JP2020171077A - Energy supply system, information processing device, and energy supply device - Google Patents

Abstract

To provide an energy supply system in which the extension of a waiting time of a user waiting for the turn of energy supply is easily suppressed, an information processing device and an energy supply device.SOLUTION: An energy supply system comprises an information processing device 101 and an energy supply device installed at an energy supply point and supplying energy to a mobile which is moved by the energy. The information processing device includes: an acquisition section 81 for acquiring positional information of the mobile which is located at the energy supply point, and information for calculation including a destination of the mobile and the residual quantity of energy stored in the mobile; a calculation section 82 for calculating the recommended residual quantity of energy of the mobile corresponding to the destination of the mobile at the energy supply point where the mobile is located, on the basis of the information for calculation; and an output section (communication section) 11 for outputting the recommended residual quantity of energy calculated by the calculation section.SELECTED DRAWING: Figure 2

Description

Embodiments of the present invention relate to energy supply systems, information processing devices, and energy supply devices.

Conventionally, an information providing system for EVs (Electric Vehicles) is used by users by referring to map information and accurately predicting the reachable range of EVs, for example, when using EVs on expressways (toll roads). It is a system that recommends the service / parking area (SA / PA) to be used.

Japanese Unexamined Patent Publication No. 2011-83166 Japanese Unexamined Patent Publication No. 2003-262525

However, in an SA / PA with a charging facility, if a user fully charges the EV battery regardless of the distance to the destination, the waiting time of the user waiting for charging may become long.

The energy supply system of the embodiment includes an information processing device and an energy supply device. The energy supply device is installed at an energy supply point and supplies the energy to a moving body that moves by energy. The information processing device includes an acquisition unit that acquires calculation information including the position information of the moving body located at the energy supply point, the destination of the moving body, and the remaining amount of the energy stored in the moving body. Based on the calculation information, the calculation unit that calculates the recommended remaining amount of energy of the moving body according to the destination of the moving body at the energy supply point where the moving body is located, and the calculation unit. It is provided with an output unit that outputs the calculated recommended remaining amount of energy. The energy supply device is a process related to the supply of the energy when the recommended remaining amount of the energy output by the output unit is input to the input unit and the recommended remaining amount of the energy is input to the input unit. To do.

FIG. 1 is a schematic block diagram of the information processing system of the embodiment. FIG. 2 is a block diagram of the information processing apparatus of the embodiment. FIG. 3 is a diagram showing an example of route information of the embodiment. FIG. 4 is a diagram showing an example of a network structure of route information of the embodiment. FIG. 5 is a diagram showing an example of traffic counter management information of the embodiment. FIG. 6 is a diagram showing an example of meteorological information of the embodiment. FIG. 7 is a diagram showing an example of road control information of the embodiment. FIG. 8 is a diagram showing an example of vehicle information of the embodiment. FIG. 9 is a diagram showing an example of charger information of the embodiment. FIG. 10 is a diagram showing an example of calculating the power consumption of the embodiment. FIG. 11 is a diagram showing another example of calculating the power consumption of the embodiment. FIG. 12 is a diagram showing an example of learning data of the embodiment. FIG. 13 is a diagram showing an example of the classification rule of the embodiment. FIG. 14 is a flowchart of an example of the operation of the model management unit of the embodiment. FIG. 15 is a flowchart showing another example of the operation of the model management unit of the embodiment. FIG. 16 is a diagram showing an example of a model management table and a category table of the embodiment. FIG. 17 is a diagram showing an example of driving data of the embodiment. FIG. 18 is a diagram for explaining a specific example of calculating the remaining battery level of the EV of the embodiment. FIG. 19 is a flowchart of an example of the operation of the prediction evaluation unit of the embodiment. FIG. 20 is a flowchart of an example of the operation of the model update management unit of the embodiment. FIG. 21 is a flowchart of another example of the operation of the model update management unit of the embodiment. FIG. 22 is a flowchart showing an example of the operation of the information processing apparatus of the embodiment. FIG. 23 is a diagram showing an example of the system management screen of the embodiment. FIG. 24 is a diagram showing a hardware configuration of the information processing apparatus of the embodiment. FIG. 25 is a block diagram of the charger of the embodiment. FIG. 26 is a flowchart showing an example of charging processing of the information processing system of the embodiment.

Next, the embodiment will be described in detail with reference to the drawings. In the following description, EV will be described as an example of the moving body, but the same can be applied to moving bodies other than EV. Examples of other moving objects include trains, hybrid vehicles, fuel cell vehicles, airplanes, drones, electric motorcycles, vehicles with diesel engines, ships, and the like.

In this embodiment, since it is assumed that the moving body is an EV, the energy supply is a charge, the supply point is a charging stand, and the energy supply device is a charger. However, if the moving body is a gasoline vehicle, the energy supply may be read as refueling, and the supply point may be read as a gas station and a refueling device. If the moving object is an airplane or a drone, the road may be read as an air route, and if it is a ship, it may be read as a route. As described above, the same processing as in this embodiment can be performed on a moving body other than the EV.

By the way, the EV uses the charging power (charging energy) of the battery to travel on the road, which is a traffic route, and move to various points. The EV point is not limited to the energy supply point, and may be any point on the map, for example, it may be a home, a restaurant, a store, or an EV user arbitrarily designated. Although it may be a point, the EV point of the present embodiment shall deal with an energy supply point which is a point where the EV charges.

The EV is supplied with electric power at an energy supply point (hereinafter referred to as a supply point or a charging point), and stores the supplied electric power in a battery. The EV then moves using the power stored in the battery. In order to continue moving in the EV, it is necessary to move to the next supply point and receive power supply at the supply point before the battery runs out of power. In this way, the EV moves to the destination while charging at each supply point. One or a plurality of chargers (energy supply devices) are installed at the supply points, and the EV is connected to an arbitrary charger 221 by wire or wirelessly to receive electric power.

<Information processing system>
FIG. 1 is a schematic block diagram of the information processing system of the embodiment.
As shown in FIG. 1, the information processing system 1 includes an information processing device 101, information devices 201A to 201N, servers 211A to 211N, and chargers 221-221N. The information processing device 101 is connected to the information devices 201A to 201N, the servers 211A to 211N, and the chargers 221A to 221N via the communication network 220. The communication network 220 is a wired or wireless network or a hybrid network thereof. The communication network 220 may include a relay device such as a wireless LAN access point. The information processing system 1 is an example of an energy supply system, and the chargers 221A to 221N are an example of an energy supply device.

In the following description, when it is not necessary to identify the information devices 201A to 201N, they are collectively referred to as the information devices 201. Further, in the following description, when it is not necessary to identify the servers 211A to 211N, they are collectively referred to as the server 211. Further, in the following description, when it is not necessary to identify the chargers 221A to 221N, they are collectively referred to as the charger 221.

<Information device 201>
The information devices 201A to 201N are, for example, communication terminals (smartphones, tablet devices, mobile phones, notebook PCs, etc.) held by the user, in-vehicle devices such as car navigation systems mounted on the EV, and supply points for charging the EV. It is a communication device such as a charger 221 and an ITS spot (ETC2.0 device) installed in. The information devices 201A to 201N can communicate with the information processing device in real time. The information devices 201A to 201N may be configured by a charger 221 installed at a supply point where the EV charges. The ETC 2.0 device is capable of communicating with at least one of a communication terminal and a car navigation system, and is arranged at, for example, a plurality of predetermined spots. The predetermined spot may be an ITS spot, a place along a route, a service area of an expressway, a tollhouse, a building, or the like. The ETC device 2.0 may be provided at the entrance and exit of the power feeding point, and in this case, the EV entry time, entry time, number of entry and number of entry may be detected. The communication terminal may be operated by another EV passenger (for example, a person sitting in the passenger seat) driven by the user. Alternatively, the user may operate the communication terminal and another agent may drive the EV. The input to the communication terminal may be manual input or voice input.

<Server 211>
The servers 211A to 211N are a map information management server that manages map information, a weather information management server that manages weather information, a vehicle information management server that manages vehicle information, a charger 221 information server that manages charger 221 information, and a road. It is a road control information server that manages control information. Servers other than those listed here may be deployed.

FIG. 2 is a block diagram of the information processing apparatus of the embodiment.
As shown in FIG. 2, the information processing device 101 includes a communication unit 11, a user ID registration unit 12, an EV navigation usage registration unit 13, a user DB (database) 14, a map information management unit 15, and a road control information management unit 16. , Charger information management unit 17, weather information management unit 18, vehicle information management unit 19, system DB 20, control unit 21.

Further, the information processing device 101 includes a model management unit 31, a model DB 32, a prediction unit 41, a traveling state management unit 51, a traveling management DB 52, a prediction evaluation unit 61, and a model update management unit 71. Further, the information processing device 101 includes an acquisition unit 81 and a calculation unit 82. In addition, the information processing device 101 may include input means for the operator to input instructions or data to the device, and display means for displaying the data to the operator. Examples of input means include a keyboard, a mouse, a touch panel, a microphone for voice input, and the like. Examples of display means include LCD (liquid crystal display), CRT (cathode ray tube), and PDP (plasma display). The information processing device 101 is an information providing system for EVs that recommends energy supply points for EVs that use highways (toll roads). The information processing device 101 is installed in a facility management company, a traffic control station, or the like as an example. However, the information processing device 101 may be incorporated in an in-vehicle device such as a car navigation system (hereinafter referred to as a car navigation system) mounted on an EV, and it is not excluded that the information processing device 101 is installed on the roadside. When arranged on the roadside, the operator may remotely operate the information processing apparatus.

The communication unit 11 communicates with the information devices 201A to 201N, the servers 211A to 211N, the chargers 221A to 221N, and the like via the communication network 220.

