WLTC cruising range standard) and the China Light-duty Vehicle Test Cycle (CLTC cruising range standard). In the above scheme, the driving conditions reflected in the announced energy consumption standards are different from the actual driving conditions of the user, and the accuracy of the calculation of the remaining cruising range of the vehicle is low.
[0051] In some embodiments, the remaining cruising range of the vehicle is calculated based on the historical average energy consumption recorded by the vehicle and the energy currently stored in the vehicle. In the above scheme, factors such as changes in road conditions, user driving habits, and changes in vehicle environment are not considered, and the accuracy of the remaining cruising range calculation of the vehicle is low.
[0052] It can be seen from this that the solution in the above embodiment has the problem of low accuracy in calculating the remaining cruising range of the vehicle.
[0053] In this regard, the embodiment of the present application provides a method, device and electronic device for predicting the cruising range of a vehicle. By obtaining the driver information of the vehicle and the vehicle history information of the driver on the vehicle side, a request is sent to the cloud server; the cloud server responds to the request, obtains the remaining energy storage information of the vehicle and the average energy consumption information of the driver through the prediction model, determines the cruising range and returns it to the vehicle side, and the vehicle side displays the cruising range information. Improve the prediction accuracy of the remaining cruising range of the vehicle.
[0054] The technical solution of the present application is described in detail below through specific embodiments. It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.
[0055] Figure 1 Schematic diagram of the process of predicting vehicle cruising range provided in this application Figure 1 .like Figure 1 As shown, the method includes:
[0056] Step 101. After the vehicle is unlocked or started, the vehicle end obtains the driver information of the vehicle and the vehicle history information related to the driver information.
[0057] Before the user drives the vehicle, the user needs to unlock or start the vehicle. In one example, the user unlocks the vehicle remotely through a Bluetooth key. In another example, the vehicle is equipped with a fingerprint unlocking device, and the user unlocks the vehicle through a fingerprint. After entering the vehicle, the user starts the vehicle by pressing the start button inside the vehicle.
[0058] After the vehicle is unlocked or started, the vehicle end obtains the driver information of the current driver driving the vehicle. As an example, the driver information includes the driver's ID. The driver's ID is used to uniquely identify and recognize the driver. Based on the driver's ID, the vehicle end searches the local database for the driver information corresponding to the ID and the vehicle history information related to the driver information. The local database includes the IDs of one or more drivers who have used the vehicle, as well as the driver information corresponding to each driver's ID and the vehicle history information related to the driver information. Among them, the vehicle history information related to the driver information includes at least one item of the driving habit information of the vehicle, historical navigation route information, historical vehicle use environment information, and vehicle status information.
[0059] Furthermore, the vehicle usage habit information includes but is not limited to the driver's travel patterns, commuting time, customary vehicle settings, customary vehicle speed, driving intensity, age, etc.
[0060] Furthermore, the historical navigation route information includes but is not limited to the type of route the driver drives the vehicle, route altitude, route height difference, congestion information, route topology trajectory, etc. It should be noted that when the user uses navigation, the route information on the current navigation route can be used. When the user does not use navigation, the vehicle-side processor can determine whether the current travel route is a historical navigation route. If the current travel route is a historical navigation route, the route information on the historical navigation route is used; otherwise, the historical navigation route information can be set to an empty set.
[0061] Furthermore, the historical vehicle use environment information includes but is not limited to weather, temperature, wind speed, air humidity, temperature difference between day and night, etc. It should be noted that the historical vehicle use environment information can be the average situation in the time period before the current vehicle use, or it can be the vehicle use environment information collected by the vehicle-side sensor during the current vehicle use.
[0062] Furthermore, the vehicle status information includes but is not limited to vehicle type, vehicle purpose, vehicle load, vehicle voltage load, vehicle component status, etc.
[0063] It should be noted that the method of obtaining the driver information of the vehicle is not limited. For details, please refer to the embodiments shown below.
[0064] In the above example, the vehicle side obtains driver information including the driver's identity, driving habits, etc., as well as vehicle history information related to the driver information, including navigation route information, vehicle usage environment information and vehicle status information, taking into account multiple factors to lay the foundation for subsequent prediction of cruising range.
[0065] Step 102. The vehicle sends a first request to the cloud server, and the first request includes driver information and vehicle history information.
[0066] The vehicle sends a request to the cloud server, which includes the driver information of the vehicle obtained by the vehicle and the vehicle history information related to the driver information. As an example, the driver information of the vehicle is represented in array form, denoted as U1. The vehicle history information related to the driver information is represented in array form, denoted as M1.
[0067] In one example, the vehicle sends a request to the cloud server, and the request includes U1 and M1.
[0068] In another example, the U1 and M1 obtained by the vehicle can be uploaded to the cloud server synchronously during the non-use period, and the cloud server can store U1 and M1 in association. Therefore, the vehicle sends a request to the cloud server, which can only include U1, and the cloud server determines the corresponding M1 based on U1.
[0069] Step 103. The cloud server receives a first request from the vehicle side, where the first request includes the driver information of the vehicle side and vehicle history information related to the driver information.
[0070] The cloud server parses the received request and obtains the driver information of the vehicle and the vehicle history information related to the driver information.
[0071] Step 104. The cloud server inputs the driver information and vehicle history information into the prediction model to predict the remaining energy storage information on the vehicle side and the average energy consumption information of the driver when driving the vehicle.
[0072] The cloud server is configured with a prediction model, which can be trained using a Transformer model structure based on a constructed training data set. The input of the prediction model includes driver information and vehicle history information, and the output of the prediction model includes the remaining energy storage information on the vehicle side and the average energy consumption information of the driver driving the vehicle. For the specific structure of the prediction model and the processing logic within the model, please refer to the embodiments below, which will not be elaborated here.
[0073] Step 105. The cloud server determines the first remaining cruising range of the vehicle at the current moment based on the remaining energy storage information and the average energy consumption information.
[0074] As an example, the remaining energy storage information of the vehicle is represented in array form, which is recorded as M2. The average energy consumption information of the driver driving the vehicle is represented in array form, which is recorded as M3.
[0075] Furthermore, the remaining energy storage information M2 of the vehicle side includes at least one of the following: the remaining fuel amount of the vehicle side, and the remaining available power of the power battery of the vehicle side. The remaining fuel amount of the vehicle side can be represented by the volume of the remaining fuel, for example, the remaining fuel amount is 50L; the remaining available power of the power battery of the vehicle side can be represented by a percentage, for example, the remaining available power is 75%.
[0076] Furthermore, the average energy consumption information M3 of the driver driving the vehicle includes at least one of the following: the driver's electricity consumption in at least a historical mileage, and the driver's fuel consumption in at least a historical mileage.
[0077] The average energy consumption information of the driver driving the vehicle refers to the energy consumption of the driver driving the vehicle within a certain mileage. Taking a traditional internal combustion engine vehicle as an example, the vehicle consumes 0.72L of fuel within the historical 10km of driving. Based on this calculation, the fuel consumption per unit mileage of the vehicle is 0.072L / km.
