WO2023159562A1 - 一种续驶里程确定方法、装置和车辆 - Google Patents

一种续驶里程确定方法、装置和车辆 Download PDF

Info

Publication number
WO2023159562A1
WO2023159562A1 PCT/CN2022/078273 CN2022078273W WO2023159562A1 WO 2023159562 A1 WO2023159562 A1 WO 2023159562A1 CN 2022078273 W CN2022078273 W CN 2022078273W WO 2023159562 A1 WO2023159562 A1 WO 2023159562A1
Authority
WO
WIPO (PCT)
Prior art keywords
destination
energy consumption
per unit
unit distance
consumption per
Prior art date
Application number
PCT/CN2022/078273
Other languages
English (en)
French (fr)
Inventor
李帅飞
周勇有
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to CN202280004038.9A priority Critical patent/CN116981587A/zh
Priority to PCT/CN2022/078273 priority patent/WO2023159562A1/zh
Publication of WO2023159562A1 publication Critical patent/WO2023159562A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
    • B60L3/00—Electric devices on electrically-propelled vehicles for safety purposes; Monitoring operating variables, e.g. speed, deceleration or energy consumption
    • B60L3/12—Recording operating variables ; Monitoring of operating variables

Definitions

  • the present application relates to the field of vehicles, in particular to a method, device and vehicle for determining driving range.
  • the present application provides a method, device and vehicle for determining the driving range, which can determine the driving range of the vehicle more accurately without turning on the navigation.
  • a method for determining the driving distance including: obtaining a first path from the current position of the vehicle to the first destination; and determining the first unit distance of the first path according to the first path Energy consumption; according to the energy consumption per unit distance and historical energy consumption per unit distance, determine the energy consumption per unit distance; and determine the driving range of the vehicle according to the remaining available power of the vehicle and the energy consumption per unit distance.
  • acquiring the route from the current position of the vehicle to the first destination specifically includes: acquiring current position information and environmental information of the vehicle; and determining the first destination and the first destination according to the position information and environmental information. path.
  • determining the first destination specifically includes: determining the second destination and the corresponding probability of the second destination according to the location information and the environment information, when the maximum value of the probability is less than the first preset value, outputting at least one of the second destinations according to the probability; and determining the first destination from the at least one outputted second destination in response to a user's selection.
  • At least one of the second destinations can be output for the user to select or confirm, so as to improve the accuracy of destination determination, and further improve the determination of vehicle driving range. Accuracy.
  • determining the first destination specifically includes: determining the probability corresponding to the second destination and the second destination according to the location information and environmental information; when the remaining available power of the vehicle is less than the second preset value , outputting at least one of the second destinations according to the magnitude of the probability; and determining the first destination from the outputted at least one second destination in response to a user's selection.
  • At least one of the second destinations can be output for the user to select or confirm, thereby improving the accuracy of destination determination, and further improving the accuracy of vehicle driving range determination.
  • determining the probability corresponding to the second destination and the second destination according to the location information and the environment information specifically includes: inputting the location information and the environment information into the first model to obtain the second destination The probability corresponding to the second destination, where the first model is obtained through training based on route information and environmental information of historical trips.
  • the first model includes a random forest model.
  • determining the energy consumption per unit distance of the first path specifically includes: obtaining multiple energy consumption per unit distance of the first path; and according to the multiple energy consumption per unit distance, Calculate the energy consumption per unit distance.
  • the multiple paths of the first path can be determined according to the ratio of the average value of the historical energy consumption of the first path to the length of the first path. Energy consumption per unit distance.
  • determining the energy consumption per unit distance of the first path specifically includes: obtaining the average energy consumption per unit distance of the first path; The average energy consumption per unit distance of the first route to the destination, determining the average energy consumption per unit distance to the first destination; and determining the first energy consumption per unit distance according to the average energy consumption per unit distance to the first destination.
  • determining the average energy consumption per unit distance to the first destination specifically includes:
  • the average energy consumption per unit distance to the first destination is determined; wherein, the first weight is based on the first Calculating the length of the path, or/and calculating the selection probability based on each first path.
  • the first path for the vehicle to reach a certain destination from the current position includes multiple (for example, when the weight value of each first path can be determined in the above-mentioned manner, and then the time to reach the certain destination can be calculated. Average energy consumption per unit distance.
  • the first energy consumption per unit distance is calculated according to the average energy consumption per unit distance to each first destination, including: according to the average energy consumption per unit distance to each first destination, each second The second weight value corresponding to a destination is used to calculate the energy consumption per unit distance; wherein, the second weight value is calculated based on the path length or equivalent path length to each first destination, and/or based on each first purpose Calculation of land selection probability.
  • the weight value of the average energy consumption per unit distance to each destination can be determined in the above-mentioned manner, and then calculated Energy consumption per unit distance.
  • the equivalent path length to the first destination is calculated based on the length of each first path to the first destination and/or based on the selection probability of each first path.
  • the energy consumption per unit distance is determined according to the energy consumption per unit distance and the energy consumption per unit distance historically, which specifically includes: weight; and determining the second energy consumption per unit distance according to the first energy consumption per unit distance, the historical energy consumption per unit distance, and the weight.
  • determining the weight based on historical energy consumption per unit distance, remaining available power, and the first path specifically includes: determining a rough estimate of driving range based on historical energy consumption per unit distance and remaining and the corresponding relationship between the first path and the preset energy consumption prediction accuracy, determine the energy consumption prediction accuracy; determine the credibility of the first destination; The credibility and the accuracy of predicted energy consumption determine the weight.
  • the accuracy of determining the energy consumption per unit distance can be improved, thereby improving the accuracy of determining the driving range.
  • a device for determining the driving range including: a transceiver module, configured to obtain a first path from the current position of the vehicle to a first destination; a first determination module, configured to A path, determining the energy consumption per unit distance of the first path; the second determination module, used to determine the energy consumption per unit distance according to the first energy consumption per unit distance and the historical energy consumption per unit distance; and the third determination module, It is used to determine the driving range of the vehicle according to the remaining available power of the vehicle and the energy consumption per unit distance.
  • the transceiver module is specifically configured to: acquire current location information and environment information of the vehicle; and determine the first destination and the first route according to the location information and environment information.
  • the transceiver module is specifically configured to: determine the second destination and the corresponding probability of the second destination according to the location information and the environment information, and when the maximum value of the probability is smaller than the first preset value, Outputting at least one of the second destinations according to the probability; and determining the first destination from the outputted at least one second destination in response to a user selection.
  • the transceiver module is specifically configured to: determine the second destination and the probability corresponding to the second destination according to the location information and environmental information; when the remaining available power of the vehicle is less than the second preset value, outputting at least one of the second destinations based on the magnitude of the probability; and determining the first destination from the outputted at least one second destination in response to a user's selection.
  • the transceiver module is specifically configured to: input location information and environment information into the first model to obtain the second destination and the probability corresponding to the second destination, wherein the first model is based on the Path information and environment information are trained.
  • the first model includes a random forest model.
  • the first determining module is specifically configured to: obtain the average energy consumption per unit distance of the first path; for the first destination, according to the average energy consumption per unit distance of the first path to the first destination , determine the average energy consumption per unit distance to the first destination; and determine the first energy consumption per unit distance according to the average energy consumption per unit distance to the first destination.
  • the second determination module is specifically configured to: determine the weight according to the historical energy consumption per unit distance, remaining available power, and the first path; and determine the weight according to the first energy consumption per unit distance, historical energy consumption per unit distance, and Weight, to determine the second unit distance energy consumption.
  • the second determination module is specifically configured to: determine the roughly estimated mileage according to the historical energy consumption per unit distance and the remaining available power; The corresponding relationship is to determine the accuracy of energy consumption prediction; determine the credibility of the first destination; and determine the weight according to the ratio of the first route to the roughly estimated mileage, the credibility of the first destination, and the accuracy of predicted energy consumption.
  • the technical effect brought by the device for determining the driving range provided by the second aspect of the embodiment of the present application and any possible implementation thereof is the same as that of the method for determining the driving range provided by the first aspect of the present application and any possible implementation thereof.
  • the technical effects brought about correspond to each other, and for the sake of brevity, details are not repeated here.
  • a third aspect of the embodiments of the present application provides a computer-readable storage medium, storing a computer to execute the method for determining the driving range provided in the first aspect of the embodiments of the present application and possible implementations thereof.
  • the fourth aspect of the embodiments of the present application provides a computing device, including a processor and a memory, and a program is stored in the memory, and the first aspect of the embodiments of the present application and its possible implementations are executed by running the program by the processor The provided method for determining the driving range.
  • the fifth aspect of the embodiment of the present application provides a computer program product, which, when the computer program is run on a computer, causes the computer to execute the method for determining the driving range provided in the first aspect of the embodiment of the present application and possible implementations thereof.
  • a sixth aspect of the embodiments of the present application provides a vehicle, including the device for determining the driving range provided in the second aspect of the embodiments of the present application and possible implementations thereof.
  • the driving range of the vehicle can be determined more accurately when the navigation is not turned on in the vehicle, avoiding inconvenience to the user due to inaccurate prediction of the driving range, and improving user experience.
  • energy consumption can determine the driving range of the vehicle more accurately.
  • FIG. 1A is a flow chart of a method for determining driving range provided by an embodiment of the present application
  • FIG. 1B-FIG. 1F are sub-flow charts of the method for determining the driving range provided by one embodiment of the present application shown in FIG. 1A;
  • Fig. 2A is a flow chart of a method for determining driving range provided by another embodiment of the present application.
  • FIG. 2B-FIG. 2D are sub-flowcharts of the method for determining the driving range provided by another embodiment of the present application shown in FIG. 2A;
  • 3A is a schematic diagram of a specific example of an endpoint prediction decision tree model
  • Fig. 3B is a schematic diagram of a specific example of a road network node decision tree model
  • Fig. 4 is a schematic diagram of the path of the vehicle from the starting point to the destinations A, B, and C respectively;
  • Fig. 5 is a schematic diagram of the corresponding relationship between equivalent path length (referred to as navigation path length when using navigation) and energy consumption prediction accuracy;
  • FIG. 6 is a schematic diagram of a destination option pop-up window
  • Figure 7 is an example of a map provided by an embodiment of the present application.
  • Fig. 8 is a block diagram of a device for determining driving range provided by an embodiment of the present application.
  • Fig. 9 is a schematic diagram of a computing device provided by an embodiment of the present application.
  • the method for determining the driving range provided in the embodiment of the present application may be applied to a scene of determining the driving range of an electric vehicle.
  • FIG. 1A-FIG. 1F show a flowchart of a method for determining driving range provided by an embodiment of the present application.
  • the method for determining the driving range in the embodiment of the present application can be executed by a terminal, such as a terminal such as a smart vehicle or a vehicle-mounted device, or by an electronic device applied in a terminal, such as a system chip, a general-purpose chip, and the like.
  • the method for determining the driving range provided in the embodiment of the present application may include the following steps S100-S400:
  • Step S100 Obtain a first route from the current position of the vehicle to the first destination.
  • the first route from the current position of the vehicle to the first destination can be obtained through the navigation system.
  • the navigation system may obtain the first destination by receiving input from the user.
  • the first path from the current position of the vehicle to the first destination can be obtained through the following steps S110-S120:
  • Step S110 Obtain the current location information and environment information of the vehicle.
  • the current position information of the vehicle can be acquired through the positioning device.
  • the positioning device is, for example, a positioning device based on a Global Positioning System (Global Positioning System, GPS), a Beidou satellite positioning system or a Galileo satellite positioning system, a positioning device based on a base station positioning, and the like.
  • the current environmental information of the vehicle may include: weather information and road condition information.
  • the road condition information may include real-time traffic flow information of each road section (traffic flow information such as road congestion information, road construction information, etc.), which may be obtained by receiving information issued by the traffic information release system or by receiving information issued by roadside equipment .
  • Step S120 Determine the first destination and the first route according to the location information and environment information.
  • determining the first destination may include the following steps S121-S123:
  • Step S121 Determine the second destination and the probability corresponding to the second destination according to the location information and the environment information. Wherein, there may be multiple second destinations.
  • determining the second destination and the probability corresponding to the second destination may include: inputting location information and environment information into the first model to obtain the second destination and the probability corresponding to the second destination.
  • the first model is trained according to route information and environmental information of historical trips.
  • the first model may comprise a random forest model.
  • the random forest model can include the terminal prediction decision tree model and the road network node decision pair tree model.
  • the terminal prediction decision tree model is used to determine the predicted destination and the probability corresponding to the predicted destination according to the current environment information and location information.
  • the end point prediction decision tree model may take the starting point as the root node, sequentially use the time of week, time period of the day, and weather as nodes, and use the end point as the leaves (ie, output).
  • Fig. 3A shows a schematic diagram of a specific example of the end point prediction decision tree model, combined with the map example shown in Fig.
  • the end point Y is Tianpingqiao Park
  • the starting point S is Huayuan Fang
  • the week time is Monday
  • the time period is Monday 6:00 am to 9:00 am
  • the weather is rainy
  • the end point Z is Huangpu Center Building.
  • the starting point, end point, weather and time of the historical trip can be input into the end point prediction decision tree model as samples, and the probability that the number of the output end points accounted for the number of all end points can be summarized to obtain the end point correspondence The probability.
  • the road network node decision tree model is used to determine the probability of going to each route at each intersection according to the current environmental information.