The user ID registration unit 12 receives the user registration request from the information device 201, and registers the user of the service (EV navigation service) of the information providing system for EV according to the present embodiment. For example, the user operates the information device 201 to open an application or a web page for user registration of the EV navigation service, and accesses the user ID registration unit 12. The user ID registration unit 12 acquires the user's personal information and EV information (vehicle type, battery capacity, battery deterioration degree, cumulative mileage, tire type, etc.) used by the user, and uses these as user information. The user ID registration unit 12 issues a user ID (EV_ID) to the user, associates the user ID with the user information, and registers the user ID in the user DB 14.

The EV navigation usage registration unit 13 receives the usage registration request from the information device 201, and performs usage registration for starting the EV navigation service. For example, when the user goes out, he / she operates the information device 201 at home or in the EV, opens an application or a web page for receiving the EV navigation service, and obtains information necessary for receiving the service from the information device 201. The usage registration request including the usage registration request is transmitted to the EV navigation usage registration unit 13. For example, travel date and time (scheduled departure date and time of departure IC (interchange), current date and time, scheduled departure date and time of home, etc.), departure place (departure IC of expressway, etc.), destination (destination IC, etc.), EV battery capacity ( If notified at the time of user registration, it may be omitted), battery deterioration degree (may be omitted if notified at the time of user registration), EV battery level (energy level), air conditioner usage status (on) / Off, setting mode, temperature setting, etc.), cumulative mileage (may be omitted if notified at the time of user registration), tire type (may be omitted if notified at the time of user registration), boarding Send information such as the number of people. If the information device 201 is a car navigation system, the information set in the car navigation system may be transmitted, or if the information device 201 is a smartphone or the like, the information input by the user may be transmitted. These acquired information is referred to as usage registration information. The EV navigation usage registration unit 13 issues an ID (driving ID) for this service use, associates the driving ID with the usage registration information, stores it in the user DB 14, and also manages the driving state management unit or the model, which will be described later. Notify department or both. In addition, this device communicates with the user's information device 201 after registration to acquire information such as GPS position information, current time, remaining battery power (remaining battery power), and air conditioner usage status, which will be described later. Notify the driving condition management department, the model management department, or both of them. The communication timing is real-time, timing at regular time intervals, timing when a predetermined IC such as a departure IC registered by the user is passed, timing when the device issues a request and acquires a response, service area / parking area (SA / There are timings when entering or exiting PA), timings when passing near SA / PA, and the like.

The user DB 14 holds information registered by the user ID registration unit 12 and the EV navigation use registration unit 13. The user DB 14 is a hardware storage device such as a memory device, a hard disk device, or an SSD device.

By controlling each part of the information processing device 101, the control unit 21 controls the entire information processing device 101 and realizes the operation of the information providing system for EV.

The map information management unit 15 acquires map information from the server 211, and holds and manages the acquired map information in the system DB 20. Map information is information that represents information such as the position (latitude, longitude), size, and range of map elements. For example, altitude information associated with each position on the map, distance information of each route (each route of an expressway, each route such as a general road), slope, curve angle, route, direction, KP (kilopost), JCT ( Includes the shape of the junction), the tunnel, the light (a place other than the tunnel), and the road surface condition (paving condition, etc.). In addition, the map information includes the number of lanes on the expressway, the location of the interchange (IC), the service area / parking area (SA / PA), and the like.

In addition, the map information includes information on supply points, SA / PA points, ICs, and JCT points as the above map elements. Further, the map information may include information on the distance of the route and information on the required traveling time of the route as route information between the supply point, the SA / PA point, the IC and the JCT point.

FIG. 3 is a diagram showing an example of route information of the embodiment. The required traveling time may be the average of past measured values, or may be the time required when traveling a distance at a predetermined speed. Further, it may be information on the required energy and electricity cost required for traveling on the route. The required energy and electricity cost may be actual statistical values (mean value, median value, etc.), or may be values calculated by a calculation formula or simulation. The route information may be represented by a general network structure.

FIG. 4 is a diagram showing an example of a network structure of route information of the embodiment. The nodes representing the supply points Q1 to Qn are connected by a link shown by a broken line. The link connects the supply points adjacent to each other. It can be seen that the supply point Q1 is adjacent to the supply points Q3 and Q2, respectively. Further, there is one route from the supply point Q1 to the supply point Q3, and one route from the supply point Q1 to the supply point Q2. The link is assigned the characteristics of the route between the supply points represented by both nodes connected by the link (the notation of the characteristics of the route is omitted in FIG. 4). In this example, the network structure of only the supply points is shown, but the SA / PA points, ICs and JCT points may be included as nodes in addition to the supply points.

Further, the map information may include TC management information that identifies a traffic counter (TC) existing in a section between each supply point. The TC is a device that acquires information on traffic in the section between supply points. TC is an example of the above map elements.

FIG. 5 is a diagram showing an example of traffic counter management information of the embodiment. In the data of the first entry, the traffic counters TC1, TC2, ... Are arranged in the section between the supply point Qj and the adjacent supply point Qj'. It is not necessary that the traffic counters are arranged in the order of TC1, TC2, ....

The map information management unit 15 may acquire all or a part of the map information from the server 211 at regular intervals or in real time and update it.

The weather information management unit 18 acquires weather information from the server 211, and retains and manages the acquired weather information in the system DB 20.

FIG. 6 is a diagram showing an example of meteorological information of the embodiment. Meteorological information includes, for example, predetermined temperature in each area and each date and time, presence / absence of rainfall, precipitation, wind speed, wind direction, total solar radiation, snowfall, road surface temperature, light intensity, visibility (fog), radiation, guerrilla rainstorm, etc. including. The meteorological information may include past and present meteorological information, as well as forecasted meteorological information if future forecasted meteorological information can be obtained. The weather information management unit 18 may acquire weather information from the server 211 at regular intervals or in real time.

The road control information management unit 16 acquires road control information for each route (section) from the server 211, and holds and manages the acquired information in the system DB 20. Road control information includes, for example, traffic counter (TC) information and ETC information (number of inflows, number of outflows, EV vehicle type, EV battery level, etc.). In addition, information on events that occur includes road closures, traffic jams, accidents, broken cars, construction, falling objects, fires, disasters, speed regulations, and so on. In addition, examples of forecast information include traffic jam forecast, accident occurrence forecast, guerrilla rainstorm forecast, and sediment disaster forecast. The installation position of the traffic counter is known in advance in the above map information (see FIG. 5).

FIG. 7 is a diagram showing an example of road control information of the embodiment. The information of the traffic counter is, for example, information such as speed [km / h], occupancy rate (occupancy) [%], traffic volume [vehicle / h], vehicle density [vehicle / km], and the like. The speed is, for example, an average speed, a maximum speed, a minimum speed, or the like at regular intervals. The road control information management unit 16 may acquire road control information from the server 211 at regular intervals or in real time. Further, the road control information may be acquired from the server 211 every time the road control information is updated. The road control information management unit 16 may acquire the traffic counter information directly from the traffic counter instead of from the server 211. The time is assigned to the row name and the TC ID is assigned to the column name. Velocity (average velocity) values are stored in each element of the table. In the following, the case of traffic counter information is mainly assumed as road control information.

The vehicle information management unit 19 includes the vehicle type ID, EV manufacturer, battery capacity, battery type (lithium-ion battery, etc.), total weight (weight when the EV is loaded up to the capacity, weight of the EV itself), electricity cost, and so on. Information (vehicle information) such as battery deterioration speed and release year is acquired, and the acquired information is retained and managed in the system DB 20.

FIG. 8 is a diagram showing an example of vehicle information of the embodiment. The vehicle type ID has a different value for each vehicle type. The server 211 that manages vehicle information may be a server of an EV manufacturer, or may be a server that collectively manages vehicle type information of a plurality of EV manufacturers. The vehicle information management unit 19 may acquire vehicle type information from the server 211 at regular intervals. Alternatively, the vehicle type information may be acquired from the information device 201 instead of the server 211.

The charger information management unit 17 acquires charger 221 information about one or more chargers 221 (energy supply devices) installed at each supply point from the server 211. The charger information management unit 17 holds and manages the acquired charger 221 information in the system DB 20. The charger information management unit 17 keeps track of the number of chargers 221 at each supply point.

FIG. 9 is a diagram showing an example of the charger 221 information of the embodiment. The charger 221 information includes, for example, a user ID (EV_ID) of a user who has charged with the charger 221, a supply point ID, a start charge amount, an end charge amount, a charge start time, and a charge end time. In addition, information such as charging efficiency and the number of charging times may be retained. The start charge amount is the amount of power stored in the EV battery at the charge start time of the charger 221. The end charge amount is the amount of power stored in the EV battery at the end time of charging in the charger 221. The difference between the end charge amount and the start charge amount is the amount of power charged by the EV. Instead of the start charge amount and the end charge amount, the charger 221 information may include information on either the start charge amount or the end charge amount and the charged electric energy amount. The charger 221 information represents the energy supply history at the relevant supply point. The charger information management unit 17 may acquire the charger 221 information from the server 211 at regular intervals or in real time.

The charger information management unit 17 may acquire the charger 221 information from the charger 221 by direct communication instead of from the server 211. Alternatively, the user may input the charger 221 information (GPS position information, charged electric energy, etc.) into the information device 201, and the charger information management unit 17 may acquire the charger 221 information from the information device 201. Alternatively, the information device 201 (vehicle-mounted device such as a car navigation system) may read the information on the charged electric energy from the EV and transmit the charger 221 information to the information processing device 101.

By using the charger 221 information for the same user in chronological order, consumption history information indicating the power consumption amount, running time, running speed, etc. of the user for each section between supply points can be obtained. As an example, the traveling time is obtained by subtracting the charging end time of the previous supply point from the charging start time of a certain supply point. The running speed (average running speed) is obtained by dividing the running time by the distance of the section. It is also possible to communicate with the EV to acquire information on the traveling speed and the traveling time in real time, and to grasp the traveling speed and the traveling time from the information acquired from the EV.