[0078] Taking into account the different road conditions of the driver, the vehicle will calculate the energy consumption per mileage within different historical mileage ranges. In actual applications, the energy consumption per mileage within different historical mileage ranges may be different. For example, within the historical 30km, the first 20km is a freeway road, and the last 10km is a congested city road. Due to the different driving speeds on highways and urban roads, the fuel consumption is different. For example, the vehicle consumed 2.1L of fuel within the historical 30km, based on which the fuel consumption per mileage of the vehicle is calculated to be 0.07L / km; and the vehicle consumed 1L of fuel within the historical 10km, based on which the fuel consumption per mileage of the vehicle is calculated to be 0.1L / km. The comparison shows that there is a difference in the fuel consumption per mileage within the historical 30km and the historical 10km. In order to prevent the inaccurate calculation of the remaining cruising range caused by the difference in the fuel consumption per mileage within different historical mileages, appropriate judgment logic is required to select which section of the historical mileage to use for the energy consumption per mileage.
[0079] For the unit mileage energy consumption within multiple different historical mileage ranges, if there is a large difference between the unit mileage energy consumption within different historical mileage ranges, the unit mileage energy consumption calculated within the longer historical mileage range is selected to calculate the remaining cruising range; if the difference between the unit mileage energy consumption within different historical mileage ranges is small or there is no difference, the unit mileage energy consumption calculated within the shorter historical mileage range is selected to calculate the remaining cruising range.
[0080] In one example, the fuel consumption per mileage of the vehicle within the historical 10 km, historical 20 km, and historical 30 km is calculated respectively, and the difference in the fuel consumption per mileage within different historical mileages is calculated. Specifically, the variance between the fuel consumption per mileage within different historical mileages is calculated. The larger the variance, the greater the difference between the numerical values, and vice versa. If the calculated variance between the fuel consumption per mileage within different historical mileages is greater than or equal to the threshold, the fuel consumption per mileage within the historical 30 km is selected as the driver's fuel consumption in the historical mileage; if the calculated variance between the fuel consumption per mileage within different historical mileages is less than the threshold, the fuel consumption per mileage within the historical 10 km is selected as the driver's fuel consumption in the historical mileage.
[0081] For new energy vehicles, the judgment logic of the above example is still valid, and the power consumption per mileage within different historical mileages is used for judgment. As an example, the power consumption per mileage within the historical 10km, historical 20km, and historical 30km of the vehicle is calculated respectively, and the variance of the power consumption per mileage within different historical mileages is calculated. If the calculated variance between the power consumption per mileage within different historical mileages is greater than or equal to the threshold, the power consumption per mileage within the historical 30km is selected as the driver's power consumption in the historical mileage; if the calculated variance between the power consumption per mileage within different historical mileages is less than the threshold, the power consumption per mileage within the historical 10km is selected as the driver's power consumption in the historical mileage.
[0082] In the above example, the variance of the energy consumption per mileage in different historical mileages is calculated to determine the driver's energy consumption in the historical mileage, eliminate the difference in energy consumption per mileage caused by differences in road conditions, and improve the accuracy of subsequent calculations of the remaining cruising range.
[0083] In step 105, as an example, the remaining cruising range of the vehicle at the current moment is calculated by using the remaining energy storage information and the average energy consumption information, specifically including:
[0084] Step 1051. Determine the remaining energy storage capacity of the vehicle end based on the remaining fuel amount of the vehicle end, the remaining available power of the power battery and the preset first oil-to-electricity conversion coefficient.
[0085] Step 1052. Determine the historical energy consumption information per unit mileage of the vehicle end based on the electricity consumption of at least one historical mileage, the fuel consumption of at least one historical mileage, and a preset second fuel-to-electricity conversion coefficient.
[0086] Step 1053. Determine the first remaining cruising range based on the remaining energy storage capacity of the vehicle and the historical energy consumption information per unit mileage of the vehicle.
[0087] It should be noted that the above steps 1051 and 1052 may be executed sequentially or simultaneously, and the present application does not limit the execution order of the above steps 1051 and 1052.
[0088] In one example, the cloud server may determine the first remaining cruising range of the vehicle at the current moment by the following formula:
[0089]
[0090] Where, M4 is the first remaining cruising range, M2 Oil K1 Oil2Elc +M2 BattElc Indicates the remaining energy storage at the vehicle end, (M3 OilConsump / M3 OilRange )·K2 Oil2Elc +(M3 ElcConsump / M3 ElcRange ) represents the historical energy consumption information of the vehicle per unit mileage. Specifically, M2 Oil is the remaining fuel amount at the vehicle end, K1 Oil2Elc is the first oil-to-electric conversion calculation coefficient, M2 BattElc The remaining available power of the vehicle's power battery, M3 OilConsump is the fuel consumption of the current driver driving the vehicle, M3 OilRange K2 is the mileage corresponding to the fuel consumption of the current driver. Oil2Elc is the second oil-to-electricity conversion calculation coefficient, M3 ElcConsump M3 is the current power consumption of the driver driving the vehicle. ElcRange The mileage corresponding to the power consumption of the current driver when driving the vehicle.
[0091] It should be noted that the above M2 Oil 、M2 BattElc are all elements of the remaining energy storage information M2 at the vehicle end; the above M3 OilConsump 、M3 ElcConsump 、M3ElcRange All are elements of the average energy consumption information M3 of the driver driving the vehicle.
[0092] It should be noted that formula (1) can be adapted to a variety of vehicles.
[0093] For traditional internal combustion engine vehicles, the vehicle is driven only by the energy of gasoline or fuel combustion. Therefore, the remaining available power M2 of the power battery at the vehicle end BattElc 、The current power consumption of the driver driving the vehicle M3 ElcConsump , the mileage corresponding to the amount of electricity consumed by the current driver driving the vehicle M3 ElcRange All are 0; the first oil-to-electric conversion calculation coefficient K1 Oil2Elc 、The second oil-to-electric conversion calculation coefficient K2 Oil2Elc All are 1. At this point, only the physical quantity related to fuel consumption remains in formula (1), and the remaining cruising range of traditional internal combustion engine vehicles can be calculated.
[0094] For pure electric vehicles, the vehicle is driven only by the power of the power battery. Therefore, the remaining fuel amount M2 on the vehicle side Oil 、The current fuel consumption of the driver driving the vehicle M3 OilConsump , the mileage corresponding to the fuel consumption consumed by the current driver driving the vehicle M3 OilRange 、The first oil-to-electric conversion calculation coefficient K1 Oil2Elc , The second oil-to-electric conversion calculation coefficient K2 Oil2Elc are all 0. At this point, only the physical quantity related to the power consumption remains in formula (1), and the remaining cruising range of the pure electric vehicle can be calculated.
[0095] In the above example, the remaining cruising range is calculated by formula (1), and formula (1) is adaptively designed for vehicles of different energy types and can be adapted to the calculation of the remaining cruising range of different types of vehicles.
[0096] Step 106. The cloud server sends a first response to the vehicle end, the first response including the first remaining cruising range. The cloud server returns the value of the first remaining cruising range calculated in step 105 to the vehicle end through the first response.
