Information processing program, information processing method, and information processing device

Abstract

To determine a service measure at no cost.SOLUTION: An information processing device 10 causes an agent corresponding to a person present in a real world to generate use experience of a service by performing a simulation regarding use of the service by the agent corresponding to the person in a digital twin in which the real world is reproduced on a virtual space. The information processing device 10 sets information regarding use intention of the service possessed by the agent corresponding to the person based on the generated use experience. The processing of the information processing device 10 can be applied to, for example, a case of examining a deployment measure for sharing mobility that has not yet spread.SELECTED DRAWING: Figure 3

Description

[Technical Field]

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

[0002] Before offering a new service, surveys are sometimes used as market research to investigate user experience and determine details about how the service will be provided.

[0003] There is also a technology called Digital Twin, which is used to represent objects that exist in the physical space of the real world in a virtual space. Digital Twin includes a method called an agent-based model, which virtually reproduces people, objects, and time-space and simulates their interactions. It is known that by combining such an agent-based model with a questionnaire survey, it is possible to reproduce the experience of using a service within a simulation. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2016-076125 Summary of the Invention [Problem to be solved by the invention]

[0005] To estimate people's intentions to use a service, based on changes in their service usage experience, it is necessary to conduct a survey before and after implementing some kind of service measure. However, conducting a survey to verify the effectiveness of a measure while it is still being implemented poses the problem of being costly in terms of time and money.

[0006] One aspect of the present invention is to enable service measures to be determined without incurring any costs. [Means for solving the problem]

[0007] In one aspect, the information processing program causes a computer to execute a process in which, in a digital twin that recreates the real world in a virtual space, a simulation is carried out regarding the use of a service by an agent corresponding to a person existing in the real world, thereby generating a usage experience of the service for the agent corresponding to the person, and setting information regarding the agent corresponding to the person's intention to use the service based on the generated usage experience. [Effects of the Invention]

[0008] On the one hand, it makes it possible to decide on service measures without incurring any costs. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram showing a reference example of a mobility sharing deployment policy. [Figure 2] FIG. 2 is a diagram showing a reference example of simulating the intention to use a service. [Figure 3] FIG. 3 is a diagram showing an example of the flow of a simulation according to this embodiment. [Figure 4] FIG. 4 is a diagram showing an example of the configuration of an information processing system according to this embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of the functional configuration of the information processing device according to this embodiment. [Figure 6] FIG. 6 is a diagram showing an example of the behavior selection model generation process according to this embodiment. [Figure 7] FIG. 7 is a diagram showing an example of usage intention estimation according to this embodiment. [Figure 8] FIG. 8 is a diagram showing an image of the movement reproduction process according to this embodiment. [Figure 9A] FIG. 9A is a diagram (1) showing an example of the usage experience update process according to this embodiment. [Figure 9B] FIG. 9B is a diagram (2) showing an example of the usage experience update process according to this embodiment. [Figure 9C] FIG. 9C is a diagram (3) showing an example of the usage experience update process according to this embodiment. [Figure 10] FIG. 10 is a diagram showing an example of the policy evaluation process according to this embodiment. [Figure 11] FIG. 11 is a diagram showing an example of a flowchart of a simulation according to this embodiment. [Figure 12] FIG. 12 is a diagram showing a specific example of usage experience update according to this embodiment. [Figure 13] FIG. 13 is a diagram showing an example of a flowchart of the policy evaluation process according to this embodiment. [Figure 14A] FIG. 14A is a diagram (1) showing a specific example of policy evaluation according to this embodiment. [Figure 14B] FIG. 14B is a diagram (2) showing a specific example of policy evaluation according to this embodiment. [Figure 15] FIG. 15 is a diagram showing an example of the effect of the simulation according to this embodiment. [Figure 16] FIG. 16 is a diagram illustrating an example of the hardware configuration of an information processing device. DETAILED DESCRIPTION OF THE INVENTION

[0010] Examples of the information processing program, information processing method, and information processing device according to the present embodiment will be described in detail below with reference to the accompanying drawings. Note that the present embodiment is not limited to these examples. Furthermore, the examples can be combined as appropriate within a consistent range.

[0011] First, we will explain the deployment measures for mobility sharing, which show how vehicle redeployment is carried out in vehicle (mobility) sharing services that are not yet widespread.

[0012] (Reference example of mobility sharing deployment measures) Figure 1 shows a reference example of a mobility sharing deployment policy. For example, when introducing a mobility sharing service to a new area, it is difficult to determine how many vehicles should be deployed. Therefore, a survey is conducted to investigate intentions. Service usage experience changes during the survey period and after the implementation of redeployment measures.

[0013] For example, suppose the operator of a mobility sharing service gathers information about past usage experiences through a survey. At Station A, there are few people who want to use the vehicles provided by the service, but there are many vehicles deployed. On the other hand, at Station B, there are many people who want to use the vehicles provided by the service, but there are few vehicles deployed. Therefore, the service operator will carry out redeployment based on the information gathered. However, because service usage experience changes, redeployment measures will be implemented in a situation where the service usage experience is unknown.

[0014] Here, to estimate people's intentions to use the service, indicating whether they want to use it or not, based on changes in their service usage experience, it is necessary to conduct a survey before and after the redeployment measures are actually implemented. However, conducting a survey to verify the effectiveness of a redeployment measure while it is being implemented involves the problem of being costly in terms of time and money. In other words, conducting a survey multiple times in a short period of time is not realistic.

[0015] It is known that by combining an agent-based model with a questionnaire survey, it is possible to reproduce the service usage experience within a simulation. For example, a technique called "Simulation Analysis on the Possibility of Introducing a One-Way Micro Electric Vehicle (MEV) Sharing System" has been disclosed (see https: / / doi.org / 10.2208 / jscejipm.71.I_805). This technique examines the possibility of introducing a one-way sharing system that does not involve redistribution (allowing drop-off) by building a trip replacement model and conducting an operational simulation analysis. To this end, a SP survey assuming MEV sharing was designed and implemented. Furthermore, an operational simulation program using the model has been developed, and its introduction feasibility is being examined.

[0016] A reference example using this technology is as follows: An information processing device estimates a behavioral choice model from the results of a questionnaire survey. The questionnaire contains information obtained by investigating decision-making (intention to use) regarding the level of service (LOS (Level Of Service)). LOS is a number that represents the level of service, such as the fee, number of units, and the probability that the service cannot be used. The information processing device then verifies the impact of the LOS on the use of the service using an agent simulation. In the agent simulation, the LOS (here, the number of units, the probability that the service cannot be used, etc.) changes from moment to moment depending on the results of using the service, and the change also changes the decision-making (intention to use).

[0017] Figure 2 is a diagram showing a reference example of simulating intentions to use a service. In the left diagram of Figure 2, an information processing device generates a behavioral selection model that estimates behavior from the results of a questionnaire. For example, the information processing device generates a behavioral selection model that estimates behavior using a questionnaire that investigates intentions to use the LOS of a service.

[0018] In the right diagram of FIG. 2, an information processing device verifies the influence of LOS on behavior through agent simulation. For example, the information processing device sets conditions for executing the agent simulation (S900). Then, the information processing device acquires LOS information in the virtual space for each agent corresponding to a person (S910). To select an action based on the LOS, the information processing device inputs the LOS information into a behavior selection model and estimates the action (S920, S930). The information processing device updates the LOS based on the results of the action taken in the virtual space (S940). In this case, the LOS that changes depending on the action taken by the agent corresponding to the person is, for example, the probability that a service cannot be used. Then, the information processing device repeats the process of acquiring LOS information (S910), the process of estimating the action (S930), and the process of updating the LOS (S940) any number of times, and outputs a KPI (Key Performance Indicator) (S950). The KPI is an evaluation index that indicates the results of the verification. This allows the information processing device to reproduce changes in LOS within the simulation and reproduce usage intentions based on the changed LOS. In addition, since the information processing device handles LOS as numbers, interpretation is also easy.