  • the road network node decision tree model can take intersections (including starting points) as root nodes, time of week, time of day, weather, and road conditions as nodes in turn, and routes as leaves (ie, output).
  • Fig. 3B shows a schematic diagram of a specific example of the road network node decision tree model. In conjunction with the map example shown in Fig.
  • the route is route 1a; when the intersection is intersection 1, the week time is Monday, and the time period is Monday 6:00-9:00 am, and the weather is sunny and the road condition is congested, the route is route 2a; when the intersection is Intersection 1, when the week is on Monday, the time period is from 6:00 am to 9:00 am on Monday and the weather is rainy, the route is route 2a.
  • the weather information, road condition information, track information and time of the historical journey can be input into the road network node decision tree model as samples, and the number of routes output by it is summed up to account for the number of all routes. Probability, get the probability corresponding to the route.
  • the second destination and the probability corresponding to the second destination obtained by inputting the location information and environmental information into the first model are shown in Table 1,
  • the probability of going to each route at each intersection is obtained after inputting location information and environment information into the first model. As shown in FIG. 7 , the two arrows shown at intersection 1 represent two different routes respectively.
  • the first model can also be implemented using a deep neural network, wherein a classification network can be used to predict the destination or predict the path, such as a convolutional neural network (Convolutional Neural Networks, CNN), a fully connected neural network Network (Fully Connected Net, FCN), Graph Convolutional Network (Graph Convolutional Network, GCN), etc.
  • a classification network can be used to predict the destination or predict the path, such as a convolutional neural network (Convolutional Neural Networks, CNN), a fully connected neural network Network (Fully Connected Net, FCN), Graph Convolutional Network (Graph Convolutional Network, GCN), etc.
  • the sampling data can be the current environment information and location information, and the labels of the data are the destination and path.
  • the trained classification network can output the predicted destination and predicted path according to the current environment information and location information in the inference stage.
  • the corresponding confidence degree (such as softmax value) at the time of output is the corresponding probability.
  • the trained classification network can realize the
  • Step S122 When the maximum value of the probability corresponding to the second destination is smaller than the first preset value, output some of the second destinations according to the order of the probability values.
  • step S122 may also be, or further include: when the remaining available power of the vehicle is less than a second preset value, outputting the part of the second destinations according to the order of probability values.
  • the first preset value can be selected in the range of 50%-90%, and the second preset value can be selected in the range of 1-40%, but the application is not limited thereto, the first preset value or the second
  • the second preset value can also be set as required.
  • the second destinations output according to the probability may be to pop up the second destinations corresponding to the top three in the probability for the user to select, as shown in FIG. 2C .
  • each second destination corresponding to a probability value greater than a third preset value (the third preset value is, for example, 60%, where the third preset value is smaller than the first preset value) may also be popped up for users to choose.
  • the manner of outputting the second destination is not limited to the manner of displaying a pop-up window on the screen, and may also be output by means of voice broadcast for the user to select.
  • Step S123 In response to the user's selection, determine the first destination from the output second destinations.
  • the user's choice can be obtained by receiving the user's operation on the screen, or the user's choice can be obtained by receiving the user's voice instruction.
  • the user can choose one of the multiple second destinations displayed on the screen as the first destination, or choose "none".
  • the user can further manually or voice input the desired destination The first destination to go to.
  • all the displayed second destinations may be determined as the first destinations.
  • the output second destination includes: destination A, destination B and destination C, and the user does not respond to it, destination A, destination B and destination C are all used as the first destination.
  • the one with the highest probability value among the displayed second destinations may also be determined as the first destination.
  • a first route from the current location to the first destination may be determined according to the first destination.
  • the probability of each first path may be determined according to the output of the network node decision tree model, and part of the first paths may be selected according to the order of the probabilities.
  • the first path may include: the path from the current position to the first destination in the vehicle's historical journey; wherein, the path may be based on the road network node decision tree model in the first model described in step S121 above what you get.
  • the first route when the navigation system is turned on, may include a route from the current location to the first destination recommended by the navigation system.
  • the second destination when the maximum value of the probability corresponding to the second destination is greater than the first preset value, it means that the accuracy of the second destination determined by the first model is relatively high, then The second destination may be directly determined as the first destination without outputting to the user.
  • the remaining available power of the vehicle when the remaining available power of the vehicle is greater than the second preset value, it means that the error of the second destination determined by the first model has little impact on the user experience, and the second destination may not be output to the user but directly The destination is determined as the first destination.
  • step S200 According to the first route, determine the first energy consumption per unit distance of the first route, and the first energy consumption per unit distance is also referred to as known energy consumption per unit distance in the following embodiments.
  • the following situations may be included:
  • the historical energy consumption record of the first path can be obtained, and the historical energy consumption record records the average energy consumption per unit distance of the first path, and the It serves as the first energy consumption per unit distance.
  • the average value of the historical energy consumption records of the first path can be taken as the first energy consumption per unit distance, for example, the historical records include Monday and Tuesday , Wednesday, Thursday, and Friday for the five energy consumption records of the first path, then calculate the average value of the energy consumption per unit distance in the five energy consumption records as the first energy consumption per unit distance of the first path.
  • the energy consumption per unit distance of the first path can be determined in the above manner.
  • the energy consumption per unit distance described in step S200 in these two cases may include the following sub-steps S210-S220:
  • Step S210 Obtain the average energy consumption per unit distance of each first path.
  • the acquisition method can be obtained according to the historical energy consumption records as described above, and will not be repeated here.
  • Step S220 For each first destination, calculate the average energy consumption per unit distance to the first destination.
  • the average energy consumption per unit distance of the first path is the average energy consumption per unit distance to the first destination.
  • the average energy consumption per unit distance of the vehicle from the current position to destination B is the destination
  • the average energy consumption per unit distance of the first path of land B; the average energy consumption per unit distance of the vehicle from the current position to destination C is the average energy consumption per unit distance of the first path to destination C.
  • the formulas for calculating E2 and calculating E3 in step S63 of this application please refer to the description of the formulas for calculating E2 and calculating E3 in step S63 of this application.
  • the average energy consumption per unit distance of each first path is obtained first, and then the average energy consumption per unit distance of each first path is weighted to calculate the The average energy consumption per unit distance of the multiple first paths is used as the average energy consumption per unit distance to the first destination.
  • the weight used for weight calculation may be calculated based on the length of each first path, or/and based on the selection probability of each first path.
  • the lengths of the first routes from the starting point to the destination A are l_route1, l_route2, and l_route3, and the selection probabilities of each first route are: p12*p24, p13*p34, p12*p23*p34.
  • Step S230 Determine the first energy consumption per unit distance according to the average energy consumption per unit distance to each first destination.
  • the first path for the vehicle to reach at least one of the first destinations includes multiple first routes, according to the average energy consumption per unit distance to each first destination, each first destination Calculate the energy consumption of the first unit distance.
  • the weight used for weight calculation may be calculated based on the path length to each first destination, or the equivalent path length, and the probability calculation of each first destination selected.
  • weighting may be performed on the calculated average energy consumption per unit distance to destination A, destination B, and destination C (for example, E1, E2, and E3 in step S63).
  • the probabilities P1, P2, P3 of each first destination A, B, C are calculated.
  • the equivalent path length L1 to a first destination may be calculated based on the lengths of the first paths to the first destination and the selection probabilities of the first paths.
  • the calculation method refer to the formula for calculating L1 in step S61.
  • step S300 Determine the second energy consumption per unit distance according to the first energy consumption per unit distance and historical energy consumption per unit distance.
  • step S300 may include the following substeps S310-S320:
  • Step S310 Determine the weight according to the historical energy consumption per unit distance, the remaining available power and the first path.
  • step S310 includes the following sub-steps S311-S314:
  • Step S311 Determine the roughly estimated mileage according to the historical energy consumption per unit distance and the remaining available power.
  • the historical energy consumption per unit distance can be determined according to the ratio of the historical total power consumption (that is, the historical total energy consumption) to the length of the historical cumulative trip; according to the ratio of the remaining available power and the historical energy consumption per unit distance Estimated driving range.
  • Step S312 According to the first path and the corresponding relationship between the first path and the energy consumption prediction accuracy, determine the energy consumption prediction accuracy.
  • the corresponding relationship between the first path and the energy consumption prediction accuracy can be established in a fitting manner, as shown in FIG. 5 , the fitted length or equivalent length of the first path (when using navigation An example of the correspondence between the length of the navigation path) and the accuracy of the energy consumption prediction.
  • Step S313 Determine the credibility of the first destination.
  • the credibility of the first destination can be based on the probability of going to each first destination from the current location (see FIG. 4, for example, the probability P of going to destination A, destination B, and destination B destina1 , P destina2 , P destina3 ) and the probabilities p12*p24, p13*p34, p12*p23*p34, p15, p16 of each path in each first path from the current position to each first destination are determined.
  • the determination method reference may be made to the description of step S61, and for the sake of brevity, details are not repeated here.
  • Step S314 Determine the weight according to the ratio of the first route to the roughly estimated mileage, the credibility of the first destination, and the accuracy of predicted energy consumption.
  • step S71-step S74 the way of determining the weight can refer to the description of step S71-step S74, and for the sake of brevity, details are not repeated here.
  • step S320 Determine the second energy consumption per unit distance according to the first energy consumption per unit distance, historical energy consumption per unit distance and weight.
  • the energy consumption per unit distance can be calculated by the following formula:
  • E_Pre E_ave*(1-f_Navi)+E_Navi*f_Navi
  • E_Pre is the second unit distance energy consumption
  • E_ave is the historical unit distance energy consumption
  • E_Navi is the first unit distance energy consumption
  • f_Navi is the weight.
  • step S400 Determine the driving range of the vehicle according to the remaining available power of the vehicle and the energy consumption per unit distance.
  • the mileage may be determined according to the ratio of the remaining available power to the energy consumption per unit distance.
  • Figure 2A shows a flow chart of the method for determining the driving range provided by the embodiment of the present application.
  • the method for determining the driving range provided by the embodiment of the present application includes the following steps S1-S9:
  • Step S1 Determine whether navigation is enabled.
  • step S2 is executed: obtaining the navigation destination and the navigation route.
  • the user departs from Huayuan Fang at the starting point S to Huangpu Center Building at the end point Z, and the navigation route can be determined according to the navigation function.
  • Step S3 Determine the energy consumption per unit distance of the known trip according to the navigation route.
  • the energy consumption per unit distance of the known trip is also referred to as the first energy consumption per unit distance.
  • the known itinerary is a route from the current position of the vehicle to the predicted destination, the navigation destination, or the final destination selected by the user according to the predicted destination.
  • step S4 is performed: obtaining the itinerary information.
  • the travel information includes: the current location information of the vehicle and environmental information, the environmental information may include current weather information, and the environmental information may also include current road condition information.
  • Step S5 Determine the final route from the current location to the final destination according to the itinerary information and the road network model.
  • the road network model is also referred to as the first model in the present application, and for the description of the road network model, please refer to the description of the first model in step S121 in the above embodiment of the present application. For the sake of brevity, details are omitted here.
  • step S5 may include the following substeps S51-S56:
  • Step S51 Determine the predicted destination, the probability corresponding to the predicted destination, and the probability of going to each route from the current location to each intersection of the predicted destination according to the current location information, environmental information and road network model.
  • the predicted destination is also referred to as the second destination in this application.
  • the predicted destination may include: Xiangyangming Junior High School at the end point X, Tianpingqiao Park at the end point Y, and Huangpu Center Building at the end point Z; intersections include intersection 1, intersection 2, and intersection 3, as shown in the figure The directions of the arrows indicate the different routes 1a, 2a leading from the intersection 1 . It should be noted that, for the sake of brevity, only three intersections and destinations are schematically shown in FIG. 7 , but the present application is not limited thereto.
  • the predicted destination and the probability corresponding to the predicted destination determined according to the current location information, environmental information and road network model are shown in Table 2.
  • Step S52 Determine whether the maximum value of the probability is less than a first preset value or determine whether the vehicle SOC (State of Charge, battery state of charge) is less than a second preset value.
  • the first preset value can be selected from the range of 50% to 90%, but the present application is not limited thereto, and the first preset value can also be set as required.
  • the second preset value can be selected from a range of 1% to 40%, and the present application is not limited thereto, and the second preset value can be set as required.
  • Step S53 is executed: a destination confirmation window pops up on the display screen according to the probability corresponding to the predicted destination.
  • One or more destination options are displayed in the destination confirmation window.
  • the destinations corresponding to the top three in the probability values may be popped up for the user to select, as shown in FIG. 6 .
  • corresponding destinations whose probability values are greater than a third preset value may also be popped up for the user to select.
  • the destination confirmation window displays a preset time by default, for example, it can be displayed for 10 seconds.
  • the destination confirmation window can be closed manually.
  • the destination confirmation window only pops up once in a drive.
  • one or more destination options may also be announced by voice for the user to select.
  • Execute step S54 take the predicted destination as the final destination.
  • the final destination is also referred to as the first destination in this application.
  • the destination confirmation window may not pop up; or, when the vehicle SOC is greater than the second preset value , it is considered that the remaining battery power of the vehicle is relatively high, so the destination confirmation window may not pop up.
  • Step S55 Determine the final destination in response to the user's selection.
  • the user can select the final destination by operating the screen, or issue a voice command to determine the final destination.
  • step S54 is performed.
  • Step S56 Determine the final route from the current location to the final destination according to the final destination.
  • the final path is also referred to as the first path in this application.
  • the final route may include: a route from the current position to the final destination in the vehicle's historical travel; and a route from the current position to the final destination recommended by the navigation system.
  • Step S6 Determine the known energy consumption per unit distance according to the final route.
  • step S6 may include the following substeps S61-S63:
  • Step S61 Determine the reliability of the final destination according to the probability of going to each route at each intersection and the probability of going to the final destination from the current position.