[0097] Step 107. The vehicle receives a first response from the cloud server, where the first response includes a first remaining cruising range, which is determined by the cloud server based on the driver information and vehicle history information.
[0098] The vehicle receives the response from the cloud server and parses the first remaining cruising range contained in the response. Specifically, the cloud server predicts the remaining energy storage information M2 of the vehicle and the average energy consumption information M3 of the driver driving the vehicle based on the driver information U1 and the vehicle history information M1 through a model. Based on the elements in M2 and M3, the first remaining cruising range M4 is calculated according to formula (1).
[0099] Step 108. The vehicle side displays the second remaining cruising range on the display device, and the second remaining cruising range is the first remaining cruising range.
[0100] The display device on the vehicle side includes but is not limited to the vehicle dashboard, the in-vehicle display screen, etc. As an example, the second remaining cruising range is recorded as M final . Assign the value of the first cruising range M4 to M final , so that the display device displays M final .
[0101] In the above embodiment, the driver information and vehicle history information are obtained by the vehicle side and sent to the cloud server. The remaining energy storage information and the average energy consumption information are predicted by the prediction model configured by the cloud server. The remaining cruising range is calculated based on the remaining energy storage information and the average energy consumption information, and sent to the vehicle side, which updates the remaining cruising range on the display device. On the one hand, based on the driver information and vehicle history information including various factors obtained by the vehicle side, the prediction model is used to predict and calculate the remaining cruising range, thereby improving the prediction accuracy of the remaining cruising range. On the other hand, the prediction model and the prediction and calculation of the remaining cruising range are all performed on the cloud server, and transmitted to the vehicle side through data, thereby reducing the computing load on the vehicle side.
[0102] In step 101 of the above embodiment, the vehicle side needs to determine the identity of the driver currently driving the vehicle, that is, to obtain the driver information of the vehicle side. Based on the above embodiment, the specific way to obtain the driver information includes but is not limited to automatically connected Bluetooth terminal recognition, driver face recognition, vehicle computer login account recognition, driver weight recognition, etc.
[0103] In one example, the vehicle side identifies a terminal connected to the vehicle side and obtains driver information associated with the terminal.
[0104] Specifically, the user holds a terminal device, and the terminal device is connected to the vehicle side. The connection method is not limited, and includes but is not limited to Bluetooth connection, Near Field Communication (NFC), etc. Taking Bluetooth connection as an example, the vehicle side is equipped with a Bluetooth communication module, and the user holds a terminal device. The Bluetooth communication module can identify the user's terminal device and determine the identification code of the terminal device. The local database of the vehicle side is preset with the driver information associated with the terminal device identification code, and the Bluetooth communication module is connected to the local database. When the user enters the communication range of the Bluetooth communication module, the vehicle side identifies the identification code of the current terminal device through the Bluetooth communication module, and searches the local database for the associated driver information according to the identification code to obtain the driver information associated with the terminal device.
[0105] In one example, the vehicle collects an image containing the driver's face, identifies the driver's facial features in the image, and obtains driver information whose similarity with the facial features is greater than a similarity threshold.
[0106] Specifically, a camera is configured inside the vehicle cockpit, a face recognition module is configured on the vehicle side, and the camera is connected to the face configuration module. The local database on the vehicle side is preset with multiple images of the driver's face, and each image of the driver's face has associated driver information, and the face configuration module is connected to the local database. When the user enters the acquisition range of the camera in the vehicle cockpit, the driver's face image is acquired and transmitted to the face recognition module. The facial feature similarity of the acquired facial image and multiple preset facial images is calculated respectively. If the facial feature similarity between the acquired facial image and the preset facial image is greater than or equal to a threshold, the associated driver information is determined in the local database according to the preset facial image whose facial feature similarity is greater than or equal to the threshold, so as to obtain the driver information corresponding to the currently acquired driver facial image.
[0107] It should be noted that if the facial feature similarity between the collected facial image and multiple preset facial images is greater than or equal to a threshold, or the facial feature similarity between the collected facial image and all preset facial images in the local database is less than a threshold, the driver information associated with the preset facial image with the greatest facial feature similarity to the collected facial image is selected.
[0108] Optionally, the vehicle side is configured with an interactive device, which displays to the user the driver information associated with the currently selected preset facial image with the greatest facial feature similarity to the collected facial image, and asks the user to confirm the driver information.
[0109] In one example, the vehicle side obtains the account information of the person logging into the vehicle side, and obtains the driver information based on the account information.
[0110] Specifically, the vehicle side is equipped with an interactive device, which includes but is not limited to a touch screen display, and the interactive interface is displayed on the touch screen display. Figure 2 is a schematic diagram of an exemplary interactive interface. Figure 2 As shown, the interactive interface 20 includes an account selection button 201, and the account selection button 201 specifically includes: a "user A" button, a "user B" button, and a "user C" button. The local database of the vehicle is preset with the driver information corresponding to each account selection button, and the interactive device is connected to the local database. When the user clicks the "user A" button, according to the user's button click operation, the driver information corresponding to the button is searched in the local database to obtain the driver information corresponding to the "user A" button.
[0111] In one example, the vehicle side obtains the driver's weight data and obtains the driver information that is consistent with the weight data.
[0112] Specifically, the main driver's seat of the vehicle is equipped with a pressure sensor, which is connected to the vehicle-side processor. The local database of the vehicle-side is preset with driver information corresponding to different pressure sensor values, and the vehicle-side processor is connected to the local database. When the user sits in the main driver's seat, the pressure sensor converts the user's weight data into a pressure sensor value and sends it to the vehicle-side processor, so that the vehicle-side processor searches the local database for the driver information corresponding to the pressure sensor value.
[0113] It should be noted that due to factors such as differences in sensor accuracy and different user sitting postures, the pressure sensor values may have errors. Optionally, a floating range is set for the pressure sensor values corresponding to different driver information preset in the local database of the vehicle. If the actual pressure sensor value is within the floating range, the driver information corresponding to the preset pressure sensor value is selected.
[0114] In the above examples, the method of obtaining the driver information is specifically described. The above examples can be implemented separately or in combination, and this embodiment does not limit this.
[0115] The user-related data involved in this application (such as images of the driver's face, account information logged into the vehicle, driver's weight data, etc.) are all obtained after obtaining the user's permission or consent; that is, when this application is applied to specific products or technologies, it is necessary to obtain user permission to obtain and process relevant data, and the processing of relevant data needs to comply with relevant laws, regulations and regulatory standards of relevant countries and regions.
[0116] In one example, when it is necessary to capture an image containing the driver's face, a capture prompt may pop up on the display device of the vehicle end. After receiving the driver's confirmation operation for the capture prompt, the vehicle end may control the camera to capture the image containing the driver's face. Figure 3 Schematic diagram of obtaining prompts for an exemplary driver's face image. Figure 3 As shown, a prompt pops up on the vehicle-side display device, requesting the driver to confirm the prompt. The driver clicks the "Agree" button, and the vehicle-side responds to the click operation and controls the camera to collect an image containing the driver's face. If the driver clicks the "Reject" button, the vehicle-side does not start the camera to collect the driver's face image.