[0019] (Problems with the reference example) However, while the reference example can reproduce usage intentions based on changed LOS, it does not take into account the subjective meaning of the changed LOS, such as whether it is good or bad. In other words, the reference example does not take into account the evaluation of the experience in the behavior. Therefore, the technology of the reference example does not take into account changes in the evaluation of the experience.

[0020] Therefore, in the embodiment, a simulation method is described that can determine a service measure while virtually verifying the effect of the service measure by estimating the change in evaluation of the service usage experience and the intention to use the service due to the measure. That is, a simulation method is described that can determine a service measure without resurveying by questionnaire.

[0021] The simulation method described below will be for a mobility sharing service. The mobility vehicles that are the target of the mobility sharing service are, for example, electric scooters and electric motorcycles, but are not limited to these. Any vehicle that is not yet in widespread use and is eligible for sharing can be used.

[0022] (An example of a simulation flow using an information processing device) FIG. 3 is a diagram showing an example of the flow of a simulation according to this embodiment. This simulation is an agent simulation of service use by an agent corresponding to a person existing in the real world in a digital twin that recreates the real world in a virtual space. The simulation generates a service use experience for the agent corresponding to the person. Then, based on the generated usage experience, the simulation sets and updates information about the agent corresponding to the person's intention to use the service, which indicates whether or not the agent wishes to use the service.

[0023] In the left diagram of FIG. 3, the information processing device 10 generates a behavioral selection model that infers behavior from response information for each survey item in a questionnaire. Note that ordered logit, ordered probit, or the like may be applied as the behavioral selection model. For example, the information processing device 10 generates a behavioral selection model that infers behavior (use intention) using response information for each survey item in a questionnaire and response information on use intention. The response information includes subjective data and is expressed, for example, by numbers ranging from 1 to 5. Furthermore, the numbers 1 to 5 in the response information can be changed, and the depth of the level of the response information can also be changed.

[0024] In the right diagram of Fig. 3, the information processing device 10 verifies the influence of experience on behavior through agent simulation. For example, the information processing device 10 sets conditions for executing the agent simulation (S100). The conditions here are conditions as measures, and an example is the number of vehicles to be deployed per station of the mobility to be serviced (deployment number).

[0025] The information processing device 10 acquires information on the LOS of the virtual space and information on the surrounding environment for each agent corresponding to a person (S110). The information on the surrounding environment is, for example, information on the vehicle status and road status.

[0026] The information processing device 10 inputs evaluation information on the service usage experience into the behavior selection model to estimate the behavior (use intention) in order to select a behavior corresponding to the person (S120, S130). The evaluation information on the service usage experience here is information in which the experience of using the service in a simulation is reflected in the response information for each survey item in the questionnaire. Note that, for the first time, the evaluation information on the service usage experience is the response information for each survey item in the questionnaire immediately after the survey.

[0027] Then, the information processing device 10 updates the information on the LOS and the surrounding environment based on the results of the action taken in the virtual space (S140). Then, the information processing device 10 proceeds to step S110 to update the information on environmental changes that occur as a result of using the service.

[0028] Furthermore, the information processing device 10 quantifies the change in the service usage experience obtained from the behavioral results of the behavior in the virtual space (S150). Then, the information processing device 10 proceeds to step S130 to update the quantified change in the service usage experience. That is, by creating a loop structure in which the information processing device 10 estimates the usage intention based on the information on the changed service usage experience, the feelings of the agent corresponding to the person toward the service change, and the intention to use the service can be estimated based on the changed feelings.

[0029] Then, the information processing device 10 evaluates measures using the service usage experience (S160). The measures referred to here include, for example, adjusting the number of deployed mobility vehicles that are the subject of the service, or adjusting the battery recovery of the mobility vehicles that are the subject of the service. In other words, by using the service usage experience to evaluate the measures, the information processing device 10 can allow the service operator to consider the merits and demerits of the proposed measures obtained by the evaluation. Then, the information processing device 10 updates the conditions with the evaluation results (S160).

[0030] As a result, the information processing device 10 can generate service usage experiences through simulation and reflect them in the agent, thereby updating changes in service usage experiences without re-surveying the questionnaire. Furthermore, the information processing device 10 can determine service measures at no cost. That is, the service operator can consider proposed measures through trial and error based on changes in virtual service usage intentions.

[0031] (Functional configuration of information processing system) Next, an information processing system for carrying out such an embodiment will be described. Fig. 4 is a diagram showing an example of the configuration of the information processing system according to this embodiment. As shown in Fig. 4, the information processing system 1 is a system in which, for example, an information processing device 10 and information processing terminals 100-1 to 100-N (N is an arbitrary natural number, hereinafter collectively referred to as "information processing terminals 100") are connected via a network 50 so as to be mutually usable.

[0032] Various communication networks such as the Internet can be used for the network 50. Furthermore, the network 50 may not be a single network, but may be configured, for example, by connecting an intranet and the Internet via a network device such as a gateway or other device (not shown).

[0033] The information processing terminal 100 is, for example, a mobile terminal such as a smartphone or tablet PC (Personal Computer) carried by a respondent to a questionnaire. For example, an application for responding to a questionnaire may be pre-installed in the information processing terminal 100. The information processing terminal 100 may then display a questionnaire screen via the application and respond to the questionnaire. Alternatively, the information processing terminal 100 may access, for example, a website or application for conducting a questionnaire and respond to the questionnaire. In this case, the information processing terminal 100 may not have an application for responding to the questionnaire installed.

[0034] The information processing device 10 is, for example, an information processing device such as a desktop PC, a notebook PC, or a server computer that is installed in the facilities of a service operating company or the like and used by a service operator or the like. Note that while FIG. 4 illustrates the information processing device 10 as a single computer, it may also be a distributed computing system made up of multiple computers. Furthermore, the information processing device 10 may also be a cloud computer device managed by a service provider that provides cloud computing services.

[0035] (Functional configuration of information processing device) Next, a functional configuration of the information processing device 10 will be described. Fig. 5 is a diagram showing an example of the functional configuration of the information processing device according to this embodiment. As shown in Fig. 5, the information processing device 10 has a communication unit 20, a storage unit 30, and a control unit 40.

[0036] The communication unit 20 is a processing unit that controls communication with other information processing devices such as the information processing terminal 100, and is, for example, a communication interface such as a network interface card or a USB (Universal Serial Bus) interface.

[0037] The storage unit 30 has a function of storing various data and programs executed by the control unit 40, and is realized by a storage device such as a memory or a hard disk. The storage unit 30 stores travel history data 31, questionnaire response results 32, behavior selection model parameters 33, road network map information 34, vehicle information 35, and the like.

[0038] The travel history data 31 is data indicating the travel history of each agent corresponding to a person. The travel history data 31 includes information such as the departure point, destination, departure time, time for each movement, and location information for each agent corresponding to a person. The location information is represented, for example, by coordinate data on a map in road network map information 34, which will be described later. The departure point, destination, and departure time are obtained, for example, from questionnaire response results 32 of a questionnaire, which will be described later.

