Processing device, processing method, and program

Abstract

The present invention provides a processing device (10) comprising: a prediction information acquisition unit (11) that acquires remaining-fuel-amount prediction information which indicates changes in a predicted value of the remaining amount of fuel in a vehicle when the vehicle travels on the basis of a transport plan and which is created on the basis of a prediction model; an actual measurement information acquisition unit (12) that acquires remaining-fuel-amount actual measurement information which indicates changes in the actual measurement value of the remaining amount of the fuel in the vehicle while the vehicle is travelling on the basis of the transport plan; and a determination unit (13) that, on the basis of the remaining-fuel-amount prediction information and of the remaining-fuel-amount actual measurement information, determines whether or not the prediction model needs to be corrected.

Description

[Technical Field]

[0001] The present invention relates to a processing device, a processing method, and a program. [Background technology]

[0002] Patent document 1 discloses a technology for evaluating delivery plans based on the target time for each delivery destination indicated in the delivery plan, the actual time when delivery is made based on the delivery plan, and the quality of driving by the delivery person.

[0003] Patent Document 2 discloses a technique for determining the transition of a predicted value of SOC (state of charge) up to a destination. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2020-095315 [Patent Document 2] Japanese Patent Application Laid-Open No. 2003-111209 Summary of the Invention [Problem to be solved by the invention]

[0005] It is necessary to create a transportation plan that prevents vehicles from running out of fuel during transportation (delivery / collection) using vehicles. To achieve this, it is necessary to accurately estimate the transition of the remaining fuel amount in a vehicle when traveling based on a transportation plan.

[0006] An object of the present invention is to provide a technology for accurately estimating the transition of the remaining amount of fuel in a vehicle when traveling based on a transportation plan. [Means for solving the problem]

[0007] According to the present invention, a prediction information acquisition means for acquiring remaining fuel amount prediction information that indicates a transition of a predicted value of the remaining fuel amount of the vehicle when traveling based on the transportation plan and is created based on a prediction model; an actual measurement information acquisition means for acquiring actual fuel remaining amount information indicating a change in the actual measurement value of the remaining fuel amount of the vehicle while the vehicle is traveling based on the transportation plan; a determination means for determining whether or not the prediction model needs to be corrected based on the remaining fuel amount prediction information and the remaining fuel amount actual measurement information; A processing device is provided having:

[0008] Further, according to the present invention, The computer a prediction information acquisition step of acquiring remaining fuel amount prediction information that indicates a transition of a predicted value of the remaining fuel amount of the vehicle when traveling based on the transportation plan and is created based on a prediction model; an actual measurement information acquisition step of acquiring remaining fuel amount actual measurement information indicating a change in the actual measurement value of the remaining fuel amount of the vehicle while the vehicle is traveling based on the transportation plan; a determination step of determining whether or not the prediction model needs to be corrected based on the remaining fuel amount prediction information and the remaining fuel amount actual measurement information; A processing method for performing the above is provided.

[0009] Further, according to the present invention, Computer, a prediction information acquisition means for acquiring remaining fuel amount prediction information that indicates a transition of a predicted value of the remaining fuel amount of the vehicle when traveling based on the transportation plan and is created based on a prediction model; an actual measurement information acquisition means for acquiring actual fuel remaining amount information indicating a change in the actual measurement value of the remaining fuel amount of the vehicle while the vehicle is traveling based on the transportation plan; a determination means for determining whether or not the prediction model needs to be corrected based on the remaining fuel amount prediction information and the remaining fuel amount actual measurement information; A program is provided to function as a [Effects of the Invention]

[0010] According to the present invention, it is possible to accurately estimate the transition of the remaining amount of fuel in a vehicle when the vehicle travels based on a transportation plan. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 2 is a diagram illustrating an example of a hardware configuration of a processing device. [Figure 2] FIG. 2 is a functional block diagram of a processing device. [Figure 3] FIG. 10 is a diagram schematically illustrating an example of prediction information. [Figure 4] FIG. 10 is a diagram schematically illustrating an example of prediction information. [Figure 5] FIG. 10 is a diagram for explaining the difference between a predicted value and an actual measurement value. [Figure 6] 10 is a flowchart illustrating an example of a processing flow of the processing device. [Figure 7] FIG. 1 is a diagram schematically illustrating an example of a transportation plan. [Figure 8] FIG. 10 is a diagram illustrating an example of a prediction model. [Figure 9] 10 is a flowchart illustrating an example of a processing flow of the processing device. [Figure 10] 10 is a flowchart illustrating an example of a processing flow of the processing device. [Figure 11] 10 is a flowchart illustrating an example of a processing flow of the processing device. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In all drawings, like components are designated by like reference numerals, and their description will be omitted where appropriate. In this specification, "transportation" is a concept that includes both delivering a package to a destination and collecting the package at the destination.

[0013] First Embodiment "overview" The processing device of this embodiment has a function of determining whether or not it is necessary to correct the "prediction model that predicts the transition of the remaining amount of fuel in the vehicle when traveling based on the transportation plan."

[0014] More specifically, the processing device determines whether the prediction model needs to be revised based on remaining fuel amount prediction information and remaining fuel amount actual measurement information. The remaining fuel amount prediction information is information created based on the prediction model and indicates the progress of the predicted value of the remaining fuel amount of the vehicle when traveling based on the transportation plan. The remaining fuel amount actual measurement information indicates the progress of the actual value of the remaining fuel amount of the vehicle while traveling based on the transportation plan.

[0015] The processing device that determines whether the prediction model needs to be modified based on the remaining fuel amount prediction information and the remaining fuel amount actual measurement information can accurately determine whether the prediction model needs to be modified. As a result, the prediction model can be modified when truly necessary, improving the prediction accuracy of the prediction model. In addition, it is possible to suppress the inconvenience of deteriorating the prediction accuracy of the prediction model due to unnecessary modification of the prediction model when it is not necessary.

[0016] "Hardware Configuration" Next, an example of the hardware configuration of a processing device will be described. Each functional unit of the processing device is realized by any combination of hardware and software, centered around a CPU (Central Processing Unit) of any computer, memory, programs loaded into the memory, a storage unit such as a hard disk that stores the programs (this can store programs that are pre-loaded when the device is shipped, as well as programs downloaded from storage media such as CDs (Compact Discs) or servers on the Internet), and a network connection interface. Those skilled in the art will understand that there are many variations in the realization methods and devices.

[0017] FIG. 1 is a block diagram illustrating an example of the hardware configuration of a processing device. As shown in FIG. 1, the processing device has a processor 1A, a memory 2A, an input / output interface 3A, a peripheral circuit 4A, and a bus 5A. The peripheral circuit 4A includes various modules. The processing device does not necessarily have to have the peripheral circuit 4A. Note that the processing device may be composed of multiple devices that are physically and / or logically separated. In this case, each of the multiple devices may have the above hardware configuration.

[0018] The bus 5A is a data transmission path for the processor 1A, memory 2A, peripheral circuit 4A, and input / output interface 3A to transmit and receive data among them. The processor 1A is an arithmetic processing device such as a CPU or a GPU (Graphics Processing Unit). The memory 2A is a memory such as a RAM (Random Access Memory) or a ROM (Read Only Memory). The input / output interface 3A includes an interface for acquiring information from an input device, an external device, an external server, an external sensor, a camera, etc., and an interface for outputting information to an output device, an external device, an external server, etc. Examples of input devices include a keyboard, a mouse, a microphone, physical buttons, a touch panel, etc. Examples of output devices include a display, a speaker, a printer, a mailer, etc. The processor 1A can issue commands to each module and perform calculations based on the results of those calculations.

[0019] "Function Configuration" Next, the functional configuration of the processing device will be described. An example of a functional block diagram of the processing device 10 is shown in Figure 2. As shown in the figure, the processing device 10 has a predicted information acquisition unit 11, an actual measurement information acquisition unit 12, and a determination unit 13.

[0020] The prediction information acquisition unit 11 acquires remaining fuel amount prediction information that indicates the transition of the predicted value of the remaining fuel amount of the vehicle when traveling based on the transportation plan. The remaining fuel amount prediction information is information created based on a prediction model created in advance. The prediction information acquisition unit 11 may acquire the remaining fuel amount prediction information by accepting input of the remaining fuel amount prediction information. Alternatively, the prediction information acquisition unit 11 may create the remaining fuel amount prediction information based on the transportation plan.

