Information processing device, information processing method, and program

Abstract

An information processing device according to an embodiment of the present invention comprises: an acquisition unit that acquires a departure point and a destination point of a target vehicle; and a calculation unit that calculates the total consumption energy predicted to be consumed by the entire target vehicle. The calculation unit: calculates, as the total consumption energy of the target vehicle, the sum of auxiliary device consumption energy of the target vehicle and travel consumption energy of the target vehicle; calculates the auxiliary device consumption energy of the target vehicle on the basis of weather prediction data for when the target vehicle travels the route; and calculates the travel consumption energy of the target vehicle on the basis of the travel consumption energy of a reference vehicle actually measured when the reference vehicle travelled the route.

Description

Information processing device, information processing method, and program

[0001] The present invention relates to an information processing device, an information processing method, and a program. This application claims priority to Japanese Patent Application No. 2024-027720, filed on February 27, 2024, the contents of which are incorporated herein by reference.

[0002] Techniques for predicting or estimating the energy consumption of a vehicle are known (see, for example, Patent Documents 1 and 2).

[0003] JP 2009-031046 A International Publication No. 2020 / 189771

[0004] However, conventional technologies predict energy consumption using machine learning models, and the prediction accuracy depends on the reliability of the machine learning models. Therefore, the prediction accuracy of energy consumption may be low. When a vehicle travels a planned route, using a machine learning model to predict the amount of energy consumed along the entire route tends to increase the processing load. In particular, the increase in processing load becomes more pronounced as the route distance becomes longer.

[0005] The present invention has been made in consideration of the above circumstances, and one of its objects is to provide an information processing device, an information processing method, and a program that can predict the energy consumption of a vehicle with a low load.

[0006] An information processing device, an information processing method, and a program according to the present invention are configured as follows: (1) A first example of the present invention is an information processing device including an acquisition unit that acquires a departure point and a destination point of a target vehicle, and a calculation unit that calculates a total energy consumption predicted to be consumed by the entire target vehicle when the target vehicle travels a route from the departure point to the destination, wherein the calculation unit calculates the total energy consumption of the target vehicle as the sum of auxiliary equipment energy consumption, which is energy consumed by operating auxiliary equipment mounted on the target vehicle, and traveling energy consumption, which is energy consumed by traveling the target vehicle, calculates the auxiliary equipment energy consumption of the target vehicle based on weather forecast data for when the target vehicle travels the route, and calculates the traveling energy consumption of the target vehicle based on the traveling energy consumption of the reference vehicle that is actually measured when the reference vehicle travels the route.

[0007] (2) A second example of the present invention is an information processing device according to the first example, wherein the target vehicle is an electric vehicle or a plug-in hybrid vehicle, the auxiliary equipment includes an air conditioning device, and the auxiliary equipment consumption energy includes the energy consumed by the air conditioning device.

[0008] (3) A third example of the present invention is an information processing device according to the first or second example, wherein the calculation unit calculates the predicted required time for the target vehicle to travel the route, and uses a machine learning model that has been pre-trained to output the auxiliary energy consumption when the weather forecast data is input to calculate the auxiliary energy consumption of the target vehicle for a predetermined unit time from the weather forecast data for when the target vehicle travels the route, and calculates the auxiliary energy consumption of the target vehicle for the predetermined unit time by integrating the auxiliary energy consumption of the target vehicle for the predetermined unit time over the required time.

[0009] (4) A fourth example of the present invention is an information processing device according to the first or second example, wherein the calculation unit calculates the driving energy consumption of the target vehicle based on driving history data, which is a database in which the driving energy consumption of the reference vehicle is associated with the departure point and destination of the reference vehicle and the date and time when the reference vehicle traveled.

[0010] (5) A fifth example of the present invention is an information processing device according to the fourth example, wherein the calculation unit extracts from the driving history data the driving energy consumption of the reference vehicle whose departure point and destination of the target vehicle match some or all of the dates and times on which the target vehicle is scheduled to travel, and calculates the driving energy consumption of the extracted reference vehicle as the driving energy consumption of the target vehicle.

[0011] (6) A sixth example of the present invention is an information processing device according to the fifth example, wherein, when the driving history data does not contain the driving energy consumption of the reference vehicle that matches the departure point and destination of the target vehicle, the calculation unit divides the target route, which is the route from the departure point of the target vehicle to the destination, into a first section that is common to the reference route, which is the route from the departure point of the reference vehicle to the destination, and a second section that is not common to the reference route, and calculates, for the first section, the driving energy consumption of the reference vehicle included in the driving history data, which is actually measured when the reference vehicle traveled through the first section, as the driving energy consumption of the target vehicle, and calculates, for the second section, the driving energy consumption of the target vehicle based on map data including altitude information and a resistance calculation model for calculating the resistance of the target vehicle.