[0039] The questionnaire response results 32 are data of response results corresponding to survey items regarding intention to use the service and usage experience. The survey items include not only intention to use the service and usage experience, but also social attribute information such as age and gender, and information regarding actual travel and transportation methods used. Such information may include information such as the departure point, destination, and departure time of the travel source. The questionnaire response results 32 are an example of information regarding intention to use the service.

[0040] Examples of survey items regarding usage experience in the questionnaire include "Do you think the service is easy to use?" and "Do you think there is a large number of vehicles?". Examples of survey items regarding usage intention in the questionnaire include "Would you like to try using the service?". The response information to the questionnaire is expressed, for example, on a scale of 1 to 5.

[0041] The behavioral selection model parameters 33 are parameters used in the behavioral selection model. The behavioral selection model parameters 33 are coefficients that explain the intention to use a service, and are set for each explanatory variable corresponding to a survey item. The behavioral selection model parameters 33 are set in advance before learning. The behavioral selection model parameters 33 will be described later.

[0042] The road network map information 34 is information that represents a road network on a map. For example, road network data may be acquired from Open Street Map (OSM) or the like. Map data may be acquired from the Folium library or the like.

[0043] Vehicle information 35 is information about mobility (vehicles) shared in the mobility sharing service. For example, vehicle information 35 includes, for each station, the number of vehicles deployed, the number in stock, the maximum number, the number of vehicles loaned, the number of vehicles returned, and the location information of each station. Examples of vehicles that can be shared include electric scooters and electric motorcycles. Note that the "number of deployed vehicles" here refers to the number of vehicles deployed at a station through a policy. The "number in stock" refers to the number of vehicles present at a station.

[0044] The control unit 40 has a behavior selection model generation unit 41, a data acquisition unit 42, a behavior selection unit 43, a movement reproduction unit 44, a vehicle state update unit 45, a vehicle management unit 46, a usage experience update unit 47, and a policy evaluation unit 48. The behavior selection unit 43, the movement reproduction unit 44, the vehicle state update unit 45, and the vehicle management unit 46 are examples of a simulation unit. The usage experience update unit 47 is an example of a setting unit.

[0045] The behavioral selection model generation unit 41 generates a behavioral selection model using the questionnaire response results 32. For example, the behavioral selection model generation unit 41 generates a behavioral selection model by training using data on service usage experience from the questionnaire response results 32 as features and data on service usage intention from the questionnaire response results 32 as correct labels.

[0046] An example of the behavioral selection model generation process will now be described with reference to FIG. 6. FIG. 6 is a diagram illustrating an example of the selection behavior model generation process according to this embodiment. As shown in FIG. 6, questionnaire response results 32 are shown. The behavioral selection model generation unit 41 trains the model using data related to service usage experience from the questionnaire response results 32 as explanatory variables and data related to service usage intention from the questionnaire response results 32 as explained variables. Here, the behavioral selection model generation unit 41 trains the model using response information indicating whether the service is available smoothly and whether there is an abundance of vehicles, as well as social attribute information, which are shown in the questionnaire response results 32, as explained variables and using response information related to usage intention from the questionnaire response results 32 as explained variables. Parameters corresponding to the explanatory variables are stored in the behavioral selection model parameters 33 and set in the behavioral selection model. The behavioral selection model generation unit 41 then inputs information related to the service usage experience to generate a behavioral selection model that estimates service usage intention.

[0047] Here, we will explain the parameters. Parameters are coefficients that explain the intention to use a service, and are set for each explanatory variable corresponding to a survey item. When the parameter is a positive value, it means that the higher the value of the explanatory variable (1 to 5), the higher the possibility of intention to use. When the parameter is a negative value, it means that the higher the value of the explanatory variable (1 to 5), the lower the possibility of intention to use. In this example, when the explanatory variable is "Do you think the service can be used smoothly?", the parameter is a positive value (0.42), so the higher the value of the explanatory variable, the higher the possibility of intention to use. In contrast, when the explanatory variable is "age...", the parameter is a negative value (-0.29), so the higher the value of the explanatory variable, the lower the possibility of intention to use.

[0048] Returning to FIG. 5, the data acquisition unit 42 acquires data used to perform a simulation for an agent corresponding to a person. For example, the data acquisition unit 42 acquires the departure point, destination, departure time, and location information of the agent corresponding to the target person from the movement history data 31. The data acquisition unit 42 also acquires questionnaire data of the target person from the questionnaire response results 32. The questionnaire data includes data on service usage experience and data on social attribute information. In other words, the data acquisition unit 42 acquires data for generating an agent that is aggregated as information on an individual basis.

[0049] The behavior selection unit 43 selects a behavior using a behavior selection model. For example, the behavior selection unit 43 inputs questionnaire data of the target person into a trained behavior selection model to estimate the target person's intention to use the service. Then, the behavior selection unit 43 selects a means of transportation using the intention to use the service and the target person's coordinate data. As an example, if the intention to use the service indicates that the target person will use the service, the behavior selection unit 43 inquires of the vehicle management unit 46 (described later) whether the target person can borrow a vehicle from the service based on the target person's coordinate data. If the vehicle from the service can be borrowed, the behavior selection unit 43 sets the vehicle from the service as the means of transportation. If the intention to use the service indicates that the target person will not use the service or if the vehicle from the service cannot be borrowed, the behavior selection unit 43 acquires information on another means of transportation from the travel history data 31 and sets the vehicle as the acquired means of transportation.

[0050] An example of usage intention estimation will now be described with reference to FIG. 7. FIG. 7 is a diagram illustrating an example of usage intention estimation according to this embodiment. The behavior selection unit 43 inputs questionnaire data of a target person into a trained behavior selection model to estimate the usage intention of a service. As shown in FIG. 7, the behavior selection unit 43 inputs social attribute information and data related to service usage experience in the questionnaire response results 32 of the target person as explanatory variables into the trained behavior selection model. Here, the data related to the usage experience of the service is response information indicating whether the service can be used smoothly and response information indicating whether there is an abundant number of vehicles. Then, the behavior selection unit 43 estimates the usage intention using the trained behavior selection model. That is, the behavior selection unit 43 estimates the usage intention (1 to 5) using the values ​​of the explanatory variables (1 to 5) and the values ​​of the parameters associated with the explanatory variables.

[0051] Returning to FIG. 5, the movement reproduction unit 44 reproduces the movement of people and mobility in the digital twin. For example, the movement reproduction unit 44 reproduces in a virtual space objects corresponding to facilities obtained from the target person's social attribute information and vehicle information 35. The virtual space referred to here may be generated from map data and road network data, for example. The facilities referred to here include, for example, the target person's home and service stations. The movement reproduction unit 44 then places an agent corresponding to the target person in the virtual space of the digital twin and associates the placed agent with current coordinates, current time, departure point, destination, departure time, social attribute information such as age and gender, and survey data including survey responses.

[0052] The movement reproducing unit 44 also uses a route generation tool to determine a movement route on a road network based on the means of transportation from the departure point and destination associated with the agent. The route generation tool may be, for example, a tool or library that can utilize a route generation algorithm, such as Open Trip Planner or OSMNX. The movement reproducing unit 44 then reproduces in a virtual space the movement of the agent along the movement route by the means of transportation. In other words, the movement reproducing unit 44 reproduces, through simulation, the experience of the agent corresponding to the person with the service.

[0053] The travel reproduction unit 44 also notifies the usage experience update unit 47 of the travel distance traveled by the means of transportation, route information, and information on usage experience. Examples of the information on usage experience include "the number of vehicles available for sharing as a means of transportation is low" and "sharing was not available," and "the number of vehicles available for sharing as a means of transportation is high" and "sharing was available." Other examples of the information on usage experience include "the station was very crowded" and "the station was not very crowded."