[0021] The "vehicle" in this embodiment is a so-called electric vehicle that runs on electricity as fuel. The "remaining fuel amount prediction information" in this embodiment indicates the transition of the predicted value of the SOC. As a modified example, the vehicle may be a vehicle that runs on other fuels such as gasoline, diesel, or hydrogen, and the remaining fuel amount prediction information may indicate the transition of the predicted value of the remaining amount of these fuels. Even if the vehicle is one of these modified examples, the same effects can be achieved by processing similar to the processing described below. Note that the "vehicle" referred to below means an electric vehicle unless otherwise specified.

[0022] FIG. 3 shows an example of remaining fuel amount prediction information. The illustrated remaining fuel amount prediction information shows predicted SOC values at all times between departure from the base and return to the base. FIG. 4 shows another example of remaining fuel amount prediction information. The illustrated remaining fuel amount prediction information shows predicted SOC values at predetermined times between departure from the base and return to the base. For example, as shown in the figure, predicted SOC values may be shown every 30 minutes, or the time interval may be different from the example shown in the figure. Furthermore, the time interval may be shortened as the predicted SOC value becomes smaller.

[0023] In this embodiment, the configuration of the prediction model and the details of the method for creating the remaining fuel amount prediction information are not particularly limited, and any configuration can be adopted. An example will be described in the following embodiment.

[0024] Returning to FIG. 2 , the actual measurement information acquisition unit 12 acquires remaining fuel amount actual measurement information indicating the change in the actual measurement value of the SOC of the vehicle while traveling based on the transportation plan. The actual measurement information acquisition unit 12 acquires remaining fuel amount actual measurement information indicating the change in the SOC detected by an on-board device installed in the vehicle. The actual measurement information acquisition unit 12 may acquire the remaining fuel amount actual measurement information by communicating with the on-board device, or may acquire the remaining fuel amount actual measurement information by communicating with a management device that communicates with the on-board device and collects and manages remaining fuel amount actual measurement information of the vehicle, or may acquire remaining fuel amount actual measurement information input by a user operation.

[0025] The determination unit 13 determines whether or not the prediction model used to create the remaining fuel amount prediction information needs to be corrected based on the remaining fuel amount prediction information and the remaining fuel amount actual measurement information. If the remaining fuel amount prediction information and the remaining fuel amount actual measurement information differ by a first reference level or more, the determination unit 13 determines that the prediction model needs to be corrected.

[0026] There are various conditions for determining that the difference is equal to or greater than the first reference level, and for example, any of the following conditions 1 to 3 may be included.

[0027] (Condition 1) There is a location where the difference d (see FIG. 5) between the predicted value indicated by the remaining fuel amount prediction information and the actual measured value indicated by the remaining fuel amount actual measurement information is equal to or greater than a first reference value.

[0028] (Condition 2) The cumulative time during which the difference d (see Figure 5) between the predicted value indicated by the remaining fuel amount prediction information and the actual measured value indicated by the remaining fuel amount actual measurement information is equal to or greater than a first reference value is equal to or greater than a second reference value.

[0029] (Condition 3) There is a time period during which the difference d (see Figure 5) between the predicted value indicated by the remaining fuel amount prediction information and the actual measured value indicated by the remaining fuel amount actual measurement information remains equal to or greater than the first reference value, and the length of time during which this state continues is equal to or greater than the third reference value.

[0030] As shown in Figure 5, the difference d is the difference between the predicted value of the vehicle's SOC at a certain timing when traveling based on the transportation plan and the actual measured value of the vehicle's SOC at that timing when traveling based on the transportation plan.

[0031] Next, an example of the processing flow of the processing device 10 will be described with reference to the flowchart of FIG.

[0032] First, the processing device 10 acquires remaining fuel amount prediction information and remaining fuel amount actual measurement information (S10). The remaining fuel amount prediction information is information created based on a prediction model and indicates the transition of the predicted value of the vehicle's SOC when traveling based on the transportation plan. The remaining fuel amount actual measurement information indicates the transition of the actual value of the vehicle's SOC while traveling based on the transportation plan.

[0033] Next, the processing device 10 determines whether the remaining fuel amount prediction information and the remaining fuel amount actual measurement information deviate by a first reference level or more (S11). If the remaining fuel amount prediction information and the remaining fuel amount actual measurement information deviate by a first reference level or more (Yes in S11), the processing device 10 determines that the prediction model needs to be corrected (S12). On the other hand, if the remaining fuel amount prediction information and the remaining fuel amount actual measurement information do not deviate by a first reference level or more (No in S11), the processing device 10 determines that the prediction model does not need to be corrected (S13).

[0034] The processing device 10 may output the determination results of S12 and S13 via any output device, including, but not limited to, a display, a projection device, a speaker, a warning lamp, a printer, a mailer, etc.

[0035] "Action and effect" The processing device 10 of this embodiment can determine whether or not a prediction model used to create remaining fuel amount prediction information needs to be modified, based on remaining fuel amount prediction information and remaining fuel amount actual measurement information. Such a processing device 10 can accurately determine whether or not a prediction model needs to be modified. As a result, the prediction model can be modified when truly necessary, improving the prediction accuracy of the prediction model. Furthermore, it is possible to suppress the inconvenience of deteriorating the prediction accuracy of the prediction model by unnecessary modification of the prediction model when unnecessary.

[0036] <Second embodiment> In this embodiment, the process of creating remaining fuel amount prediction information described in the first embodiment is embodied. The remaining fuel amount prediction information is created based on a transportation plan and a prediction model. Below, the transportation plan and the prediction model will be described in this order, and then the process of creating remaining fuel amount prediction information using them will be described.

[0037] "Transportation Plan" First, the transportation plan will be described. The transportation plan indicates the transportation destination, the transportation order, the weight of the cargo, and the like.

[0038] FIG. 7 shows a schematic diagram of an example of a transportation plan. FIG. 7 shows a list of multiple delivery plans for November 19, 2021. In FIG. 7, plan identification information, vehicle identification information, transportation information, and base departure times are linked to one another. Note that the transportation plan may also include other information.

[0039] "Plan identification information" is information that identifies multiple transportation plans from each other. The "vehicle identification information" is information for identifying multiple vehicles used for transportation from one another. Each piece of plan identification information is linked to the vehicle identification information of a vehicle assigned to each transportation plan. The "transportation information" includes the order, destination, classification, work time, package weight, work start time, and work end time.

[0040] "Order" indicates the order of transportation. "Destination" indicates the name and address of the party to whom the package is to be delivered or the party from whom the package is to be collected. "Classification" indicates the type of work, ie, delivery or collection. "Working time" indicates the time required for the work (delivery / collection) to be performed at the destination. "Luggage weight" indicates the weight of the luggage to be delivered to the delivery destination or the weight of the luggage to be collected at the collection destination. The "work start time" indicates the time when work (delivery / collection) starts at the destination. The "work completion time" indicates the time when the work (delivery / collection) ends at the destination.

[0041] The "Departure time from base" indicates the time when the vehicle departs from a base such as an office. After departing from the base, the vehicle visits multiple destinations and then returns to the base. The departure base and the return base may be the same or different.

[0042] Such transportation plans can be created using a variety of technologies.

[0043] "Predictive Model" Next, a prediction model will be described. In this embodiment, the prediction model is created by machine learning based on predetermined training data. The prediction model is used to predict the SOC of a vehicle, and there are many variations in its design (what is used as the objective variable and what is used as the explanatory variable). An example of a prediction model will be described below.

[0044] The prediction model is a model for predicting the electric fuel consumption of a vehicle. Specifically, the prediction model is created by machine learning based on training data in which at least one parameter from among the vehicle load, information about the route the vehicle will travel (road pavement condition, predicted road congestion, road inclination, radius of curvature of curves on the route, number of right and left turns on the route, etc.), weather conditions on the day (weather, temperature, humidity, wind speed, etc.), vehicle type, air resistance depending on the vehicle type, power consumption due to bodywork, etc., is used as an explanatory variable, and electric fuel consumption is used as a response variable. The prediction model can be expressed, for example, by a regression equation such as that shown in Figure 8.

[0045] "Process for creating remaining fuel amount prediction information" Next, a process for creating remaining fuel amount prediction information based on the above-described transportation plan and prediction model will be described. This process is executed by a creating device. The creating device may be the processing device 10 or a device different from the processing device 10.

[0046] -Processing to obtain vehicle SOC when departing from base- First, the creation device acquires the SOC of the vehicle when it departs from the base. For example, the acquisition of the SOC of the vehicle when it departs from the base may be realized by any one of the following first to third examples.

[0047] "First Example" For example, a user may input the vehicle's SOC at the time of departure from the base into the creation device. The creation device may then acquire the vehicle's SOC at the time of departure from the base input by the user. For example, the user may visually check the information displayed by an on-board device or the like installed in the vehicle at any time between the end of work on the previous day and the time of departure from the base on the current day, thereby checking the vehicle's SOC at that time. The user then inputs the checked vehicle's SOC into the creation device as the vehicle's SOC at the time of departure from the base.