[0012] (7) A seventh example of the present invention is the information processing device of the fifth example, wherein, when the travel history data does not include the travel history data of the reference vehicle that matches the departure point and the destination of the target vehicle, the calculation unit calculates the travel consumption energy of the target vehicle based on map data including altitude information and a resistance calculation model for calculating the resistance of the target vehicle, and when the travel history data includes the travel consumption energy of the reference vehicle that matches the departure point and the destination of the target vehicle, The method determines whether the number of energy data is equal to or greater than a predetermined number, and if the number of data is less than the predetermined number, calculates the running energy consumption of the reference vehicle, which is the largest among the running energy consumptions of the reference vehicles, as the running energy consumption of the target vehicle.If the number of data is equal to or greater than the predetermined number, selects the running energy consumption of one reference vehicle from the running energy consumptions of the reference vehicles based on statistical indicators of the running energy consumption of the reference vehicles, and calculates the running energy consumption of the selected reference vehicle as the running energy consumption of the target vehicle.

[0013] (8) An eighth example of the present invention is an information processing method using a computer, which includes: obtaining a departure point and destination of a target vehicle; calculating the total energy consumption predicted to be consumed by the entire target vehicle when the target vehicle travels a route from the departure point to the destination; calculating the total energy consumption of the target vehicle as the sum of auxiliary energy consumption, which is the energy consumed by operating auxiliary equipment installed in the target vehicle, and driving energy consumption, which is the energy consumed by driving the target vehicle; calculating the auxiliary energy consumption of the target vehicle based on weather forecast data for when the target vehicle travels the route; and calculating the driving energy consumption of the target vehicle based on the driving energy consumption of the reference vehicle actually measured when the reference vehicle traveled the route.

[0014] (9) A ninth example of the present invention is a program to be executed by a computer, the program including: acquiring a departure point and a destination point of a target vehicle; calculating the total energy consumption predicted to be consumed by the entire target vehicle when the target vehicle travels a route from the departure point to the destination; calculating the total energy consumption of the target vehicle as the sum of auxiliary energy consumption, which is the energy consumed by operating auxiliary equipment installed in the target vehicle, and driving energy consumption, which is the energy consumed by driving the target vehicle; calculating the auxiliary energy consumption of the target vehicle based on weather forecast data for when the target vehicle travels the route; and calculating the driving energy consumption of the target vehicle based on the driving energy consumption of the reference vehicle actually measured when the reference vehicle traveled the route.

[0015] According to the above example, the energy consumption of a vehicle can be predicted at a low load.

[0016] 1 is a diagram for explaining an overview of an energy management support system 1 according to an embodiment. A diagram illustrating an example of the configuration of the energy management support system 1 according to an embodiment. A diagram illustrating an example of the configuration of a terminal device 100 according to an embodiment. A diagram illustrating an example of a reservation screen for a vehicle 10. A diagram illustrating an example of a reservation screen for a vehicle 10. A diagram illustrating an example of an editing panel. A diagram illustrating an example of an editing panel. A diagram illustrating an example of an editing panel. A diagram illustrating an example of a configuration of a server 200 according to an embodiment. A flowchart illustrating an example of a series of processes performed by the server 200 according to an embodiment. A diagram illustrating a method for calculating auxiliary device consumed energy. A diagram illustrating an example of actual driving data. A diagram illustrating a method for calculating traveling consumed energy when no completely matching actual driving data exists. A flowchart illustrating another example of a series of processes performed by the server 200 according to an embodiment. A flowchart illustrating another example of a series of processes performed by the server 200 according to an embodiment. A diagram illustrating clustering of actual driving data. A diagram illustrating a method for calculating traveling consumed energy using the quartile method.

[0017] Hereinafter, an information processing device, an information processing method, and a program according to an embodiment of the present invention will be described with reference to the drawings.

[0018] [System Overview] Fig. 1 is a diagram illustrating an overview of an energy management support system 1 according to an embodiment. The energy management support system 1 according to an embodiment is a system that supports energy management for demand response. Hereinafter, energy refers to "electricity" unless otherwise specified.

[0019] For example, the energy management support system 1 supports the management of energy consumption within a company 20 that receives power from an electric power company (electric utility). The company 20 may be, for example, a business that conducts sales activities with clients 30. Such businesses may include businesses in various fields, such as delivery, postal service, maintenance, security, medical care, pharmaceuticals, finance, insurance, and IT.

[0020] For example, company 20 has a plurality of vehicles 10 used for business purposes. The vehicles 10 include, for example, electric vehicles or plug-in hybrid vehicles. An employee of company 20 gets into the vehicle 10 to visit a client 30 and then returns to the store (building) of company 20. The client 30 is typically an existing client, but is not limited to this and may also be a new client. If the vehicle 10 is an electric vehicle or a plug-in hybrid vehicle, the employee of company 20 charges the vehicle 10 at the store of company 20. In other words, the vehicle 10 is charged using power supplied by a power company.