FIG. 10 is a diagram showing an example of calculating the power consumption of the embodiment. An example of calculating the power consumption of a movement in a certain section from the charger 221 information for a certain EV is shown. Another supply point (supply point of the second entry) having a charge start time closest to the charge end time at one supply point (supply point of the first entry) is specified as the next supply point. That is, the ID of the supply point Qj (previous supply point) indicated by the three black circles and the ID of the next supply point Qj'(next supply point) indicated by the three Δ are specified. In addition, the time when charging at the supply point Qj ends (previous use end time), the charging start time at the supply point Qj'(next use start time), and the amount of charge when charging starts at the supply point Qj'. (Next start charge amount) and charge amount when charging at the supply point Qj is completed (previous end charge amount) are specified. By subtracting the next start charge amount from the previous end charge amount, the power consumption amount consumed by the movement from the supply point Qj to the supply point Qj'is calculated.

FIG. 11 is a diagram showing another example of calculating the power consumption of the embodiment. In this example, information acquired from an information device (smartphone) is used. This information represents an ID (EV_ID) that identifies the user, a GPS information point, and a charge amount. In this case, the power consumption is calculated by subtracting the charge amount at a certain point from the charge amount at the next point. The GPS information point may be the coordinates acquired by GPS, or may be the name of a place, facility, or the like associated with the coordinates in the map information.

The system DB 20 holds information (sometimes referred to as external information) acquired by each of the above management units. The external information acquired by each management unit may be held in a buffer in each management unit. The buffer is, for example, a memory device, a hard disk device, an SSD device, or a hardware storage device. Further, the system DB 20 stores an operating system, an information processing program, and various data used for information processing. The operating system is a computer program for controlling the overall operation of the information processing device 101. The information processing program is a computer program for the information processing apparatus 101 to realize each function of information processing described later. The system DB 20 is, for example, a memory device, a hard disk device, an SSD device, and a hardware storage device.

The model management unit 31 generates a model (prediction model) for calculating the predicted power consumption of the EV using a plurality of training data. As an example, the learning data uses all or part of the information acquired from consumption history information (charger 221 information), weather information, geographic information, vehicle information, road control information, and information devices (smartphones, car navigation systems, etc.). Generate. These information are acquired from the geographic information management unit 15, the road control information management unit 16, the charger information management unit 17, the weather information management unit 18, the vehicle information management unit 19, and the information device 201.

The model management unit 31 generates learning data by associating all or part of the acquired information. For example, it corresponds to the power consumption of a certain traveling section (section between supply points), the weather information (temperature, etc.) of the traveling date and time of the route, and the geographical information (distance, gradient, etc.) of the route of a certain traveling section. Then, driving data is generated, and this is used as training data. The running data acquired and managed by the running state management unit 51, which will be described later, may be used as learning data. Here, the traveling data generated for learning and the traveling data managed by the traveling state management unit 51 may be the same or different.

FIG. 12 is a diagram showing an example of learning data of the embodiment. The history ID is an identifier for identifying the learning data. The power consumption is the amount of power used for traveling in the traveling section. For example, it can be obtained from the charger 221 information (history information) described above. The distance is the distance of the traveled section, and the speed is the average speed of traveling. The traveling time is the time required to travel in the traveling section. The battery capacity is the battery capacity of the EV (also called the total battery capacity). Whether or not the air conditioner is operating depends on whether or not the air conditioner was turned on while the EV was running. The air temperature indicates the air temperature during driving. In addition, the vehicle type indicates the type of EV registered by the user. The items shown here are merely examples, and other items may exist, or some of the items shown in the figure may not exist. For example, the learning data may include information for specifying a traveling section, a slope of a route, humidity, a remaining battery level, and the like. Each item included in the training data corresponds to the feature amount of EV. Speed (average speed), distance, running time, power consumption, presence / absence of air conditioner operation, etc. represent the operating status of EV, remaining battery level, degree of battery deterioration, etc. represent EV characteristics, and temperature, gradient, etc. represent EV characteristics. Represents the driving environment of. These are examples of information indicating the movement status of the EV.

The route (traveling section) used by the EV to move from the supply point Qj to the next supply point Qj'may be specified from the information (GPS information, etc.) acquired by directly communicating with the information device 201. Alternatively, the route used by the EV can be estimated from consumption history information and geographic information. When estimating the route used to move between the supply point Qj (for example, Q1) that supplied energy to an EV and the supply point Qj'(for example, Q6) that supplied energy to the EV next, supply point Qj The shortest movement route (shortest route) from to the next supply point Qj'may be estimated as the route used for movement. As a method for solving the shortest path problem, a general Dijkstra method, a Bellman-Ford method, a Gabo method, a Worshall-Floyd method, and the like can be used. The obtained route can be represented by a list of supply points such as (Qj, Q4, ..., Qj').

The above-mentioned generation of training data is only an example, and the combination of types of information used to create the training data can be arbitrarily determined. Learning data may be generated by further using at least one of the vehicle information of the EV and the road control information of the date and time when the EV travels. The learning data is generated using, for example, information for a certain period in the past.

The model management unit 31 classifies a plurality of training data into a plurality of groups (may be called clusters) according to a classification rule. The classification rule has, for example, a standard based on at least one such as mileage, mileage, mileage, battery level, gradient information, air temperature, and vehicle type.

One or more classification rules are stored in the model DB 32. The classification rule is created in advance by the operation of the operator and stored in the model DB 32. The classification rule may be updated by the operation of the operator. Further, the classification rule may be created or updated by a process described later. Further, when a plurality of classification rules are stored, a flag for specifying the classification rule used for prediction may be set. The structure of the classification rule may be a decision tree, a cluster model, or whatever.

FIG. 13 is a diagram showing an example of the classification rule of the embodiment. This classification rule is an example of a decision tree. It includes nodes (non-terminal nodes) 301 and 302 to which features are assigned, and terminal nodes 303, 304 and 305 to which groups A, B and C are assigned. Feature condition (branch condition) is set in nodes 301 and 302, and the node is branched to a lower node according to the satisfying branch condition. The training data is finally classified into any of Group A, Group B, and Group C corresponding to the terminal nodes 303 to 305 by such a structure. For example, if the value of the traveling speed (feature amount) included in the learning data is less than 40 km / h and the air temperature (feature amount) is less than 20 degrees, the learning data is classified into group A. In this example, the features of the nodes of the decision tree are only the traveling speed and the air temperature, but other items (for example, gradient) may be selected as the features. The depth of the decision tree is 2 in the example shown in the figure, but the depth may be 1 or 3 or more. As will be described later, each group is associated with a prediction model. Therefore, the decision tree is a classification rule that associates a plurality of first conditions of feature quantities with a plurality of first prediction models.

The model management unit 31 generates a prediction model (model parameter) for each group based on the learning data belonging to each group classified by the classification rule. The model management unit 31 stores the generated prediction model in the model DB 32. The model DB 32 stores a prediction model for each group.

There are many methods for constructing predictive models, such as artificial intelligence, machine learning, black box modeling, and white box modeling that defines physical models. Black box modeling is a method of modeling using regression, neural networks, support vector machines (SVM), statistics, etc. when the characteristics of an object are unknown. White box modeling is modeling performed by defining a physical model or the like when the characteristics of the target are known. In this embodiment, as an example, a prediction model based on the sum of a plurality of models is shown. In this case, the individual models that make up the prediction model may be called submodels. The type of the prediction model can be generally expressed by the following equation (1).

^ Yi is the predicted value (output value) of the i-th model, and βi is the weighting coefficient of the i-th model. LP is the number of models. ^ Y is the output value of the prediction model, and is the total weighted sum of the power consumption calculated from each submodel ^ yi. The number of submodels may be one. The predicted value ^ y of the power consumption indicated by the submodel is a value including the section power consumption during EV running, and other submodels include the power consumption of the air conditioner, the power consumption of the wiper, and the car navigation system. It may include the power consumption, the charging capacity of the smartphone that the EV user charges in the car, and the like.

Examples of submodels are regression models, spec models, and discrete value models. The regression model and the spec model are examples of continuous value models that handle continuous values as features. The discrete value model is an example of a discrete value model that handles discrete values as features. The model management unit 31 includes a regression modeling means 35 that generates a regression model, a spec modeling means 36 that generates a spec model, and a discrete value modeling means 37 that generates a discrete value model. As an example, ^ y1 is a regression model, ^ y2 is a spec model, and ^ y3 is a discrete value model. Regarding the regression model, the following (1-1) may be used in consideration of the standard deviation of the error between the predicted value and the true value (measured value).

ＳＤは、予測モデルの予測値と実測値との誤差の標準偏差等の値であり、γは重み係数である。以下の説明では予測モデルの型として（１）を用いるが（１−１）を用いた場合も同様に実施可能である。また、ＳＤは操作オペレータが入力してもよい。

SD is a value such as a standard deviation of the error between the predicted value and the measured value of the predicted model, and γ is a weighting coefficient. In the following description, (1) is used as the type of the prediction model, but the same can be applied when (1-1) is used. Further, the SD may be input by the operation operator.

When the model is a multiple regression model, the basic function ^ y1 = f (x) is expressed as follows, for example.

w0, w1, w2, w3, ..., Wn are model parameters to be estimated. x1, x2, x3 ..., Xn are input variables (features). ^ Y1 is an output variable. In addition, in order to absorb the difference in the measurement unit of each input variable, the output variable and all the input variables may be normalized to the mean value 0 and the variance 1 (scaling). Examples of input variables include distance, required time, and outside air temperature. These are the items included in the training data. For example, x1 is the distance, x2 is the required time, and x3 is the outside air temperature. The input variable may be another value calculated from a plurality of items included in the training data. For example, the speed obtained by dividing the distance by the required time may be used as an input variable.

In the case of the spec model, the basic function ^ y2 = f (x) is expressed by the following equation (3). w is a coefficient or constant to be estimated. x is a feature quantity. ^ Y2 is an output variable. w may be a fixed value (for example, 1). x may be the value of the item included in the training data, or may be the output value ^ y1 of the regression model of (2). The power consumption calculated by the spec model depends on, for example, the vehicle type and the battery capacity.