[0117] In the above embodiment, the identity of the driver is determined in a variety of ways, thereby determining the driver information corresponding to the driver identity according to the driver identity, and determining the vehicle history information related to the driver information according to the driver information, thereby improving the efficiency of vehicle information acquisition and improving the intelligence of the vehicle.
[0118] In step 104 of the above embodiment, the cloud server predicts the remaining energy storage information of the vehicle and the average energy consumption information of the driver driving the vehicle through the prediction model. The prediction process of the prediction model is explained below.
[0119] For example, Figure 4 Schematic diagram of the process of predicting vehicle cruising range provided in this application Figure 2 The execution subject of this embodiment is the cloud server, such as Figure 4 As shown, the cloud server inputs the driver information and vehicle history information into the prediction model, and predicts the remaining energy storage information of the vehicle and the average energy consumption information of the driver driving the vehicle, including:
[0120] Step 401: Perform data cleaning on driver information and vehicle history information.
[0121] Specifically, data cleaning includes but is not limited to removing duplicate records, unifying data types, processing abnormal data, etc.
[0122] Step 402: Construct a first feature vector based on the driver information and vehicle history information after data cleaning.
[0123] In practical applications, the driver information and vehicle history information after data cleaning are in the form of an array, and the array is vectorized. Specifically, the method of vectorization is not limited. For example, for a one-dimensional array, the one-dimensional array can be directly vectorized to obtain the first eigenvector. For multidimensional arrays, vectorization is performed based on the row priority principle. That is, first traverse the elements of a row in the array and convert them into vectors, then traverse all rows in the array in turn and convert them into vectors respectively, and concatenate the vectors of all rows to obtain the first eigenvector. As an example, the first eigenvector obtained is denoted as Q0.
[0124] Step 403: Perform dimensionality reduction processing on the first eigenvector to obtain a second eigenvector; the vector dimension of the second eigenvector is smaller than the vector dimension of the first eigenvector.
[0125] The first eigenvector is subjected to dimensionality reduction. Specifically, the dimensionality reduction processing method is not limited. For example, the dimensionality reduction processing method includes but is not limited to dimensionality reduction operators, principal component analysis (PCA), linear discriminant analysis (LDA), etc. The first eigenvector is subjected to dimensionality reduction processing to obtain a second eigenvector with a smaller vector dimension. As an example, the obtained second eigenvector is denoted as Q1.
[0126] Step 404: Encode the second feature vector in the time dimension to obtain a third feature vector.
[0127] The second eigenvector is encoded in the time dimension. As an example, a time encoding vector is created in the time dimension, denoted as T1. T1 includes multiple time elements, and the time element is the time corresponding to the element in Q1. For example, Q1 includes vehicle history information, and the vehicle history information may include multiple vehicle speed data. During the actual driving process of the vehicle, different vehicle speed data have corresponding times, and the time corresponding to the vehicle speed data in Q1 is used as the corresponding time element in T1. T1 and Q1 are embedded to obtain the third eigenvector, denoted as Q2. Among them, the embedding method is not limited, and the embedding method includes but is not limited to addition, splicing, weighted summation, etc.
[0128] In the above example, the second eigenvector is encoded in the time dimension to obtain the third eigenvector. The time scale feature can be given to the elements in the second eigenvector, which can facilitate the prediction model to understand the change trend of the data and improve the prediction accuracy of the prediction model.
[0129] Step 405. Input the third eigenvector into the prediction model to predict the remaining energy storage information on the vehicle side and the average energy consumption information of the driver when driving the vehicle.
[0130] For example, Figure 5 is a schematic diagram of the structure of an exemplary prediction model. Figure 5 As shown, the prediction model 50 adopts a Transformer model structure, which may include N encoding layers 501, a pooling layer 502, a fully connected layer 503, and a linear layer 504. The Transformer model is a deep learning architecture with features such as a self-attention mechanism and a multi-head attention mechanism.
[0131] based on Figure 5 The model structure shown, Figure 4 Step 405 in the embodiment may include:
[0132] Step 4051. The cloud server inputs the third feature vector Q2 into the prediction model, and obtains the encoded output vector Q3 through N encoding layers.
[0133] Furthermore, each encoding layer specifically includes: a multi-head attention module, a first-layer normalization module, a feed-forward neural network (FFN) module, and a second-layer normalization module.
[0134] Taking the first coding layer as an example, the steps of data processing in the coding layer specifically include:
[0135] Step (1). The third feature vector Q2 is calculated through the multi-head attention module to calculate the correlation between the elements in Q2 and obtain the intermediate vector Z1.
[0136] Step (2). Perform residual connection on the intermediate vectors Z1 and Q2, and perform layer normalization through the first layer normalization module to obtain the first residual vector Z2.
[0137] Step (3). The first residual vector Z2 is subjected to nonlinear transformation and feature extraction by the FFN module to obtain the neural network output vector Z3.
[0138] Step (4). Perform residual connection on the first residual vector Z2 and the neural network output vector Z3, and perform layer normalization through the second layer normalization module to obtain the encoding layer output vector Z4.
[0139] Step (5). Input the coding layer output vector Z4 into the next coding layer.
[0140] Repeat the above steps (1) to (5) until the last coding layer outputs the coded output vector Q3.
[0141] Step 4052. Input the encoded output vector Q3 into the pooling layer, and after being processed by the pooling layer, obtain the output vector Q4.
[0142] Step 4053. Input the output vector Q4 into the fully connected layer, and after being processed by the fully connected layer, obtain the output vector Q5.
[0143] Step 4054: Input the output vector Q5 into the linear layer, and after being processed by the linear layer, obtain the output vector Q6. The output vector Q6 includes the remaining energy storage information M2 of the vehicle end and the average energy consumption information M3 of the driver driving the vehicle.
[0144] In the above embodiment, a prediction model trained based on the Transformer framework is used to predict the remaining energy storage information on the vehicle side and the average energy consumption information of the driver driving the vehicle, thereby improving the prediction accuracy of the vehicle's remaining energy storage information and the driver's average energy consumption information, and laying the foundation for the subsequent calculation of the remaining cruising range.
[0145] In the aforementioned embodiment, the prediction model is trained based on the constructed training data set. As an example, the prediction model is built based on the Transformer framework and trained on a cloud server. The cloud server stores the training data set, which includes sample driver information Uh1 and vehicle history information Mh1 related to the sample driver information. The training of the prediction model is supervised training. Therefore, the training data set also includes sample remaining energy storage information Mh2 and sample average energy consumption information Mh3 corresponding to Uh1 and Mh1. The training data set is divided into a training set and a test set.
[0146] Input Uh1 and Mh1 in the training set into the prediction model for training to obtain the prediction result Qh3, which includes the predicted remaining energy storage information and the predicted average energy consumption information. Calculate the value of the loss function based on the prediction result Qh3, the sample remaining energy storage information Mh2, and the sample average energy consumption information Mh3. Calculate the parameter gradient of the prediction model through the back propagation algorithm, and update the parameters based on the Adam optimizer. Adam optimizer refers to an algorithm used to optimize neural networks in machine learning. Adam optimizer has the characteristics of fast convergence and adaptive learning rate. When the number of training cycles reaches the preset number, the prediction model is tested with the test set to determine the prediction effect of the prediction model on the new data, and adjust the parameters and structure of the prediction model according to the prediction effect.