[0021] As described above, the company 20, which is supplied with power as a consumer by a power company, may receive a demand request from the power company. When the company 20 receives the demand request, the company 20 reduces its energy consumption during a time period specified by the power company as a demand response.

[0022] In this case, it is important to predict or estimate how much energy will be consumed throughout the company 20 during the specified time period. Therefore, it is desirable to know more accurately how much power remains in the vehicle 10 that has returned from the client 30 and how much power should be charged before the time period for which demand response is specified (for example, the morning of the day or the day before).

[0023] Therefore, in this embodiment, a machine learning model is used to more accurately predict energy consumption.

[0024] [System Configuration] Fig. 2 is a diagram illustrating an example of the configuration of the energy management support system 1 according to the embodiment. The energy management support system 1 according to the embodiment includes, for example, a terminal device 100 and a server 200. The terminal device 100 and the server 200 are connected via a network NW such as a LAN (Local Area Network) or a WAN (Wide Area Network). The server 200 is an example of an "information processing device."

[0025] The terminal device 100 may be a general-purpose device such as a smartphone, a tablet, or a personal computer. The terminal device 100 is used by employees of the company 20. The terminal device 100 may be placed in a store of the company 20 or provided to each employee of the company 20, for example. Furthermore, the functions of the terminal device 100 may be incorporated into a car navigation system installed in the vehicle 10.

[0026] The server 200 acquires various information or data from the terminal device 100 and predicts the energy consumption of the vehicle 10 of the company 20 based on the information or data.

[0027] 3 is a diagram illustrating an example of the configuration of the terminal device 100 according to the embodiment. The terminal device 100 includes, for example, a communication interface 110, an input interface 120, an output interface 130, a storage unit 140, and a processing unit 150.

[0028] The communication interface 110 includes, for example, a network interface card (NIC), a wireless communication module including a receiver and a transmitter, etc. The communication interface 110 communicates with the server 200 via the network NW.

[0029] The input interface 120 accepts various input operations from the user, converts the accepted input operations into electrical signals, and outputs the electrical signals to the processing unit 150. For example, the input interface 120 is a mouse, a keyboard, a trackball, a switch, a button, a joystick, a touch panel, etc. The input interface 120 may also be a voice user interface that accepts voice input including a microphone, etc.

[0030] The output interface 130 includes, for example, a display and a speaker. The display displays images generated by the processing unit 150, a GUI (Graphical User Interface) for receiving various input operations from the user, and the like. For example, the display is an LCD (Liquid Crystal Display) or an organic EL (Electro Luminescence) display. The speaker outputs information input from the processing unit 150 as sound. When the input interface 120 is a touch panel, the input interface 120 and the output interface 130 may be configured as an integrated unit.

[0031] The storage unit 140 is realized by, for example, a hard disk drive (HDD), a flash memory, an electrically erasable programmable read-only memory (EEPROM), a read-only memory (ROM), a random access memory (RAM), etc. The storage unit 140 stores firmware, application programs, etc.

[0032] The processing unit 150 is realized by a processor such as a central processing unit (CPU) or a graphics processing unit (GPU) executing a program stored in the storage unit 140. The processing unit 150 may be realized by hardware such as a large-scale integration (LSI), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a system-on-chip (SOC), or may be realized by a combination of software and hardware.

[0033] For example, when an employee of the company 20 visits the client 30 , he or she uses the terminal device 100 to reserve the use of the vehicle 10 .

[0034] [Method for reserving a vehicle using a terminal device] A method for reserving a vehicle 10 will be described below with reference to Figures 4 to 8. Figures 4 and 5 are diagrams showing examples of reservation screens for the vehicle 10. These reservation screens are displayed as GUIs on the terminal device 100.

[0035] In the figure, R1 is a button for newly reserving a vehicle 10. R2 is a field in which the date and time of use of the vehicle 10 is input. R3 is an area showing the reservation status of each vehicle 10 for the date and time of use input in field R2. In the example shown, the vehicle with identification number 001 indicates that it is reserved for use in the time period from 1:00 PM to 6:00 PM, the vehicle with identification number 002 indicates that it is reserved for use in the time period from approximately 10:30 AM to 12:00 PM, and the vehicle with identification number 003 indicates that it is reserved for use in the time period from 8:00 AM to 3:00 PM.

[0036] As shown in FIG. 5, for example, when a reservation for a vehicle with identification number 002 (R4 in the figure) is tapped or clicked, an editing panel that allows editing of the reservation for the vehicle with identification number 002 is displayed on the terminal device 100 as a GUI.

[0037] 6 to 8 are diagrams showing examples of the editing panel. As shown, the editing panel displays the date, the identification number of the employee of company 20 who has reserved vehicle 10, the identification number of vehicle 10, the departure point of vehicle 10, the departure time from the departure point to the first destination, the first destination, the arrival time at the first destination, the departure time from the first destination, the final destination of vehicle 10, the arrival time, a remarks column (memo), etc.