  • the path from the current position to the destination A passes through intersection 2 and intersection 3. There are multiple paths from the current position to the destination A.
  • the three paths with the top three probabilities are taken: path 1 (i.e. starting point-intersection 2-destination A), path 2 (i.e. starting point-intersection 3 destination A) and path 3 (i.e. starting point-intersection 2-intersection 3-destination A); there is one path from the current position to destination B, this In the embodiment, this one path (ie, path 4) is taken; there is one path from the current position to the destination C, and in this embodiment, this one path (ie, path 5) is taken.
  • Proute destination1 p12*p24+p13*p34+p12*p23*p34
  • Proute destination1 is the probability sum of the three paths from the current location to destination A; p12 is the probability from the current location to intersection 2; p13 is the probability from the current location to intersection 3; p23 is the probability from intersection 2 to intersection 3 Probability; p24 is the probability of going from intersection 2 to destination A; p34 is the probability of going from intersection 3 to destination A; that is, p12, p13, p23, p24, and p34 are the probabilities of each intersection going to each route.
  • the probability that the user chooses the three paths to destination A is:
  • Proute destination1 is the probability sum of the three paths from the current location to destination A
  • P destination1 is the probability that the user goes to destination A
  • P1 is the probability that the user chooses the three paths to destination A.
  • the paths with the top three probabilities can be selected to calculate their probability sum, or the top two or N paths can be selected. Compute the sum of their probabilities for the paths.
  • Proute destination2 is the probability sum of the path from the current location to destination B; p15 is the probability of going to destination B from the current location.
  • the probability that the user chooses the path to destination B is:
  • Proute destination2 is the probability sum of the path from the current location to destination B; P destination2 is the probability that the user goes to destination B from the current location; P2 is the probability that the user chooses the path to destination B.
  • the probability sum of the path from the current position to the destination C is:
  • Proute destination2 is the probability sum of the path from the current location to destination C; p16 is the probability of going to destination C from the current location.
  • the probability that the user chooses the path to destination C is:
  • Proute destination3 is the probability sum of the path from the current location to destination C; P destination3 is the probability that the user goes to destination C from the current location; P3 is the probability that the user chooses the path to destination C.
  • Proute destination is:
  • Step S62 determine the equivalent path length according to the length of the final path and the probability that each crossing goes to each route.
  • the equivalent path length needs to be determined according to the multiple final paths.
  • L1 (l_route1*p12*p24+l_route2*p13*p34+l_route3*p12*p23*p34)/(p12*p24+p13*p34+p12*p23*p34)
  • L_Navi (P1*L1+P2*L2+P3*L3)/(P1+P2+P3)
  • L_Navi is the equivalent path length of the vehicle from the current position to the final destination
  • P1 is the probability that the user chooses the three paths of destination A
  • P2 is the probability that the user chooses the path of destination B
  • P3 is the probability that the user chooses destination C
  • L1 is the equivalent path length of the vehicle from the current location to destination A
  • L2 is the equivalent path length of the vehicle from the current location to destination B
  • L3 is the equivalent path length of the vehicle from the current location to destination C path length.
  • Step S63 According to the length of the final path, the required energy consumption of the final path, the probability of going to each route at each intersection, and the equivalent path length, determine the energy consumption per unit distance of the known trip.
  • the average energy consumption per unit distance of the vehicle from the current location to destination A is:
  • E1 E_route1*l_route1*p12*p24+E_route2*l_route2*p13*p34+E_route3*l_route3*p12*p23*p34)/(p12*p24+p13*p34+p12*p23*p34)/(l_route1+l_route2+ l_route3)
  • E1 is the average energy consumption per unit distance of the vehicle from the current position to the destination A
  • l_route1 is the length of the route 1 of the vehicle from the current position to the destination A
  • l_route2 is the length of the route 2 of the vehicle from the current position to the destination A
  • l_route3 is the length of route 3 of the vehicle from the current position to destination A
  • p12 is the probability of going to intersection 2 from the current position
  • p13 is the probability of going to intersection 3 from the current position
  • p23 is the probability of going from intersection 2 to intersection 3
  • p24 is the probability of going to destination A from intersection 2
  • p34 is the probability of going to destination A from intersection 3 that is, p12, p13, p23, p24, and p34 are the probability of each intersection going to each route
  • E_route1 is the vehicle going from the current position to The average energy consumption per unit distance of destination A path 1
  • E_route2 is the average energy consumption per unit distance of the vehicle from
  • the average energy consumption per unit distance of the vehicle from the current location to destination B is:
  • E1 is the average energy consumption per unit distance of the vehicle from the current location to destination B
  • E_route4 is the average energy consumption per unit distance of the vehicle from the current location to destination B
  • l_route4 is the path of the vehicle from the current location to destination B
  • the length of 4 p15 is the probability of going to destination B from the current position.
  • the average energy consumption per unit distance of the vehicle from the current location to the destination C is:
  • E3 is the average energy consumption per unit distance of the vehicle from the current position to the destination C
  • E_route5 is the average energy consumption per unit distance of the vehicle from the current position to the destination C route
  • l_route5 is the route 5 of the vehicle from the current position to the destination C
  • the length of , p16 is the probability of going to destination C from the current position.
  • E_Navi (P1*E1*L1+P2*E2*L2+P3*E3*L3)/(P1+P2+P3)/L_Navi
  • step S7 determine the final energy consumption per unit distance according to known energy consumption per unit distance of the trip, historical energy consumption per unit distance, and weights.
  • step S7 may include the following sub-steps S71-S75:
  • Step S71 Determine the historical energy consumption per unit distance according to the historical cumulative travel distance and the historical total energy consumption.
  • the historical energy consumption per unit distance can be determined according to the quotient of the historical total energy consumption and the accumulated distance of the historical travel.
  • Step S72 Determine the roughly estimated remaining mileage according to the remaining available power and the historical energy consumption per unit distance.
  • the roughly estimated remaining mileage may be determined according to the ratio of the remaining available power to the historical energy consumption per unit distance.
  • Step S73 According to the equivalent path length, the corresponding relationship between the equivalent path length and the energy consumption prediction accuracy, determine the energy consumption prediction accuracy.
  • the road condition information may include the real-time traffic flow information of each road section of the Ministry of Communications, the location information and speed information of the user currently using the navigation, and the traffic condition information of each road at historical moments.
  • the contingency of the energy consumption prediction model will affect the accuracy of energy consumption prediction; when the navigation path is too long, the accuracy of road condition prediction will also decrease.
  • the relationship between the finally fitted equivalent path length (referred to as the navigation path length when using navigation) and the energy consumption prediction accuracy is shown in FIG. 5 .
  • Step S74 Determine the weight according to the equivalent path length, roughly estimated remaining mileage, energy consumption prediction accuracy and the credibility of the final destination.
  • the weight can be calculated by the following formula:
  • f_Navi is the weight
  • L_Navi is the equivalent path length
  • L_Ave is the roughly estimated remaining mileage
  • P_Navi is the accuracy of energy consumption prediction
  • Proute_destina is the credibility of the final destination. From step S61 the confidence Proute destination of the final destination has been determined. It should be noted that when the user starts navigation, the reliability Proute destination of the final destination is 1.
  • Step S75 Determine the final energy consumption per unit distance according to the historical energy consumption per unit distance, known travel energy consumption per unit distance and weight.
  • the final energy consumption per unit distance can be calculated by the following formula:
  • E_Pre E_ave*(1-f_Navi)+E_Navi*f_Navi
  • E_Pre is the final energy consumption per unit distance
  • E_ave is the historical energy consumption per unit distance
  • E_Navi is the known travel energy consumption per unit distance
  • f_Navi is the weight.
  • step S8 determine the driving range according to the remaining available power and the final energy consumption per unit distance.
  • the driving range can be determined according to the quotient of the remaining available power and the final energy consumption per unit distance.
  • the determined mileage can be further displayed on the central control screen or in the vehicle instrument, and/or broadcast to the user by voice.
  • the location information, end point information, road condition information, weather information, energy consumption and time data obtained by the vehicle during a trip can be stored in the road network database and used to execute step S9 to train and Update the road network model.
  • Fig. 8 is a module schematic diagram of a driving range determination device 5000 provided by an embodiment of the present application, including: a transceiver module 1000, configured to obtain a first path from the current position of the vehicle to a first destination; a first determination module 2000, configured to According to the first path, determine the first energy consumption per unit distance of the first path; the second determination module 3000 is used to determine the second energy consumption per unit distance according to the first energy consumption per unit distance and the historical energy consumption per unit distance; the third determination Module 4000, configured to determine the driving range of the vehicle according to the remaining available power of the vehicle and the energy consumption per unit distance.
  • the transceiver module 1000 is specifically configured to: acquire current location information and environment information of the vehicle; and determine a first destination and a first route according to the location information and environment information.
  • the transceiver module 1000 is specifically configured to: determine the second destination and the corresponding probability of the second destination according to the location information and environmental information, and when the maximum value of the probability is less than the first preset value, according to the probability outputting at least one of the second destinations; and determining a first destination from the outputted at least one second destination in response to a user selection.
  • the transceiver module 1000 is specifically configured to: determine the second destination and the probability corresponding to the second destination according to the location information and environmental information; when the remaining available power of the vehicle is less than the second preset value, according to the probability outputting at least one of the second destinations in size; and determining the first destination from the outputted at least one second destination in response to a user selection.
  • the transceiver module 1000 is specifically configured to: input location information and environment information into the first model, and obtain the second destination and the probability corresponding to the second destination, wherein the first model is based on the path information of the historical trip and environmental information training.
  • the first model includes a random forest model.
  • the first determining module 2000 is specifically configured to: acquire the average energy consumption per unit distance of the first path; for the first destination, determine the average energy consumption per unit distance of the first path to the first destination The average energy consumption per unit distance to the first destination; and determining the first energy consumption per unit distance according to the average energy consumption per unit distance to the first destination.
  • the second determining module 3000 is specifically configured to: determine the weight according to the historical energy consumption per unit distance, the remaining available power, and the first path; and according to the first energy consumption per unit distance, the historical energy consumption per unit distance, and the weight, Determine the energy consumption per unit distance.
  • the second determination module 3000 is specifically configured to: determine the roughly estimated mileage according to the historical energy consumption per unit distance and the remaining available power; according to the first path and the corresponding relationship between the first path and the preset energy consumption prediction accuracy , determine the accuracy of energy consumption prediction; determine the credibility of the first destination; and determine the weight according to the ratio of the first route to the roughly estimated mileage, the credibility of the first destination, and the accuracy of predicted energy consumption.
  • the device for determining the driving range is presented in the form of a module.
  • a “module” here may refer to an application-specific integrated circuit (ASIC), a processor and memory executing one or more software or firmware programs, an integrated logic circuit, and/or other devices that can provide the above functions .
  • the above device for determining the driving range can be implemented by the processor 1510 of the vehicle-mounted device shown in FIG. 9 .
  • FIG. 9 is a schematic structural diagram of a computing device 1500 provided by an embodiment of the present application.
  • the computing device 1500 includes: a processor 1510 and a memory 1520 .
  • the processor 1510 may be connected to the memory 1520 .
  • the memory 1520 can be used to store the program codes and data. Therefore, the memory 1520 may be a storage unit inside the processor 1510, or an external storage unit independent of the processor 1510, or may include a storage unit inside the processor 1510 and an external storage unit independent of the processor 1510. part.
  • computing device 1500 may further include a bus.
  • the memory 1520 and the communication interface may be connected to the processor 1510 through a bus.
  • the bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (Extended Industry Standard Architecture, EISA) bus or the like.
  • PCI Peripheral Component Interconnect
  • EISA Extended Industry Standard Architecture
  • the bus can be divided into address bus, data bus, control bus and so on.
  • the processor 1510 may be a central processing unit (central processing unit, CPU).
  • the processor can also be other general-purpose processors, digital signal processors (digital signal processors, DSPs), ASICs, field programmable gate arrays (field programmable gate arrays, FPGAs) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.
  • a general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.
  • the processor 1510 uses one or more integrated circuits for executing related programs, so as to implement the technical solutions provided by the embodiments of the present application.
  • the memory 1520 may include read-only memory and random-access memory, and provides instructions and data to the processor 1510 .
  • a portion of processor 1510 may also include non-volatile random access memory.
  • processor 1510 may also store device type information.
  • the processor 1510 executes computer-implemented instructions in the memory 1520 to perform the operation steps of the above method.
  • the computing device 1500 may correspond to a corresponding body executing the methods according to the various embodiments of the present application, and the above-mentioned and other operations and/or functions of the modules in the computing device 1500 are for realizing the present invention For the sake of brevity, the corresponding processes of the methods in the embodiments are not repeated here.
  • the disclosed systems, devices and methods may be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components can be combined or integrated. to another system, or some features may be ignored, or not implemented.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.
  • the functions described above are realized in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium.
  • the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disc and other media that can store program codes. .
  • the embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it is used to perform a method for determining the driving range, and the method includes the methods described in the above-mentioned embodiments at least one of the options.
  • the computer storage medium in the embodiments of the present application may use any combination of one or more computer-readable media.
  • the computer readable medium may be a computer readable signal medium or a computer readable storage medium.
  • a computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples (non-exhaustive list) of computer readable storage media include: electrical connections with one or more leads, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), Erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer readable signal medium may include a data signal carrying computer readable program code in baseband or as part of a carrier wave. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. .
  • Program code contained on a computer readable medium may be transmitted by any appropriate medium, including but not limited to wireless, wire, optical cable, radio frequency (radio frequency, RF), etc., or any suitable combination of the above.
  • Computer program code for performing the operations of the present application may be written in one or more programming languages or combinations thereof, including object-oriented programming languages—such as Java, Smalltalk, C++, and conventional Procedural Programming Language - such as "C" or a similar programming language.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer can be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as through the Internet using an Internet service provider). connect).
  • LAN local area network
  • WAN wide area network
  • connect such as AT&T, MCI, Sprint, EarthLink, MSN, GTE, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Sustainable Development (AREA)
  • Sustainable Energy (AREA)
  • Power Engineering (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Navigation (AREA)