[0048] "Second Example" Alternatively, the creation device may communicate with a device that manages the vehicle's SOC and obtain the vehicle's SOC from that device. For example, the creation device may obtain the vehicle's SOC at any time between the end of business on the previous day and the departure from the base on that day from that device as the vehicle's SOC at the time of departure from the base.

[0049] "Third Example" Additionally, the creation device may acquire reservation information indicating the reservation status of the charging facility. The reservation information indicates a reservation time (reservation start time and reservation end time) and vehicle identification information of the vehicle to be charged at the reserved time.

[0050] Then, after obtaining the SOC of the vehicle at the time of departure from the base using the method of the first or second example (hereinafter referred to as the "first SOC"), for a vehicle for which a reservation for charging equipment has been made thereafter and before departure from the base, the creation device calculates the SOC of the vehicle at the time of departure from the base as the SOC obtained by adding the amount of charging for the reservation to the first SOC. The amount of charging for the reservation can be the smaller of the product of the time from the reservation start time to the reservation end time and the charging speed of the charging equipment, and the available capacity of the vehicle (100% - capacity of (first SOC)).

[0051] -Processing to create forecast information based on the vehicle's SOC at the time of departure from the base and the transportation plan- The forecast information acquisition unit 11 divides the distance from the departure base to the return base into multiple sections. Specifically, the creation device defines each of "from the departure base to the first transport destination," "from the first transport destination to the second transport destination," "from the second transport destination to the third transport destination," ..., "from the final transport destination to the return base" as one section.

[0052] The creation device then uses the prediction model to estimate the vehicle's electricity consumption for each section. The prediction model receives input of at least one value from information about each section, specifically, the vehicle's load, information about the route the vehicle will travel (road pavement condition, predicted road congestion, road inclination, radius of curvature of curves on the route, number of right and left turns on the route, etc.), weather conditions on the day (weather, temperature, humidity, wind speed, etc.), vehicle type, air resistance depending on the vehicle type, power consumption due to bodywork, etc.

[0053] The creation device then calculates the transition of the SOC of the vehicle during transportation, that is, the transition of the SOC of the vehicle from the departure base to the return base, assuming that power is consumed at the power efficiency of each section in each section.

[0054] Here, we will explain the process of identifying the vehicle load for each section. As shown in Figure 7, the transportation plan indicates the order of transportation and the weight of the cargo to be delivered / collected at each destination. Using this information, the load during transportation can be identified.

[0055] First, by adding up the cargo weights corresponding to the "Delivery" category in Figure 7, the load volume from the departure base to the first destination (hereinafter referred to as "departure load volume") can be calculated.

[0056] If the classification of the first destination is "delivery," the load capacity between the first destination and the second destination can be calculated by subtracting the weight of the cargo to be delivered at the first destination from the load capacity at departure.

[0057] On the other hand, if the classification of the first destination is "collection," the load volume between the first destination and the second destination can be calculated by adding the weight of the cargo to be collected at the first destination to the load volume at departure.

[0058] Similarly, the load amount from one transport destination to the next transport destination and the load amount from the last transport destination to the return base can be calculated.

[0059] Other configurations of the processing apparatus 10 of this embodiment are the same as those of the first embodiment. According to the processing apparatus 10 of this embodiment, the same effects as those of the first embodiment are achieved.

[0060] <Third embodiment> The processing device 10 of this embodiment has a function for more accurately determining whether or not a prediction model needs to be corrected. Specifically, the processing device 10 determines whether or not a prediction model needs to be corrected based on the degree of deviation between the planned value of a parameter input to the prediction model and the actual value of the parameter. This will be described in detail below.

[0061] The prediction information acquisition unit 11 acquires parameter planning values, which are values of various parameters used to create remaining fuel amount prediction information and are values planned based on a transportation plan.

[0062] As explained in the second embodiment, the various parameters include at least one of the following: vehicle load, information about the route the vehicle will take (road pavement condition, predicted road congestion, road inclination, radius of curvature of curves on the route, number of right and left turns on the route, etc.), weather conditions on the day (weather, temperature, humidity, wind speed, etc.), vehicle type, air resistance depending on the vehicle type, power consumption due to the bodywork, etc.

[0063] The method for acquiring the planned parameter values for the vehicle load capacity is as described in the second embodiment. Furthermore, by using a well-known route search technology to determine a route that visits multiple destinations in the order indicated in the transportation plan and acquiring information about the route from map data, the planned parameter values for information about the route the vehicle will take can be acquired. Furthermore, by acquiring forecasted weather information for the day from a server that provides weather information, the planned parameter values for the weather conditions for the day can be acquired. Furthermore, by identifying the vehicles assigned to each vehicle indicated in the transportation plan and acquiring various pre-registered information about the vehicles from a database, the planned parameter values for the vehicle type, the air resistance corresponding to the vehicle type, and the power consumption due to the vehicle body can be acquired.

[0064] The actual measurement information acquisition unit 12 acquires actual parameter values, which are actual values of various parameters while traveling based on the transportation plan. For example, the actual measurement information acquisition unit 12 may acquire actual vehicle load values collected by various sensors mounted on the vehicle or information on the routes actually traveled by the vehicle. Alternatively, the actual measurement information acquisition unit 12 may acquire actual weather information for the day from a server that provides weather information. Alternatively, the actual measurement information acquisition unit 12 may acquire information identifying the vehicle actually used to execute each transportation plan through user input or the like, and then acquire various pre-registered information about the vehicle from a database.

[0065] The determination unit 13 determines whether or not the prediction model needs to be corrected, further based on the comparison result between the planned parameter values and the actual parameter values.

[0066] The purpose of this determination will now be explained. The parameter values input into the prediction model when generating the remaining fuel amount prediction information are planned parameter values based on a transportation plan. When actually traveling based on the transportation plan, for some reason, the transportation order, route, and vehicles actually used may differ from those specified based on the transportation plan. As a result, actual values such as information on vehicle load capacity and route, vehicle type, and actual values of air resistance and power consumption due to vehicle bodywork may differ from the planned parameter values based on the transportation plan. This deviation between the planned parameter values and the actual parameter values may cause a deviation between the remaining fuel amount prediction information and the actual fuel amount information. If the deviation between the remaining fuel amount prediction information and the actual fuel amount information is caused by a deviation between the planned parameter values and the actual parameter values, there is no need to modify the prediction model. The determination unit 13 is configured to make a determination based on this purpose.

[0067] Specifically, the determination unit 13 may determine that the prediction model needs to be corrected if the remaining fuel amount prediction information and the actual fuel amount measurement information deviate by a first reference level or more, and the planned parameter value and the actual parameter value do not deviate by a second reference level. In this case, it is determined that the cause of the deviation between the remaining fuel amount prediction information and the actual fuel amount measurement information is not the deviation between the planned parameter value and the actual parameter value. Therefore, it is determined that the prediction model needs to be corrected.

[0068] On the other hand, the determination unit 13 may determine that correction of the prediction model is unnecessary when the remaining fuel amount prediction information and the actual fuel amount measurement information deviate by a first reference level or more and the planned parameter value and the actual parameter value deviate by a second reference level or more. In this case, it is determined that the cause of the deviation between the remaining fuel amount prediction information and the actual fuel amount measurement information is the deviation between the planned parameter value and the actual parameter value. Therefore, it is determined that correction of the prediction model is unnecessary.

[0069] As a variant example, the judgment unit 13 may perform the following judgment process when the fuel remaining amount prediction information and the fuel remaining amount actual measurement information deviate by more than a first reference level and the parameter planned value and the parameter actual value deviate by more than a second reference level.

[0070] First, the determination unit 13 inputs the parameter actual values into a prediction model to create remaining fuel amount prediction information. Then, the determination unit 13 may determine that the prediction model needs to be corrected if the remaining fuel amount prediction information created by inputting the parameter actual values into the prediction model deviates from the remaining fuel amount actual measurement information by a first reference level or more. Furthermore, the determination unit 13 may determine that the prediction model does not need to be corrected if the remaining fuel amount prediction information created by inputting the parameter actual values into the prediction model does not deviate from the remaining fuel amount actual measurement information by a first reference level or more.

[0071] There are various conditions for determining that there is a "deviation by more than the second reference level," but it may be, for example, that "there is a deviation that satisfies a predetermined reference in M or more of the multiple parameters," where M is an integer of 1 or greater.