[0038] For example, "Client A" is entered as the first destination, but when the pull-down indicated by R5 is tapped or clicked, a history of previously entered destinations is suggested, as indicated by R7 in FIG. 7. In the illustrated example, "Clients B to E" are suggested. This allows the reserving user to select the first destination from the history.

[0039] Furthermore, when the add button indicated by R6 is tapped or clicked, an edit field for a second destination can be added, as indicated by R8 in Fig. 8. By operating this add button R6, the person reserving the trip can freely add any number of clients that will serve as stopovers between the departure point and the return point.

[0040] The processing unit 150 of the terminal device 100 transmits various information (hereinafter referred to as vehicle reservation information) entered on the reservation screen or editing panel to the server 200 via the communication interface 110. The vehicle reservation information may include various information such as the identification number of the reserved vehicle 10, the vehicle model, the planned date and time of use, the departure point, intermediate points (destination client), and return point.

[0041] [Server Configuration] The following describes the configuration of server 200. Server 200 may be a single device, or a system in which multiple devices connected via a network NW operate in cooperation with each other. In other words, server 200 may be implemented by multiple computers (processors) included in a distributed computing system or a cloud computing system.

[0042] 9 is a diagram illustrating an example of the configuration of the server 200 according to the embodiment. The server 200 includes, for example, a communication interface 210, a storage unit 220, and a processing unit 230.

[0043] The communication interface 210 includes, for example, a NIC, a wireless communication module including a receiver and a transmitter, etc. The communication interface 210 communicates with the terminal device 100 via the network NW.

[0044] The storage unit 220 is realized by, for example, a HDD, a flash memory, an EEPROM, a ROM, a RAM, etc. The storage unit 220 stores firmware, application programs, etc. The storage unit 220 also stores driving history data. The driving history data will be described in detail later.

[0045] The processing unit 230 includes, for example, an acquisition unit 232, a calculation unit 234, and an output control unit 236. These components of the processing unit 230 are realized by, for example, a processor such as a CPU or a GPU executing a program stored in the storage unit 220. Furthermore, some or all of the components of the processing unit 230 may be realized by hardware such as an LSI, an ASIC, an FPGA, or an SOC, or may be realized by a combination of software and hardware.

[0046] [Server Processing Flow: Vehicle Reservation] A series of processing flows of the server 200 will be described below with reference to a flowchart. Fig. 10 is a flowchart showing an example of a series of processing flows of the server 200 according to the embodiment. The processing of this flowchart is executed, for example, when the use of the vehicle 10 is reserved.

[0047] First, the acquisition unit 232 acquires vehicle reservation information of the vehicle 10 that is the subject of the reservation for use (hereinafter referred to as the subject vehicle 10) from among the plurality of vehicles 10 (step S100).

[0048] For example, the acquisition unit 232 may access the terminal device 100 via the communication interface 210 and acquire the vehicle reservation information from the terminal device 100. Furthermore, if the vehicle reservation information is stored in the storage unit 220 via a portable storage medium such as an SD memory card or a USB flash drive, the acquisition unit 232 may acquire the vehicle reservation information from the storage unit 220.

[0049] Next, the acquisition unit 232 acquires weather forecast data (also referred to as weather forecast information) for the date and time period for which the use of the target vehicle 10 is reserved (step S102). The weather forecast data includes, for example, weather, temperature, humidity, etc.

[0050] For example, the acquisition unit 232 may access a government or private weather data server via the communication interface 210 and acquire weather forecast data from the weather data server.

[0051] Next, the calculation unit 234 calculates the total energy consumption predicted to be consumed by the entire target vehicle 10 along the route along which the target vehicle 10 is scheduled to travel, based on the vehicle reservation information of the target vehicle 10 (vehicle type, date, time zone, departure point, intermediate points, and return point, etc.) and weather forecast data (weather, temperature, humidity, etc.) for the date and time zone on which the use of the target vehicle 10 is reserved (step S104).

[0052] For example, the calculation unit 234 calculates the sum of the auxiliary energy consumption and the traveling energy consumption as the total energy consumption.

[0053] Auxiliary energy consumption is the energy consumed by operating auxiliary devices installed in the target vehicle 10. Auxiliary devices include air conditioning equipment (e.g., compressors, heaters, defrosters, etc.) that adjust the temperature and humidity of the air inside the vehicle, adjust the temperature of the steering wheel and seats, and remove condensation from windows. It is known that such air conditioning equipment consumes significantly more energy than other auxiliary devices such as car navigation systems, audio equipment, wipers, and headlights. Furthermore, it is known that the energy consumed by air conditioning equipment is significantly dependent on driving time, weather, temperature, etc. Therefore, accurately predicting the energy consumed by air conditioning equipment leads to accurately predicting total energy consumption, in particular.