Abstract

一种续驶里程确定方法、确定装置、计算机可读存储介质、计算设备、计算机程序产品以及车辆，续驶里程确定方法包括：获取从车辆当前位置到达第一目的地的第一路径；根据第一路径，确定第一路径的第一单位距离能耗；根据第一单位距离能耗以及历史单位距离能耗，确定第二单位距离能耗；根据车辆的剩余可用电量以及第二单位距离能耗，确定车辆的续驶里程。

Description

一种续驶里程确定方法、装置和车辆 技术领域
本申请涉及车辆领域，具体涉及一种续驶里程确定方法、装置和车辆。
背景技术
随着新能源技术的发展，越来越多的人选择电动车辆。受限于电动车辆的充电功率和充电桩数量，用户需要获知电动车辆的续航里程，因此，准确地确定电动车辆的续航里程十分重要。
目前确定电动车辆的续航里程主要有三种方式，一是根据历史单位距离的平均能耗进行确定，但是这种方式误差较大；二是根据导航或智能交通确定的起点、终点以及路况信息进行确定，但是这种方式在未开启导航时无法对续驶里程进行确定；三是以车辆当前位置为中心确定车辆的续驶范围，由于道路走向复杂，这种方式同样无法准确地确定续驶里程。
有鉴于此，需要一种能够在导航未开启的情况下也能较为准确的确定车辆续驶里程的方法。
发明内容
本申请提供了一种续驶里程确定方法、装置和车辆，其能够在未开启导航的情况下较为准确的确定出车辆的续驶里程。
本申请实施例的第一方面，提供了一种续驶里程确定方法，包括：获取从车辆当前位置到达第一目的地的第一路径；根据第一路径，确定第一路径的第一单位距离能耗；根据第一单位距离能耗以及历史单位距离能耗，确定第二单位距离能耗；以及根据车辆的剩余可用电量以及第二单位距离能耗，确定车辆的续驶里程。
通过确定从车辆当前位置到达第一目的地的第一路径的第一单位距离能耗和根据第一单位距离能耗以及历史单位距离能耗确定第二单位距离能耗，能够在未开启导航的情况下较为准确的确定出车辆的续驶里程。
在一种可能的实现方式中，获取从车辆当前位置到达第一目的地的路径，具体包括：获取车辆当前的位置信息和环境信息；以及根据位置信息和环境信息确定第一目的地以及第一路径。
在一种可能的实现方式中，确定第一目的地，具体包括：根据位置信息和环境信息确定第二目的地和第二目的地的对应的概率，当概率中的最大值小于第一预设值时，根据概率输出第二目的地中的至少一个；以及响应用户的选择从所输出的至少一个第二目的地中确定出第一目的地。
通过上述设置，能够在第二目的地的对应的概率较低的情况下，从第二目的地中输出至少一个供用户选择或确定，提高目的地确定的准确度，进而提高车辆续驶里程确定准确度。
在一种可能的实现方式中，确定第一目的地具体包括：根据位置信息和环境信息确定第二目的地和第二目的地对应的概率；当车辆的剩余可用电量小于第二预设值时，根据概率的大小输出第二目的地中的至少一个；以及响应用户的选择从所输出的至少一个第二目的地中确定出第一目的地。
通过上述设置，能够在车辆的剩余可用电量较低的情况下，从第二目的地中输出至少一个供用户选择或确定，提高目的地确定的准确度，进而提高车辆续驶里程确定准确度。
在一种可能的实现方式中，根据位置信息和环境信息，确定第二目的地和第二目的地对应的概率，具体包括：将位置信息和环境信息输入至第一模型，获得第二目的地和第二目的地对应的概率，其中，第一模型根据历史行程的路径信息以及环境信息训练得到。
在一种可能的实现方式中，第一模型包括随机森林模型。
通过第一模型，能够实现对第二目的地以及第二目的地对应的概率的较为准确的预测，进而提升续驶里程的确定准确度。
在一种可能的实现方式中，根据第一路径，确定第一路径的第一单位距离能耗，具体包括：获取第一路径的多条单位距离能耗；以及根据多条单位距离能耗，计算第一单位距离能耗。
例如，从起点到达某一个目的地的第一路径仅有一条，可以根据多次行驶该第一路径的历史能耗的平均值与该第一路径的长度的比值，确定第一路径的多条单位距离能耗。
在一种可能的实现方式中，根据第一路径，确定第一路径的第一单位距离能耗，具体包括：获取第一路径的单位距离平均能耗；针对第一目的地，根据到达第一目的地的第一路径的单位距离平均能耗，确定到达第一目的地的单位距离平均能耗；以及根据到达所述第一目的地的单位距离平均能耗，确定第一单位距离能耗。
在一种可能的实现方式中，根据到达第一目的地的第一路径的单位距离平均能耗，确定到达第一目的地的单位距离平均能耗具体包括：
根据到达第一目的地的各第一路径的单位距离能耗、各第一路径对应的第一权值，确定到达第一目的地的单位距离平均能耗；其中，第一权值基于第一路径的长度计算，或/和基于各第一路径的选择概率计算。
例如，当车辆从当前位置到达某一个目的地的第一路径包括多条(例如，时，可以通过上述方式对每条第一路径进行权值的确定，进而计算出到达该某一个目的地的单位距离平均能耗。
在一种可能的实现方式中，根据到各第一目的地的单位距离平均能耗，计算出第一单位距离能耗，包括：根据到各第一目的地的单位距离平均能耗、各第一目的地对应的第二权值，计算出第一单位距离能耗；其中，第二权值基于到各第一目的地的路径长度或等效路径长度计算、和/或基于各第一目的地的选择概率计算。
例如，当到达某一个目的地的第一路径包括多条，且车辆可能到达多个目的地，则可以通过上述方式对到达每一个目的地的单位距离平均能耗进行权值的确定，进而计算出第一单位距离能耗。
在一种可能的实现方式中，到第一目的地的等效路径长度，基于到该第一目的地的各第一路径的长度、和/或基于各第一路径的选择概率计算。
在一种可能的实现方式中，根据第一单位距离能耗以及历史单位距离能耗，确定第二单位距离能耗，具体包括：根据根据历史单位距离能耗、剩余可用电量以及第一路径确定权重；以及根据第一单位距离能耗、历史单位距离能耗以及权重，确定第二单位距离能耗。
在一种可能的实现方式中，根据根据历史单位距离能耗、剩余可用电量以及第一路径确定权重，具体包括：根据历史单位距离能耗和剩余可用电量确定粗估续驶里程；根据第一路径以及第一路径与预设能耗预测准确度的对应关系，确定能耗预测准确度；确定第一目的地的可信度；以及根据第一路径与粗估续驶里程的比值、第一目的地的可信度以及预测能耗准确度确定权重。
通过计算权重，能够提升第二单位距离能耗确定的准确程度，进而提升对续驶里程确定的准确度。
本申请实施例的第二方面，提供了一种续驶里程确定装置，包括：收发模块，用于获取从车辆当前位置到达第一目的地的第一路径；第一确定模块，用于根据第一路径，确定第一路径的第一单位距离能耗；第二确定模块，用于根据第一单位距离能耗以及历史单位距离能耗，确定第二单位距离能耗；以及第三确定模块，用于根据车辆的剩余可用电量以及第二单位距离能耗，确定车辆的续驶里程。
在一种可能的实现方式中，收发模块具体用于：获取车辆当前的位置信息和环境信息；以及根据位置信息和环境信息确定第一目的地以及第一路径。
在一种可能的实现方式中，收发模块具体用于：根据位置信息和环境信息确定第二目的地和第二目的地的对应的概率，当概率中的最大值小于第一预设值时，根据概率输出第二目的地中的至少一个；以及响应用户的选择从所输出的至少一个第二目的地中确定出第一目的地。
在一种可能的实现方式中，收发模块具体用于：根据位置信息和环境信息确定第二目的地和第二目的地对应的概率；当车辆的剩余可用电量小于第二预设值时，根据概率的大小输出第二目的地中的至少一个；以及响应用户的选择从所输出的至少一个第二目的地中确定出第一目的地。
在一种可能的实现方式中，收发模块具体用于：将位置信息和环境信息输入至第一模型，获得第二目的地和第二目的地对应的概率，其中，第一模型根据历史行程的路径信息以及环境信息训练得到。
在一种可能的实现方式中，第一模型包括随机森林模型。
在一种可能的实现方式中，第一确定模块具体用于：获取第一路径的单位距离平均能耗；针对第一目的地，根据到达第一目的地的第一路径的单位距离平均能耗，确定到达第一目的地的单位距离平均能耗；以及根据到达第一目的地的单位距离平均能耗，确定第一单位距离能耗。
在一种可能的实现方式中，第二确定模块具体用于：根据根据历史单位距离能耗、剩余可用电量以及第一路径确定权重；以及根据第一单位距离能耗、历史单位距离能耗以及权重，确定第二单位距离能耗。
在一种可能的实现方式中，第二确定模块具体用于：根据历史单位距离能耗和剩余可用电量确定粗估续驶里程；根据第一路径以及第一路径与预设能耗预测准确度的对应关系，确定能耗预测准确度；确定第一目的地的可信度；以及根据第一路径与粗估续驶里程的比值、第一目的地的可信度以及预测能耗准确度确定权重。
本申请实施例第二方面及其任一可能的实现方式提供的续驶里程确定装置所带来的技术效果与本申请第一方面及其任一可能的实现方式提供的续驶里程确定方法所带来的技术效果相对应，为了简洁起见，在此不再赘述。
本申请实施例的第三方面，提供了一种计算机可读存储介质，存储有使计算机执行本申请实施例第一方面及其可能的实现方式提供的续驶里程确定方法。
本申请实施例的第四方面，提供了一种计算设备，包括处理器与存储器，存储器中存储有程序，通过由处理器运行该程序而执行本申请实施例第一方面及其可能的实现方式提供的续驶里程确定方法。
本申请实施例的第五方面，提供了一种计算机程序产品，当计算机程序在计算机上运行时，使得计算机执行本申请实施例第一方面及其可能的实现方式提供的续驶里程确定方法。
本申请实施例的第六方面，提供了一种车辆，包括本申请实施例第二方面及其可能的实现方式提供的续驶里程确定装置。
通过本申请实施例的上述方面，能够在车辆未开启导航的情况下较为准确的确定出车辆的续驶里程，避免因续驶里程预测不准给用户造成的不便，提升用户体验。
通过计算从车辆当前位置到达第一目的地(例如根据用户选择或者模型计算的目的地)的第一单位距离能耗；以及根据第一单位距离能耗和历史单位距离能耗计算第二单位距离能耗，能耗较为准确的确定出车辆的续驶里程。
附图说明
以下参照附图来进一步说明本发明的各个特征和各个特征之间的联系。附图均为示例性的，一些特征并不以实际比例示出，并且一些附图中可能省略了本申请所涉及领域的惯常的且对于本申请非必要的特征，或是额外示出了对于本申请非必要的特征，附图所示的各个特征的组合并不用以限制本申请。另外，在本说明书全文中，相同的附图标记所指代的内容也是相同的。具体的附图说明如下：
图1A是本申请一个实施例提供的续驶里程确定方法的流程图；
图1B-图1F是图1A示出的本申请一个实施例提供的续驶里程确定方法子流程图；
图2A是本申请另一实施例提供的续驶里程确定方法的流程图；
图2B-图2D是图2A示出的本申请另一实施例提供的续驶里程确定方法的子流程图；
图3A是终点预测决策树模型的一具体示例的示意图；
图3B是路网节点决策树模型的一具体示例的示意图；
图4是车辆从起点分别前往目的地A、B、C的路径示意图；
图5是等效路径长度(在使用导航时被称为导航路径长度)与能耗预测准确度的对应关系的示意图；
图6是目的地选项弹窗的示意图；
图7是本申请一个实施例提供的地图示例；
图8是本申请一个实施例提供的续驶里程确定装置的模块示意图；
图9是本申请实施例提供的计算设备的示意图。
具体实施方式
本申请实施例提供的续驶里程确定方法可以应用于电动车辆的续驶里程的确定场景。
图1A-图1F示出了本申请实施例提供的续驶里程确定方法的流程图。本申请实施例中的续驶里程确定方法可以由终端执行，例如诸如智能车辆、车载装置这样的终端，也可以是由应用在终端内的电子装置，例如系统芯片、通用芯片等。如图1A所示，本申请实施例提供的续驶里程确定方法可以包括以下步骤S100-S400：
步骤S100:获取从车辆当前位置到达第一目的地的第一路径。
其中，当用户开启导航时，可以通过导航系统获取车辆当前位置到达第一目的地的第一路径。其中，开启导航的情况下，导航系统可以通过接收用户的输入来获得第一目的地。
当用户未开启导航时，如图1B所示，可以通过以下步骤S110-S120获得从车辆当前位置到达第一目的地的第一路径：
步骤S110:获取车辆当前的位置信息和环境信息。
其中，车辆当前的位置信息可以通过定位装置获取。定位装置例如基于全球定位系统(Global Positioning System，GPS)、北斗卫星定位系统或伽利略卫星定位系统的定位装置，基于基站定位的定位装置等。车辆当前的环境信息可以包括：天气信息和路况信息。路况信息可以包括各个路段的实时交通流信息(交通流信息例如如道路拥堵信息、道路施工信息等)，可以通过接收交通信息发布系统发布的信息，或通过接收路侧设备发布的信息的方式获得。
步骤S120:根据位置信息和环境信息确定第一目的地以及第一路径。
在一些实施例中，如图1C所示，确定第一目的地可以包括以下步骤S121-S123：
步骤S121:根据位置信息和环境信息确定第二目的地和第二目的地对应的概率。其中，第二目的地可以为多个。
在步骤S121中，确定第二目的地和第二目的地对应的概率可以包括：将位置信息和环境信息输入至第一模型，获得第二目的地和第二目的地对应的概率。
其中，在一些实施例中，第一模型根据历史行程的路径信息以及环境信息训练得到。
在一些实施例中，第一模型可以包括随机森林模型。随机森林模型可以包括终点预测决策树模型和路网节点决策对树模型。
其中，终点预测决策树模型用于根据当前的环境信息和位置信息来确定预测目的地以及预测目的地对应的概率。
在一些实施例中，终点预测决策树模型可以以起点为根节点，依次以周时间、一天中的时间段以及天气作为节点，以终点作为树叶(即输出)。图3A示出了终点预 测决策树模型的一具体示例的示意图，结合图7示出的地图示例，当起点S为花园坊、周时间为周一、时间段为周一上午6点-9点且天气为晴天时，终点Y为天平桥公园；当起点S为花园坊、周时间为周一、时间段为周一上午6点-9点且天气为雨天时，终点Z为黄埔中心大厦。
在训练终点预测决策树模型时，可以将历史行程的起点、终点、天气以及时间作为样本输入至终点预测决策树模型，并汇总其输出的终点的数量占所有终点的数量的概率，获得终点对应的概率。
路网节点决策树模型用于根据当前的环境信息来确定每个路口前往各个路线的概率。
在一些实施例中，路网节点决策树模型可以以路口(包括起点)为根节点，依次以周时间、一天中的时间段、天气以及路况作为节点，以路线作为树叶(即输出)。图3B示出了路网节点决策树模型的一具体示例的示意图，结合图7示出的地图示例，当路口为路口1、周时间为周一、时间段为周一上午6点-9点且天气为晴天且路况通畅时，路线为路线1a；当路口为路口1、周时间为周一、时间段为周一上午6点-9点且天气为晴天且路况拥挤时，路线为路线2a；当路口为路口1、周时间为周一、时间段为周一上午6点-9点且天气为雨天时，路线为路线2a。
在训练路网节点决策树模型时，可以将历史行程的天气信息、路况信息、轨迹信息以及时间作为样本输入至路网节点决策树模型，并汇总其输出的路线的数量占所以路线的数量的概率，获得路线对应的概率。
在一些实施例中，将位置信息和环境信息输入至第一模型获得的第二目的地和第二目的地对应的概率如表1所示，
表1
第二目的地 目的地A 目的地B 目的地C 目的地D 目的地E
概率 70％ 15％ 5％ 2％ 1％
在一些实施例中，在将位置信息和环境信息输入至第一模型获得每个路口前往各个路线的概率。如图7所示，路口1出示出的两个箭头分别表示两个不同的路线。
在另一些实施例中，第一模型也可以采用深度神经网络实现，其中，可以采用分类网络来预测目的地或预测路径，分类网络例如卷积神经网络(Convolutional Neural Networks，CNN)、全连接神经网络(Fully Connected Net，FCN)、图卷积神经网络(Graph Convolutional Network，GCN)等。训练分类网络时，采样数据可以当前环境信息和位置信息，数据的标签为目的地和路径，这样训练出的分类网络在推理阶段可以实现根据当前环境信息和位置信息输出预测目的地和预测路径，并且输出时对应的置信度(例如softmax值)即为对应的概率。另外，当采样数据加入时间时，则训练出的分类网络在推理阶段可以实现实现根据当前环境信息、位置信息和时间输出预测目的地和预测路径及各自对应的概率。
步骤S122:当第二目的地对应的概率中的最大值小于第一预设值时，根据概率值的排序，输出其中的部分第二目的地。
在另一些实施例中，步骤S122还可以是，或者进一步包括：当车辆的剩余可用 电量小于第二预设值时，根据概率值的排序输出所述部分第二目的地。