[0147] In the above embodiment, the prediction model and the training data set are deployed on the cloud server, and the training is performed on the cloud server, which does not occupy the computing resources on the vehicle side, improves the computing efficiency, and reduces the computing load on the vehicle side.
[0148] Furthermore, when the user is actually driving the vehicle, the vehicle's environmental changes during driving may cause a deviation between the remaining energy storage information on the vehicle side predicted by the prediction model and the average energy consumption information of the driver driving the vehicle. Therefore, it is necessary to correct the remaining energy storage information of the vehicle and the average energy consumption information of the driver driving the vehicle to further improve the accuracy of the information.
[0149] For example, Figure 6 Schematic diagram of the process of predicting vehicle cruising range provided in this application Figure 3 , the execution subject of this method is the cloud server, such as Figure 6 As shown, the method also includes:
[0150] Step 601: The cloud server receives a first request from the vehicle.
[0151] Step 602. The cloud server inputs the driver information and vehicle history information into the prediction model to predict the remaining energy storage information on the vehicle side and the average energy consumption information of the driver when driving the vehicle.
[0152] In this embodiment, step 601 and step 602 are respectively the same as step 103 and step 104 of the aforementioned embodiment. For details, please refer to the aforementioned embodiment and will not be elaborated here.
[0153] Step 603. The cloud server performs linear correction on the remaining energy storage information according to the change in the current environmental parameters to obtain the corrected remaining energy storage information, and performs linear correction on the average energy consumption information according to the change in the current environmental parameters to obtain the corrected average energy consumption information.
[0154] The environmental parameters include at least one of temperature, wind speed and altitude.
[0155] In one example, the remaining energy storage information and the average energy consumption information are linearly corrected by the change in temperature in the environmental parameter.
[0156] In this example, the remaining energy storage information M2 and the average energy consumption information M3 have a linear relationship with the temperature T in the environmental parameter. Figure 7 is a schematic diagram of the linear relationship between the exemplary remaining energy storage information M2 and the temperature T in the environmental parameters, Figure 8 It is a schematic diagram of the linear relationship between the exemplary average energy consumption information M3 and the temperature T in the environmental parameters.
[0157] like Figure 7 As shown, when the temperature in the environmental parameters changes, it can be based on Figure 7 Determine the change in M2. For example, when the ambient temperature changes ΔT, it can be based on Figure 7 Determine the change in M2 when the temperature changes ΔTT Then the original remaining energy storage information M2 is corrected to obtain the corrected remaining energy storage information M22. For example, the change ΔM2 can be subtracted from M2. T The corrected remaining energy storage information M22 is obtained, that is, M22 = M2-ΔM2 T .
[0158] like Figure 8 As shown, when the temperature in the environmental parameters changes, it can be based on Figure 8 Determine the change in M3. For example, when the ambient temperature changes ΔT, it can be based on Figure 8 Determine the change ΔM3 of M3 when the temperature changes ΔT T Then the original average energy consumption information M3 is corrected to obtain the corrected average energy consumption information M32. For example, the change ΔM3 can be subtracted from M3. T The corrected average energy consumption information M32 is obtained, that is, M32 = M3-ΔM3 T .
[0159] In one example, the remaining energy storage information and the average energy consumption information are linearly corrected by the change in wind speed in the environmental parameter.
[0160] In this example, the remaining energy storage information M2 and the average energy consumption information M3 have a linear change relationship with the wind speed W in the environmental parameter. The change amount ΔM2 of the remaining energy storage information M2 and the average energy consumption information M3 when the wind speed change amount is ΔW can be determined based on the linear change relationship. W and ΔM3 W , and then modify M2 and M3 to obtain M22 and M32 respectively. The specific operation steps can be found in the description of the above example, which will not be expanded in this example.
[0161] In one example, the remaining energy storage information and the average energy consumption information are linearly corrected according to the change in altitude in the environmental parameter.
[0162] In this example, the remaining energy storage information M2 and the average energy consumption information M3 have a linear change relationship with the altitude H in the environmental parameter. The change amount ΔM2 of the remaining energy storage information M2 and the average energy consumption information M3 when the altitude change amount is ΔH can be determined based on the linear change relationship. H and ΔM3 H , and then modify M2 and M3 to obtain M22 and M32 respectively. The specific operation steps can be found in the description of the above example, which will not be expanded in this example.
[0163] It should be noted that the above examples respectively describe the linear correction methods of the remaining energy storage information M2 and the average energy consumption information M3 under different types of environmental variables. The different types of environmental variables in the above examples can be corrected individually or together. When different types of environmental variables are corrected together, they can be corrected in sequence, and the present embodiment does not limit the order in which different types of environmental variables are corrected. However, when correcting the next type of environmental variable, the remaining energy storage information and the average energy consumption information after the current environmental variable correction should be selected for correction. For example, first, the remaining energy storage information M2 and the average energy consumption information M3 are corrected for the change in temperature to obtain the remaining energy storage information M22' after temperature correction and the average energy consumption information M32' after temperature correction. Secondly, the wind speed change is corrected for M22' and M32' to obtain the remaining energy storage information M22" after wind speed correction and the average energy consumption information M32" after wind speed correction. Finally, M22" and M32" are corrected for the change in altitude to obtain the altitude-corrected remaining energy storage information M22"' and the altitude-corrected average energy consumption information M32"', and M22"' and M32"' are used as the corrected remaining energy storage information and the corrected average energy consumption information.
[0164] Step 604: The cloud server determines the first remaining cruising range based on the corrected remaining energy storage information and the corrected average energy consumption information.
[0165] Exemplarily, based on the above example, the expression for calculating the first remaining cruising range at the current moment by using the corrected remaining energy storage information and the corrected average energy consumption information is:
[0166]
[0167] Where, M22 Oil K1 Oil2Elc +M22 BattElc Indicates the remaining energy storage at the vehicle end after correction, (M32 OilConsump / M32 OilRange )·K2 Oil2Elc +(M32 ElcConsump / M32 ElcRange ) represents the corrected historical energy consumption information of the vehicle per unit mileage. Specifically, M22 Oil The remaining fuel amount at the vehicle end after correction, M22 BattElc The remaining available power of the vehicle-side power battery after correction, M32 OilConsump M32 is the corrected fuel consumption of the current driver driving the vehicle. OilRange The corrected mileage corresponding to the fuel consumption of the current driver driving the vehicle, M32 ElcConsumpM32 is the corrected current driver's power consumption. ElcRange The corrected mileage corresponding to the power consumption of the current driver when driving the vehicle.
[0168] It should be noted that the above-mentioned M22 Oil 、M22 BattElc All are elements in the revised remaining energy storage information M22; M32 OilConsump 、M32 ElcConsump 、M32 ElcRange They are all elements in the corrected average energy consumption information M32.