[0054] The traveling energy consumption is the energy consumed by traveling the target vehicle 10. In other words, the traveling energy consumption is the energy consumed by an electric traction motor mounted on the target vehicle 10 as a power source.

[0055] [Method for Calculating Auxiliary Energy Consumption] First, a method for calculating auxiliary energy consumption will be described. Fig. 11 is a diagram for explaining the method for calculating auxiliary energy consumption. As shown in the figure, for example, the calculation unit 234 selects a prediction model MDL1 whose vehicle model is the same as that of the target vehicle 10 from among multiple prediction models MDL1 generated for each vehicle model. Then, using the selected prediction model MDL1, the calculation unit 234 calculates the auxiliary energy consumption of the target vehicle 10 from weather forecast data for the date and time period when use of the target vehicle 10 is reserved.

[0056] The prediction model MDL1 is a model to which a machine learning algorithm such as supervised learning or regression analysis is applied. For example, the prediction model MDL1 may be a deep neural network, polynomial regression, multiple regression, support vector regression, random forest regression, or the like.

[0057] The prediction model MDL1 is a machine learning model that is pre-trained to output the auxiliary energy consumption of a reference vehicle per predetermined unit time when weather forecast data for the date, time, and time period when a reference vehicle is traveling is input. The reference vehicle may include the target vehicle 10.

[0058] In other words, the prediction model MDL1 is a machine learning model trained based on a large number of training data sets in which the auxiliary energy consumption of the reference vehicle per specified unit time is associated as a label (also called a target) with weather forecast data for the date, time, and time period when the reference vehicle was traveling.

[0059] For the prediction model MDL1 trained using such a large number of training data sets, the calculation unit 234 inputs weather forecast data for the date and time period for which the target vehicle 10 is scheduled to be used, as shown in the figure.

[0060] The prediction model MDL1 to which the weather forecast data has been input outputs the auxiliary energy consumption of the target vehicle 10 per predetermined unit time.

[0061] The calculation unit 234 calculates the estimated travel time (travel time) required for the target vehicle 10 to travel the planned route (a route from the destination to the return destination, including intermediate stops along the way).

[0062] Then, the calculation unit 234 calculates the auxiliary energy consumption of the target vehicle 10 that is predicted to take for the target vehicle 10 to complete the route by integrating the auxiliary energy consumption of the target vehicle 10 per specified unit time output by the prediction model MDL1 over the calculated required time.

[0063] [Method for Calculating Traveling Energy Consumption] Next, a method for calculating traveling energy consumption will be described. For example, the calculation unit 234 calculates the traveling energy consumption of the target vehicle 10 using the vehicle reservation information (such as the vehicle type, date, time zone, departure point, intermediate points, and return point) of the target vehicle 10 and the traveling performance data stored in the storage unit 220.

[0064] 12 is a diagram showing an example of driving history data. As shown in the figure, the driving history data is a database that accumulates the auxiliary energy consumption, driving energy consumption, and total energy consumption, which are measured when an unspecified number of reference vehicles (including the target vehicle 10) are driven. More specifically, the driving history data is a database in which the total energy consumption, auxiliary energy consumption, and driving energy consumption are associated with the departure point, destination (intermediate points and return points), vehicle type, driving time, temperature, weather, date, time (time zone), etc.

[0065] For example, the calculation unit 234 may extract a record from the driving history data that matches the vehicle type, departure point, intermediate points, return point, date, and time of the target vehicle 10, and calculate the driving energy consumption contained in that record as the driving energy consumption of the target vehicle 10.

[0066] If there are multiple records in the driving history data that all match the vehicle type, departure point, intermediate points, return point, date, and time of the target vehicle 10, the calculation unit 234 may calculate the average or median driving energy consumption contained in each of the multiple records as the driving energy consumption of the target vehicle 10.

[0067] On the other hand, there may be cases where the driving history data does not contain a record that matches all of the vehicle type, departure point, intermediate points, return point, date, and time of the target vehicle 10. For example, when visiting a new client 30 (i.e., a new destination), the driving history data does not contain any actual measurements of the driving energy consumption of the route to the new client 30. In such cases, the route of the target vehicle 10 (hereinafter referred to as the target route) and the route of the reference vehicle (hereinafter referred to as the reference route) only partially overlap. The calculation unit 234 may extract records that partially match the vehicle type, departure point, intermediate points, and return point (records of the driving energy consumption of a reference vehicle having a reference route that partially overlaps with the target route).

[0068] 13 is a diagram illustrating a method for calculating travel energy consumption when there is no perfectly matching travel history data. For example, assume that the travel history data includes a record of travel energy consumption of a reference vehicle having a reference route from a departure point S to an existing destination A. In such a case, when a new destination B is reserved, the calculation unit 234 divides the target route, which is the route of the target vehicle 10, into an existing section and a new section, as shown in the figure.