其中，第一预设值可以在50％～90％的范围中进行选择，第二预设值可以在1～40％的范围内选择，但本申请不限于此，第一预设值或第二预设值还可以根据需要进行设定。根据概率输出的第二目的地可以是将概率中排名前三对应的各第二目的地弹出以供用户选择，如图2C所示。在一些实施例中，也可以将概率值大于第三预设值(第三预设值例如为60％，其中，第三预设值小于第一预设值)对应的各第二目的地弹出以供用户选择。
当然，输出第二目的地的方式不限于在屏幕上显示弹窗的方式，还可以通过语音播报的方式输出以供用户选择。
步骤S123:响应用户的选择，从所输出的第二目的地中确定出第一目的地。
其中，可以通过接收用户对屏幕的操作获得用户的选择，也可以通过接收用户的语音指令获得用户的选择。如图6所示，用户可以从屏幕显示的多个第二目的地中选择出一个作为第一目的地，也可以选择“均不是”，此时，用户可以进一步手动输入或者语音输入自己想要前往的第一目的地。
当未接收到用户的选择时，例如用户未对屏幕的显示内容做出响应，此时，可以将所显示的各第二目的地均确定为第一目的地。例如，当输出的第二目的地包括：目的地A、目的地B和目的地C时，用户未对其响应，则将目的地A、目的地B和目的地C均作为第一目的地。在其他一些实施例中，也可以将所显示的各第二目的地中概率值最高的确定为第一目的地。
在一些实施例中，在确定第一目的地后，可以根据第一目的地确定从当前位置到达第一目的地的第一路径。其中，到达该第一目的地的第一路径也可以为多个，并且也可以根据网节点决策树模型的输出确定各个第一路径的概率，根据概率的排序选取部分第一路径。
其中，第一路径可以包括：在车辆历史行程中，从当前位置到达第一目的地的路径；其中，该路径可以是基于上述步骤S121中所述的第一模型中的路网节点决策树模型所得到的。
在一些实施例中，当导航系统开启的情况下，第一路径可以包括导航系统推荐的从当前位置到达第一目的地的路径。
在另一些实施例中，对于上述步骤S122，当第二目的地对应的概率中的最大值大于第一预设值时，表示第一模型确定出的第二目的地的准确程度较高，则也可以不向用户输出而直接将该第二目的地确定为第一目的地。或者，当车辆的剩余可用电量大于第二预设值时，表示第一模型确定出的第二目的地的误差对用户的体验影响很小，则也可以不向用户输出而直接将该第二目的地确定为第一目的地。
如图1A所示，步骤S200:根据第一路径，确定第一路径的第一单位距离能耗，第一单位距离能耗在下面的实施例中也称为已知行程单位距离能耗。
在一些实施例中，可以包括下面几种情况：
1)第一目的地为1个，第一路径仅为一条时，可以获取该第一路径的历史能耗记录，该历史能耗记录中记录有该第一路径的单位距离平均能耗，将其作为所述第一单位距离能耗。
在一些实施例中，对应该第一路径的历史能耗记录有多条时，可以取第一路径的历史能耗记录的均值作为所述第一单位距离能耗，例如历史记录有周一、周二、周三、周四、周五的该第一路径的5条能耗记录，则对这5条能耗记录中的单位距离能耗求取均值作为该第一路径的第一单位距离能耗。
2)第一目的地为1个，第一路径为多条时。
3)第一目的地为多个，第一路径为多条，其中，对应每个第一目的地至少有一条第一路径。
针对上面第1)种情况，可以如上方式确定第一路径的第一单位距离能耗。针对第2)、3)两种情况，均属于第一路径为多条的情况，在一些实施例中，如图1D所示，这两种情况下步骤S200所述第一单位距离能耗的确定步骤，可以包括以下子步骤S210-S220：
步骤S210:获取各第一路径的单位距离平均能耗。其中，获取方式可以如上述根据历史能耗记录得到，不再赘述。
步骤S220:针对每个第一目的地，计算到该第一目的地的单位距离平均能耗。
其中，当到达某个第一目的地仅一条第一路径时，则第一路径的单位距离平均能耗即为到该第一目的地的单位距离平均能耗。
以图4的所示的场景为例，从起点到达目的地B仅一条路径，从起点到达目的地C仅一条路径，则车辆从当前位置前往目的地B的单位距离平均能耗即为前往目的地B的第一路径和的单位距离平均能耗；车辆从当前位置前往目的地C的单位距离平均能耗即为前往目的地C的第一路径的单位距离平均能耗。它们的计算方式可以参见本申请步骤S63中关于计算E2和计算E3的公式的描述。
其中，当到某个第一目的地有多条第一路径时，则首先获得每条第一路径的单位距离平均能耗，然后对每个第一路径的单位距离平均能耗分别加权计算这多条第一路径的单位距离平均能耗，作为到该第一目的地的单位距离平均能耗。
仍以图4所示的场景为例，从起点到达目的地A的路径有三条，分别对获得的这三条路径的单位距离平均能耗(参见步骤S63的E_route1、E_route2、E_route3)进行加权，计算得到前往目的地A的单位距离平均能耗(参见步骤S63的E1)。
在一些实施例中，加权计算所使用的权值，可以基于各第一路径的长度计算，或/和基于各第一路径的选择概率计算。
以图4所示的场景为例，参见步骤S63中关于计算E1的公式可知，从起点到达目的地A的各第一路径的长度为l_route1、l_route2、l_route3，各第一路径的选择概率为：p12*p24、p13*p34、p12*p23*p34。
步骤S230:根据到各第一目的地的单位距离平均能耗，确定第一单位距离能耗。
其中，例如，当第一目的地为多个，车辆到达第一目的地中的至少一个的第一路径包括多条时，根据到各第一目的地的单位距离平均能耗、各第一目的地对应的权值，计算出第一单位距离能耗。
在一些实施例中，加权计算所使用的权值，可以基于到各第一目的地的路径长度、或等效路径长度、所选择各个第一目的地的概率计算。
仍以图4所示的场景为例，从起点到达目的地A的路径有三条，从起点到达目的 地B的路径有一条，从起点到达目的地C的路径有一条。可以对计算出的到目的地A、目的地B以及到目的地C的单位距离平均能耗(例如，步骤S63的E1、E2和E3)进行加权。参见步骤S63中关于计算E_Navi的公式可知，加权计算的权值可以根据到达各第一目的地B、C的路径长度L2＝l_route4、L3＝l_route5、到达目的地A的等效路径长度L1以及选择各个第一目的地A、B、C的概率P1、P2、P3计算得到。
在一些实施例中，到某第一目的地(例如目的地A)的等效路径长度L1，可以基于到该第一目的地的各第一路径的长度以及各第一路径的选择概率计算。其计算方式的具体实施例可以参见步骤S61中计算L1的公式。
如图1A所示，步骤S300:根据第一单位距离能耗以及历史单位距离能耗，确定第二单位距离能耗。
其中，在一些实施例中，如图1E所示，步骤S300可以包括以下子步骤S310-S320：
步骤S310:根据历史单位距离能耗、剩余可用电量以及第一路径确定权重。
在一些实施例中，如图1F所示，步骤S310包括以下子步骤S311-S314：
步骤S311:根据历史单位距离能耗和剩余可用电量确定粗估续驶里程。
其中，在一些实施例中，历史单位距离能耗可以根据历史总耗电量(即历史总能耗)与历史累计行程的长度的比值确定；根据剩余可用电量和历史单位距离能耗的比值确定粗估续驶里程。
步骤S312:根据第一路径以及第一路径与能耗预测准确度的对应关系，确定能耗预测准确度。
当导航的路径过短时，能耗预测模型的偶然性会影响能耗预测的准确度；当导航路径过长时，路况预测的准确度也会有所下降，因此第一路径与能耗预测的准确度具有一定的关系。
在一些实施例中，第一路径与能耗预测准确度的对应关系可以采用拟合的方式建立，如图5示出了拟合出的第一路径的长度或等效长度(在使用导航时被称为导航路径长度)与能耗预测准确度的对应关系的例子。
步骤S313:确定第一目的地的可信度。
其中，在一些实施例中，第一目的地的可信度可以根据从当前位置前往各个第一目的地的概率(参见图4，例如到目的地A、目的地B、目的地B的概率P destina1、P destina2、P destina3)以及从当前位置前往各个第一目的地的各个第一路径中每个路径的概率p12*p24、p13*p34、p12*p23*p34、p15、p16确定。其确定方式可以参见步骤S61的描述，为了简洁起见，在此不再赘述。
步骤S314:根据第一路径与粗估续驶里程的比值、第一目的地的可信度以及预测能耗准确度确定权重。
其中，权重的确定方式可以参见步骤S71-步骤S74的描述，为了简洁起见，在此不再赘述。
如图1E所示，步骤S320:根据第一单位距离能耗、历史单位距离能耗以及权重，确定第二单位距离能耗。
在一些实施例中，第二单位距离能耗可以通过以下公式计算得到：
E_Pre＝E_ave*(1-f_Navi)+E_Navi*f_Navi
其中，E_Pre为第二单位距离能耗；E_ave为历史单位距离能耗；E_Navi为第一单位距离能耗；f_Navi为权重。
如图1A所示，步骤S400:根据车辆的剩余可用电量以及第二单位距离能耗，确定车辆的续驶里程。
其中，在一些实施例中，续驶里程可以根据剩余可用电量和第二单位距离能耗的比值确定。
图2A示出了本申请实施例提供的续驶里程确定方法的流程图，如图2A所示，本申请实施例提供的续驶里程确定方法包括以下步骤S1-S9：
步骤S1：确定导航是否开启。
当导航开启时，执行步骤S2：获取导航目的地和导航路径。
参见图7所示的示例，用户从起点S的花园坊出发前往终点Z的黄埔中心大厦，根据导航功能可以确定导航路径。
步骤S3：根据导航路径确定已知行程单位距离能耗。
在本申请中，已知行程单位距离能耗也称为第一单位距离能耗。已知行程为从车辆当前位置前往预测目的地、导航目的地或用户根据预测目的地选择出的最终目的地的路径。
当导航未开启时，执行步骤S4：获取行程信息。
其中，行程信息包括：车辆当前的位置信息和环境信息，环境信息可以包括当前的天气信息，环境信息还可以包括当前的路况信息。
步骤S5：根据行程信息和路网模型确定从当前的位置到达最终目的地的最终路径。
其中，路网模型在本申请中也被称为第一模型，关于路网模型的描述可以参见本申请上述实施例的步骤S121中关于第一模型的描述。为了简洁起见，在此不再赘述。
如图2B所示，步骤S5可以包括以下子步骤S51-S56:
步骤S51:根据当前的位置信息、环境信息和路网模型确定预测目的地、预测目的地对应的概率以及从当前位置前往预测目的地的每个路口前往各个路线的概率。
其中，预测目的地在本申请中也被称为第二目的地。参见图7所示的示例，预测目的地可以包括：终点X的向阳明初级中学、终点Y的天平桥公园以及终点Z的黄浦中心大厦；路口包括路口1、路口2和路口3，图中箭头方向表示从路口1前往的不同路线1a、2a。需要说明的是，为了简洁起见，图7中的路口和目的地仅示意性的分别示出三个，但本申请不限于此。
在一些实施例中，根据当前的位置信息、环境信息和路网模型确定出的预测目的地和预测目的地对应的概率如表2所示。
表2
预测目的地 目的地A 目的地B 目的地C 目的地D 目的地E
概率 70％ 15％ 5％ 2％ 1％
步骤S52：确定概率中的最大值是否小于第一预设值或确定车辆SOC(State of Charge，电池荷电状态)是否小于第二预设值。
其中，第一预设值可以在50％～90％的范围中进行选择，但本申请不限于此，第 一预设值还可以根据需要进行设定。第二预设值可以在1％～40％的范围中进行选择，本申请也不限于此，第二预设值可以根据需要进行设定。
当概率中的最大值小于第一预设值或当车辆SOC小于第二预设值时，
执行步骤S53：根据预测目的地对应的概率在显示屏弹出目的地确认窗口。
目的地确认窗口中会显示一个或多个目的地选项。
在一些实施例中，可以将概率值中排名前三对应的目的地弹出供用户选择，如图6所示。在一些实施例中，也可以将概率值大于第三预设值(例如，60％)的对应的目的地弹出供用户选择。
目的地确认窗口默认显示预设时间，例如可以显示10秒。目的地确认窗口可以手动关闭。可选地，目的地确认窗口在一次驾驶中仅弹出一次。
在一些实施例中，也可以语音播报一个或多个目的地选项供用户选择。
当概率中的最大值大于第一预设值或当车辆SOC大于第二预设值时，
执行步骤S54：将预测目的地作为最终目的地。
其中，最终目的地在本申请中也被称为第一目的地。
当概率中的最大值大于第一预设值时，则认为路网模型确定的预测目的地的准确度较高，因此可以不弹出目的地确认窗口；或者，当车辆SOC大于第二预设值时，则认为车辆的剩余电池电量较高，因此可以不弹出目的地确认窗口。
步骤S55：响应用户的选择确定出最终目的地。
在一些实施例中，用户可以通过操作屏幕选择出最终目的地，也可以发出语音指令确定出最终目的地。
当用户未对目的地确认窗口进行选择时，则执行步骤S54。
步骤S56：根据最终目的地确定从当前位置到达最终目的地的最终路径。
其中，最终路径在本申请中也被称为第一路径。
最终路径可以包括：在车辆历史行程中，从当前位置到达最终目的地的路径；以及导航系统推荐的从当前位置到达最终目的地的路径。
步骤S6：根据最终路径确定已知行程单位距离能耗。
如图2C所示，步骤S6可以包括以下子步骤S61-S63:
步骤S61：根据每个路口前往各个路线的概率以及从当前位置前往最终目的地的概率确定最终目的地的可信度。
以图4所示的场景为例，通过步骤S53确认出三个预测目的地(目的地A、目的地B和目的地C)，用户未响应于目的地确认窗口，则将三个预测目的地作为最终目的地，即目的地A、目的地B以及目的地C。
示意性地，从当前位置到达目的地A经过路口2和路口3，从当前位置到达目的地A的路径包括多个，本实施例中取概率前三的三条路径：路径1(即起点-路口2-目的地A)、路径2(即起点-路口3目的地A)以及路径3(即起点-路口2-路口3-目的地A)；从当前位置达到目的地B的路径为一条，本实施例中取该一条路径(即路径4)；从当前位置到达目的地C的路径为一条，本实施例中取该一条路径(即路径5)。
则从当前位置前往目的地A的三条路径的概率和为：
Proute destina1＝p12*p24+p13*p34+p12*p23*p34
其中，Proute destina1为从当前位置前往目的地A的三条路径的概率和；p12为从当前位置前往路口2的概率；p13为从当前位置前往路口3的概率；p23为从路口2前往路口3的概率；p24为从路口2前往目的地A的概率；p34为从路口3前往目的地A的概率；即p12、p13、p23、p24以及p34为各个路口前往各个路线的概率。
用户选择目的地A的三条路径的概率为：
P1＝Proute destina1*P destina1
其中，Proute destina1为从当前位置前往目的地A的三条路径的概率和,P destina1为用户前往目的地A的概率，P1为用户选择目的地A的三条路径的概率。
需要说明的是，当从当前位置前往最终目的地(例如，目的地A)的路径多于三条时，可以选择概率前三的路径计算他们的概率和，也可以选择概率前二或概率前N的路径计算他们的概率和。
从当前位置前往目的地B的路径的概率和为：
Proute destina2＝p15
其中，Proute destina2为从当前位置前往目的地B的路径的概率和；p15为从当前位置前往目的地B的概率。
用户选择目的地B的路径的概率为：
P2＝Proute destina2*P destina2
其中，Proute destina2为从当前位置前往目的地B的路径的概率和；P destina2为用户从当前位置前往目的地B的概率；P2为用户选择目的地B的路径的概率。
从当前位置前往目的地C的路径的概率和为：
Proute destina3＝p16
其中，Proute destina2为从当前位置前往目的地C的路径的概率和；p16为从当前位置前往目的地C的概率。
用户选择目的地C的路径的概率为：
P3＝Proute destina3*P destina3
其中，Proute destina3为从当前位置前往目的地C的路径的概率和；P destina3为用户从当前位置前往目的地C的概率；P3为用户选择目的地C的路径的概率。
最终目的地的可信度(在本申请中也称为第一目的地的可信度)Proute destina为：
Proute destina＝P1+P2+P3＝Proute destina1*P destina1+Proute destina2*P destina2+Proute destina3*P destina3