[0169] In the above embodiment, the remaining energy storage information and average energy consumption information predicted by the prediction model are linearly corrected according to the changes in different environmental factors. The influence of environmental factors during vehicle driving can be taken into account in the calculation of the remaining cruising range, further improving the prediction accuracy of the vehicle's remaining cruising range.
[0170] In step 108 of the aforementioned embodiment, after the first remaining cruising range is calculated, the value of the first remaining cruising range is assigned to the second remaining cruising range, so that the vehicle-side displays the second remaining cruising range on the display device. However, considering that the calculated first remaining cruising range may differ greatly from the remaining cruising range displayed on the vehicle-side display device at the previous moment, it is necessary to set a boundary limit for the first remaining cruising range.
[0171] As an example, the vehicle side displays the second remaining cruising range on the display device, the second remaining cruising range is the third remaining cruising range, and the third remaining cruising range is determined based on the first remaining cruising range.
[0172] Specifically, the vehicle side obtains the remaining cruising range at the previous moment displayed on the display device.
[0173] The vehicle side determines the third remaining cruising range based on the remaining cruising range at the previous moment, the first remaining cruising range and a preset threshold of the cruising range difference.
[0174] The threshold of the cruising range difference includes a first value and a second value of the cruising range difference.
[0175] Exemplarily, the calculation formula for the third remaining cruising range is:
[0176]
[0177] In formula (3), M5 t The remaining range is the third, M5 t-1is the remaining cruising range at the previous moment, M4 is the first remaining cruising range, MAXRngDec is the first value, MAXRngInc is the second value, min is the minimum function, and max is the maximum function. The first value MAXRngDec represents the maximum boundary value that can be reduced in a remaining cruising range update. The second value MAXRngInc represents the maximum boundary value that can be increased in a remaining cruising range update. The following is a specific explanation of each case.
[0178] One case is that if the remaining cruising range at the previous moment is greater than the first remaining cruising range, that is, M4 <M5 t-1 When the third remaining cruising range is determined according to the remaining cruising range at the previous moment, the first remaining cruising range and the first value.
[0179] Specifically, compare M5 t-1 The difference between M4 and M4 is greater than the preset MAXRngDec.
[0180] If M5 t-1 The difference between M4 and M5 is smaller, so the minimum function is selected t-1 -M4 is calculated. Substitute into the calculation to get M5 t =M5 t-1 -(M5 t-1 -M4)=M4. It can be understood that if M5 t-1 The difference between the calculated first remaining cruising range and M4 does not exceed the preset MAXRngDec, indicating that the difference between the calculated first remaining cruising range and the remaining cruising range at the previous moment does not exceed the threshold, then the value of the first remaining cruising range M4 is assigned to the third remaining cruising range M5. t , so that the vehicle side can display M5 on the display device t .
[0181] If MAXRngDec is smaller, the minimum function selects MAXRngDec for calculation. Substitute into the calculation to get M5 t =MAXRngDec. It can be understood that if M5 t-1 The difference between M4 and M5 exceeds the preset MAXRngDec, indicating that the difference between the calculated first remaining cruising range and the remaining cruising range at the previous moment exceeds the threshold, then the remaining cruising range value M5 at the previous moment is replaced by t-1 Subtract MAXRngDec and assign it to the third remaining range M5 t , so that the vehicle side can display M5 on the display device t .
[0182] In another case, if the remaining cruising range at the previous moment is less than or equal to the first remaining cruising range, the third remaining cruising range is determined according to the remaining cruising range at the previous moment, the first remaining cruising range and the second value.
[0183] Specifically, compare M4 and M5 t-1 The difference between the two and the preset MAXRngInc.
[0184] If M4 and M5 t-1 If the difference between them is larger, the maximum value function is selected M4-M5 t-1 Calculate. Substitute into the calculation to get M5 t =M5 t-1 +(M4-M5 t-1 )=M4. It can be understood that if M4 and M5 t-1 If the difference between the first remaining cruising range and the last remaining cruising range does not exceed the preset MAXRngInc, it means that the difference between the calculated first remaining cruising range and the last remaining cruising range at the previous moment does not exceed the threshold, then the value M4 of the first remaining cruising range is assigned to the third remaining cruising range M5. t , so that the vehicle side can display M5 on the display device t .
[0185] If MAXRngInc is larger, the maximum value function selects MAXRngInc for calculation. Substitute into the calculation to get M5 t =MAXRngInc. It can be understood that if M4 and M5 t-1 If the difference between the first remaining cruising range calculated and the remaining cruising range at the previous moment exceeds the preset MAXRngInc, it means that the difference between the first remaining cruising range calculated and the remaining cruising range at the previous moment exceeds the threshold, then the value of the remaining cruising range at the previous moment M5 is set. t-1 Add MAXRngInc and assign it to the third remaining range M5 t , so that the vehicle side can display M5 on the display device t .
[0186] In the above embodiment, the first remaining cruising range calculated is compared with the remaining cruising range displayed by the current vehicle display device at the previous moment through boundary restriction, and is restricted by a preset threshold value. This prevents the remaining cruising range value on the display device from jumping, that is, prevents the remaining cruising range value from changing too much between the previous moment and the next moment. This improves the intelligence of the interactive display between the vehicle and the user.
[0187] The embodiment of the present application also provides a vehicle range prediction device which is respectively deployed on a cloud server and a vehicle-side controller. Fig. 9 A schematic diagram of the structure of the vehicle range prediction device provided in this application Figure 1The vehicle range prediction device can be integrated into the cloud server. Fig. 9 As shown, the vehicle cruising range prediction device 90 includes: a processing module 901 and a sending module 902.
[0188] The processing module 901 is used to receive a first request from the vehicle side, where the first request includes the driver information of the vehicle side and the vehicle history information related to the driver information.
[0189] The processing module 901 is also used to input the driver information and the vehicle history information into the prediction model to predict the remaining energy storage information on the vehicle side and the average energy consumption information of the driver driving the vehicle.
[0190] The processing module 901 is further used to determine a first remaining cruising range of the vehicle at the current moment according to the remaining energy storage information and the average energy consumption information.
[0191] The sending module 902 is used to send a first response to the vehicle end, where the first response includes a first remaining cruising range.
[0192] In an optional manner, the driver information and the vehicle history information are input into the prediction model to predict the remaining energy storage information of the vehicle and the average energy consumption information of the driver driving the vehicle. The processing module 901 is used to:
[0193] Perform data cleaning on driver information and vehicle history information;
[0194] Constructing a first feature vector based on the driver information and vehicle history information after data cleaning;
[0195] Performing dimensionality reduction processing on the first eigenvector to obtain a second eigenvector; the vector dimension of the second eigenvector is smaller than the vector dimension of the first eigenvector;
[0196] Encode the second eigenvector in the time dimension to obtain a third eigenvector;
[0197] The third eigenvector is input into the prediction model to predict the remaining energy storage information on the vehicle side and the average energy consumption information of the driver driving the vehicle.