[0054] Here, an image of the movement reproduction process will be explained with reference to FIG. 8. FIG. 8 is a diagram showing an image of the movement reproduction process according to this embodiment. As indicated by reference numeral g1 in FIG. 8, the movement reproduction unit 44 generates the foundation of the virtual space in the digital twin using the road network map information 34. The virtual space is, for example, <1> Map data and <2> It may be generated from road network data.

[0055] Next, as indicated by reference symbol g2, the movement reproduction unit 44 reproduces the basic data of the target sharing service on the basis of the virtual space in order to reproduce the provision of the service. For example, the movement reproduction unit 44 reproduces an object corresponding to a station obtained from the vehicle information 35 in the virtual space. Then, the movement reproduction unit 44 sets, for example, the station's coordinate data, the number of vehicles deployed, the number of vehicles in stock, the maximum number of vehicles, etc., in the object corresponding to the station. The dot indicated by reference symbol g2 represents the station.

[0056] Next, as shown by reference symbol g3, the movement reproducing unit 44 performs the following to represent the movement of the agent: <4> Using the route generation tool, <2> The travel route on the road network is determined according to the means of travel. For example, the travel reproduction unit 44 acquires the starting point and destination from the questionnaire data of the agent corresponding to the person, and uses a route generation tool to generate the travel route on the road network. <2> The travel route is determined according to the means of transportation.

[0057] Then, as indicated by reference symbol g4, ​​the movement reproduction unit 44 reproduces in the virtual space the movement of the agent corresponding to the target person from the departure point to the destination by transportation means. The group of black dots indicated by reference symbol g4 is the trajectory of the movement of the agent corresponding to the target person. The movement reproduction unit 44 stores the time and coordinate data for each movement in the movement record data 31 corresponding to the agent.

[0058] Returning to FIG. 5, the vehicle status update unit 45 updates the vehicle status of the transportation means of the target sharing service. For example, if the transportation means is a vehicle that is a target of the service, the vehicle status update unit 45 calculates the vehicle status, such as the battery status, based on the distance traveled by the vehicle after travel. The vehicle status update unit 45 also searches for information on the return destination of the vehicle based on the coordinate data of the destination after travel by the vehicle. The vehicle status update unit 45 then outputs the remaining battery charge and the return destination information of the vehicle to the vehicle management unit 46.

[0059] The vehicle state update unit 45 also notifies the usage experience update unit 47 of information on the service usage experience, such as the remaining battery level.

[0060] The vehicle management unit 46 manages vehicles.

[0061] For example, in response to an inquiry from the behavior selection unit 43, the vehicle management unit 46 determines whether the target person can rent a vehicle from the sharing service based on the target person's coordinate data. As an example, the vehicle management unit 46 references the vehicle information 35 and acquires the number of vehicles in stock corresponding to stations close to the target person's departure point. The vehicle management unit 46 then uses the acquired number of vehicles in stock to determine whether the vehicle from the service can be rented. If the vehicle from the service can be rented, the vehicle management unit 46 rents the vehicle from the service, notifies the behavior selection unit 43 that originated the inquiry that the vehicle has been rented, and decrements the number of vehicles in stock corresponding to the relevant station stored in the vehicle information 35. If the vehicle from the service can be rented, the vehicle management unit 46 notifies the behavior selection unit 43 that originated the inquiry that the vehicle cannot be rented.

[0062] Furthermore, when vehicle management unit 46 receives vehicle return destination information from vehicle status update unit 45, it increments the inventory number corresponding to the relevant station in order to return the target vehicle to the target station. When vehicle management unit 46 receives the remaining battery charge of a vehicle from vehicle status update unit 45, it updates the remaining battery charge of the vehicle returned to the relevant station.

[0063] The usage experience update unit 47 updates the evaluation information of the service usage experience. For example, the usage experience update unit 47 evaluates the service usage experience by the agent corresponding to the target person. The evaluation of the usage experience of the service used is performed, for example, for each survey item (explanatory variable) of a questionnaire. Then, the usage experience update unit 47 adds or subtracts from the value of the questionnaire response information according to the usage experience, thereby updating the value. Then, the usage experience update unit 47 updates the evaluation information to the questionnaire response result 32.

[0064] An example of the usage experience update process will now be described with reference to Figures 9A to 9C. Figures 9A to 9C are diagrams showing an example of the usage experience update process according to this embodiment.

[0065] As shown in Figure 9A, the personal IDs "0" and "1" are IDs that identify a person. h0 is the survey response result 32 that was set based on the experience at the time of answering the survey. h1 is the survey response result 32 that has been updated based on the experience generated by the simulation. When the personal ID is "0", "Yes" is set for the survey item "a) Have you used sharing in the past?", indicating that you have used it. When the survey item is "b) Have you been unable to use sharing?", "No" is set, indicating that you were able to use it. When the survey item is "c) Do you think there is a large number of units in stock?", "3" is set, indicating that you are neither.

[0066] Under these circumstances, suppose that a person with personal ID "0" experiences a situation in the simulation where there are not enough units and sharing is not available. In this case, the usage experience update unit 47 adds or subtracts from the value of the questionnaire response information according to the usage experience, and updates the value. Here, based on the experience generated by the simulation, the survey item "b) Was sharing not available?" is updated to "Yes," indicating that it was not available. The survey item "c) Do you think there are a lot of units in stock?" is decremented by 1, and updated to "2," indicating that it is not available. Note that the survey item "a) Have you used sharing in the past?" remains "Yes," unchanged from when the survey was answered.

[0067] If the personal ID is "1", the survey item "a) Have you ever used sharing in the past?" is set to "No", indicating that you have not used it. The survey item "b) Have you been unable to use sharing?" is set to "No", indicating that you were unable to use it. The survey item "c) Do you think there are a lot of units in stock?" is set to "4", indicating that you think so.

[0068] Under these circumstances, suppose that a person with personal ID "1" had an experience in the simulation where there were a large number of units and sharing was possible. In this case, the usage experience update unit 47 adds or subtracts from the value of the questionnaire response information according to the usage experience, and updates the value. Here, based on the experience generated by the simulation, the survey item "a) Have you used sharing in the past?" is updated to "Yes," indicating "I have used it." The survey item "c) Do you think there are a large number of units in stock?" is added by 1, and updated to "5," indicating "I strongly agree." Note that the survey item "b) Were you unable to use sharing?" remains "No," unchanged from when the survey was answered.

[0069] As mentioned above, experiences can be expressed in terms of presence or absence, such as Yes / No, or in terms of ranking, such as 1 to 5.

[0070] FIG. 9B explains a case where experience can be expressed by presence or absence. Experience that can be expressed by presence or absence can be expressed as a binary value. The upper diagram of FIG. 9B shows an example of whether or not there has been past experience. One example is the case of "a" shown in FIG. 9A, "Have you used sharing in the past?" In such a case, the usage experience update unit 47 regards the target event in the simulation as an experience, and if it determines that there has been experience even once, it overwrites and updates it to "Yes" and maintains that value thereafter. In this case, since it was determined that there was experience of sharing on the second day, the value of "Yes" is maintained from the second day onwards.

[0071] The lower diagram of FIG. 9B shows an example in which an experience corresponding to a situation that occurred during the simulation can be expressed as the presence or absence of the experience. One example is the case of "b" "Was sharing not available?" shown in FIG. 9A. In such a case, the usage experience update unit 47 regards the target event in the simulation as an experience, judges the experience at any timing, and updates the value. Here, since it was determined that there was an experience that sharing was not available on the second day, "Yes" is updated, and since it was determined that there was no experience that sharing was not available on the third day, "No" is updated.