(Example when model ^ y2 represents power consumption due to running)
The feature amount x may be a distance (km) / electricity cost (km / kWh). In this case, the electricity cost may be, for example, a value of a catalog specification or a coefficient to be estimated. w may be the electricity cost ratio (electricity cost of vehicle type A / electricity cost of vehicle type B), and x may be the power consumption of vehicle type B (value obtained by the regression model). The electricity cost ratio may be a coefficient to be estimated. In this case, it is conceivable that the model corresponds to the group to which the vehicle type A and the vehicle type B belong.
w may be the degree of deterioration of the battery, and x may be the amount of power consumed by the regression model. The degree of deterioration of the battery may be, for example, the SoH / average SoH of the EV battery, or the cumulative mileage / average cumulative mileage of the EV. SoH is State-of-Health, which is an index showing the degree of deterioration of the battery.
w may be the EV and the total weight of the luggage / the total weight of the EV (or the average total weight), and x may be the power consumption according to the regression model. The total EV and luggage weight / total vehicle weight (or average total weight) may be determined based on catalog values or may be a coefficient estimated by learning. The total weight of the EV and the luggage is, for example, the maximum number of people allowed for the EV and the weight when the luggage is loaded.

(Example when model ^ y2 represents power consumption by air conditioner)
The feature amount x is the air conditioner usage time (h), the coefficient w is a coefficient to be estimated, and the unit is kWh / h.
The feature amount x is the temperature difference (Δ ° C.), the coefficient w is the coefficient to be estimated, and the unit may be kWh / Δ ° C.

(Example when ^ y2 represents the power consumption by the wiper)
The feature amount x is the wiper usage time (h), the coefficient w is a coefficient to be estimated, and the unit is kWh / h.

例えば、一定の定数として、ＥＶのエアコンの消費電力量＝３（ｋＷｈ）、またはスマートフォン充電量＝１（ｋＷｈ）がある。離散値モデルの場合、Ｃが推定すべき係数、または定数（カタログスペックの値など）となる。Ｃの項目は、学習データに含まれる。離散値モデルによる消費電力量は、例えば走行以外で消費される電力量である。定数Ｃの項目は、特定の車種や季節、路面状態に対応するモデルを生成することが考えられる。特徴量が複数の値を持つ離散値の場合（例えば、特徴量を季節とした春、夏、秋、冬等）、一般的に公知であるダミー変数化を行うことで、２値の離散値と同じように扱うことができる。 In the case of the discrete value model, the basic function ^ y3 = f (x) is expressed by the following equation (4).

For example, as a constant constant, the power consumption of the EV air conditioner = 3 (kWh) or the smartphone charge amount = 1 (kWh). In the case of a discrete value model, C is a coefficient or constant to be estimated (value of catalog specifications, etc.). Item C is included in the training data. The power consumption by the discrete value model is, for example, the power consumption other than running. For the item of the constant C, it is conceivable to generate a model corresponding to a specific vehicle type, season, and road surface condition. When the feature quantity is a discrete value having multiple values (for example, spring, summer, autumn, winter, etc. with the feature quantity as a season), a generally known dummy variable conversion is performed to obtain a binary discrete value. Can be treated in the same way as.

For the model parameter w of the equation (2) and the coefficient w of the equation (3), the constant C of the equation (4) applies a known optimization algorithm such as the maximum likelihood method or the least squares method to the equation (1). You can find it by doing.

The model management unit 31 generates a prediction model using at least one of each modeling means. The prediction model ^ y is generated for each group. The generated prediction model is stored in the model DB 32. The type of each submodel that constitutes the prediction model may be different for each group. For example, the discretized model included in the prediction model of Group A may be the value of the power consumption of the air conditioner, and the discretized model included in the prediction model of Group B may be the value of the charge amount of the smartphone. In this case, a plurality of types are prepared for each submodel, combinations of types are generated among the submodels, and each combination is evaluated. The combination with the highest evaluation may be used for each group. For groups with only a small number of training data, transfer learning may also be used for the regression model.

FIG. 14 is a flowchart of an example of the operation of the model management unit of the embodiment. The operation of this flowchart is performed for each group. One or more candidates for the method for constructing the prediction model are determined for the target group (S101). Examples of the construction method include a model representing the sum of the regression model, the spec model, and the discrete value model, a model representing the sum of the regression model and the spec model, and a model representing the sum of the neural network, the spec model, and the discrete value model. More construction methods can be considered by further changing the type of each submodel.

A new prediction model is constructed from the training data belonging to the target group (S102). The prediction model constructed by each construction method is registered in the model DB 32 as a temporary model (S103). It is determined whether to provide a trial period for each provisional model (S104). For example, it is determined that a trial period is not provided when a new model is constructed, and a trial period is provided when the prediction model is updated. Further, the trial period may be arbitrarily set by the operation operator. The judgment may be made by other methods.

When the trial period is not provided (NO), the tentative model is evaluated using the training data of the target group (S105). As an example, the evaluation value (model evaluation value) is calculated from the sum of the errors (prediction error) between the output value of the tentative model and the actual value. The tentative model with the highest evaluation (the smallest model evaluation value) is selected as the prediction model (S106). The tentative model that is not selected may be deleted from the model DB 32.

Here, each tentative model may be generated and evaluated using cross-validation. In this case, in step S102, the learning data belonging to the target group is divided into K pieces (number of crossings). K is an integer greater than or equal to 2. One of them is used as test data, and the remaining K-1 is used as training data. Build a model using the training data. In step S105, the constructed model is evaluated using the test data. Each of the K divided data is used as test data K times, and the model is generated and the model is evaluated, and the evaluation value (model evaluation value) is calculated for each. In step S106, statistical values of model evaluation values (for example, mean value, median value, variance, quartile, maximum value, minimum value, etc.) are calculated. Based on the statistical values, the tentative model with the highest evaluation among each tentative model is selected as the prediction model. Depending on the evaluation method, the higher the evaluation, the larger the statistical value, and the higher the evaluation, the lower the statistical value.

On the other hand, in step S104, when a trial period is provided (YES), new learning data is collected (S107). Then, each tentative model is evaluated using the newly collected training data and the training data acquired in the past (S108). The evaluation method is the same as that described in step S105, except that the newly collected learning data is used as the data to be used for the evaluation. If there are a sufficient number of newly collected learning data for evaluation, the configuration of evaluating only with newly collected learning data is not excluded. It is also possible to use the cross-validation method described above. At this time, since the past learning data and the new learning data are mixed, the learning data may be randomly divided. For example, a predetermined number of test data are randomly sampled, and the rest is used as training data, which is repeated K times.

In the evaluation in step S108, the weight of the new data may be increased. For example, when calculating the sum of errors, the error calculated for new data is multiplied by a greater weight than the error calculated for past data. Moreover, when the cross-validation method is used, the possibility that new data is selected as test data or training data in sampling may be higher than that of past data.

Here, as the model evaluation value of the tentative model, an example is shown above which is the sum of the errors between the output value of the tentative model and the actual value, but the present invention is not limited to this. For example, it may be evaluated by the following formula (5). An example of the regression equation is shown here, but when using the sum of the regression model and the spec model, the difference between the actual value of the spec model and the estimated value is determined by the following equation according to the number of samples of training data. All you have to do is add the normalized values.

In addition, as other examples of model evaluation values, mean squared error (MSE: Mean Squared Error), mean absolute error (MAE: Mean Absolute Error), and R2 value (correlation coefficient R squared, which is called the coefficient of determination). There is also), mean squared error (RMSE: Root Mean Square Error), mean squared error rate (RMSPE: Root Mean Square Percentage Error), etc.

A model evaluation value may be defined in consideration of factors other than the error between the measured value and the predicted value of the power consumption. For example, the model evaluation value may be obtained by multiplying the data size of the model by a certain coefficient and adding the multiplication value to the value such as the sum of the errors described above. The larger the data size of the model, the longer it takes to calculate the prediction using the model. Therefore, it is expected that the calculation time and the calculation amount can be reduced by facilitating the selection of the smaller model.

In addition to using the classification rules given in advance as described above, the model management unit 31 can also automatically generate the classification rules. When the classification rule is automatically generated, after the classification rule is generated by the method described below, the process of constructing the prediction model using the classification rule is performed by the above method. Here, the case of a decision tree is shown as a classification rule, but the classification is not limited to this. When the classification rule is automatically generated, the classification rule is generated and the prediction model is constructed at the same time. The decision tree is repeatedly divided in the direction of reducing the variation in the prediction error of the prediction model. Splitting a node means creating a plurality of child nodes on the node. For example, setting the number of divisions of a certain node (parent node) to 2 means creating two child nodes in the node. In other words, the data group belonging to the parent node is divided into the data group corresponding to each child node. In this case, it is necessary to determine the feature amount to be assigned to the parent node and the branching condition based on the feature amount value. The feature amount assigned to the parent node may be an item existing in the training data or an item obtained by calculating a plurality of items in the training data. The number of divisions of the parent node may be 3 or more instead of 2.

Here, we consider an example of developing a classification rule (decision tree) by repeating dividing a node into two. In other words, by dividing the parent group into two groups (left group and right group), the classification rule is grown (the depth of the decision tree is deepened). SDR (Standard Deviation Reduction) is used when assigning which feature to the parent node and determining the value of the feature that is the condition for branching.

FIG. 15 is a flowchart showing another example of the operation of the model management unit 31 of the embodiment. First, the number of divisions is determined (S201). Here, the number of divisions is 2. The number of divisions may be a predetermined value, or may be a value determined according to the number of learning data belonging to the node to be divided and the number of items included in the learning data.

The feature amount to be assigned to the parent node and the feature amount value (feature amount condition) that is the condition for branching are determined so that the SDR is maximized (S202). The training data is divided into two child nodes (left child node (left group) and right child node (right group)) under the condition of the determined feature amount. The SDR is represented by the following equation (6) as an example. In this example, power consumption is used as a feature quantity. Further, a prediction model may be built first for the parent node and the child node, and the error between the predicted value and the measured value may be used as the feature amount of SDR.