[0072] The "predetermined criterion" is determined for each parameter. For example, the criterion for the load capacity, the air resistance according to the vehicle type, or the power consumption due to the vehicle body may be "there is a location during traveling based on the transportation plan where the difference between the parameter plan value and the parameter actual value is equal to or greater than a threshold value," or "the cumulative time during traveling based on the transportation plan where the difference between the parameter plan value and the parameter actual value is equal to or greater than a threshold value," or may be other criteria.

[0073] In addition, in the case of information regarding the route that the vehicle will take (road pavement condition, predicted road congestion condition, road inclination condition, radius of curvature of curves on the route, number of right and left turns on the route, etc.), the criteria may be "the length of the route that does not match between the route determined to calculate these parameter planning values and the route that the vehicle actually took is greater than or equal to a threshold value," or may be something else.

[0074] Furthermore, in the case of the weather conditions of the day (weather, temperature, humidity, wind speed, etc.) and vehicle type, that information may be quantified according to predetermined rules. The criteria in these cases may be "during travel based on the transportation plan, there was a location where the difference between the planned parameter value and the actual parameter value was equal to or greater than a threshold," or "during travel based on the transportation plan, the cumulative time during which the difference between the planned parameter value and the actual parameter value was equal to or greater than a threshold" or other criteria.

[0075] Next, an example of the processing flow of the processing device 10 will be described with reference to the flowchart of FIG.

[0076] First, the processing device 10 acquires remaining fuel amount prediction information, remaining fuel amount actual measurement information, parameter plan values, and parameter actual values (S20). The remaining fuel amount prediction information is information created based on parameter plan values and a prediction model, and indicates the transition of the predicted value of the vehicle's SOC when traveling based on the transportation plan. The remaining fuel amount actual measurement information indicates the transition of the actual value of the vehicle's SOC while traveling based on the transportation plan. The parameter plan values are values of various parameters input into the prediction model, and are values planned based on the transportation plan. The parameter actual values are the actual values of the various parameters when traveling based on the transportation plan.

[0077] Next, the processing device 10 determines whether the remaining fuel amount prediction information and the remaining fuel amount actual measurement information deviate by a first reference level or more (S21). If the remaining fuel amount prediction information and the remaining fuel amount actual measurement information deviate by the first reference level or more (Yes in S21), the processing device 10 determines whether the planned parameter value and the actual parameter value deviate by a second reference level or more (S22).

[0078] If the planned parameter value and the actual parameter value do not deviate by more than the second reference level (No in S22), the processing device 10 determines that the prediction model needs to be corrected (S23). On the other hand, if the planned parameter value and the actual parameter value deviate by more than the second reference level (Yes in S22), the processing device 10 inputs the actual parameter value into the prediction model to create remaining fuel amount prediction information, and determines whether the remaining fuel amount prediction information and the remaining fuel amount actual measurement information deviate by more than the first reference level (S24).

[0079] If the remaining fuel amount prediction information created by inputting the parameter actual values into the prediction model and the remaining fuel amount actual measurement information deviate by more than the first reference level (Yes in S24), the processing device 10 determines that the prediction model needs to be corrected (S23). On the other hand, if the remaining fuel amount prediction information created by inputting the parameter actual values into the prediction model and the remaining fuel amount actual measurement information do not deviate by more than the first reference level (No in S24), the processing device 10 determines that the prediction model does not need to be corrected (S25).

[0080] Furthermore, if the remaining fuel amount prediction information and the remaining fuel amount actual measurement information acquired in S20 do not deviate by more than the first reference level (No in S21), the processing device 10 determines that correction of the prediction model is not necessary (S26).

[0081] The processing device 10 may output the determination results of S23, S25, and S26 via any output device, including, but not limited to, a display, a projection device, a speaker, a warning lamp, a printer, a mailer, etc.

[0082] Other configurations of the processing apparatus 10 of this embodiment are the same as those of the first and second embodiments.

[0083] The processing device 10 of this embodiment achieves the same effects as those of the first and second embodiments. Furthermore, the processing device 10 of this embodiment can determine whether or not a prediction model needs to be corrected based on the degree of deviation between the planned value of a parameter input to the prediction model and the actual value of the parameter. As a result, it becomes possible to more accurately determine whether or not a prediction model needs to be corrected.

[0084] <Fourth embodiment> The processing device 10 of this embodiment has a function for more accurately determining whether or not a prediction model needs to be corrected. Specifically, the processing device 10 determines whether or not a prediction model needs to be corrected based on the degree of deviation between a sensor value related to the driver's vehicle operation and a reference value. This will be described in detail below.

[0085] The actual measurement information acquisition unit 12 further acquires sensor values that indicate the state of the vehicle while traveling based on the transportation plan and are measured by sensors mounted on the vehicle.

[0086] The sensor values are values related to the driver's operation of the vehicle. For example, the sensor values indicate the state of all the operational objects (operations of the driver) installed in the vehicle, such as the steering wheel, accelerator, brake, blinkers, wipers, various lamps, air conditioner, audio, etc. The sensor values may also indicate the state of the vehicle that changes depending on the driver's operation, such as speed and acceleration. Such sensor values can be obtained using well-known technology.

[0087] The determination unit 13 determines whether or not the prediction model needs to be corrected based on the comparison result between the sensor value and the reference value. The reference value is a preset value that indicates a value during standard operation.

[0088] Here, the purpose of this determination will be explained. The electric fuel consumption of a vehicle can change depending on the driver's operation. Therefore, if the driver's operation deviates from the standard operation assumed when creating the remaining fuel amount prediction information, this may cause a deviation between the remaining fuel amount prediction information and the remaining fuel amount actual measurement information. If the deviation between the remaining fuel amount prediction information and the remaining fuel amount actual measurement information is caused by the driver's operation, there is no need to modify the prediction model. The determination unit 13 is configured to make a determination with this purpose in mind.

[0089] Specifically, when the remaining fuel amount prediction information and the remaining fuel amount actual measurement information deviate by a first reference level or more, and the sensor value and the reference value do not deviate by a third reference level, the determination unit 13 determines that the prediction model needs to be corrected. In this case, it is determined that the cause of the deviation between the remaining fuel amount prediction information and the remaining fuel amount actual measurement information is not the driver's operation. Therefore, it is determined that the prediction model needs to be corrected.

[0090] On the other hand, the determination unit 13 may determine that the prediction model needs to be corrected if the remaining fuel amount prediction information and the remaining fuel amount actual measurement information deviate by a first reference level or more, and the sensor value and the reference value deviate by a third reference level or more. In this case, it is determined that the cause of the deviation between the remaining fuel amount prediction information and the remaining fuel amount actual measurement information is the driver's operation. Therefore, it is determined that the prediction model does not need to be corrected.

[0091] There are various conditions for determining that the sensor values "deviate by the third reference level or more," but it may be, for example, that "N or more of the multiple sensor values exhibit a deviation that satisfies a predetermined reference," where N is an integer equal to or greater than 1.

[0092] The "predetermined criterion" is determined for each sensor value. For example, it may be "during travel based on the transportation plan, there was a location where the difference between the sensor value and the reference value was equal to or greater than a threshold value," or "during travel based on the transportation plan, the cumulative time during which the difference between the sensor value and the reference value was equal to or greater than a threshold value," or it may be something else.

[0093] If the sensor value and the reference value deviate by a third reference level or more, the determination unit 13 may output a guidance message to prompt the driver to improve their operation. The output is realized via any output device such as a display, a projection device, a speaker, a printer, or a mailer.

[0094] Next, an example of the processing flow of the processing device 10 will be described with reference to the flowchart of FIG.

[0095] First, the processing device 10 acquires remaining fuel amount prediction information, remaining fuel amount actual measurement information, and sensor values (S30). The remaining fuel amount prediction information is information created based on a prediction model, and indicates the transition of the predicted value of the vehicle's SOC when traveling based on the transportation plan. The remaining fuel amount actual measurement information indicates the transition of the actual value of the vehicle's SOC while traveling based on the transportation plan. The sensor values are values measured by sensors mounted on the vehicle while traveling based on the transportation plan, and are values related to the driver's operation.

[0096] Next, the processing device 10 determines whether the remaining fuel amount prediction information and the remaining fuel amount actual measurement information deviate by a first reference level or more (S31). If the remaining fuel amount prediction information and the remaining fuel amount actual measurement information deviate by the first reference level or more (Yes in S31), the processing device 10 determines whether the sensor value and the reference value deviate by a third reference level or more (S32).

[0097] If the sensor value and the reference value do not deviate by more than the third reference level (No in S32), the processing device 10 determines that the prediction model needs to be corrected (S 33 On the other hand, if the difference between the sensor value and the reference value is equal to or greater than the third reference level (Yes in S32), the processing device 10 determines that correction of the prediction model is not necessary (S34).