[0198] In an optional manner, the prediction model is trained using a Transformer model structure according to a constructed training data set, where the Transformer model structure includes N encoding layers, a pooling layer, a fully connected layer, and a linear layer.
[0199] In one optional embodiment, the driver information includes an identification of the driver.
[0200] The vehicle history information related to the driver information includes at least one of the driver's driving habit information, historical navigation route information, historical vehicle usage environment information, and vehicle status information.
[0201] In an optional manner, the remaining energy storage information on the vehicle side includes at least one of the following: the remaining amount of fuel on the vehicle side, and the remaining available power of the power battery on the vehicle side.
[0202] The average energy consumption information of the driver driving the vehicle includes at least one of the following: the amount of electricity consumed by the driver in at least a historical mileage, and the amount of fuel consumed by the driver in at least a historical mileage.
[0203] In an optional manner, the first remaining cruising range of the vehicle at the current moment is determined according to the remaining energy storage information and the average energy consumption information, and the processing module 901 is used to:
[0204] Determine the remaining energy storage capacity of the vehicle end according to the remaining fuel capacity of the vehicle end, the remaining available power of the power battery and the preset first oil-to-electricity conversion coefficient;
[0205] Determine historical energy consumption information per unit mileage of the vehicle end according to the power consumption of at least one historical mileage, the fuel consumption of at least one historical mileage, and a preset second fuel-to-electricity conversion coefficient;
[0206] The first remaining cruising range is determined based on the remaining energy storage on the vehicle side and the historical energy consumption information on the vehicle side per unit mileage.
[0207] In an optional manner, before determining the first remaining cruising range of the vehicle at the current moment according to the remaining energy storage information and the average energy consumption information, the processing module 901 is further configured to:
[0208] According to the change amount of the current environmental parameter, linear correction is performed on the remaining energy storage information to obtain the corrected remaining energy storage information; and according to the change amount of the current environmental parameter, linear correction is performed on the average energy consumption information to obtain the corrected average energy consumption information; the environmental parameter includes at least one of temperature, wind speed, and altitude;
[0209] According to the remaining energy storage information and the average energy consumption information, the first remaining cruising range of the vehicle at the current moment is determined, and the processing module 901 is used to:
[0210] A first remaining cruising range is determined according to the corrected remaining energy storage information and the corrected average energy consumption information.
[0211] The above-mentioned vehicle range prediction device can be used to execute the method steps of the cloud server in any of the above-mentioned method embodiments. Its implementation principle and technical effects are similar and will not be repeated here.
[0212] Fig.10 A schematic diagram of the structure of the vehicle range prediction device provided in this application Figure 2 The vehicle range prediction device can be integrated into the vehicle-side controller. Fig.10 As shown, the vehicle cruising range prediction device 100 includes: an acquisition module 1001 , a sending module 1002 , a processing module 1003 and a display module 1004 .
[0213] The acquisition module 1001 is used to acquire the driver information of the vehicle and the vehicle history information related to the driver information after the vehicle is unlocked or started.
[0214] The sending module 1002 is used to send a first request to the cloud server, where the first request includes driver information and vehicle history information.
[0215] The processing module 1003 is used to receive a first response from the cloud server, where the first response includes a first remaining cruising range, and the first remaining cruising range is determined by the cloud server based on the driver information and the vehicle history information.
[0216] The display module 1004 is used to display a second remaining cruising range on a display device, where the second remaining cruising range is the first remaining cruising range or the third remaining cruising range, and the third remaining cruising range is determined based on the first remaining cruising range.
[0217] In an optional manner, the acquisition module 1001 is used to acquire the driver information of the vehicle, including at least one of the following:
[0218] Identify the terminal connected to the vehicle and obtain the driver information associated with the terminal;
[0219] or collecting an image containing the driver's face, identifying the driver's facial features in the image, and obtaining driver information whose similarity to the facial features is greater than a similarity threshold;
[0220] Or obtain the account information for logging into the vehicle, and obtain the driver information based on the account information;
[0221] Alternatively, the driver's weight data is obtained, and driver information that is consistent with the weight data is obtained.
[0222] In an optional manner, if the second remaining cruising range is the third remaining cruising range, before displaying the second remaining cruising range on the display device, the acquisition module 1001 is further used to acquire the remaining cruising range at a previous moment displayed on the display device;
[0223] The processing module 1003 is further configured to determine a third remaining cruising range according to the remaining cruising range at a previous moment, the first remaining cruising range, and a preset cruising range difference threshold.
[0224] In an optional manner, the threshold of the cruising range difference includes a first value and a second value of the cruising range difference;
[0225] According to the remaining cruising range at the previous moment, the first remaining cruising range and a preset cruising range difference threshold, the third remaining cruising range is determined, and the processing module 1003 is used to:
[0226] If the remaining cruising range at the previous moment is greater than the first remaining cruising range, determining a third remaining cruising range according to the remaining cruising range at the previous moment, the first remaining cruising range and the first value;
[0227] If the remaining cruising range at the previous moment is less than or equal to the first remaining cruising range, the third remaining cruising range is determined according to the remaining cruising range at the previous moment, the first remaining cruising range and the second value.
[0228] In an optional manner, the driver information includes an identification of the driver;
[0229] The vehicle history information related to the driver information includes at least one of the driver's driving habit information, historical navigation route information, historical vehicle usage environment information, and vehicle status information.
[0230] The above-mentioned vehicle range prediction device can be used to execute the method steps of the vehicle-side controller in any of the above-mentioned method embodiments. Its implementation principles and technical effects are similar and will not be repeated here.
[0231] The present application embodiment provides an electronic device, which executes the above method embodiment in which the execution subject is the cloud server on the cloud server, or executes the above method embodiment in which the execution subject is the vehicle side on the vehicle side. Fig.11 This is a schematic diagram of the structure of the electronic device provided in this application. The embodiments of this application do not limit the specific implementation of the electronic device.
[0232] like Fig.11 As shown, the electronic device 1100 may include: a processor 1101, a memory 1102, a communications interface 1103 and a communications bus 1104. The processor 1101, the memory 1102 and the communications interface 1103 communicate with each other via the communications bus 1104.
[0233] The processor 1101 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the electronic device may be processors of the same type, such as one or more CPUs; or may be processors of different types, such as one or more CPUs and one or more ASICs.
[0234] The memory 1102 is used to store a program 1105. The program 1105 may include a program code, which includes a computer-executable instruction.
[0235] The memory 1102 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.
[0236] The communication interface 1103 is used to communicate with other devices such as a client or a network element of another server, etc. The processor 1101 is used to execute a program 1105, and specifically can execute the relevant steps of the above method embodiment.
[0237] The communication bus 1104 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.
[0238] The electronic device is used to execute the method embodiment in which the execution subject is a cloud server, or the method embodiment in which the execution subject is a vehicle. The implementation principle and technical effect are similar, and this embodiment will not be described in detail here.
[0239] An embodiment of the present application provides a computer-readable storage medium, in which at least one executable instruction is stored. When the executable instruction is executed on an electronic device, the electronic device executes the method embodiment in which the execution subject is a cloud server, or executes the method embodiment in which the execution subject is a vehicle side.