其中，Proute destina1为从当前位置前往目的地A的三条路径的概率和；P destina1为用户前往目的地A的概率；P1为用户选择目的地A的三条路径的概率；Proute destina2为从当前位置前往目的地B的路径的概率和；P destina2为用户从当前位置前往目的地B的概率；P2为用户选择目的地B的路径的概率；Proute destina3为从当前位置前往目的地C的路径的概率和；P destina3为用户从当前位置前往目的地C的概率；P3为用户选择目的地C的路径的概率。
步骤S62:根据最终路径的长度以及每个路口前往各个路线的概率，确定等效路径 长度。
在最终目的地包含多个和/或前往最终目的地的最终路径为多个的时，则需要根据多个最终路径来确定等效路径长度。
仍以图4示出的三个最终目的地A、B、C为例，车辆从当前位置前往目的地A的路径为多个，那么从当前位置前往目的地A的等效路径长度：
L1＝(l_route1*p12*p24+l_route2*p13*p34+l_route3*p12*p23*p34)/(p12*p24+p13*p34+p12*p23*p34)
其中，L1是车辆从当前位置前往目的地A的等效路径长度；l_route1是车辆从当前位置前往目的地A的路径1的长度；l_route2是车辆从当前位置前往目的地A的路径2的长度；l_route3是车辆从当前位置前往目的地A的路径3的长度；p12为从当前位置前往路口2的概率；p13为从当前位置前往路口3的概率；p23为从路口2前往路口3的概率；p24为从路口2前往目的地A的概率；p34为从路口3前往目的地A的概率，即p12、p13、p23、p24以及p34为各个路口前往各个路线的概率。
车辆从当前位置前往目的地B的等效路径长度：
L2＝l_route4*p15/p15＝l_route4
L2是车辆从当前位置前往目的地B的等效路径长度；l_route4是车辆从当前位置前往目的地B的路径4的长度；p15为从当前位置前往目的地B的概率。
车辆从当前位置前往目的地C的等效路径长度：
L3＝l_route5*p16/p16＝l_route5
L3是车辆从当前位置前往目的地C的等效路径长度；l_route5是车辆从当前位置前往目的地C的路径5的长度；p16为从当前位置前往目的地C的概率。
车辆从当前位置前往最终目的地的等效路径长度：
L_Navi＝(P1*L1+P2*L2+P3*L3)/(P1+P2+P3)
其中，L_Navi是车辆从当前位置前往最终目的地的等效路径长度；P1是用户选择目的地A的三条路径的概率；P2是用户选择目的地B的路径的概率；P3是用户选择目的地C的路径的概率；L1是车辆从当前位置前往目的地A的等效路径长度，L2是车辆从当前位置前往目的地B的等效路径长度，L3是车辆从当前位置前往目的地C的等效路径长度。
步骤S63:根据最终路径的长度、最终路径的所需能耗、每个路口前往各个路线的概率以及等效路径长度确定已知行程单位距离能耗。
仍以图4示出的三个最终目的地A、B、C为例，车辆从当前位置前往目的地A的单位距离平均能耗为：
E1＝E_route1*l_route1*p12*p24+E_route2*l_route2*p13*p34+E_route3*l_route3*p12*p23*p34)/(p12*p24+p13*p34+p12*p23*p34)/(l_route1+l_route2+l_route3)
其中，E1是车辆从当前位置前往目的地A的单位距离平均能耗，l_route1是车辆从当前位置前往目的地A的路径1的长度；l_route2是车辆从当前位置前往目的地A的路径2的长度，l_route3是车辆从当前位置前往目的地A的路径3的长度，p12为从当前位置前往路口2的概率，p13为从当前位置前往路口3的概率，p23为从路口2 前往路口3的概率，p24为从路口2前往目的地A的概率，p34为从路口3前往目的地A的概率，即p12、p13、p23、p24以及p34为各个路口前往各个路线的概率，E_route1是车辆从当前位置前往目的地A路径1的单位距离平均能耗，E_route2是车辆从当前位置前往目的地A路径2的单位距离平均能耗，E_route3是车辆从当前位置前往目的地A路径3的单位距离平均能耗。
车辆从当前位置前往目的地B的单位距离平均能耗为：
E2＝E_route4*l_route4*p15/p15/l_route4＝E_route4
其中，E1是车辆从当前位置前往目的地B的单位距离平均能耗，E_route4是车辆从当前位置前往目的地B路径5的单位距离平均能耗，l_route4是车辆从当前位置前往目的地B的路径4的长度，p15为从当前位置前往目的地B的概率。
车辆从当前位置前往目的地C的单位距离平均能耗为：
E3＝E_route5*l_route5*p16/p16/l_route5＝E_route5
其中，E3是车辆从当前位置前往目的地C的单位距离平均能耗，E_route5是车辆从当前位置前往目的地C路径5的单位距离平均能耗，l_route5是车辆从当前位置前往目的地C路径5的长度，p16为从当前位置前往目的地C的概率。
车辆从当前位置前往最终目的地的已知行程单位距离能耗：
E_Navi＝(P1*E1*L1+P2*E2*L2+P3*E3*L3)/(P1+P2+P3)/L_Navi
其中，E_Navi是最终目的地的已知行程平均单位能耗；P1是用户选择目的地A的三条路径的概率；E1是车辆从当前位置前往目的地A的单位距离平均能耗，L1是车辆从当前位置前往目的地A的等效路径长度；P2是用户选择目的地B的路径的概率；E2是车辆从当前位置前往目的地B的单位距离平均能耗；L2是车辆从当前位置前往目的地B的等效路径长度；P3是用户选择目的地C的路径的概率；E3是车辆从当前位置前往目的地C的单位距离平均能耗；L3是车辆从当前位置前往目的地C的等效路径长度；L_Navi是车辆从当前位置前往最终目的地的等效路径长度。
如图2A所示，步骤S7：根据已知行程单位距离能耗、历史单位距离能耗以及权重确定最终单位距离能耗。
如图2D所示，步骤S7可以包括以下子步骤S71-S75：
步骤S71:根据历史累计行程距离、历史总能耗确定历史单位距离能耗。
其中，历史单位距离能耗可以根据历史总能耗与历史行程累计距离的商确定。
步骤S72:根据剩余可用电量以及历史单位距离能耗确定粗估剩余里程。
其中，粗估剩余里程可以根据剩余可用电量与历史单位距离能耗的比值确定。
步骤S73:根据等效路径长度、等效路径长度与能耗预测准确度的对应关系，确定能耗预测准确度。
其中，在用户使用导航时，路况信息可以包括交通部各个路段的实时交通流信息、当前使用导航的用户的位置信息和速度信息；历史时刻的各个道路的路况信息。当导航的路径过短时，能耗预测模型的偶然性会影响能耗预测的准确度；当导航路径过长时，路况预测的准确度也会有所下降。在一些实施例中，最终拟合出的等效路径长度(在使用导航时被称为导航路径长度)与能耗预测准确度的关系如图5所示。
步骤S74:根据等效路径长度、粗估剩余里程、能耗预测准确度以及最终目的地的 可信度确定权重。
其中，在一些实施例中，权重可以通过以下公式计算得到：
Figure PCTCN2022078273-appb-000001
f_Navi为权重；L_Navi为等效路径长度；L_Ave为粗估剩余里程；P_Navi为能耗预测准确度；Proute_destina为最终目的地的可信度。从步骤S61中已经确定最终目的地的可信度Proute destina。需要说明的是，当用户开启导航时，则最终目的地的可信度Proute destina为1。
步骤S75:根据历史单位距离能耗、已知行程单位距离能耗以及权重确定最终单位距离能耗。
其中，在一些实施例中，最终单位距离能耗可以通过以下公式计算得到：
E_Pre＝E_ave*(1-f_Navi)+E_Navi*f_Navi
其中，E_Pre为最终单位距离能耗；E_ave为历史单位距离能耗；E_Navi为已知行程单位距离能耗；f_Navi为权重。
如图2A所示，步骤S8:根据剩余可用电量和最终单位距离能耗确定续驶里程。
其中，续驶里程可以根据剩余可用电量和最终单位距离能耗的商确定。确定后的续驶里程可以进一步显示在中控屏幕上或显示在车载仪表中，和/或者通过语音方式播报给用户。
在一些实施例中，车辆在一次行程中获取的位置信息、终点信息、路况信息、天气信息、消耗的能耗以及时间等数据可以存储至路网数据库中，用于执行步骤S9，以训练和更新路网模型。
图8是本申请实施例提供的续驶里程确定装置5000的模块示意图，包括：收发模块1000，用于获取从车辆当前位置到达第一目的地的第一路径；第一确定模块2000，用于根据第一路径，确定第一路径的第一单位距离能耗；第二确定模块3000，用于根据第一单位距离能耗以及历史单位距离能耗，确定第二单位距离能耗；第三确定模块4000，用于根据车辆的剩余可用电量以及第二单位距离能耗，确定车辆的续驶里程。
在一些实施例中，收发模块1000具体用于：获取车辆当前的位置信息和环境信息；以及根据位置信息和环境信息确定第一目的地以及第一路径。
在一些实施例中，收发模块1000具体用于：根据位置信息和环境信息确定第二目的地和第二目的地的对应的概率，当概率中的最大值小于第一预设值时，根据概率输出第二目的地中的至少一个；以及响应用户的选择从所输出的至少一个第二目的地中确定出第一目的地。
在一些实施例中，收发模块1000具体用于：根据位置信息和环境信息确定第二目的地和第二目的地对应的概率；当车辆的剩余可用电量小于第二预设值时，根据概率的大小输出第二目的地中的至少一个；以及响应用户的选择从所输出的至少一个第二目的地中确定出第一目的地。
在一些实施例中，收发模块1000具体用于：将位置信息和环境信息输入至第一 模型，获得第二目的地和第二目的地对应的概率，其中，第一模型根据历史行程的路径信息以及环境信息训练得到。
在一些实施例中，第一模型包括随机森林模型。
在一些实施例中，第一确定模块2000具体用于：获取第一路径的单位距离平均能耗；针对第一目的地，根据到达第一目的地的第一路径的单位距离平均能耗，确定到达第一目的地的单位距离平均能耗；以及根据到达第一目的地的单位距离平均能耗，确定第一单位距离能耗。
在一些实施例中，第二确定模块3000具体用于：根据根据历史单位距离能耗、剩余可用电量以及第一路径确定权重；以及根据第一单位距离能耗、历史单位距离能耗以及权重，确定第二单位距离能耗。
在一些实施例中，第二确定模块3000具体用于：根据历史单位距离能耗和剩余可用电量确定粗估续驶里程；根据第一路径以及第一路径与预设能耗预测准确度的对应关系，确定能耗预测准确度；确定第一目的地的可信度；以及根据第一路径与粗估续驶里程的比值、第一目的地的可信度以及预测能耗准确度确定权重。
本申请实施例提供的续驶里程确定装置所带来的技术效果以及详细描述参见本申请实施例提供的续驶里程确定方法，为了简洁起见，在此不再赘述。
在本实施例中，续驶里程确定装置是以模块的形式来呈现。这里的“模块”可以指特定应用集成电路(application-specific integrated circuit，ASIC)，执行一个或多个软件或固件程序的处理器和存储器，集成逻辑电路，和/或其他可以提供上述功能的器件。此外，以上续驶里程确定装置可以通过图9所示的车载装置的处理器1510来实现。
图9是本申请实施例提供的一种计算设备1500的结构性示意性图。该计算设备1500包括：处理器1510和存储器1520。
其中，该处理器1510可以与存储器1520连接。该存储器1520可以用于存储该程序代码和数据。因此，该存储器1520可以是处理器1510内部的存储单元，也可以是与处理器1510独立的外部存储单元，还可以是包括处理器1510内部的存储单元和与处理器1510独立的外部存储单元的部件。
可选的，计算设备1500还可以包括总线。其中，存储器1520、通信接口可以通过总线与处理器1510连接。总线可以是外设部件互连标准(Peripheral Component Interconnect，PCI)总线或扩展工业标准结构(Extended Industry Standard Architecture，EISA)总线等。总线可以分为地址总线、数据总线、控制总线等。
应理解，在本申请实施例中，该处理器1510可以采用中央处理单元(central processing unit，CPU)。该处理器还可以是其它通用处理器、数字信号处理器(digital signal processor，DSP)、ASIC、现场可编程门阵列(field programmable gate Array，FPGA)或者其它可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。或者该处理器1510采用一个或多个集成电路，用于执行相关程序，以实现本申请实施例所提供的技术方案。
该存储器1520可以包括只读存储器和随机存取存储器，并向处理器1510提供指令和数据。处理器1510的一部分还可以包括非易失性随机存取存储器。例如，处理 器1510还可以存储设备类型的信息。
在计算设备1500运行时，处理器1510执行存储器1520中的计算机执行指令执行上述方法的操作步骤。
应理解，根据本申请实施例的计算设备1500可以对应于执行根据本申请各实施例的方法中的相应主体，并且计算设备1500中的各个模块的上述和其它操作和/或功能分别为了实现本实施例各方法的相应流程，为了简洁，在此不再赘述。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
本申请实施例还提供了一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时用于执行一种续驶里程确定方法，该方法包括上述各个实施例所描述的方案中的至少之一。
本申请实施例的计算机存储介质，可以采用一个或多个计算机可读的介质的任意组合。计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质。计算机可读存储介质例如可以是，但不限于，电、磁、光、电磁、红外线、或半导体的系统、 装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本文件中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。
计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。
计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括、但不限于无线、电线、光缆、射频(radio frequency，RF)等等，或者上述的任意合适的组合。
可以以一种或多种程序设计语言或其组合来编写用于执行本申请操作的计算机程序代码，所述程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络，包括局域网(LAN)或广域网(WAN)，连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
说明书和权利要求书中的词语“第一、第二”等类似用语，仅用于区别类似的对象，不代表针对对象的特定排序，可以理解地，在允许的情况下可以互换特定的顺序或先后次序，以使这里描述的本申请实施例能够以除了在这里图示或描述的以外的顺序实施。
说明书和权利要求书中使用的术语“包括”不应解释为限制于其后列出的内容；它不排除其它的元件或步骤。因此，其应当诠释为指定所提到的所述特征、整体、步骤或部件的存在，但并不排除存在或添加一个或更多其它特征、整体、步骤或部件及其组群。因此，表述“包括装置A和B的设备”不应局限为仅由部件A和B组成的设备。
本说明书中提到的“一个实施例”或“实施例”意味着与该实施例结合描述的特定特征、结构或特性包括在本申请的至少一个实施例中。因此，在本说明书各处出现的用语“在一个实施例中”或“在实施例中”并不一定都指同一实施例，但可以指同一实施例。此外，在一个或多个实施例中，能够以任何适当的方式组合各特定特征、结构或特性，如从本公开对本领域的普通技术人员显而易见的那样。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (22)