[0098] Furthermore, if the remaining fuel amount prediction information and the remaining fuel amount actual measurement information acquired in S30 do not deviate by a first reference level or more (No in S31), the processing device 10 determines that correction of the prediction model is not necessary (S34).

[0099] The processing device 10 may output the determination results of S33 and S34 via an arbitrary output device. Furthermore, if the determination in S32 is Yes, the processing device 10 may output guidance for encouraging the driver to improve their operation via an arbitrary output device. Examples of the output device include, but are not limited to, a display, a projection device, a speaker, a warning lamp, a printer, a mailer, etc.

[0100] Other configurations of the processing apparatus 10 of this embodiment are the same as those of the first to third embodiments.

[0101] The processing device 10 of this embodiment achieves the same effects as those of the first to third embodiments. Furthermore, the processing device 10 of this embodiment can determine whether or not a prediction model needs to be corrected based on the driver's operation. As a result, it becomes possible to more accurately determine whether or not a prediction model needs to be corrected.

[0102] <Fifth embodiment> The processing device 10 of this embodiment has a function for more accurately determining whether or not the prediction model needs to be corrected. Specifically, the processing device 10 determines whether or not the prediction model needs to be corrected based on the degree of deviation between the sensor value related to the vehicle performance and the reference value. This will be described in detail below.

[0103] The actual measurement information acquisition unit 12 further acquires sensor values that indicate the state of the vehicle while traveling based on the transportation plan and are measured by sensors mounted on the vehicle.

[0104] The sensor values are values related to the performance of the vehicle. For example, the sensor values may be values measured by sensors used for engine control (such as a pressure sensor, an exhaust gas sensor, or a crank angle sensor), values indicating the state of an object to be operated (such as a steering wheel, an accelerator, or a brake), or values indicating the state of the vehicle (such as speed or acceleration), but are not limited to these. Such sensor values can be obtained using well-known techniques.

[0105] The determination unit 13 determines whether or not the prediction model needs to be corrected based on the comparison result between the sensor value and the reference value. The reference value is a preset value that indicates the performance of the vehicle in a standard state.

[0106] Here, the purpose of this determination will be explained. A vehicle's electricity consumption can change depending on the vehicle's performance. If performance deteriorates due to a malfunction, aging, or the like, electricity consumption will worsen. Therefore, if the vehicle's performance deviates from the standard performance assumed when the remaining fuel amount prediction information is created, this may cause a deviation between the remaining fuel amount prediction information and the remaining fuel amount actual measurement information. If the deviation between the remaining fuel amount prediction information and the remaining fuel amount actual measurement information is caused by the vehicle's performance, there is no need to modify the prediction model. The determination unit 13 is configured to make a determination with this purpose in mind.

[0107] Specifically, when the remaining fuel amount prediction information and the remaining fuel amount actual measurement information deviate by a first reference level or more, and the sensor value and the reference value do not deviate by a fourth reference level or more, the determination unit 13 determines that the prediction model needs to be corrected. In this case, it is determined that the cause of the deviation between the remaining fuel amount prediction information and the remaining fuel amount actual measurement information is not the vehicle performance. Therefore, it is determined that the prediction model needs to be corrected.

[0108] On the other hand, the determination unit 13 may determine that the prediction model needs to be corrected if the remaining fuel amount prediction information and the remaining fuel amount actual measurement information deviate by more than a first reference level and the sensor value and the reference value deviate by more than a fourth reference level. In this case, it is determined that the cause of the deviation between the remaining fuel amount prediction information and the remaining fuel amount actual measurement information is the performance of the vehicle. Therefore, it is determined that the prediction model does not need to be corrected.

[0109] There are various conditions for determining that the sensor values "deviate by the fourth reference level or more," but it may be, for example, that "P or more of the multiple sensor values exhibit a deviation that satisfies a predetermined reference," where P is an integer of 1 or greater.

[0110] The "predetermined criterion" is determined for each sensor value. For example, it may be "during travel based on the transportation plan, there was a location where the difference between the sensor value and the reference value was equal to or greater than a threshold value," or "during travel based on the transportation plan, the cumulative time during which the difference between the sensor value and the reference value was equal to or greater than a threshold value," or it may be something else.

[0111] If the sensor value and the reference value deviate by a fourth reference level or more, the determination unit 13 may output information notifying of a problem with the vehicle's performance. The output is realized via any output device, such as a display, a projection device, a speaker, a printer, or a mailer.

[0112] Next, an example of the processing flow of the processing device 10 will be described with reference to the flowchart of FIG.

[0113] First, the processing device 10 acquires remaining fuel amount prediction information, remaining fuel amount actual measurement information, and sensor values (S30). The remaining fuel amount prediction information is information created based on a prediction model and indicates the transition of the predicted value of the vehicle's SOC when traveling based on the transportation plan. The remaining fuel amount actual measurement information indicates the transition of the actual value of the vehicle's SOC while traveling based on the transportation plan. The sensor values are values measured by sensors mounted on the vehicle while traveling based on the transportation plan, and are values related to the vehicle's performance.

[0114] Next, the processing device 10 determines whether the remaining fuel amount prediction information and the remaining fuel amount actual measurement information deviate by a first reference level or more (S31). If the remaining fuel amount prediction information and the remaining fuel amount actual measurement information deviate by the first reference level or more (Yes in S31), the processing device 10 determines whether the sensor value and the reference value deviate by a fourth reference level or more (S32).

[0115] If the sensor value and the reference value do not deviate by more than the fourth reference level (No in S32), the processing device 10 determines that the prediction model needs to be corrected (S23). On the other hand, if the sensor value and the reference value deviate by more than the fourth reference level (Yes in S32), the processing device 10 determines that the prediction model does not need to be corrected (S34).

[0116] Furthermore, if the remaining fuel amount prediction information and the remaining fuel amount actual measurement information acquired in S30 do not deviate by a first reference level or more (No in S31), the processing device 10 determines that correction of the prediction model is not necessary (S34).

[0117] The processing device 10 may output the determination results of S33 and S34 via an arbitrary output device. Furthermore, if the determination in S32 is Yes, the processing device 10 may output information notifying of a problem with the vehicle's performance via an arbitrary output device. Examples of output devices include, but are not limited to, a display, a projection device, a speaker, a warning lamp, a printer, a mailer, etc.

[0118] Other configurations of the processing apparatus 10 of this embodiment are the same as those of the first to fourth embodiments.

[0119] The processing device 10 of this embodiment achieves the same effects as those of the first to fourth embodiments. Furthermore, the processing device 10 of this embodiment can determine whether or not a prediction model needs to be corrected based on the vehicle performance. As a result, it becomes possible to more accurately determine whether or not a prediction model needs to be corrected.

[0120] Sixth Embodiment The processing device 10 of this embodiment determines whether or not a prediction model needs to be corrected by combining at least two of the "determination based on the comparison result between the planned parameter values and the actual parameter values" described in the third embodiment, the "determination based on the comparison result between the sensor values related to the driver's operation and the reference values" described in the fourth embodiment, and the "determination based on the comparison result between the sensor values related to the vehicle performance and the reference values" described in the fifth embodiment. These will be explained in detail below.

[0121] "First Example" The first example combines the "determination based on the comparison result between the parameter planning value and the parameter actual value" described in the third embodiment, the "determination based on the comparison result between the sensor value related to the driver's operation and the reference value" described in the fourth embodiment, and the "determination based on the comparison result between the sensor value related to the vehicle performance and the reference value" described in the fifth embodiment to determine whether or not a prediction model needs to be modified.

[0122] The judgment unit 13 judges that the prediction model needs to be corrected if the fuel remaining amount prediction information and the fuel remaining amount actual measurement information deviate by more than a first reference level, the parameter planning value and the parameter actual value do not deviate from a second reference level, the sensor value and the reference value related to the driver's operation do not deviate from a third reference level, and the sensor value and the reference value related to the vehicle performance do not deviate from a fourth reference level.

[0123] Then, even if the remaining fuel amount prediction information and the remaining fuel amount actual measurement information deviate by more than a first reference level, the judgment unit 13 judges that correction of the prediction model is unnecessary if the parameter planning value and the parameter actual value deviate from a second reference level, the sensor value and the reference value related to the driver's operation deviate from a third reference level, or the sensor value and the reference value related to the vehicle performance deviate from a fourth reference level.

[0124] Furthermore, when the remaining fuel amount prediction information and the remaining fuel amount actual measurement information do not deviate by a first reference level or more, the determination unit 13 determines that correction of the prediction model is not necessary.