[0072] FIG. 9C illustrates a case where the experience is ranked. Ranked experiences can be expressed, for example, by numerical values ​​on an ordinal scale of 1 to 5. The left diagram in FIG. 9C shows the update of experience when the parameters of the explanatory variables (survey items) set in the behavioral selection model are positively related. In this case, the occurrence of an experience leads to an increase in usage intention. In other words, as the experience rating increases, the usage intention also increases. An example is the case of "c) Is there a large number of units in stock?" shown in FIG. 9A. In this case, the usage experience update unit 47 evaluates the number of units in stock, and if it determines that the number of units in stock is sufficient, it adds 1 to the evaluation value, and if it determines that the number of units is insufficient, it subtracts 1 from the evaluation value. That is, suppose the evaluation of the experience relative to the number of units in stock at the time of answering the questionnaire was "2." If it is determined that the number of units in stock is sufficient, the evaluation of the experience relative to the number of units in stock is updated to "3" by adding 1 from "2." Therefore, when this evaluation value is substituted into the behavioral selection model, the usage intention increases.

[0073] The right diagram of Figure 9C shows the update of experience when the parameters of the explanatory variables (survey items) set in the behavioral selection model are in a negative relationship. In this case, when an experience occurs, the intention to use decreases. In other words, as the experience rating increases, the intention to use decreases. As an example, consider a case where a question is asked about "station congestion." In this case, the usage experience update unit 47 evaluates the congestion experience, and if it determines that the congestion is high, it adds 1 to the evaluation value, and if it determines that the congestion is low, it subtracts 1 from the evaluation value. That is, suppose the evaluation of the experience regarding station congestion when the questionnaire was answered was "3." If it is determined that the congestion is high, the evaluation of the experience regarding station congestion is updated to "4" by adding 1 to "3." Therefore, when this evaluation value is substituted into the behavioral selection model, the intention to use decreases.

[0074] Returning to FIG. 5, the policy evaluation unit 48 evaluates the policy based on the simulation results. For example, the policy evaluation unit 48 identifies the state of the target for which the policy is to be introduced based on the simulation results. The policy here refers to, for example, adjusting (redeploying) the number of mobility vehicles at stations or adjusting the battery recovery of mobility vehicles. If the policy is adjusting the number of mobility vehicles at stations, the target for which the policy is to be introduced refers to, for example, the number of vehicles deployed at each station or the number of people who intend to use the mobility vehicles. If the policy is adjusting the battery recovery of mobility vehicles, the target for which the policy is to be introduced refers to, for example, the remaining battery power of mobility vehicles at each station. Then, the policy evaluation unit 48 displays information regarding the evaluation result of the policy on the display screen based on the state of the target for which the policy is to be introduced.

[0075] As an example, the policy evaluation unit 48 tally, for each station, the number of people who intend to use the service, as output by the behavior selection model, for people whose departure point is nearby. The policy evaluation unit 48 generates a priority list of redeployment stations for each station in descending order of "number of people intending to use the service - number of deployed vehicles" (number of vehicles in short supply). That is, the policy evaluation unit 48 generates a priority list of redeployment stations in descending order of the number of vehicles in short supply. The policy evaluation unit 48 then selects a station i to be prioritized from the priority list. The policy evaluation unit 48 then performs redeployment processing starting with station j, which is lowest in the priority list. In the redeployment processing, if the distance between station i and station j is an allowable distance and the number of deployed vehicles at station j is large, one vehicle is moved from station j to station i, as set in information about the evaluation results of the policy. In the redeployment processing, if the number of deployed vehicles at station i is still insufficient, one vehicle is moved from station j to station i if the number of deployed vehicles at station j is large. On the other hand, in the redeployment process, if the number of deployed units at station i is still insufficient, when the number of deployed units at station j runs out, the next lower station j is selected and the redeployment process is carried out. In this way, the policy evaluation unit 48 carries out the redeployment process in descending order of the number of units that are in short supply. Then, the policy evaluation unit 48 displays information related to the evaluation results of the policy on the display screen. Note that the policy evaluation unit 48 may use the number of units in stock instead of the number of deployed units.

[0076] Furthermore, the policy evaluation unit 48 updates the information on the evaluation results of the policy in the vehicle information 35 based on the displayed display screen. This allows the policy evaluation unit 48 to support the evaluation and consideration of the policy for each station. Note that the service operator may manually update the information on the evaluation results of the policy in the vehicle information 35 while referring to the display screen.

[0077] An example of the policy evaluation process will now be described with reference to Fig. 10. Fig. 10 is a diagram showing an example of the policy evaluation process according to this embodiment. As shown in Fig. 10, at the time of the questionnaire survey, three people at station B indicated an intention to use the service. Therefore, when N days have passed since the time of the survey, the operator of the service implements a redeployment measure to move three mobilities from station A to station B. It is assumed that one mobility is deployed at station A and three mobilities are deployed at station B.

[0078] Under these circumstances, suppose a simulation is conducted N days after the survey. Three people are found to have expressed an intention to use the service at station A. At station B, only one person is found to have expressed an intention to use the service. Therefore, the policy evaluation unit 48 proposes a revised policy to move two vehicles from station B to station A. The service operator can then refer to the proposed revision and ultimately decide on the policy direction.

[0079] (Simulation flowchart) Here, a flowchart of a simulation in a mobility sharing service performed by the information processing device 10 will be described with reference to Fig. 11. Fig. 11 is a diagram showing an example of a flowchart of a simulation according to this embodiment. It is assumed that the behavior selection model has already been trained. Also, Fig. 11 will be described by distinguishing between agents corresponding to people (human agents), agents corresponding to stations (station agents), and agents corresponding to mobility (mobility agents).

[0080] As shown in FIG. 11, the information processing device 10 executes processing for agents corresponding to N people. The following flowcharts show the processing for an agent corresponding to one person. For a human agent, the information processing device 10 determines whether to select a service for the target agent (step S11). For example, the information processing device 10 inputs the questionnaire response results 32 of the person corresponding to the target agent into a trained behavior selection model to estimate the intention to use the service. Then, the information processing device 10 determines to select the service if the intention to use the service indicates that the service will be used, and determines not to select the service if the intention to use the service indicates that the service will not be used.

[0081] If it is determined that the service is selected (step S11; Yes), the information processing device 10 inquires of the station agent to collect information on whether the service is available at a station near the departure point (step S12). The departure point of the target agent is included in the questionnaire response result 32, for example.

[0082] In the station agent, the information processing device 10 lists stations within a certain range and collects information (step S13). The collected information includes, for example, the location of each station and the number of mobility vehicles in stock. The information processing device 10 then refers to the collected information and determines whether rental is available at a station near the departure point (step S14). If it is determined that rental is not available (step S14; No), the information processing device 10 proceeds to step S23 to start traveling with another mobility vehicle. Note that the other mobility vehicle may be searched for, for example, from the questionnaire response results 32.

[0083] On the other hand, if it is determined that the mobility is available for rental (step S14; Yes), the information processing device 10 starts sharing with the rented mobility (step S15).Then, the information processing device 10 deletes the rented bike object corresponding to the mobility to be serviced from the number of bikes in stock at the station (step S16).

[0084] In the case of the human agent, the information processing device 10 reproduces the movement of the person and mobility through sharing (step S17). That is, the information processing device 10 generates an experience of using a mobility service for the target agent. Then, the information processing device 10 inquires of the station agent to collect information on whether the vehicle can be returned at a station near the destination (step S18). The destination of the target agent is included in the questionnaire response result 32, for example.