A plurality of feature value values that are candidates for the condition are set, and the above SDR is calculated with the plurality of candidates. At this time, the candidates may sort the power consumption belonging to the parent node and use all the values as candidates. Select the set of the feature amount with the largest SDR and the feature amount condition. In this way, two child nodes are temporarily generated in the parent node. The SDR can be calculated in the same manner when it is divided into three or more. In the case of three divisions, there are, for example, two feature quantity values that are candidates for the condition.

Using the generated decision tree, the training data is divided into a plurality of groups, a prediction model is generated by the method described above (S203), and the evaluation value (model evaluation value) of the prediction model is calculated. Based on the model evaluation value of the prediction model of the parent node and the model evaluation value of the prediction model of each child node, it is determined whether the decision tree satisfies the division condition (S204). For example, if the model evaluation value of the prediction model of the parent node is larger than the average of the model evaluation values of the prediction model of the two child nodes (the smaller the model evaluation value, the higher the evaluation), the decision tree sets the division condition. Satisfy, otherwise it is judged that the division condition is not satisfied. When the division condition is satisfied (YES), the division of the parent node is confirmed (the above two provisionally generated child nodes are adopted) (S205). Returning to step S202, the same process as above is repeated with each child node as a parent node. When determining the feature amount as a candidate to be assigned to each child node in the returned step S202, the feature amount already assigned to the upper node (including the parent node) may be excluded.

If the division condition is not satisfied (NO), the temporarily generated child node is deleted (division is stopped), the child node is returned to the decision tree before the temporary generation (S206), and the process is terminated. As a result of recursive processing for each child node, multiple decision trees can be identified. In this case, for example, the decision tree is finally selected from the plurality of decision trees. For example, an evaluation value (rule evaluation value) representing a prediction error of a child node is calculated. For example, calculate statistics such as mean, median, and maximum prediction errors. Select the decision tree with the lowest rule evaluation value. When calculating the average, the prediction error may be weighted according to the number of data belonging to the child nodes (groups). Further, the larger the value obtained by dividing the total battery capacity of EVs belonging to the child nodes (groups) (the total number of EVs in the battery capacity) by the electricity cost, the smaller the weight may be (the larger the division value, the more the power shortage). It means that it is difficult to do). Further, the number of child nodes whose prediction error is larger than the threshold value may be counted, and the decision tree having the smallest number may be selected. Further, the rule evaluation value may be obtained by multiplying the number of child nodes by a certain coefficient and adding the value to the statistical value calculated as described above. This makes it easier to select a decision tree with a small number of child nodes, and it is possible to reduce the amount of calculation and the calculation time.

Conditions other than the above-mentioned division condition may be used as the processing end condition. For example, the process may be terminated on the condition that the decision tree has reached a predetermined depth. The process may be terminated on the condition that the maximum value of SDR is less than the threshold value. Other conditions may be used.

The model management unit 31 manages each generated prediction model and the classification rule in the model DB 32. The model management unit 31 may manage the model ID of each prediction model and the coefficient of the feature amount used in each prediction model in the model management table.

FIG. 16 is a diagram showing an example of a model management table and a category table of the embodiment. The value of the coefficient to be used is shown for each feature amount (input variable) such as power consumption amount and battery capacity ((A) in FIG. 16). A feature with a value of 0 means that it is not used. A table (category table) showing a category of continuous value or discrete value for each feature amount may be managed as shown in FIG. 16B. This table may be used to determine whether each feature is used in a discrete value model or a continuous value model (regression model, spec model). Further, the classification rule may be held in the model DB 32 in the form of implementing a general tree structure (see FIG. 13), or may be held in the form of a program. Further, the model management unit 31 may hold the program code of each prediction model (program code of the function constituting the prediction model) in the model DB 32.

The prediction unit 41 predicts the power consumption of the EV in the traveling section to be predicted by using the prediction model and the EV prediction data. The forecast data is data including items used in each submodel of the forecast model. However, the items used in the submodel may be the output values of other submodels. The travel section to be predicted is, for example, a section to a supply point that is a candidate for charging next.

The traveling state management unit 51 manages the traveling state (for example, the amount of power consumption for each section) of the traveling section of the EV during traveling. The traveling state management unit 51 acquires the traveling data of the traveling section between the charged bases for the EV during traveling, and manages the EV in the traveling management DB 52. The running data can be generated based on the data (information about the running state of the moving body) acquired by each management unit 15 to 19 and the EV navigation use registration unit 13.

FIG. 17 is a diagram showing an example of driving data of the embodiment. For each EV, the first charging point, the second charging point, and various variables are managed. If you charge 3 times or more, 1
The value of the second charging point is entered in the column of the second charging point, and the value of the third rechargeable battery point is entered in the column of the second charging point. When charging is performed four times or more, the value is entered in the same manner. The time is the time required for traveling in the traveling section, the power consumption is the power consumption (actual value) used in traveling in the traveling section, and the distance is the distance in the traveling section. The uphill is the length of the route having a gradient of a certain value or more in the traveling section. The downhill is the length of the route with a gradient of less than a certain value in the traveling section (expressed as a negative value). The variables shown here are just an example, and various types of variables are possible. For example, the total charge amount of the two charging points may be added as the total charge amount. The traveling state management unit 51 may add the power consumption predicted in each traveling section to the traveling data of the EV after the traveling is completed. Further, the first charging point and the second charging point may be any two points for which the power consumption is to be obtained. A plurality of combinations of the two arbitrary points, such as between TCs and ICs, and between ICs and charging points, can be considered.

Further, the traveling state management unit 51 uses the prediction unit 41 to find a candidate for a supply point within a reachable range from the remaining battery level of the EV, and determines the next supply point of the EV from the found candidates. You may perform the process of doing. The starting point of the traveling section to be predicted may be, for example, an arbitrary supply point or an arbitrary point during traveling. The end point of the traveling section is, for example, a candidate supply point. In order to calculate the predicted value of power consumption for the EV being driven, the running state management unit 51 sets the time and average speed of the running data as the predicted value, the road information, and the real-time current value obtained from the weather information. May be used. When EV position information is required, it may be acquired by communication from, for example, the GPS of the information device 201. If information such as the remaining power amount (remaining battery level) of the EV battery is required, it may be acquired by communication from the information device 201, or the information such as the remaining battery level is calculated from the charger 221 information. May be good. Alternatively, the remaining battery level may be estimated using the electricity cost of the EV. When the remaining battery level is required as the feature amount used in the prediction model, the remaining battery level acquired or estimated in this way can be used.

The traveling state management unit 51 narrows down the supply points that can be reached by the remaining battery level of the EV from the power consumption calculated for each candidate, and determines the next supply point from these. The method of determining the supply point may be any method as long as the supply point that can be reached with the current battery level is selected. For example, when there is only one route to the destination, the supply point with as little waiting time as possible may be selected in consideration of the congestion situation of each supply point, or there are a plurality of routes to the destination. If so, the supply point on the shortest route may be selected, or the supply point on the route with the least congestion or the least slope may be selected. The supply point before getting off the destination IC may be determined in consideration of the location of the next reachable supply point after getting off the destination IC. Information on the determined supply point is transmitted to the user's information device 201 (EV). The transmitted information is displayed on the screen of the information device 201, and the user grasps the supply point to be next.

A specific example in which the traveling state management unit 51 calculates the remaining battery level of the EV will be described with reference to FIG. Supply points A, B, C, D, E, F, and G (hereinafter, points A to G) are located on the highway. These points A to G are SA / PAs arranged along a certain route to the destination (destination IC) of the EV. The EV is charging at the point C, and the traveling state management unit 51 determines the remaining battery level (may be SoC (State of Charge)) after charging is completed from the charger 221 information or the information acquired from the information device 201. I know. The remaining battery level is expressed as Ea. In addition, the traveling state management unit 51 can acquire EV speed and time information from the GPS of the information device 201. The EV is currently running and is located between points D and E. The section between the two supply points X and Y is described as the section XY. The traveling state management unit 51 shows an example of calculating the power consumption of the section CD, the section DE, the section EF, and the section FG when the EV is at the current position. As an example of the feature amount used in the prediction model, the speed of the section (average speed) and the running time required for running the section are used.

The section CD is a past section on which the EV has already traveled. The mileage DIScd of the section CD and the mileage DISdn from the point D to the current position N can be grasped from the map information. The time when charging is completed at the point C can be grasped from the charger 221 information or the information acquired from the information device 201. The time at the current position can be obtained from the timer inside the device. Therefore, if the time when charging is completed at the point C is regarded as the departure time of the point C, the time tcn required for traveling from the point C to the current position N can be calculated. The time when the EV departs from the point C may be determined based on the information acquired from the GPS of the EV. When the traveling speed (average speed) vcd from the point C to the point D is calculated as (DIScd + DISdn) / tcn, the time tcd required for traveling the section CD can be calculated by DIScd * vcd. Therefore, the power consumption (^ ycd) of the section CD can be calculated (predicted) by incorporating vcd, tcd and other necessary features into the prediction model. If the time when traveling at point D can be obtained, vcd may be calculated by dividing the distance between the section CDs by the time required for traveling from point C to point D.

The section DE includes a section (past section) DN on which the EV has already traveled and a section (future section) NE on which the EV has not yet traveled. When the speed vdn of the section DN is calculated as (DIScd + DISdn) / tcn as in the section CD, the time tdn required for traveling in the section DN can be calculated by DISdn * vdn. Further, the value of the traffic counter (TC) arranged in the section is used as the speed vne of the section NE. For example, it may be the latest value of the TC speed, or it may be the average of the past fixed period (for example, 30 minutes). The time tne required for traveling in the section NE can be calculated by DISne / vne. DISne is the distance of the interval NE. Therefore, the time tde required for traveling in the section DE can be calculated by tdn + tne. Further, the traveling speed (average speed) vde of the section DE can be calculated by (DISdn + DISne) / tde. In addition, instead of DISdn + DISne, the distance DISde of the section DE may be acquired directly from the map information. Therefore, the power consumption (^ yde) of the interval DE can be calculated (predicted) by incorporating vde, tde and other necessary features into the prediction model.