[0125] In addition, if the fuel remaining amount prediction information and the fuel remaining amount actual measurement information deviate by more than the first reference level, the sensor value and the reference value related to the driver's operation do not deviate from the third reference level, the sensor value and the reference value related to the vehicle performance do not deviate from the fourth reference level, and the parameter planning value and the parameter actual value deviate from the second reference level, the following judgment processing may be performed.

[0126] First, the determination unit 13 inputs the parameter actual values into a prediction model to create remaining fuel amount prediction information. Then, the determination unit 13 may determine that the prediction model needs to be corrected if the remaining fuel amount prediction information created by inputting the parameter actual values into the prediction model deviates from the remaining fuel amount actual measurement information by a first reference level or more. Furthermore, the determination unit 13 may determine that the prediction model does not need to be corrected if the remaining fuel amount prediction information created by inputting the parameter actual values into the prediction model does not deviate from the remaining fuel amount actual measurement information by a first reference level or more.

[0127] "Second Example" The second example combines the "determination based on the comparison result between the parameter planning value and the parameter actual value" described in the third embodiment with the "determination based on the comparison result between the sensor value related to the driver's operation and the reference value" described in the fourth embodiment to determine whether or not the prediction model needs to be corrected.

[0128] The judgment unit 13 judges that the prediction model needs to be corrected if the fuel remaining amount prediction information and the fuel remaining amount actual measurement information deviate by more than a first reference level, the parameter planning value and the parameter actual value do not deviate from a second reference level, and the sensor value and the reference value related to the driver's operation do not deviate from a third reference level.

[0129] Then, even if the fuel remaining amount prediction information and the fuel remaining amount actual measurement information deviate by more than a first reference level, the judgment unit 13 judges that correction of the prediction model is unnecessary if the parameter planning value and the parameter actual value deviate from a second reference level, or if the sensor value and the reference value related to the driver's operation deviate from a third reference level.

[0130] Furthermore, when the remaining fuel amount prediction information and the remaining fuel amount actual measurement information do not deviate by a first reference level or more, the determination unit 13 determines that correction of the prediction model is not necessary.

[0131] In addition, if the fuel remaining amount prediction information and the fuel remaining amount actual measurement information deviate by more than the first reference level, if the sensor value and reference value related to the driver's operation do not deviate from the third reference level, and if the parameter planning value and parameter actual value deviate from the second reference level, the following judgment processing may be performed.

[0132] First, the determination unit 13 inputs the parameter actual values into a prediction model to create remaining fuel amount prediction information. Then, the determination unit 13 may determine that the prediction model needs to be corrected if the remaining fuel amount prediction information created by inputting the parameter actual values into the prediction model deviates from the remaining fuel amount actual measurement information by a first reference level or more. Furthermore, the determination unit 13 may determine that the prediction model does not need to be corrected if the remaining fuel amount prediction information created by inputting the parameter actual values into the prediction model does not deviate from the remaining fuel amount actual measurement information by a first reference level or more.

[0133] "Third Example" The third example combines the "determination based on the comparison result between the parameter planning value and the parameter actual value" described in the third embodiment with the "determination based on the comparison result between the sensor value related to the vehicle performance and the reference value" described in the fifth embodiment to determine whether or not the prediction model needs to be corrected.

[0134] The judgment unit 13 judges that the prediction model needs to be corrected if the fuel remaining amount prediction information and the fuel remaining amount actual measurement information deviate by more than a first reference level, the parameter planning value and the parameter actual value do not deviate from a second reference level, and the sensor value and the reference value related to the vehicle performance do not deviate from a fourth reference level.

[0135] Then, even if the remaining fuel amount prediction information and the remaining fuel amount actual measurement information deviate by more than a first reference level, if the parameter planning value and the parameter actual value deviate from a second reference level, or if the sensor value and the reference value related to the vehicle performance deviate from a fourth reference level, the judgment unit 13 judges that correction of the prediction model is unnecessary.

[0136] Furthermore, when the remaining fuel amount prediction information and the remaining fuel amount actual measurement information do not deviate by a first reference level or more, the determination unit 13 determines that correction of the prediction model is not necessary.

[0137] In addition, if the fuel remaining amount prediction information and the fuel remaining amount actual measurement information deviate by more than the first reference level, if the sensor value and reference value related to the vehicle performance do not deviate by more than the fourth reference level, and if the parameter planning value and parameter actual value deviate by more than the second reference level, the following judgment processing may be performed.

[0138] First, the determination unit 13 inputs the parameter actual values into a prediction model to create remaining fuel amount prediction information. Then, the determination unit 13 may determine that the prediction model needs to be corrected if the remaining fuel amount prediction information created by inputting the parameter actual values into the prediction model deviates from the remaining fuel amount actual measurement information by a first reference level or more. Furthermore, the determination unit 13 may determine that the prediction model does not need to be corrected if the remaining fuel amount prediction information created by inputting the parameter actual values into the prediction model does not deviate from the remaining fuel amount actual measurement information by a first reference level or more.

[0139] "Fourth Example" The fourth example combines the "determination based on the comparison results between sensor values related to driver operation and reference values" described in the fourth embodiment with the "determination based on the comparison results between sensor values related to vehicle performance and reference values" described in the fifth embodiment to determine whether or not a prediction model needs to be modified.

[0140] The judgment unit 13 judges that the prediction model needs to be corrected if the fuel remaining amount prediction information and the fuel remaining amount actual measurement information deviate by more than a first reference level, the sensor value and the reference value related to the driver's operation do not deviate by more than a third reference level, and the sensor value and the reference value related to the vehicle performance do not deviate by more than a fourth reference level.

[0141] Then, even if the fuel remaining amount prediction information and the fuel remaining amount actual measurement information deviate by more than the first reference level, the judgment unit 13 judges that correction of the prediction model is not necessary if the sensor value and the reference value related to the driver's operation deviate by more than the third reference level, or if the sensor value and the reference value related to the vehicle performance deviate by more than the fourth reference level.

[0142] Furthermore, when the remaining fuel amount prediction information and the remaining fuel amount actual measurement information do not deviate by a first reference level or more, the determination unit 13 determines that correction of the prediction model is not necessary.

[0143] Next, an example of the processing flow of the first example will be described with reference to the flowchart of FIG.

[0144] First, the processing device 10 acquires remaining fuel amount prediction information, remaining fuel amount actual measurement information, parameter planned values, parameter actual values, and sensor values (S40).

[0145] Next, the processing device 10 determines whether the remaining fuel amount prediction information and the remaining fuel amount actual measurement information deviate by a first reference level or more (S41). If the remaining fuel amount prediction information and the remaining fuel amount actual measurement information do not deviate by the first reference level or more (No in S41), the processing device 10 determines that correction of the prediction model is unnecessary (S48). On the other hand, if the remaining fuel amount prediction information and the remaining fuel amount actual measurement information deviate by the first reference level or more (Yes in S41), the processing device 10 determines whether the planned parameter value and the actual parameter value deviate by a second reference level or more (S42).

[0146] If the parameter planning value and the parameter actual value deviate by more than the second reference level (Yes in S42), the processing device 10 performs the processes from S46 onwards. On the other hand, if the parameter planning value and the parameter actual value do not deviate by more than the second reference level (No in S42), the processing device 10 determines whether the sensor value and the reference value related to the driver's operation deviate by more than the third reference level (S43).

[0147] If the sensor value and the reference value relating to the driver's operation deviate by a third reference level or more (Yes in S43), the processing device 10 determines that correction of the prediction model is unnecessary (S48). On the other hand, if the sensor value and the reference value relating to the driver's operation do not deviate by the third reference level or more (No in S43), the processing device 10 determines whether the sensor value and the reference value relating to the vehicle performance deviate by a fourth reference level or more (S44).

[0148] If the sensor value and the reference value regarding the vehicle performance deviate by more than the fourth reference level (Yes in S44), the processing device 10 determines that the prediction model does not need to be corrected (S48). On the other hand, if the sensor value and the reference value regarding the vehicle performance do not deviate by more than the fourth reference level (No in S44), the processing device 10 determines that the prediction model needs to be corrected (S45).

[0149] If the answer is Yes in S42, the processing device 10 inputs the actual parameter values into the prediction model to create fuel remaining amount prediction information, and determines whether the fuel remaining amount prediction information and the actual fuel remaining amount information deviate by more than a first reference level (S46).

[0150] If the remaining fuel amount prediction information created by inputting the parameter actual values into the prediction model and the remaining fuel amount actual measurement information deviate by more than the first reference level (Yes in S46), the processing device 10 determines that the prediction model needs to be corrected (S45). On the other hand, if the remaining fuel amount prediction information created by inputting the parameter actual values into the prediction model and the remaining fuel amount actual measurement information do not deviate by more than the first reference level (No in S46), the processing device 10 determines that the prediction model does not need to be corrected (S47).