  1. 一种续驶里程确定方法，其特征在于，包括：
    获取从车辆当前位置到达第一目的地的第一路径；
    根据所述第一路径，确定所述第一路径的第一单位距离能耗；
    根据所述第一单位距离能耗以及历史单位距离能耗，确定第二单位距离能耗；以及
    根据所述车辆的剩余可用电量以及所述第二单位距离能耗，确定所述车辆的续驶里程。
  2. 根据权利要求1所述的方法，其特征在于，所述获取从车辆当前位置到达第一目的地的第一路径，包括：
    获取车辆当前的位置信息和环境信息；以及
    根据所述位置信息和所述环境信息确定所述第一目的地以及所述第一路径。
  3. 根据权利要求2所述的方法，其特征在于，所述确定所述第一目的地，包括：
    根据所述位置信息和所述环境信息确定第二目的地和所述第二目的地的对应的概率，
    当所述概率中的最大值小于第一预设值时，根据所述概率输出所述第二目的地中的至少一个；以及
    响应用户的选择从所输出的所述至少一个第二目的地中确定出所述第一目的地。
  4. 根据权利要求2所述的方法，其特征在于，确定所述第一目的地具体包括：
    根据所述位置信息和所述环境信息确定第二目的地和所述第二目的地对应的概率；
    当所述车辆的剩余可用电量小于第二预设值时，根据所述概率的大小输出所述第二目的地中的至少一个；以及
    响应用户的选择从所输出的所述至少一个第二目的地中确定出所述第一目的地。
  5. 根据权利要求3或4所述的方法，其特征在于，根据所述位置信息和所述环境信息，确定第二目的地和所述第二目的地对应的概率，具体包括：
    将所述位置信息和所述环境信息输入至第一模型，获得所述第二目的地和所述第二目的地对应的概率，
    其中，所述第一模型根据历史行程的路径信息以及环境信息训练得到。
  6. 根据权利要求5所述的方法，其特征在于，所述第一模型包括随机森林模型。
  7. 根据权利要求1-6任一项所述的方法，其特征在于，根据所述第一路径，确定所述第一路径的第一单位距离能耗，具体包括：
    获取所述第一路径的单位距离平均能耗；
    针对所述第一目的地，根据到达所述第一目的地的所述第一路径的单位距离平均能耗，确定到达所述第一目的地的单位距离平均能耗；以及
    根据到达所述第一目的地的单位距离平均能耗，确定所述第一单位距离能耗。
  8. 根据权利要求1-7任一项所述的方法，其特征在于，根据所述第一单位距离能耗以及历史单位距离能耗，确定第二单位距离能耗，具体包括：
    根据根据历史单位距离能耗、所述剩余可用电量以及所述第一路径确定权重；以及
    根据所述第一单位距离能耗、所述历史单位距离能耗以及所述权重，确定所述第二单位距离能耗。
  9. 根据权利要求8所述的方法，其特征在于，根据根据历史单位距离能耗、所述剩余可用电量以及所述第一路径确定权重，具体包括：
    根据所述历史单位距离能耗和所述剩余可用电量确定粗估续驶里程；
    根据所述第一路径以及所述第一路径与预设能耗预测准确度的对应关系，确定能耗预测准确度；
    确定所述第一目的地的可信度；以及
    根据所述第一路径与所述粗估续驶里程的比值、所述第一目的地的可信度以及所述预测能耗准确度确定所述权重。
  10. 一种续驶里程确定装置，其特征在于，包括：
    收发模块，用于获取从车辆当前位置到达第一目的地的第一路径；
    第一确定模块，用于根据所述第一路径，确定所述第一路径的第一单位距离能耗；
    第二确定模块，用于根据所述第一单位距离能耗以及历史单位距离能耗，确定第二单位距离能耗；以及
    第三确定模块，用于根据所述车辆的剩余可用电量以及所述第二单位距离能耗，确定所述车辆的续驶里程。
  11. 根据权利要求10所述的装置，其特征在于，所述收发模块具体用于：
    获取车辆当前的位置信息和环境信息；以及
    根据所述位置信息和所述环境信息确定所述第一目的地以及所述第一路径。
  12. 根据权利要求11所述的装置，其特征在于，所述收发模块具体用于：
    根据所述位置信息和所述环境信息确定第二目的地和所述第二目的地的对应的概率，
    当所述概率中的最大值小于第一预设值时，根据所述概率输出所述第二目的地中的至少一个；以及
    响应用户的选择从所输出的所述至少一个第二目的地中确定出所述第一目的地。
  13. 根据权利要求11所述的装置，其特征在于，所述收发模块具体用于：
    根据所述位置信息和所述环境信息确定第二目的地和所述第二目的地对应的概率；
    当所述车辆的剩余可用电量小于第二预设值时，根据所述概率的大小输出所述第二目的地中的至少一个；以及
    响应用户的选择从所输出的所述至少一个第二目的地中确定出所述第一目的地。
  14. 根据权利要求12或13所述的装置，其特征在于，所述收发模块具体用于：
    将所述位置信息和所述环境信息输入至第一模型，获得所述第二目的地和所述第二目的地对应的概率，
    其中，所述第一模型根据历史行程的路径信息以及环境信息训练得到。
  15. 根据权利要求14所述的装置，其特征在于，所述第一模型包括随机森林模型。
  16. 根据权利要求10-15任一项所述的装置，其特征在于，所述第一确定模块具体用于：
    获取所述第一路径的单位距离平均能耗；
    针对所述第一目的地，根据到达所述第一目的地的所述第一路径的单位距离平均能耗，确定到达所述第一目的地的单位距离平均能耗；以及
    根据到达所述第一目的地的单位距离平均能耗，确定所述第一单位距离能耗。
  17. 根据权利要求10-16任一项所述的装置，其特征在于，所述第二确定模块具体用于：
    根据根据历史单位距离能耗、所述剩余可用电量以及所述第一路径确定权重；以及
    根据所述第一单位距离能耗、所述历史单位距离能耗以及所述权重，确定所述第二单位距离能耗。
  18. 根据权利要求17所述的装置，其特征在于，所述第二确定模块具体用于：
    根据所述历史单位距离能耗和所述剩余可用电量确定粗估续驶里程；
    根据所述第一路径以及所述第一路径与预设能耗预测准确度的对应关系，确定能耗预测准确度；
    确定所述第一目的地的可信度；以及
    根据所述第一路径与所述粗估续驶里程的比值、所述第一目的地的可信度以及所述预测能耗准确度确定所述权重。
  19. 一种计算机可读存储介质，其特征在于，存储有使计算机执行权利要求1-9中任一项所述的续驶里程确定方法。
  20. 一种计算设备，包括处理器与存储器，其特征在于，存储器中存储有程序，通过由处理器运行该程序而执行权利要求1-9中任一项所述的续驶里程确定方法。
  21. 一种计算机程序产品，其特征在于，当所述计算机程序在计算机上运行时，使得计算机执行如权利要求1至9中任意一项所述的方法。
  22. 一种车辆，其特征在于，包括如权利要求10-18中任一项所述的续驶里程确定装置。
PCT/CN2022/078273 2022-02-28 2022-02-28 一种续驶里程确定方法、装置和车辆 WO2023159562A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202280004038.9A CN116981587A (zh) 2022-02-28 2022-02-28 一种续驶里程确定方法、装置和车辆
PCT/CN2022/078273 WO2023159562A1 (zh) 2022-02-28 2022-02-28 一种续驶里程确定方法、装置和车辆