[0069] An existing section is a section of the entire target route that is common to the reference route. On the other hand, a new section is a section of the entire target route that is not common to the reference route. In other words, an existing section is a section of the entire target route for which actual driving data exists, and a new section is a section of the entire target route for which actual driving data does not exist. An existing section is an example of a "first section," and a new section is an example of a "second section."

[0070] For example, the reference route is divided into sections on the map data by a plurality of waypoints WP. Each waypoint WP is associated with an altitude in addition to latitude and longitude. In the driving performance data, the driving energy consumption of the reference vehicle is assigned to each section divided by the waypoints WP.

[0071] Therefore, the calculation unit 234 calculates the travel energy consumption W of the reference vehicle in the section from the departure point S to the waypoint WP1. Ｓ１ and the travel energy consumption W of the reference vehicle in the section from waypoint WP1 to waypoint WP2. １２ and the travel energy consumption W of the reference vehicle in the section from waypoint WP2 to waypoint WP3. ２３ and the travel energy consumption W of the reference vehicle in the section from waypoint WP5 to existing destination A. ５Ａ The sum of these is calculated as the traveling energy consumption of the target vehicle 10 in the existing section.

[0072] On the other hand, for the section from waypoint WP3 to new destination B and the section from new destination B to waypoint WP5, which correspond to new sections, there is no actual travel energy consumption data for the reference vehicle.

[0073] Therefore, the calculation unit 234 may calculate the traveling energy consumption of the new section using a resistance calculation model MDL2 as shown in Equation (1).

[0074]

[0075] Fr [N] represents rolling resistance, Fs [N] represents gradient resistance, Fa [N] represents air resistance, and Fh [N] represents acceleration resistance. V represents the speed of the target vehicle 10, and η represents power transmission efficiency.

[0076] As described above, each waypoint WP included in the map data is associated with an altitude in addition to latitude and longitude. Therefore, the calculation unit 234 can calculate various resistances for the section from waypoint WP3 to new destination B and the section from new destination B to waypoint WP5. The calculation unit 234 may calculate the time integral value of these various resistances as the energy consumption while traveling in the new section.

[0077] Returning to the explanation of the flowchart in Fig. 10, once the calculation unit 234 calculates the auxiliary energy consumption and the driving energy consumption and further calculates the sum of these as the total energy consumption, the output control unit 236 transmits the total energy consumption to the terminal device 100 via the communication interface 210 (step S106). This allows the company 20 to accurately know the total energy consumption of the target vehicle 10, and therefore allows the company 20 to appropriately respond to the demand request from the electric power company.

[0078] ​[Server Processing Flow: Accumulation of Driving Performance Data] A series of processing flows of the server 200 will be described below with reference to a flowchart. Fig. 14 is a flowchart showing another example of the series of processing flows of the server 200 according to the embodiment. The processing of this flowchart is executed, for example, when the reserved target vehicle 10 is actually used and thereafter, the traveling energy consumption and the like actually measured by the target vehicle 10 are accumulated as traveling performance data.

[0079] First, the acquisition unit 232 waits until the reserved target vehicle 10 actually travels along the scheduled target route (step S200).

[0080] When the target vehicle 10 actually travels along the scheduled target route, the acquisition unit 232 acquires from the target vehicle 10 the travel energy consumption actually measured while traveling along the target route (step S202). In addition to the travel energy consumption, the acquisition unit 232 may also acquire total energy consumption, auxiliary energy consumption, departure point, destination (intermediate point or return point), vehicle type, travel time, temperature, weather, date, time (time zone), and the like.

[0081] Next, the acquisition unit 232 stores the acquired traveling energy consumption data and the like in the storage unit 220 as one record of the traveling history data (step S204), thereby expanding the traveling history data.

[0082] According to the embodiment described above, the server 200 acquires vehicle reservation information including the departure point and destination of the target vehicle 10. The server 200 calculates the total energy consumption that is predicted to be consumed by the entire target vehicle 10 when the target vehicle 10 travels the target route, which is the route from the departure point to the destination.

[0083] To calculate the total energy consumption, the server 200 calculates the auxiliary energy consumption, which is the energy consumed by operating the auxiliary equipment (e.g., air conditioning equipment) installed in the target vehicle 10, and the driving energy consumption, which is the energy consumed by driving the target vehicle 10.

[0084] Using the prediction model MDL1, the server 200 calculates the auxiliary energy consumption of the target vehicle 10 from weather forecast data when the target vehicle 10 travels along the target route. The server 200 extracts the traveling energy consumption of a reference vehicle that has traveled under the same conditions as when the target vehicle 10 was booked from the travel history data that includes the traveling energy consumption of the reference vehicle as a record, and calculates the traveling energy consumption of the extracted reference vehicle as the traveling energy consumption of the target vehicle 10.