[0151] The processing device 10 may output the determination results of S45, S47, and S48 via any output device. Furthermore, if the result of S43 is Yes, the processing device 10 may output, via any output device, guidance to encourage the driver to improve their operation. Furthermore, if the result of S44 is Yes, the processing device 10 may output, via any output device, information notifying the driver of a problem with vehicle performance. Examples of output devices include, but are not limited to, a display, a projection device, a speaker, a warning lamp, a printer, a mailer, etc.

[0152] The processing order of S42, S43 and S44 is not limited to that shown in FIG. 11, and other orders may also be used.

[0153] Other configurations of the processing apparatus 10 of this embodiment are the same as those of the first to fifth embodiments.

[0154] The processing device 10 of this embodiment achieves the same effects as those of the first to fifth embodiments. Furthermore, the processing device 10 of this embodiment can determine whether or not a prediction model needs to be corrected based on at least two of the degree of deviation between the planned value of a parameter input to the prediction model and the actual value of the parameter, the driver's operation, and the vehicle performance. As a result, it becomes possible to more accurately determine whether or not a prediction model needs to be corrected.

[0155] Here, a modified example applicable to all the embodiments will be described. In the above embodiment, the prediction model is created by machine learning based on predetermined training data. As a modified example, the prediction model may be created by rule-based logic, and various parameters may be adjusted using the same method as in the above embodiment.

[0156] Although the embodiments of the present invention have been described above with reference to the drawings, these are merely examples of the present invention, and various other configurations may be adopted. The configurations of the above-described embodiments may be combined with each other, or some of the configurations may be replaced with other configurations. Furthermore, various modifications may be made to the configurations of the above-described embodiments without departing from the spirit of the invention. Furthermore, the configurations and processes disclosed in the above-described embodiments and modified examples may be combined with each other.

[0157] In this specification, "acquisition" includes at least one of the following: "the device retrieves data stored in another device or storage medium (active acquisition)" based on user input or program instructions, such as receiving data by making a request or inquiry to another device, or accessing and reading out another device or storage medium; "the device inputs data output from another device (passive acquisition)" based on user input or program instructions, such as receiving data that is distributed (or transmitted, push notification, etc.), and selecting and acquiring data from received data or information; and "the device generates new data by editing data (converting it to text, rearranging data, extracting some data, changing the file format, etc.), and then acquires the new data."

[0158] Furthermore, although the present specification has described the invention using a transportation plan as an example, the present invention is not limited to this and may be applied to a movement plan or the like. An example of a movement plan is route information displayed on a car navigation system installed in a vehicle. By applying the present invention to a movement plan, similar effects can be obtained not only during transportation but also when the vehicle is moving.

[0159] Some or all of the above-described embodiments can be described as, but are not limited to, the following supplementary notes. 1. A prediction information acquisition means for acquiring remaining fuel prediction information that shows the transition of the predicted value of the remaining fuel of the vehicle when traveling based on the transportation plan and is created based on a prediction model; an actual measurement information acquisition means for acquiring actual fuel remaining amount information indicating a change in the actual measurement value of the remaining fuel amount of the vehicle while the vehicle is traveling based on the transportation plan; a determination means for determining whether or not the prediction model needs to be corrected based on the remaining fuel amount prediction information and the remaining fuel amount actual measurement information; A processing device having: 2. The processing device according to 1, wherein the remaining amount of fuel in the vehicle is indicated by SOC. 3. The prediction information acquisition means further acquires parameter planning values, which are values of various parameters used to create the remaining fuel amount prediction information and are values planned based on the transportation plan; The actual measurement information acquisition means further acquires parameter actual values, which are actual values of the various parameters while traveling based on the transportation plan, 3. The processing device according to 1 or 2, wherein the determining means determines whether or not the prediction model needs to be corrected based further on a comparison result between the planned parameter value and the actual parameter value. 4. The processing device described in 3, wherein the determination means determines that the prediction model needs to be corrected if the fuel remaining amount prediction information and the fuel remaining amount actual measurement information deviate by more than a first reference level and the parameter planning value and the parameter actual value do not deviate by more than a second reference level. 5. The actual measurement information acquisition means further acquires sensor values that indicate the state of the vehicle while traveling based on the transportation plan, the sensor values being measured by sensors mounted on the vehicle; 3. The processing device according to 1 or 2, wherein the determining means determines whether or not the prediction model needs to be corrected based further on a result of comparing the sensor value with a reference value. 6. The sensor value is a value related to a driver's operation, The reference value indicates a value during standard operation, The processing device described in 5, wherein the determination means determines that the prediction model needs to be corrected if the fuel remaining amount prediction information and the fuel remaining amount actual measurement information deviate by more than a first reference level and the sensor value and the reference value do not deviate by more than a third reference level. 7. The processing device according to 6, wherein the determination means outputs a guide to encourage the driver to improve their operation when the sensor value and the reference value deviate by more than the third reference level. 8. The sensor value is a value related to the performance of the vehicle, the reference value indicates a standard performance value of the vehicle; The processing device described in 5, wherein the determination means determines that the prediction model needs to be corrected if the fuel remaining amount prediction information and the fuel remaining amount actual measurement information deviate by more than a first reference level and the sensor value and the reference value do not deviate by more than a fourth reference level. 9. The processing device according to 8, wherein the determination means outputs information notifying of a problem with the vehicle's performance when the sensor value and the reference value deviate by more than the fourth reference level. 10. The prediction information acquisition means further acquires parameter planning values, which are values of various parameters used to create the remaining fuel amount prediction information and are values planned based on the transportation plan; The actual measurement information acquisition means further acquires parameter actual values, which are actual values of the various parameters while traveling based on the transportation plan, the actual measurement information acquisition means further acquires sensor values that indicate the state of the vehicle while traveling based on the transportation plan, the sensor values being measured by sensors mounted on the vehicle; 3. The processing device according to claim 1 or 2, wherein the determination means determines whether or not the prediction model needs to be corrected based on the comparison result between the parameter planning value and the parameter actual value, and the comparison result between the sensor value and a reference value. 11. The computer a prediction information acquisition step of acquiring remaining fuel amount prediction information that indicates a transition of a predicted value of the remaining fuel amount of the vehicle when traveling based on the transportation plan and is created based on a prediction model; an actual measurement information acquisition step of acquiring remaining fuel amount actual measurement information indicating a change in the actual measurement value of the remaining fuel amount of the vehicle while the vehicle is traveling based on the transportation plan; a determination step of determining whether or not the prediction model needs to be corrected based on the remaining fuel amount prediction information and the remaining fuel amount actual measurement information; How to process. 12. Computer a prediction information acquisition means for acquiring remaining fuel amount prediction information that indicates a transition of a predicted value of the remaining fuel amount of the vehicle when traveling based on the transportation plan and is created based on a prediction model; an actual measurement information acquisition means for acquiring actual fuel remaining amount information indicating a change in the actual measurement value of the remaining fuel amount of the vehicle while the vehicle is traveling based on the transportation plan; a determination means for determining whether or not the prediction model needs to be corrected based on the remaining fuel amount prediction information and the remaining fuel amount actual measurement information; A program that functions as a [Explanation of symbols]

[0160] 10 Processing equipment 11. Prediction information acquisition unit 12 Measurement information acquisition unit 13 Judgment section 1A processor 2A Memory 3A input / output I / F 4A peripheral circuit 5A Bus

Claims

1. a prediction information acquisition means for acquiring remaining fuel amount prediction information that indicates a transition of a predicted value of the remaining fuel amount of the vehicle when traveling based on the transportation plan and is created based on a prediction model; an actual measurement information acquisition means for acquiring actual fuel remaining amount information indicating a change in the actual measurement value of the remaining fuel amount of the vehicle while the vehicle is traveling based on the transportation plan; a determination means for determining whether or not the prediction model needs to be corrected based on the remaining fuel amount prediction information and the remaining fuel amount actual measurement information; and The prediction information acquisition means further acquires parameter planning values, which are values of various parameters used to create the remaining fuel amount prediction information and are values planned based on the transportation plan; The actual measurement information acquisition means further acquires parameter actual values, which are actual values of the various parameters while traveling based on the transportation plan, The determination means is a processing device that determines whether or not the prediction model needs to be corrected, further based on a comparison result between the planned parameter value and the actual parameter value.

2. 2. The processing device according to claim 1, wherein the determination means determines that the prediction model needs to be corrected when the fuel remaining amount prediction information and the fuel remaining amount actual measurement information deviate by a first reference level or more, and the parameter planning value and the parameter actual value do not deviate by a second reference level.