The section EF is a section (future section) in which the EV has not yet traveled. The speed vef of the section EF uses the value of the traffic counter (TC) arranged in the section. For example, it may be the latest value of the TC speed, or it may be the average of the past fixed period (for example, 30 minutes). The time tef required for traveling in the section EF can be calculated by DISef / vef. Therefore, the power consumption (^ if) of the section EF can be calculated (predicted) by incorporating vef, tef and other necessary features into the prediction model.

The section FG is a section (future section) in which the EV has not yet traveled. Therefore, the power consumption (^ yfg) of the section FG can be calculated (predicted) in the same manner as the section FG.

In this way, when the traveling section is a past section, when both the past and future sections are included, and in the case of the future section, the power consumption of the EV can be calculated. Therefore, the reachable point can be specified by the current remaining battery level of the EV based on the remaining battery level Ea at the point C and the power consumption of each section.

The prediction evaluation unit 61 calculates the difference (error) between the predicted value of the power consumption and the actual value of the power consumption of the EV that has completed the running of the section in which the power consumption is predicted by the running state management unit 51. .. Based on the calculated error, the evaluation value (hereinafter referred to as the update judgment evaluation value) for a plurality of prediction models and classification rule sets is calculated. The actual value of the power consumption may be calculated from the charger 221 information. For example, the actual value of the power consumption of the section XY can be calculated based on the difference between the electric energy at the end of charging at a certain supply point X and the electric energy at the start of charging at the supply point Y that has been charged next. The predicted value of the power consumption in the section XY can be specified from the prediction result of the traveling state management unit 51. The section XY may include a plurality of continuous sections predicted by the traveling state management unit 51. For example, if the section XY is a section CF, the predicted value of the power consumption of the section CF can be calculated by summing the predicted values of the section CD, the section DE, and the section EF. When the information on the remaining battery level of the EV can be acquired from the information device 201 by direct communication, it is also possible to acquire the information and calculate the actual value of the power consumption.

The update judgment evaluation value is used for determining whether or not to start the process for updating the classification rule and the prediction model. When the update judgment evaluation value satisfies the update start condition based on the threshold value (for example, when the update judgment evaluation value is larger than the threshold value), the process for updating the classification rule and the prediction model is started. If the update judgment condition is not satisfied (for example, when the update judgment evaluation value is smaller than the threshold value), the process for updating the classification rule and the prediction model is not started.

The update judgment evaluation value is calculated based on the error calculated once or multiple times for a plurality of EVs so far. Every time the error is calculated for EV, the update judgment evaluation value is recalculated (updated). Specific examples of the update judgment evaluation value include mean squared error (MSE), mean absolute error (MAE), R2 value, mean squared error (RMSE), and mean squared error rate (RMSPE).

The update judgment evaluation value may be calculated for each group classified by the classification rule. When the group that satisfies the update start condition is equal to or greater than the threshold value, it may be determined that the update start condition is satisfied. Calculate the statistical value of the update judgment evaluation value (mean, center, maximum value, etc.) between groups, and whether the statistical value is above the threshold value (or below the threshold value. Whether above or below the threshold value or below the threshold value is used depends on the type of statistical value. In the case of (depending on), it may be determined that the update start condition is satisfied. When calculating the average of the update determination thresholds between groups, the weights may be set for the groups to calculate the weighted average. The weight may be increased as the number of data belonging to the group increases. In addition, the larger the value obtained by dividing the total battery capacity of EVs belonging to the group (the total number of EVs in the battery capacity) by the electricity cost, the smaller the weight may be. means).

FIG. 19 is a flowchart of an example of the operation of the prediction evaluation unit 61 of the embodiment. The difference (error) between the predicted value of the power consumption and the actual value of the power consumption is calculated for the EV that has completed the running in the section in which the running state management unit 51 has predicted the power consumption (S301). Based on the calculated error, an evaluation value (update judgment evaluation value) for a plurality of prediction models and a set of classification rules is calculated (S302). It is determined whether the update judgment evaluation value satisfies the update start condition based on the threshold value (S303), and if the update start condition is satisfied (YES), the start of the process for updating the classification rule and the prediction model is determined (. S304). If the update start condition is not satisfied (NO), the process ends without starting the process for updating the classification rule and the prediction model. This flowchart may be performed, for example, every time the actual value and the predicted value of the power consumption of one EV are acquired, or may be performed every fixed time or every time a certain number of errors are calculated. ..

When the model update management unit 71 determines that the update start condition is satisfied by the prediction evaluation unit 61, the model update management unit 71 starts a process for updating at least one of the classification rule and the prediction model.

FIG. 20 is a flowchart of an example of the operation of the model update management unit 71 of the embodiment. It is determined whether or not to update the classification rule (S401). Whether or not to update the classification rule can be determined by any method.

As an example, the error of the prediction model is calculated for each group classified by the classification rule. For the calculation of the error, for example, data for a certain period is used. As the data used to calculate the error, the data acquired after the prediction model is created is used. In addition to the data, the data used to create the prediction model may be used. The evaluation value (rule evaluation value) is calculated based on the error of each group. For example, calculate statistics such as mean, median or maximum error. If the rule evaluation value is greater than or equal to the threshold value, it is determined that the classification rule is updated, and if it is less than the threshold value, it is determined that the classification rule is not updated. When calculating the above average, the prediction error may be weighted according to the number of data belonging to the child node (group). Further, the larger the value obtained by dividing the total battery capacity of EVs belonging to the child nodes (groups) (the total number of EVs in the battery capacity) by the electricity cost, the smaller the weight may be (the larger the division value, the more the power shortage). It means that it is difficult to do).

The above threshold value may be input by the operator to the present device using the input means. Further, a value obtained by multiplying the average of errors in a predetermined period by a certain coefficient may be used as a threshold value. For example, if an error of β times the average error of the period is allowed, a value of a certain coefficient is set to β.

As another example of determining whether to update the classification rule, count the number of groups whose error is equal to or greater than a certain value. Determines to update the classification rule when the count value is greater than or equal to the threshold. If it is less than the threshold, it is decided not to update the classification rule. The threshold value in this case may be input by the operator to the present device using the above input means. Further, the threshold value may be a value obtained by multiplying the number of groups by a certain coefficient. For example, when the number of groups with a large error is allowed to be less than 5% of the number of groups, the value of a certain coefficient is set to 0.05.

When updating the classification rule (YES), the classification rule update process described with reference to FIG. 15 is performed (S402). The currently used classification rule (called the original classification rule or the first classification rule) is combined with the classification rule newly generated by the classification rule update process (called the update classification rule or the second classification rule) in the model DB 32. Save it in. This is because there is a possibility that the update classification rule may be discarded and returned to the original classification rule in the model update process described later. Subsequently, the model update process is performed based on the update classification rule generated in the classification rule update process (S403). The details of the model update process will be described later.

On the other hand, if the classification rule is not updated (NO), the model update process is performed based on the currently used classification rule (original classification rule) (S403).

FIG. 21 is a flowchart of another example of the operation of the model update management unit of the embodiment. It is assumed that the update classification rule is used as the classification rule. Steps S101 to S108 are the same as in FIG.

The model update management unit 71 determines the prediction model of each group by the processing of steps S101 to S108. The prediction model determined here is called an update prediction model. The update classification rule and the original classification rule are evaluated (S501). That is, the rule evaluation value (update rule evaluation value) is calculated using the update prediction model of each group of the update classification rule. In addition, the rule evaluation value (original rule evaluation value) is calculated using the original prediction model for the original classification rule. The new data collected in step S107 corresponds to the learning data (running data) acquired after the generation of the update classification rule and after the generation of each provisional model. The data used in step S105 corresponds to the training data (running data) acquired before the generation of the update classification rule and before the generation of each provisional model.

The update rule evaluation value is compared with the original rule evaluation value to determine whether the update classification rule and the update prediction model are improved over the original classification rule and the original classification rule (S502). For example, if the update rule evaluation value is smaller than the original rule evaluation value, it is judged that it has improved, and if it is not, it is judged that it has not improved. When it is determined that the improvement is made (YES), the original classification rule and the original prediction model are updated with the update classification rule and the update prediction model (S503). The prediction model before the update corresponds to the first prediction model, and the prediction model after the update corresponds to the second prediction model. The plurality of feature quantity conditions included in the update classification rule correspond to the plurality of second feature quantity conditions. The plurality of second conditions may be the same as the plurality of first conditions included in the original classification rule. On the other hand, if it is determined that there is no improvement (NO), it is decided to continue to use the original classification rule (first classification rule) and the original prediction model (first prediction model) (S504). In this case, the update classification rule and the update prediction model may be discarded.

In the above description, it is assumed that the update classification rule is used as the classification rule, but when it is decided to use the original classification rule in the above classification rule update process, the original classification rule is used. In this case as well, the same processing as in the flowchart of FIG. 21 may be performed. However, in step S503, the process of updating the original prediction model with the update prediction model is the same, but the classification rule is different from the case of using the update classification rule in that the original classification rule is used as it is.

(Another processing example when the model update processing is performed using the original classification rule as the classification rule) It is judged whether or not to update for each group, and the prediction model is updated only for the group that decides to update. , It is not necessary to update the prediction model for the group that has decided not to update. More specifically, the model evaluation value of the group prediction model (original prediction model) is calculated. If the model evaluation value is equal to or greater than the threshold value, it is determined to start the process for updating the prediction model, and if it is less than the threshold value, it is determined not to start the update process for updating the prediction model. When it is decided to start the processing, the processing of S101 to S108 of FIG. 21 is performed to generate a prediction model (update prediction model) of the group. The model evaluation value of the generated prediction model (update model evaluation value) and the model evaluation value of the original prediction model (original model evaluation value) are calculated and compared. If the update model evaluation value is smaller than the original model evaluation value, it is determined that the update prediction model is improved over the original prediction model, and the original prediction model is updated with the update prediction model. The updated prediction model corresponds to the third prediction model. Otherwise, it is decided to use the original prediction model as it is.