[0085] Then, the server 200 calculates the total energy consumption as the sum of the auxiliary energy consumption and the traveling energy consumption.

[0086] In this way, the auxiliary energy consumption of the target vehicle 10, which is prone to uncertainty due to factors such as weather and season, is calculated using weather forecast data and the prediction model MDL1, while the driving energy consumption of the target vehicle 10 is searched for in the actual driving data. By combining these two types of calculation methods, the total energy consumption of the target vehicle 10 can be predicted at a low load.

[0087] Furthermore, according to the above-described embodiment, when a target route includes a section for which no historical driving data exists, the server 200 divides the target route into new sections, which are sections for which no historical driving data exists, and existing sections, which are sections for which historical driving data exists. Then, for the existing sections, the server 200 calculates the traveling energy consumption of the reference vehicle included in the historical driving data as the traveling energy consumption of the target vehicle 10. For the new sections, the server 200 calculates the traveling energy consumption of the target vehicle 10 using the resistance calculation model MDL2 as shown in Equation (1). In this way, the total energy consumption of the target vehicle 10 can be predicted even if the target route includes a new section for which no historical driving data exists.

[0088] <Modifications of the embodiment> Modifications of the above-described embodiment will be described below. In the above-described driving history data, the departure point, intermediate points, and destination points do not need to be completely identical in terms of latitude and longitude coordinates, but only need to match to a certain degree of granularity (clusters, which will be described later). Hereinafter, the intermediate points and destination points will be collectively referred to as destinations.

[0089] 15 is a flowchart illustrating another example of the flow of a series of processes performed by the server 200 according to the embodiment. The process of this flowchart is executed, for example, when classifying the driving performance data into clusters and then extracting the driving energy consumption from each cluster.

[0090] First, the calculation unit 234 performs clustering on a plurality of records (i.e., each piece of data on energy consumption during driving) included in the driving performance data to generate one or more clusters (step S300).

[0091] A cluster is a group of records that share a common combination of a departure point and a destination among a plurality of records included in the travel history data.

[0092] 16 is a diagram illustrating clustering of driving history data. For example, the calculation unit 234 classifies records of driving history data within a predetermined latitude and longitude range (for example, within a radius of 30 m) into the same cluster. In the illustrated example, three types of clusters, clusters A, B, and C, are generated.

[0093] Next, the calculation unit 234 determines whether the number of records of the driving performance data included in the cluster is three or more (step S304). The number 3 compared with the number of records is an example of a "predetermined number."

[0094] If the number of records is three or more, the calculation unit 234 uses the quartile method to extract one record from the three or more records, and calculates the driving energy consumption contained in that record as the driving energy consumption of the target vehicle 10 (step S306).

[0095] 17 is a diagram illustrating a method for calculating traveling energy consumption using the quartile method. For example, the calculation unit 234 regards the traveling energy consumption of each record as a sample point and extracts a first quartile Q1, a second quartile Q2, and a third quartile Q3 from the multiple sample points according to the magnitude of the traveling energy consumption. Then, for example, the calculation unit 234 calculates the largest traveling energy consumption within the range from the first quartile Q1 to the third quartile Q3 as the traveling energy consumption of the target vehicle 10.

[0096] Furthermore, the calculation unit 234 may use, instead of the quartiles, for example, a standard deviation (1σ, 2σ, 3σ), a mode, an average value, a median value, a variance value, or the like to extract records that are to be the traveling energy consumption of the target vehicle 10 from the traveling performance data. The quartiles, the standard deviation, the mode, the average value, the median value, the variance value, and the like are examples of "statistical indicators."

[0097] On the other hand, if there are two records, the calculation unit 234 calculates the larger of the traveling energy consumption values ​​of the records as the traveling energy consumption value of the subject vehicle 10 (step S308).

[0098] In this way, by treating records in the driving history data that have a common combination of departure point and destination as the same cluster, the driving energy consumption of the target vehicle 10 can be calculated more flexibly.

[0099] The above describes the form for carrying out the present invention using an embodiment, but the present invention is not limited to such an embodiment, and various modifications and substitutions can be made within the scope that does not deviate from the gist of the present invention.

[0100] 1...Energy management support system, 10...Vehicle, 20...Company, 30...Client, 100...Terminal device, 110...Communication interface, 120...Input interface, 130...Output interface, 140...Memory unit, 150...Processing unit, 200...Server, 210...Communication interface, 220...Memory unit, 230...Processing unit, 232...Acquisition unit, 234...Calculation unit, 236...Output control unit

Claims

1. An information processing device comprising: an acquisition unit that acquires the departure point and destination of a target vehicle; and a calculation unit that calculates the total energy consumption predicted to be consumed by the entire target vehicle when the target vehicle travels a route from the departure point to the destination, wherein the calculation unit: calculates the total energy consumption of the target vehicle as the sum of auxiliary energy consumption, which is the energy consumed by operating auxiliary equipment installed in the target vehicle, and traveling energy consumption, which is the energy consumed by traveling the target vehicle; calculates the auxiliary energy consumption of the target vehicle based on weather forecast data for when the target vehicle travels the route; and calculates the traveling energy consumption of the target vehicle based on the traveling energy consumption of the reference vehicle actually measured when the reference vehicle traveled the route.