3. a prediction information acquisition means for acquiring remaining fuel amount prediction information that indicates a transition of a predicted value of the remaining fuel amount of the vehicle when traveling based on the transportation plan and is created based on a prediction model; an actual measurement information acquisition means for acquiring actual fuel remaining amount information indicating a change in the actual measurement value of the remaining fuel amount of the vehicle while the vehicle is traveling based on the transportation plan; a determination means for determining whether or not the prediction model needs to be corrected based on the remaining fuel amount prediction information and the remaining fuel amount actual measurement information; and the actual measurement information acquisition means further acquires sensor values that indicate the state of the vehicle while traveling based on the transportation plan, the sensor values being measured by sensors mounted on the vehicle; The determination means is a processing device that determines whether or not the prediction model needs to be corrected, further based on a comparison result between the sensor value and a reference value.

4. the sensor value is a value related to a driver's operation, The reference value indicates a value during standard operation, 4. The processing device according to claim 3, wherein the determination means determines that the prediction model needs to be corrected when the fuel remaining amount prediction information and the fuel remaining amount actual measurement information deviate by a first reference level or more, and the sensor value and the reference value do not deviate by a third reference level.

5. the sensor value is a value related to performance of the vehicle, the reference value indicates a standard performance value of the vehicle; 4. The processing device according to claim 3, wherein the determination means determines that the prediction model needs to be corrected when the fuel remaining amount prediction information and the fuel remaining amount actual measurement information deviate by a first reference level or more, and the sensor value and the reference value do not deviate by a fourth reference level.

6. a prediction information acquisition means for acquiring remaining fuel amount prediction information that indicates a transition of a predicted value of the remaining fuel amount of the vehicle when traveling based on the transportation plan and is created based on a prediction model; an actual measurement information acquisition means for acquiring actual fuel remaining amount information indicating a change in the actual measurement value of the remaining fuel amount of the vehicle while the vehicle is traveling based on the transportation plan; a determination means for determining whether or not the prediction model needs to be corrected based on the remaining fuel amount prediction information and the remaining fuel amount actual measurement information; and The prediction information acquisition means further acquires parameter planning values, which are values of various parameters used to create the remaining fuel amount prediction information and are values planned based on the transportation plan; The actual measurement information acquisition means further acquires parameter actual values, which are actual values of the various parameters while traveling based on the transportation plan, the actual measurement information acquisition means further acquires sensor values that indicate the state of the vehicle while traveling based on the transportation plan, the sensor values being measured by sensors mounted on the vehicle; The determination means is a processing device that determines whether or not the prediction model needs to be corrected based on a comparison result between the planned parameter value and the actual parameter value, and a comparison result between the sensor value and a reference value.

7. The processing device according to any one of claims 1 to 6, wherein the remaining amount of fuel in the vehicle is indicated by an SOC (state of charge).

8. The computer a prediction information acquisition step of acquiring remaining fuel amount prediction information that indicates a transition of a predicted value of the remaining fuel amount of the vehicle when traveling based on the transportation plan and is created based on a prediction model; an actual measurement information acquisition step of acquiring remaining fuel amount actual measurement information indicating a change in the actual measurement value of the remaining fuel amount of the vehicle while the vehicle is traveling based on the transportation plan; a determination step of determining whether or not the prediction model needs to be corrected based on the remaining fuel amount prediction information and the remaining fuel amount actual measurement information; Run In the prediction information acquisition step, parameter planning values are further acquired, which are values of various parameters used to create the remaining fuel amount prediction information and are values planned based on the transportation plan; The actual measurement information acquisition step further acquires actual parameter values, which are actual values of the various parameters while traveling based on the transportation plan, In the determination step, the processing method determines whether or not the prediction model needs to be corrected based on the comparison result between the planned parameter values and the actual parameter values.

9. The computer a prediction information acquisition step of acquiring remaining fuel amount prediction information that indicates a transition of a predicted value of the remaining fuel amount of the vehicle when traveling based on the transportation plan and is created based on a prediction model; an actual measurement information acquisition step of acquiring remaining fuel amount actual measurement information indicating a change in the actual measurement value of the remaining fuel amount of the vehicle while the vehicle is traveling based on the transportation plan; a determination step of determining whether or not the prediction model needs to be corrected based on the remaining fuel amount prediction information and the remaining fuel amount actual measurement information; Run The actual measurement information acquisition step further acquires sensor values that indicate the state of the vehicle while traveling based on the transportation plan, the sensor values being measured by sensors mounted on the vehicle; In the determination step, the processing method determines whether or not the prediction model needs to be corrected based on the comparison result between the sensor value and a reference value.

10. The computer a prediction information acquisition step of acquiring remaining fuel amount prediction information that indicates a transition of a predicted value of the remaining fuel amount of the vehicle when traveling based on the transportation plan and is created based on a prediction model; an actual measurement information acquisition step of acquiring remaining fuel amount actual measurement information indicating a change in the actual measurement value of the remaining fuel amount of the vehicle while the vehicle is traveling based on the transportation plan; a determination step of determining whether or not the prediction model needs to be corrected based on the remaining fuel amount prediction information and the remaining fuel amount actual measurement information; Run In the prediction information acquisition step, parameter planning values are further acquired, which are values of various parameters used to create the remaining fuel amount prediction information and are values planned based on the transportation plan; The actual measurement information acquisition step further acquires actual parameter values, which are actual values of the various parameters while traveling based on the transportation plan, The actual measurement information acquisition step further acquires sensor values that indicate the state of the vehicle while traveling based on the transportation plan, the sensor values being measured by sensors mounted on the vehicle; In the determination step, the processing method determines whether or not the prediction model needs to be corrected based on the comparison result between the planned parameter value and the actual parameter value and the comparison result between the sensor value and a reference value.

11. Computer, a prediction information acquisition means for acquiring remaining fuel amount prediction information that indicates a transition of a predicted value of the remaining fuel amount of the vehicle when traveling based on the transportation plan and is created based on a prediction model; an actual measurement information acquisition means for acquiring actual measurement information on the remaining fuel amount, which indicates a change in the actual measurement value of the remaining fuel amount of the vehicle while the vehicle is traveling based on the transportation plan; a determination means for determining whether or not the prediction model needs to be corrected based on the remaining fuel amount prediction information and the remaining fuel amount actual measurement information; It functions as The prediction information acquisition means further acquires parameter planning values, which are values of various parameters used to create the remaining fuel amount prediction information and are values planned based on the transportation plan; The actual measurement information acquisition means further acquires parameter actual values, which are actual values of the various parameters while traveling based on the transportation plan, The determination means is a program that determines whether or not the prediction model needs to be corrected, further based on a comparison result between the planned parameter value and the actual parameter value.

12. Computer, a prediction information acquisition means for acquiring remaining fuel amount prediction information that indicates a transition of a predicted value of the remaining fuel amount of the vehicle when traveling based on the transportation plan and is created based on a prediction model; an actual measurement information acquisition means for acquiring actual measurement information on the remaining fuel amount, which indicates a change in the actual measurement value of the remaining fuel amount of the vehicle while the vehicle is traveling based on the transportation plan; a determination means for determining whether or not the prediction model needs to be corrected based on the remaining fuel amount prediction information and the remaining fuel amount actual measurement information; It functions as the actual measurement information acquisition means further acquires sensor values that indicate the state of the vehicle while traveling based on the transportation plan, the sensor values being measured by sensors mounted on the vehicle; The determination means is a program that determines whether or not the prediction model needs to be corrected based on the comparison result between the sensor value and a reference value.

13. Computer, a prediction information acquisition means for acquiring remaining fuel amount prediction information that indicates a transition of a predicted value of the remaining fuel amount of the vehicle when traveling based on the transportation plan and is created based on a prediction model; an actual measurement information acquisition means for acquiring actual measurement information on the remaining fuel amount, which indicates a change in the actual measurement value of the remaining fuel amount of the vehicle while the vehicle is traveling based on the transportation plan; a determination means for determining whether or not the prediction model needs to be corrected based on the remaining fuel amount prediction information and the remaining fuel amount actual measurement information; It functions as The prediction information acquisition means further acquires parameter planning values, which are values of various parameters used to create the remaining fuel amount prediction information and are values planned based on the transportation plan; The actual measurement information acquisition means further acquires parameter actual values, which are actual values of the various parameters while traveling based on the transportation plan, the actual measurement information acquisition means further acquires sensor values that indicate the state of the vehicle while traveling based on the transportation plan, the sensor values being measured by sensors mounted on the vehicle; The determination means is a program that determines whether or not the prediction model needs to be corrected based on the comparison result between the parameter planning value and the parameter actual value, and the comparison result between the sensor value and the reference value.

Images