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/078273 WO2023159562A1 (zh) 2022-02-28 2022-02-28 一种续驶里程确定方法、装置和车辆

Publications (1)

Publication Number Publication Date
WO2023159562A1 true WO2023159562A1 (zh) 2023-08-31

Family

ID=87764405

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/078273 WO2023159562A1 (zh) 2022-02-28 2022-02-28 一种续驶里程确定方法、装置和车辆

Country Status (2)

Country Link
CN (1) CN116981587A (zh)
WO (1) WO2023159562A1 (zh)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102248946A (zh) * 2010-04-08 2011-11-23 罗伯特·博世有限公司 具有电机驱动的车辆的可到达范围的管理的方法以及装置
CN111216730A (zh) * 2020-01-15 2020-06-02 山东理工大学 电动汽车剩余续驶里程估算方法、装置、存储介质及设备
CN112860782A (zh) * 2021-02-07 2021-05-28 吉林大学 一种基于大数据分析的纯电动车续驶里程估计方法
CN113119793A (zh) * 2020-01-10 2021-07-16 上海汽车集团股份有限公司 一种车辆续驶里程计算方法及装置
JP2021196295A (ja) * 2020-06-16 2021-12-27 トヨタ自動車株式会社 情報処理装置
CN113858959A (zh) * 2021-10-12 2021-12-31 东风汽车集团股份有限公司 纯电动汽车续驶里程计算方法、车辆及电子设备

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102248946A (zh) * 2010-04-08 2011-11-23 罗伯特·博世有限公司 具有电机驱动的车辆的可到达范围的管理的方法以及装置
CN113119793A (zh) * 2020-01-10 2021-07-16 上海汽车集团股份有限公司 一种车辆续驶里程计算方法及装置
CN111216730A (zh) * 2020-01-15 2020-06-02 山东理工大学 电动汽车剩余续驶里程估算方法、装置、存储介质及设备
JP2021196295A (ja) * 2020-06-16 2021-12-27 トヨタ自動車株式会社 情報処理装置
CN112860782A (zh) * 2021-02-07 2021-05-28 吉林大学 一种基于大数据分析的纯电动车续驶里程估计方法
CN113858959A (zh) * 2021-10-12 2021-12-31 东风汽车集团股份有限公司 纯电动汽车续驶里程计算方法、车辆及电子设备

Also Published As

Publication number Publication date
CN116981587A (zh) 2023-10-31

Similar Documents

Publication Publication Date Title
EP3683548B1 (en) Road matching-based positioning method, chip subsystem and electronic device
US10352718B2 (en) Discovering points of entry to a location
EP3800445A1 (en) Method, apparatus, and system for generating vehicle paths in a limited graph area
US9689702B2 (en) Navigation system with map mechanism and method of operation thereof
EP3227873B1 (en) Method and apparatus for providing point of interest information
US10055981B2 (en) Traffic speed modeling
US9200910B2 (en) Ranking of path segments based on incident probability
US9620007B2 (en) Method of generating expected average speeds of travel
US20180156623A1 (en) Generating travel instructions in multimodal transportation scenarios
US9301099B2 (en) Method of analyzing points of interest with probe data
US20100082226A1 (en) System and Methods For Providing Predictive Traffic Information
US11170138B2 (en) Geographic position calculation for sign placement based on destination profiling of probe data
US11348452B2 (en) Method, apparatus, and system for automatic closure verification using multiple possible vehicle paths
US20060047422A1 (en) Item search device
US11756417B2 (en) Method, apparatus, and system for detecting road incidents
US11867528B2 (en) Method, apparatus, and system for providing road closure graph inconsistency resolution
JP2004354086A (ja) ナビゲーションシステム
JP2000055689A (ja) 可変的ル―ト案内のために交通情報を使用する方法
JP4054596B2 (ja) サーバ
WO2023159562A1 (zh) 一种续驶里程确定方法、装置和车辆
TW201017112A (en) A system and method for determining road attributes
US11546724B2 (en) Method, apparatus, and system for determining a non-specific location according to an observed mobility pattern derived from non-positioning related sensor data
US20240085193A1 (en) Automated dynamic routing unit and method thereof
CN114724414B (zh) 城市空中交通分担率的确定方法、装置、电子设备及介质
US20220207993A1 (en) Method, apparatus, and system for verifying a lane closure using probe data

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 202280004038.9

Country of ref document: CN

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22927844

Country of ref document: EP

Kind code of ref document: A1