[0085] In the station agent, the information processing device 10 lists stations within a certain range and collects information (step S19). The collected information includes, for example, the location of each station, the number of mobility vehicles to be returned, and the maximum number of vehicles that can be returned. The information processing device 10 then refers to the collected information and determines whether or not the vehicle can be returned to a station near the destination using the maximum number of vehicles in the collected information (step S20). If it determines that the vehicle cannot be returned (step S20; No), the information processing device 10 proceeds to step S18 to collect information.

[0086] On the other hand, if it is determined that the bike object is returnable (step S20; Yes), the information processing device 10 returns the bike object to a station where it can be returned, and adds the bike object to the number of bikes in stock at the station (step S21).Then, the information processing device 10 ends the mobility sharing (step S22).Then, the information processing device 10 proceeds to step S24.

[0087] If the human agent determines that the service is not to be selected (step S11; No), the information processing device 10 reproduces the movement with another mobility (step S23). The other mobility may be searched for from the questionnaire response results 32. Then, the information processing device 10 proceeds to step S24.

[0088] In step S24, the information processing device 10 ends the movement reproduction (step S24).Then, the information processing device 10 updates the evaluation of the service usage experience to the questionnaire response result 32 (step S25).

[0089] Here, a specific example of updating the evaluation of the usage experience of a target agent will be described with reference to FIG. 12. FIG. 12 is a diagram showing a specific example of updating the usage experience according to this embodiment. The questionnaire response result 32 includes the following survey item regarding the experience of the service: Is there a large number of units in stock? <ii>This includes whether or not you have experience using the service. The current answer to this question is set to "3," which indicates that the inventory is neither high nor low. <ii>The current answer to this question is "No," which indicates that the user has no experience using the service.

[0090] Under such circumstances, the information processing device 10 inputs the questionnaire response results 32 of the person corresponding to the target agent into a trained behavioral selection model (m0) to estimate the intention to use the service. The method (m1) of the intention to use may be expressed as a binary value of "yes" or "no", or may be expressed on an ordinal scale such as 1 to 5.

[0091] Then, the information processing device 10 generates an action (m2) based on the predicted value and selection probability obtained from the usage intention (m1). The action here may be, for example, traveling by the mobility of the service target or traveling by another means of transportation. Then, the information processing device 10 generates various usage experiences of the service for the target agent (m3).

[0092] Then, the information processing device 10 calculates an updated value based on the usage experience (m4). The method for calculating the updated value is, for example, as follows. Regarding the above, there is a tendency for intentions to increase when there are a large number of units in stock (for example, If the parameter is positive, the update value is calculated as "+1" if the inventory quantity is determined to be two or more, and "-1" if the inventory quantity is determined to be any other way. <ii>Regarding this, if there is usage experience, the updated value is calculated as "yes", and if there is no usage experience, the updated value is calculated as "no".

[0093] Here, it is assumed that a service has been used, but the number of mobility vehicles available for the service is low. In this case, the information processing device 10 performs the following update based on the update method: In addition, the information processing device 10 calculates the update value for "-1" based on the update method. <ii>The updated value for is calculated as "yes".

[0094] Then, the information processing device 10 updates the evaluation of the service usage experience to the questionnaire response result 32. For , the value "2" obtained by subtracting "1" from "3" is updated. <2> For the above, "yes" is updated.

[0095] This allows the information processing device 10 to update the change in the service usage experience without having to re-survey the questionnaire.

[0096] (Flowchart of policy evaluation process) Here, a flowchart of the policy evaluation process performed by the information processing device 10 will be described with reference to Fig. 13. Fig. 13 is a diagram showing an example of a flowchart of the policy evaluation process according to this embodiment. It is assumed that a simulation has been executed. Also, the flowchart describes a case where the policy evaluation process is executed using the number of inventory units, but the number of deployment units may be used instead of the number of inventory units.

[0097] As shown in FIG. 13, the information processing device 10 counts, for each station, the number of intending users among people located near each station (step S31). The number of intending users is the number of people who intend to use the service among the intentions to use output by the behavior selection model. The information processing device 10 generates a priority list of redeployment stations in descending order of "number of intending users - number of units in stock" (step S32). That is, the information processing device 10 generates a priority list of redeployment stations in descending order of the number of units in short supply.

[0098] The information processing device 10 processes from the highest-priority station i in the highest priority list (step S33). The information processing device 10 determines whether "number of intending users i - number of units in stock i" is greater than 0 (step S34). That is, the information processing device 10 determines whether there is a shortage of stock at the station i with priority for redeployment. The number of intending users i here is the number of intending users at station i. The number of units in stock i is the number of units in stock at station i.

[0099] If it is determined that "number of intending users i - number of vehicles in stock i" is greater than 0 (step S34; Yes), the information processing device 10 performs the following processes starting from station j, which is at the bottom of the redeployment priority list, to generate a redeployment plan (step S35). This is because there is a shortage of stock at station i, which has priority for redeployment. The information processing device 10 determines whether or not the distance between stations i and j is an acceptable travel distance (step S36). The coordinate data of stations i and j on the map in the road network map information 34 is stored, for example, in the vehicle information 35. Whether or not the distance is an acceptable travel distance may be determined using a predetermined specified value.

[0100] If it is determined that the distance between stations i and j is an acceptable distance for movement (step S36; Yes), the information processing device 10 determines whether "number of intending users j - number of vehicles in stock j" is less than 0 (step S37). That is, the information processing device 10 determines whether there is a surplus in stock on the station j side. If it is determined that "number of intending users j - number of vehicles in stock j" is less than 0 (step S37; Yes), the information processing device 10 moves one vehicle from station j to station i to redeploy vehicles (step S38). This is because there is a surplus in stock on the station j side. For example, the information processing device 10 sets information related to the evaluation results of the policy to move one vehicle from station j to station i.

[0101] Then, the information processing device 10 determines whether "intending number of people i - inventory quantity i" is greater than 0 (step S39). That is, the information processing device 10 determines whether there is a shortage of inventory at the redeployment target station i. If it is determined that "intending number of people i - inventory quantity i" is greater than 0 (step S39; Yes), the information processing device 10 proceeds to step S37 because there is still a shortage of inventory at the redeployment priority station i.

[0102] On the other hand, if it is determined that "number of intending users i - number of units in stock i" is not greater than 0 (step S39; No), the information processing device 10 proceeds to step S42 because there is no shortage of stock at the redeployment priority station i.

[0103] In step S36, if it is determined that the distance between stations i and j is not an allowable movement distance (step S36; No), the information processing device 10 subtracts 1 from j so that the next redeployment proceeds to a station with a lower priority (step S40). Then, the information processing device 10 determines whether stations i and j are the same (step S41). If it is determined that stations i and j are not the same (step S41; No), the information processing device 10 proceeds to step S35.

[0104] On the other hand, if it is determined that stations i and j are the same (step S41; Yes), the information processing device 10 proceeds to step S42 to terminate the redeployment of station i with redeployment priority, because station i cannot be redeployed by station j.

[0105] In step S42, the information processing device 10 ends the redeployment of station i and increments i by 1 (step S42). Then, the information processing device 10 proceeds to step S33 to process the next redeployment target station i.

[0106] In step S34, if it is determined that "number of intending users i - number of units in stock i" is not greater than 0 (step S34; No), the information processing device 10 terminates the policy evaluation process because there is no shortage of stock at the redeployment priority station i.

[0107] In the flowchart shown in Figure 13, the information processing device 10 automatically implements a redeployment measure for each station, but this is not limited to this, and the redeployment measure for each station may also be implemented using a user interface between the user and the information processing device 10.