2. The information processing device according to claim 1, wherein the target vehicle is an electric vehicle or a plug-in hybrid vehicle, the auxiliary equipment includes an air conditioning device, and the auxiliary equipment consumption energy includes energy consumed by the air conditioning device.

3. The information processing device described in claim 1 or 2, wherein the calculation unit calculates the predicted required time for the target vehicle to travel the route, calculates the auxiliary energy consumption of the target vehicle for a predetermined unit time from the weather forecast data when the target vehicle travels the route using a machine learning model that has been pre-trained to output the auxiliary energy consumption when the weather forecast data is input, and calculates the auxiliary energy consumption of the target vehicle for the required time by integrating the auxiliary energy consumption of the target vehicle for the predetermined unit time over the required time.

4. The information processing device described in claim 1 or 2, wherein the calculation unit calculates the driving energy consumption of the target vehicle based on driving history data, which is a database in which the driving energy consumption of the reference vehicle is associated with the departure point and destination of the reference vehicle and the date and time when the reference vehicle traveled.

5. The information processing device described in claim 4, wherein the calculation unit extracts the travel energy consumption of the reference vehicle from the travel history data, the reference vehicle having some or all of the departure point and destination of the target vehicle that match the date and time on which the target vehicle is scheduled to travel, and calculates the travel energy consumption of the extracted reference vehicle as the travel energy consumption of the target vehicle.

6. The information processing device described in claim 5, wherein, when the driving history data does not contain the driving energy consumption of the reference vehicle that matches the departure point and destination of the target vehicle, the calculation unit divides the target route, which is the route from the departure point of the target vehicle to the destination, into a first section that is common to the reference route, which is the route from the departure point of the reference vehicle to the destination, and a second section that is not common to the reference route; for the first section, calculates the driving energy consumption of the reference vehicle included in the driving history data, which is the driving energy consumption actually measured when the reference vehicle traveled the first section, as the driving energy consumption of the target vehicle; and for the second section, calculates the driving energy consumption of the target vehicle based on map data including altitude information and a resistance calculation model for calculating the resistance of the target vehicle.

7. The information processing device according to claim 5, wherein the calculation unit: when the driving history data does not include driving history data of the reference vehicle that matches the departure point and destination of the target vehicle, calculates the driving energy consumption of the target vehicle based on map data including altitude information and a resistance calculation model for calculating the resistance of the target vehicle; when the driving history data includes the driving energy consumption of the reference vehicle that matches the departure point and destination of the target vehicle, determines whether the number of data points of the driving energy consumption of the reference vehicle that matches the departure point and destination of the target vehicle is equal to or greater than a predetermined number; when the number of data points is less than the predetermined number, calculates the driving energy consumption of the reference vehicle that is the largest of the driving energy consumptions of the reference vehicles as the driving energy consumption of the target vehicle; and when the number of data points is equal to or greater than the predetermined number, selects the driving energy consumption of one of the reference vehicles from the driving energy consumptions of the reference vehicles based on statistical indicators of the driving energy consumption of the reference vehicle, and calculates the driving energy consumption of the selected reference vehicle as the driving energy consumption of the target vehicle.

8. An information processing method using a computer, comprising: obtaining the departure point and destination of a target vehicle; calculating the total energy consumption predicted to be consumed by the entire target vehicle when the target vehicle travels a route from the departure point to the destination; calculating the total energy consumption of the target vehicle as the sum of auxiliary energy consumption, which is the energy consumed by operating auxiliary equipment installed in the target vehicle, and traveling energy consumption, which is the energy consumed by traveling the target vehicle; calculating the auxiliary energy consumption of the target vehicle based on weather forecast data for when the target vehicle travels the route; and calculating the traveling energy consumption of the target vehicle based on the traveling energy consumption of the reference vehicle actually measured when the reference vehicle traveled the route.

9. A program to be executed by a computer, comprising: obtaining the departure point and destination of a target vehicle; calculating the total energy consumption predicted to be consumed by the entire target vehicle when the target vehicle travels a route from the departure point to the destination; calculating the total energy consumption of the target vehicle as the sum of auxiliary energy consumption, which is the energy consumed by operating auxiliary equipment installed in the target vehicle, and driving energy consumption, which is the energy consumed by driving the target vehicle; calculating the auxiliary energy consumption of the target vehicle based on weather forecast data for when the target vehicle travels the route; and calculating the driving energy consumption of the target vehicle based on the driving energy consumption of the reference vehicle actually measured when the reference vehicle traveled the route.

Images