The threshold value used for determining whether or not to start the update process may be input by the operator using an input means. Further, a value obtained by multiplying the average of errors in a predetermined period by a certain coefficient may be used as a threshold value. For example, if an error of β times the average error of the period is allowed, a value of a certain coefficient is set to β.

Further, in the above-mentioned classification rule update process, only a part of the classification rule may be updated. For example, the model evaluation value of the prediction model of each group of the classification rule is calculated, and the group whose model evaluation value is equal to or more than the threshold value is specified. The target of the update is lower than the parent node of the child node to which the specified group belongs. In the example of FIG. 13, it is assumed that the model evaluation values of groups A and B are equal to or more than the threshold value and the model evaluation values of group C are less than the threshold value. In this case, the lower part of the parent node with "temperature <20" is targeted for update. The feature amount of "velocity <40" and the feature amount value (= 40) that defines the branching condition are maintained. The model update process may be the same as the process of FIG. 21 described above, but the group C may be excluded from the update target by deciding to continue using the predicted model as it is, or the process of the flowchart of FIG. 21. Therefore, a prediction model for update may be generated.

FIG. 22 is a flowchart showing an example of the operation of the information processing apparatus of the embodiment. The traveling state management unit 51 acquires the traveling data of the EV during traveling from the information device 201 (smartphone, car navigation system, etc.) via the communication unit 11 (S601). The traveling state management unit 51 stores the acquired traveling data in the traveling management DB 52.

The prediction unit 41 calculates the predicted value of the power consumption for the running section indicated by the running data by using the acquired running data, the classification rule, and a plurality of prediction models (prediction models of each group) (S602). .. That is, the prediction model to be used is specified based on the driving data and the classification rule, and the predicted value of the power consumption is calculated based on the specified prediction model and the driving data.

The traveling state management unit 51 acquires the actual value of the power consumption of the EV in the traveling section (S603). The actual value may be acquired from the charger 221 information or from the information device 201.

The prediction evaluation unit 61 calculates an evaluation value (update determination evaluation value) based on the calculated predicted value of the power consumption amount and the acquired actual value of the power consumption amount (S604).

The control unit 21 determines whether the end condition of this process is satisfied (S605). For example, when the operator inputs an end instruction, it is determined that the end condition is satisfied. If the end condition is satisfied (YES), this process is terminated, and if it is not satisfied (NO), the process proceeds to step S606.

The prediction evaluation unit 61 determines whether or not to start the process for updating the classification rule and the prediction model based on the evaluation value calculated in step S604 (S606). Specifically, it is determined whether the evaluation value satisfies the update start condition. For example, if the evaluation value is equal to or greater than the threshold value, it is determined that the update start condition is satisfied, and if it is less than the threshold value, it is determined that the update start condition is not satisfied. If it is determined that the condition is not satisfied, the process returns to step S601.

When it is determined that the update start condition is satisfied (YES), the model update management unit 71 performs the classification rule update process (see FIG. 15) (S607). Subsequently, a model update process (see FIG. 21) is performed (S608). After that, the process returns to step S601.

When neither the classification rule nor the prediction model is updated, when only one of them is updated, or when a part of the classification rule and a part of the prediction model are updated due to the result of the classification rule update process and the model update process. , There are various aspects such as when only a part of the prediction model is updated.

FIG. 23 is a diagram showing an example of the system management screen of the embodiment. In the above figure, the transition data of the prediction error of the prediction model (prediction model of models 1 to 4) of each group of the classification rule is shown. The date and time when each model was built, the latest prediction error, and the date and time when the model was discontinued are shown in the table below. Model 1 and model 2 are used until time t1, and the prediction error of model 1 soars at time t1. Due to the increase in the prediction error of the model 1 at time t1, the classification rule update process and the model update process are performed by the operation of the present embodiment. Models 3 and 4 are generated as models for updating model 1. Model 2 has been determined to not need to be updated and is still in use. During the trial period, model 3 and model 4 are used in parallel with model 1. The trial period ends at time t2 (= YYYY / MM / DD HH: MM: SS2). Since the average model evaluation value of the model 3 and the model 4 was smaller than the model evaluation value of the model 1, the model 1 was discontinued and the model 3 and the model 4 were used after the time t2. Model 2 will continue to be used after time 2. In the table below the figure, the current prediction error of model 1 is the value at time t2 (use date and time).

The details of the acquisition unit 81 and the calculation unit 82 of the information processing device 101 will be described later.

FIG. 24 shows the hardware configuration of the information processing device 101 according to the present embodiment. The information processing device 101 according to the present embodiment is composed of a computer device 100. The computer device 100 includes a CPU 151, an input interface 152, a display device 153, a communication device 154, a main storage device 155, and an external storage device 156, which are connected to each other by a bus 157.

The CPU (Central Processing Unit) 151 executes a computer program that realizes each of the above-mentioned functional configurations of the information processing device 101 on the main storage device 155. Each functional configuration is realized by the CPU 151 executing a computer program.

The input interface 152 is a circuit for inputting operation signals from input devices such as a keyboard, a mouse, and a touch panel to the information processing device 101.

The display device 153 displays data or information output from the information processing device 101. The display device 153 is, for example, an LCD (liquid crystal display), a CRT (cathode ray tube), and a PDP (plasma display), but is not limited thereto. The data or information output from the computer device 100 can be displayed by the display device 153.

The communication device 154 is a circuit for the information processing device 101 to communicate with the external device wirelessly or by wire. Information can be input from an external device via the communication device 154. Information input from an external device can be stored in the DB. The communication unit 11 can be built on the communication device 154.

The main storage device 155 stores a program that realizes the processing of the present embodiment, data necessary for executing the program, data generated by executing the program, and the like. The program is deployed and executed on main storage 155. The main storage device 155 is, for example, RAM, DRAM, and SRAM, but is not limited thereto. The storage unit in each embodiment may be built on the main storage device 155.

The external storage device 156 stores the program, data necessary for executing the program, data generated by executing the program, and the like. These programs and data are read out to the main storage device 155 during the processing of the present embodiment. The external storage device 156 is, for example, a hard disk, an optical disk, a flash memory, and a magnetic tape, but is not limited thereto. The storage unit in each embodiment may be built on the external storage device 156.

The above-mentioned program may be pre-installed in the computer device 100, or may be stored in a storage medium such as a CD-ROM. In addition, the program may be uploaded on the Internet.

The computer device 100 may include one or more CPU 151, an input interface 152, a display device 153, a communication device 154, and a main storage device 155, respectively, and is connected to peripheral devices such as a printer and a scanner. You may.

Further, the information processing device 101 may be configured by a single computer device 100, or may be configured as a system composed of a plurality of computer devices 100 connected to each other.

<Charger 221>
FIG. 25 is a block diagram of the charger 221 of the embodiment. The charger 221 includes a control unit 310, an operation unit 311, an output unit 312, a charging unit 313, and a communication interface unit 314. The charger 221 is an example of an energy supply device.

The operation unit 311 includes a display device with a touch panel and the like, and receives operations by the user. The output unit 312 includes a display device, a speaker, and the like, and outputs various types of information by display, voice, and the like. The charging unit 313 includes a charging circuit and is electrically connected to the EV battery to supply electric power to the battery. The communication interface unit 314 executes communication with the information processing devices 101, the information devices 201A to 201N, the servers 211A to 211N, and the like via the communication network 220.

The control unit 310 is composed of, for example, a computer having a CPU (Central Processing Unit) and a storage unit. The control unit 310 storage unit includes a ROM (Read Only Memory) and a RAM (Random Access Memory), and stores a program or the like executed by the CPU. The control unit 310 controls each unit of the charger 221 and performs various calculations. Further, the control unit 310 realizes functional units such as a communication unit 320, a charge control unit 321 and a notification unit 322 by the CPU executing a program stored in the storage unit.

The communication unit 320 transmits and receives information from the information processing device 101, the information devices 201A to 201N, the servers 211A to 211N, and the like via the communication interface unit 314. The charge control unit 321 controls the charging of the EV battery by the charge unit 313. The notification unit 322 notifies various information by the output unit 312.

<Charging process>
Next, an example of a method of charging the EV battery at the supply point will be described. In charging the EV battery, the information processing system 1 executes a charging process. In the information processing device 101, the communication unit 11, the acquisition unit 81, and the calculation unit 82 perform a part of the charging process, and in the charger 221 the communication unit 320, the charge control unit 321 and the notification unit 322 perform the charging process. Do some. The communication unit 11 of the information processing device 101 is an example of an output unit, and the communication unit 320 of the charger 221 is an example of an input unit.

The acquisition unit 81 of the information processing device 101 acquires calculation information including the position information of the EV located at the supply point, the destination of the EV, and the remaining amount of electric power (remaining amount of battery) stored in the EV. At this time, for example, the user operates a charging start button or the like displayed on the information device 201 owned by the user at the supply point. Then, the user inputs the remaining battery level of the EV displayed on the EV display unit to the information device 201 (manual input). The remaining battery level input in this way is transmitted from the information device 201 to the information processing device 101 as charging start request information including the current position of the information device 201 and the user ID (EV_ID). The current position of the information device 201 is also the current position of the EV (the position of the supply point where the EV is located). The acquisition unit 81 acquires other calculation information that is not included in the charging start request information among the calculation information from the user DB 14, the travel management DB, and the system DB. The remaining amount of the EV battery and the user ID (EV_ID) are acquired from the EV by the charger 221 and transmitted to the information processing device 101 when the EV battery and the charger 221 are electrically connected. May (automatic input).