[0108] (Specific examples of policy evaluation) 14A and 14B are diagrams showing a specific example of the policy evaluation according to the present embodiment. Note that, in Fig. 14A and Fig. 14B, a case where a redeployment policy for each station is evaluated using a user interface between a user and the information processing device 10 will be described.

[0109] The right diagram in FIG. 14A shows a priority list L0 for each station after the simulation is performed. For example, the information processing device 10 calculates the relationship between the number of intended users and the number of deployed vehicles for each station. That is, the information processing device 10 generates a priority list L0 of redeployment stations for each station using the number of vehicles in short supply, which is the value obtained by subtracting the number of deployed vehicles from the number of intended users. The redeployment priorities included in the priority list L0 are assigned in descending order of the number of vehicles in short supply. That is, the information processing device 10 generates a priority list L0 in which the priority is assigned in descending order of the number of vehicles in short supply. Here, for example, when the station ID is "0," the priority list L0 is configured with the number of intended users set to "6," the number of deployed vehicles set to "2," the number of vehicles in short supply set to "4," and the highest redeployment priority set to "1." Furthermore, with regard to the relationship between station IDs and redeployment priorities, the station ID "0" indicates the first priority. The station ID "1" indicates the second priority, the station ID "3" indicates the third priority, and the station ID "2" indicates the fourth priority. The station ID "4" has the lowest priority of 5. The number of units in stock may be used instead of the number of units deployed.

[0110] In the left diagram of FIG. 14A, the simulation results are displayed on the screen. That is, the simulation results are displayed on a map in the road network map information 34. Each station is located on the map. Then, based on the priority list L0, the number of deployed vehicles, the number of vehicles in short supply, and the redeployment priority are associated with each station. Here, as an example, when the station ID is "0," the number of deployed vehicles is "2," the number of vehicles in short supply is "4," and the redeployment priority is "1st" associated with the station ID "0."

[0111] Under these circumstances, as shown in the left diagram of FIG. 14B, the information processing device 10 performs policy evaluation processing based on the priority list L0. As shown in FIG. 14B, the information processing device 10 processes the station with the highest redeployment priority, station id "0," which has the largest "number of people intending to use the station - number of deployed units." The information processing device 10 selects station id "4," which has the lowest redeployment priority. Here, station id "0" and station id "4" are highlighted.

[0112] The information processing device 10 determines whether the distance between station ID "0" and station ID "4" is an allowable distance for movement. Here, the distance between station ID "0" and station ID "4" is "1 km", so the information processing device 10 determines that the distance is an allowable distance for movement. Then, based on the priority list L0, the information processing device 10 has two surplus units at station ID "4", so it prompts the user to input "The travel distance is 1 km, so two units can be moved. Do you want to move?" Here, "Yes" is input, indicating that the units will move.

[0113] Then, for station ID "4", the information processing device 10 displays "0 units" as the number of deployed units and "0 units" as the number of shortage units (there is no longer any surplus due to redeployment). In addition, for station ID "0", the information processing device 10 displays "4 units" as the number of deployed units and "2 units" as the number of shortage units. Then, the information processing device 10 prompts the user to input "Do you want to adopt the proposal?" Here, "No" is entered, indicating that the proposal is not adopted. Furthermore, the information processing device 10 prompts the user to input "Do you want to revise the number of units to be moved?" Here, "1" is entered as the number of units to be moved.

[0114] As a result, as shown in the middle diagram of FIG. 14B, the information processing device 10 associates the number of deployed vehicles with "3 vehicles," the number of vehicles in short supply with "3 vehicles," and the redeployment priority with "1st place." Then, based on the priority list L0, the information processing device 10 still has one surplus vehicle at station id "4," so it prompts the user to input, "You can move one vehicle, a distance of 1 km. Do you want to move?" Here, "No" is entered, indicating that you do not want to move.

[0115] Next, as shown in the right diagram of Fig. 14B, the information processing device 10 selects the station ID "2" with the next lowest redeployment priority. Here, the station ID "0" and the station ID "2" are displayed in a highlighted manner.

[0116] The information processing device 10 determines whether the distance between station ID "0" and station ID "2" is an allowable distance for movement. Here, the distance between station ID "0" and station ID "2" is "2 km", so the information processing device 10 determines that the distance is an allowable distance for movement. Then, based on the priority list L0, the information processing device 10 has one surplus unit at station ID "2", so it prompts the user to input "The travel distance is 2 km, so you can move one unit. Do you want to move?" Here, "Yes" is input, indicating that the unit will move.

[0117] Then, the information processing device 10 displays "1 unit" as the number of deployed units and "0 units" as the number of units in short supply for station ID "2" (there is no longer any surplus due to redeployment). In addition, the information processing device 10 displays "4 units" as the number of deployed units and "2 units" as the number of units in short supply for station ID "0". Then, the information processing device 10 prompts the user to input "Do you want to adopt the proposal?" Here, "Yes" is input, indicating that the proposal is adopted.

[0118] In this way, the information processing device 10 can continue the policy evaluation process and allow the user to consider policy proposals for vehicle redeployment at each station through trial and error. That is, the service operator can consider policy proposals through trial and error based on changes in the virtual intention to use the service.

[0119] (An example of the effect of simulation) FIG. 15 is a diagram showing an example of the effect of a simulation according to this embodiment. The upper diagram of FIG. 15 shows a case where a redeployment measure was implemented before the implementation of the simulation according to this embodiment. As shown in the upper diagram of FIG. 15, before the implementation of the simulation, the service operator considers redeployment measures based only on the number of people who showed a high intention to use up to the time of the questionnaire survey. Therefore, the number of people who showed a high intention to use will differ between the time of the questionnaire survey and the current time N days after the time of the questionnaire survey, and the need for redeployment may differ.

[0120] The lower diagram of Figure 15 shows a case where a redeployment measure is implemented after the introduction of a simulation according to this embodiment. As shown in the lower diagram of Figure 15, after the introduction of the simulation, the information processing device 10 can quantify changes in service usage experience and estimate evaluations of the experience over time in the simulation. In addition, the information processing device 10 can use trial and error to consider redeployment measures based on evaluations of the experience. In other words, the information processing device 10 can use trial and error to consider proposed measures based on changes in the intention to use the virtual service. As a result, the information processing device 10 can determine service measures at low cost.

[0121] (effect) As described above, the information processing device 10 generates service usage experiences for the agents corresponding to people existing in the real world by simulating the use of services by the agents in the real world in a digital twin that recreates the real world in a virtual space. Based on the generated usage experiences, the information processing device 10 sets information regarding the intention to use services held by the agents corresponding to the people. This enables the information processing device 10 to determine service measures at low cost.

[0122] The information processing device 10 also acquires information about a person's service usage intention from the storage unit 30, which stores information about the person's service usage intention. The information processing device 10 uses the acquired information about the usage intention to generate a behavioral selection model indicating whether the person will use the service. In the information processing device 10, a process for generating a service usage experience uses the generated behavioral selection model to conduct a simulation about the service usage of an agent corresponding to the target person, thereby generating information about the target person's service usage experience. In addition, a process for setting information about the service usage intention uses the generated information about the service usage experience to update the information about the target person's usage intention stored in the storage unit 30. In this way, the information processing device 10 can update the information about the target person's usage intention to conduct a simulation about the target person's service usage again. As a result, the information processing device 10 can conduct a simulation about the use of a service that takes into account changes in the service usage experience without conducting another survey (questionnaire). Furthermore, the information processing device 10 can reduce the number of surveys (questionnaires), thereby reducing the time and cost required to determine a policy proposal.