[0240] The computer-readable storage medium mentioned above can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory, electrically erasable programmable read-only memory, erasable programmable read-only memory, programmable read-only memory, read-only memory, magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special purpose computer.
[0241] Optionally, a readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.
[0242] An embodiment of the present application provides a computer program product, which includes a computer program. The computer program is stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium. When the at least one processor executes the computer program, it can implement the method embodiment in which the execution subject is a cloud server, or implement the method embodiment in which the execution subject is a vehicle-side.
[0243] The algorithms or displays provided by the embodiments of the present application are not inherently related to any specific computer, virtual system or other device. In addition, the embodiments of the present application are not directed to any specific programming language.
[0244] In the specification provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. Similarly, in order to simplify the application and help understand one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present application, the various features of the embodiments of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. Wherein, the claims that follow the specific embodiment are thus clearly incorporated into the specific embodiment, wherein each claim itself is used as a separate embodiment of the application.
[0245] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and further may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive.
[0246] It should be noted that the above embodiments illustrate the present application rather than limit the present application, and that those skilled in the art may design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be constructed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of multiple such elements. The present application may be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim that lists several devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be understood as limitations on the order of execution.
[0247] The serial numbers of the embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments. The above are only preferred embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.
Claims
1. A method for predicting vehicle range, It is characterized in that Applied to a cloud server, the method includes: receiving a first request from a vehicle end, wherein the first request includes driver information of the vehicle end and vehicle history information related to the driver information; Inputting the driver information and the vehicle history information into a prediction model to predict the remaining energy storage information of the vehicle and the average energy consumption information of the driver driving the vehicle; Determining a first remaining cruising range of the vehicle at a current moment according to the remaining energy storage information and the average energy consumption information; A first response is sent to the vehicle end, where the first response includes the first remaining cruising range.
2. The method according to claim 1, It is characterized in that The driver information and the vehicle history information are input into a prediction model to predict the remaining energy storage information of the vehicle and the average energy consumption information of the driver driving the vehicle, including: Performing data cleaning on the driver information and the vehicle history information; Constructing a first feature vector based on the driver information and vehicle history information after data cleaning; Performing dimensionality reduction processing on the first eigenvector to obtain a second eigenvector; the vector dimension of the second eigenvector is smaller than the vector dimension of the first eigenvector; Encoding the second feature vector in the time dimension to obtain a third feature vector; The third eigenvector is input into the prediction model to predict the remaining energy storage information of the vehicle and the average energy consumption information of the driver driving the vehicle.
3. The method according to claim 1 or 2, It is characterized in that The remaining energy storage information of the vehicle end includes at least one of the following: the remaining fuel amount of the vehicle end, the remaining available power of the power battery of the vehicle end; The average energy consumption information of the driver driving the vehicle includes at least one of the following: the power consumption of the driver in at least a historical mileage, and the fuel consumption of the driver in at least a historical mileage.
4. The method according to claim 3, It is characterized in that The determining, according to the remaining energy storage information and the average energy consumption information, a first remaining cruising range of the vehicle at a current moment includes: Determining the remaining energy storage capacity of the vehicle end according to the remaining fuel amount of the vehicle end, the remaining available power of the power battery, and a preset first oil-to-electricity conversion coefficient; Determine the historical energy consumption information of the vehicle end per unit mileage according to the power consumption of the at least one historical mileage, the fuel consumption of the at least one historical mileage, and a preset second fuel-to-electricity conversion coefficient; The first remaining cruising range is determined based on the remaining energy storage of the vehicle and the historical energy consumption information of the vehicle per unit mileage.
5. The method according to any one of claims 1 to 4, It is characterized in that Before determining a first remaining cruising range of the vehicle at a current moment according to the remaining energy storage information and the average energy consumption information, the method further includes: According to the change amount of the current environmental parameter, the remaining energy storage information is linearly corrected to obtain the corrected remaining energy storage information; and according to the change amount of the current environmental parameter, the average energy consumption information is linearly corrected to obtain the corrected average energy consumption information; the environmental parameter includes at least one of temperature, wind speed, and altitude; The determining, according to the remaining energy storage information and the average energy consumption information, a first remaining cruising range of the vehicle at a current moment includes: The first remaining cruising range is determined according to the corrected remaining energy storage information and the corrected average energy consumption information.
6. A method for predicting vehicle range, It is characterized in that Applied to the vehicle side, the method includes: After the vehicle is unlocked or started, obtaining the driver information of the vehicle and the vehicle history information related to the driver information; Sending a first request to a cloud server, wherein the first request includes the driver information and the vehicle history information; receiving a first response from the cloud server, the first response including a first remaining cruising range, the first remaining cruising range being determined by the cloud server according to the driver information and the vehicle history information; A second remaining cruising range is displayed on the display device, where the second remaining cruising range is the first remaining cruising range or a third remaining cruising range, and the third remaining cruising range is determined based on the first remaining cruising range.
7. The method according to claim 6, It is characterized in that Obtaining the driver information of the vehicle, including at least one of the following: Identify a terminal connected to the vehicle end, and obtain driver information associated with the terminal; or Collecting an image containing the driver's face, identifying facial features of the driver in the image, and obtaining driver information whose similarity to the facial features is greater than a similarity threshold; or Obtaining account information for logging into the vehicle terminal, and obtaining the driver information according to the account information; or The weight data of the driver is obtained, and the driver information consistent with the weight data is obtained.
8. The method according to claim 6 or 7, It is characterized in that If the second remaining cruising range is the third remaining cruising range, before displaying the second remaining cruising range on the display device, the method further includes: Obtain the remaining cruising range displayed on the display device at the previous moment; The third remaining cruising range is determined according to the remaining cruising range at the previous moment, the first remaining cruising range, and a preset cruising range difference threshold.
9. The method according to claim 8, It is characterized in that The cruising range difference threshold value includes a first value and a second value of the cruising range difference; The determining the third remaining cruising range according to the remaining cruising range at the previous moment, the first remaining cruising range, and a preset cruising range difference threshold includes: If the remaining cruising range at the previous moment is greater than the first remaining cruising range, determining the third remaining cruising range according to the remaining cruising range at the previous moment, the first remaining cruising range and the first value; If the remaining cruising range at the previous moment is less than or equal to the first remaining cruising range, the third remaining cruising range is determined according to the remaining cruising range at the previous moment, the first remaining cruising range and the second value.
10. The method according to claim 1 or 6, It is characterized in that The driver information includes an identification of the driver; The vehicle history information related to the driver information includes at least one of the driver's driving habit information, historical navigation route information, historical vehicle usage environment information, and vehicle status information.
Citation Information
Patent Citations
Method for displaying the remaining range of a motor vehicle
CN101817309A
Electric vehicle remaining mileage estimation method and device and electric vehicle
CN111591141A
Environmental visibility prediction method and equipment based on priori knowledge and data driving
CN117218375A
Method, device and equipment for predicting remaining endurance mileage of vehicle and storage medium
CN117818362A
Method and device for predicting remaining capacity of battery and computer equipment
CN118096435A