The calculation unit 82 of the information processing device 101 calculates the recommended battery remaining amount (recommended remaining amount of electric power) of the EV according to the destination of the EV at the supply point where the EV is located. In other words, the calculation unit 82 calculates the recommended battery level in the EV according to the movement of the EV from the supply point where the EV is located to the destination of the EV. Specifically, the calculation unit 82 calculates the distance from the current position (supply point) of the EV to the destination. The calculation unit 82 calculates the power consumption required for the EV to reach the calculated distance to the destination. At this time, the calculation unit 82 is based on various information (battery capacity, battery type, total weight), electricity cost, battery deterioration rate, release year, etc. (vehicle information) stored in the system DB. , The required power consumption can be calculated. The calculation unit 82 calculates the difference between the calculated power consumption and the current remaining battery level of the EV, and sets the difference as the recommended remaining battery level. That is, the recommended remaining electric power is, for example, the amount of electric power required (necessary and sufficient) for moving the EV to the destination. Further, the calculation unit 82 determines the power supply time (hereinafter, also referred to as the required supply time) required to make the current remaining battery level of the EV the recommended battery level, based on the power supply performance of the charger 221. calculate. The calculation unit 82 may use the method of calculating the power consumption performed by the prediction unit 41. That is, the prediction unit 41 may also serve as the calculation unit 82. Further, the recommended remaining power of EV is not limited to the above calculation method. For example, the recommended remaining power of the EV may be calculated according to the degree of deterioration of the battery. Further, when the battery is close to full charge, the charging efficiency may be extremely deteriorated. Therefore, the recommended remaining power of the EV may be calculated according to, for example, the required time for supplying power. Furthermore, the recommended remaining power of the EV may be calculated by combining each of the above examples. The recommended battery level is an example of the recommended energy level.

The communication unit 11 of the information processing device 101 outputs the recommended battery remaining amount and the required supply time calculated by the calculation unit 82. Specifically, the communication unit 11 transmits the recommended battery remaining amount and the required supply time to the charger 221.

The communication unit 320 of the charger 221 receives the recommended battery remaining amount and the required supply time transmitted by the communication unit 11 of the information processing device 101. That is, the recommended battery remaining amount and the required supply time output by the communication unit 11 of the information processing device 101 are input to the communication unit 320.

The notification unit 322 of the charger 221 performs the following processing related to power supply when the recommended battery remaining amount is input to the communication unit 320. That is, the notification unit 322 notifies the recommended battery remaining amount and the required supply time by the output unit 312. In addition, the notification unit 322 may notify one of the recommended battery remaining amount and the required supply time by the output unit 312. That is, the notification unit 322 may notify at least one of the recommended battery remaining amount and the required supply time by the output unit 312.

The charge control unit 321 of the charger 221 performs the following processing related to power supply when the recommended battery level is input to the communication unit 320. That is, the charge control unit 321 starts supplying power to the EV battery, and when the remaining amount of EV power reaches the recommended remaining amount of power while supplying power to the EV, the power to the EV is supplied. End the supply. At this time, the charge control unit 321 determines whether or not the remaining amount of EV power has reached the recommended remaining amount of battery, for example, based on the elapsed time from the start of charging and the required charging time. Further, as another example, the charge control unit 321 is based on the difference between the current remaining amount of electric power of the EV and the recommended remaining amount of battery of the EV, and the voltage and current of the electric power supplied by the charger 221. It may be determined whether or not the remaining amount of EV power has reached the recommended remaining amount of battery.

Next, an example of the charging process executed by the information processing system 1 will be described with reference to FIG.
FIG. 26 is a flowchart showing an example of the charging process of the information processing system 1 of the embodiment.

The acquisition unit 81 of the information processing device 101 acquires the calculation information (S701). Next, the calculation unit 82 of the information processing device 101 calculates the recommended remaining battery level in the EV (S702). At this time, the calculation unit 82 also calculates the required power supply time.

Next, the communication unit 11 of the information processing device 101 transmits the recommended battery remaining amount and the required power supply time calculated by the calculation unit 82 to the charger 221 (S703).

The communication unit 320 of the charger 221 receives the recommended battery remaining amount and the required power supply time from the communication unit 11 of the information processing device 101 (S711).

Next, the notification unit 322 of the charger 221 notifies the recommended battery remaining amount and the required supply time by the output unit 312 (S712).

Next, the charge control unit 321 of the charger 221 starts supplying electric power to the EV battery (S713). The charge control unit 321 continues charging until the remaining amount of EV power reaches the recommended remaining amount of battery (S714: No). When the remaining amount of electric power of the EV reaches the recommended remaining amount of battery (S714: Yes), the charge control unit 321 ends the supply of electric power to the EV (S715).

As described above, in the present embodiment, the information processing system 1 (power supply system) is installed at the information processing device 101 and the supply point (energy supply point), and supplies power (energy) to the EV that moves by power. It is equipped with a charger 221 (energy supply device). The information processing device 101 includes an acquisition unit 81, a calculation unit 82, and a communication unit 11 (output unit). The acquisition unit 81 acquires calculation information including the position information of the EV located at the supply point, the destination of the EV, and the remaining amount of electric power stored in the EV. The calculation unit 82 is based on the calculation information.
The recommended battery level (recommended amount of energy) of the EV according to the destination of the EV at the supply point where the EV is located is calculated. The communication unit 11 outputs the recommended battery level calculated by the calculation unit 82. The charger 221 includes a communication unit 320 (input unit), a notification unit 322 (supply processing unit), and a charge control unit 321 (supply processing unit). The recommended battery level output by the communication unit 11 is input to the communication unit 320. The notification unit 322 and the charge control unit 321 (supply processing unit) perform processing related to power supply when the recommended battery remaining amount is input to the communication unit 320.

Therefore, according to the present embodiment, the calculation unit 82 calculates the recommended battery level of the EV according to the destination of the EV at the supply point where the EV is located, so that the recommended battery level is notified to the user. Or, charging can be stopped when the battery is charged to the recommended remaining battery level. Therefore, it is easy to suppress the long waiting time of the user waiting for the power supply.

Further, in the present embodiment, the notification unit 322 notifies at least one of the recommended battery remaining amount and the power supply time required to make the remaining amount of EV power the recommended battery remaining amount. Therefore, the user can adjust the power supply amount based on the recommended battery remaining amount and the power supply time required to make the remaining amount of EV power the recommended battery remaining amount.

Further, in the present embodiment, the charge control unit 321 terminates the supply of electric power to the EV when the remaining amount of electric power of the EV reaches the recommended remaining amount of the battery while the electric power is being supplied to the EV. Therefore, the user does not need to adjust the amount of power supply. Further, the information processing system 1 can manage the charge amount of the EV.

In the above embodiment, in the process of FIG. 26, an example is shown in which the charge control unit 321 terminates the supply of electric power to the EV when the remaining amount of electric power of the EV reaches the recommended remaining amount of battery. However, it is not limited to this. For example, even if the remaining amount of EV power reaches the recommended remaining amount of battery on condition of payment of an additional charge, the battery is charged to the amount specified by the charger 221 or the information device 201 (for example, fully charged). You may do so.

Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other embodiments, and various omissions, replacements, and changes can be made without departing from the gist of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are also included in the scope of the invention described in the claims and the equivalent scope thereof.

1 ... Information processing system (power supply system), 11 ... Communication unit (output unit), 81 ... Acquisition unit, 82 ... Calculation unit, 101 ... Information processing device, 221 ... Charger (energy supply device), 320 ... Communication unit (Input unit), 322 ... Notification unit (supply processing unit), 321 ... Charge control unit (supply processing unit).

Claims (7)

Information processing device and
An energy supply device installed at an energy supply point that supplies the energy to a moving body that moves by energy,
With
The information processing device
An acquisition unit that acquires calculation information including the position information of the moving body located at the energy supply point, the destination of the moving body, and the remaining amount of the energy stored in the moving body.
Based on the calculation information, a calculation unit that calculates the recommended remaining amount of energy of the moving body according to the destination of the moving body at the energy supply point where the moving body is located, and a calculation unit.
An output unit that outputs the recommended remaining amount of energy calculated by the calculation unit, and
With
The energy supply device is
An input unit into which the recommended remaining amount of energy output by the output unit is input, and
A supply processing unit that performs processing related to the supply of energy when the recommended remaining amount of energy is input to the input unit.
An energy supply system equipped with. As the process, the supply processing unit has at least one of the recommended remaining amount of the energy and the supply time of the energy required to make the remaining amount of the energy of the moving body the recommended remaining amount of the energy. The energy supply system according to claim 1, which notifies one of them. As the process, the supply processing unit performs the energy to the moving body when the remaining amount of the energy of the moving body reaches the recommended remaining amount of the energy while supplying the energy to the moving body. The energy supply system according to claim 1 or 2, wherein the supply of the energy supply is terminated. Acquires calculation information including the position information of the moving body which is a moving body moving by the supplied energy and is located at the energy supply point, the destination of the moving body, and the remaining amount of the energy stored in the moving body. Acquisition department and
Based on the calculation information, a calculation unit that calculates the recommended remaining amount of energy of the moving body at the energy supply point where the moving body is located according to the destination, and a calculation unit.
An output unit that outputs the recommended remaining amount of energy calculated by the calculation unit, and
Information processing device equipped with. An energy supply device that is installed at an energy supply point and supplies the energy to a moving body that moves by energy.
An input unit for inputting the recommended remaining amount of energy of the moving body according to the destination of the moving body at the energy supply point where the moving body is located.
A supply processing unit that performs processing related to the supply of energy when the recommended remaining amount of energy is input to the input unit.
Energy supply device equipped with. As the processing, the supply processing unit has at least one of the recommended remaining amount of the energy and the supply time of the energy required to make the remaining amount of the energy of the moving body the recommended remaining amount of the energy. The energy supply device according to claim 5, which notifies one of them. As the process, the supply processing unit performs the energy to the moving body when the remaining amount of the energy of the moving body reaches the recommended remaining amount of the energy while supplying the energy to the moving body. The energy supply device according to claim 5 or 6, wherein the supply of the energy supply is terminated.

Images