[0123] Furthermore, in the information processing device 10, the process of generating a behavioral selection model uses information on updated usage intentions to generate a behavioral selection model that indicates whether or not a person will use a service. Then, the process of performing a simulation uses the generated behavioral selection model to perform a simulation of the target person in a digital twin in which the real world and the virtual space are time-synchronized. As a result, the information processing device 10 can generate an accurate behavioral selection model by generating the behavioral selection model using information on updated usage intentions.

[0124] The information processing device 10 also receives information regarding the conditions of measures for a service to be introduced into the real world. Based on the received information regarding the conditions of the measures, the information processing device 10 generates a digital twin that recreates the real world in a virtual space. Then, in the information processing device 10, a process of performing a simulation uses the generated behavioral selection model in the generated digital twin to perform a simulation regarding the target person's use of the service. Based on the results of the performed simulation, the information processing device 10 identifies the state of the target for introducing the measures, and displays information regarding the verification results of the measures on the display screen based on the state of the target for introducing the measures. This allows the information processing device 10 to allow the operator of the service to efficiently consider proposed measures.

[0125] In addition, in the information processing device 10, the process of identifying the state of the target for policy introduction acquires the number of deployed mobile objects that are the target for service introduction from the results of a simulation for each station in the digital twin where the service is introduced. The process of identifying the state of the target for policy introduction counts the number of intending users who intend to use the service for each station in the digital twin. The process of identifying the state of the target for policy introduction includes a process of calculating the number of mobile objects in short supply for each station from the number of intending users and the number of deployed mobile objects. Then, the process of displaying on the display screen executes verification of the policy, in which mobile objects are moved from a first station with a large shortage of mobile objects to a second station with a small shortage of mobile objects to the first station. Then, the information processing device 10 displays the number of deployed mobile objects for each station on the display screen as the verification result of the policy. This allows the information processing device 10 to allow the service operator to efficiently consider policy proposals for the redeployment of mobile objects.

[0126] Furthermore, in the information processing device 10, the process of conducting a simulation inputs information about the target person's usage intention into a behavioral selection model to obtain information indicating whether the target person will use a mobile object for which the service is to be introduced. The process of conducting the simulation includes a process of generating information about the target person's experience using the service by conducting a simulation of the agent's use of the mobile object corresponding to the target person based on the information indicating whether the target person will use a mobile object for the service and the number of mobile objects in stock at each station where the service is introduced. This allows the information processing device 10 to conduct a simulation of the use of the mobile object for the service, taking into account changes in the experience using the service, without conducting another survey (questionnaire). Furthermore, the information processing device 10 can reduce the number of surveys (questionnaires), thereby reducing the time and cost required to decide on a policy proposal.

[0127] Furthermore, in the information processing device 10, the information regarding usage intention and the information regarding usage experience are expressed by graded numerical values ​​for each item, which makes it easier for the information processing device 10 to interpret the contents of the information regarding usage intention and the information regarding usage experience.

[0128] Furthermore, in the information processing device 10, the process of generating a behavioral selection model generates a behavioral selection model in which the information on the use experience included in the person's attribute information and the information on the use intention is used as an explanatory variable, and the information on whether or not the person wants to use the service included in the information on the use intention is used as an explained variable. This enables the information processing device 10 to generate a behavioral selection model that estimates the intention to use a service based on the service usage experience.

[0129] (system) The information, including the processing procedures, control procedures, specific names, various data, and parameters shown in the above documents and drawings, may be changed as desired unless otherwise specified. Furthermore, the specific examples, distributions, and numerical values ​​described in the embodiments are merely examples and may be changed as desired.

[0130] Furthermore, the specific form of distribution or integration of the components of each device is not limited to that shown in the drawings. That is, all or part of the components may be functionally or physically distributed or integrated in any unit depending on various loads, usage conditions, etc. Furthermore, all or any part of the processing functions of each device may be realized by a CPU (Central Processing Unit) and a program analyzed and executed by the CPU, or may be realized as hardware using wired logic.

[0131] (Hardware) Fig. 16 is a diagram illustrating an example of the hardware configuration of the information processing device 10. As shown in Fig. 16, the information processing device 10 includes a communication interface 10a, a hard disk drive (HDD) 10b, a memory 10c, and a processor 10d. The components shown in Fig. 16 are connected to each other via a bus or the like.

[0132] The communication interface 10a is a network interface card or the like, and communicates with other servers. The HDD 10b stores programs and DBs that operate the functions shown in FIG.

[0133] The processor 10d is a hardware circuit that operates a process that executes each function described in FIG. 5 and other figures by reading a program that executes the same processing as each processing unit shown in FIG. 5 from the HDD 10b or the like and loading the program into the memory 10c. That is, this process executes the same functions as each processing unit of the information processing device 10. Specifically, the processor 10d reads a program having the same functions as the behavior selection model generation unit 41, the data acquisition unit 42, the behavior selection unit 43, the movement reproduction unit 44, the vehicle state update unit 45, the vehicle management unit 46, the usage experience update unit 47, the policy evaluation unit 48, and the like from the HDD 10b or the like. Then, the processor 10d executes a process that executes the same processing as the behavior selection model generation unit 41, the data acquisition unit 42, the behavior selection unit 43, the movement reproduction unit 44, the vehicle state update unit 45, the vehicle management unit 46, the usage experience update unit 47, the policy evaluation unit 48, and the like.

[0134] In this way, the information processing device 10 operates as an information processing device that executes a simulation by reading and executing a program that executes the same processes as the respective processing units shown in Fig. 5. The information processing device 10 can also realize functions similar to those of the above-described embodiment by reading a program from a recording medium using a medium reading device and executing the read program. Note that the program in these other embodiments is not limited to being executed by the information processing device 10. For example, this embodiment may also be applied in the same way to cases where another information processing device executes a program or where the information processing device 10 and another information processing device cooperate to execute a program.

[0135] A program that executes the same processes as those of the processing units shown in Fig. 5 can be distributed via a network such as the Internet. This program can be recorded on a computer-readable recording medium such as a hard disk, a flexible disk (FD), a CD-ROM, a magneto-optical disk (MO), or a digital versatile disc (DVD), and can be executed by being read from the recording medium by a computer.

[0136] The simulation of the information processing device 10 according to the above embodiment can be applied, for example, to the case where deployment measures for mobility sharing, which is not yet widespread, are considered. [Explanation of symbols]

[0137] 1. Information Processing Systems 10. Information processing equipment 20 Communications Department 30 Storage section 31 Travel history data 32 Survey Results 33 Behavioral Selection Model Parameters 34 Road network map information 35 Vehicle Information 40 Control Unit 41 Action selection model generation unit 42 Data Acquisition Section 43 Action Selection Section 44 Moving Reproduction Section 45 Vehicle status update unit 46 Vehicle Management Department 47 User Experience Update Department 48 Policy Evaluation Department 50 Network 100 Information processing terminal < / ii> < / ii> < / ii> < / ii>

Claims

1. In a digital twin that reproduces the real world in a virtual space, a simulation is carried out regarding the use of a service by an agent corresponding to a person existing in the real world, thereby generating an experience of using the service for the agent corresponding to the person; Based on the generated usage experience, information regarding the intention to use the service held by an agent corresponding to the person is set. An information processing program that causes a computer to execute a process.

2. acquiring information about the person's intention to use the service from a storage unit that stores information about the person's intention to use the service; Using the acquired information on usage intention, a behavioral selection model is generated that indicates whether or not a person will use the service; the process of generating a service usage experience includes using the generated behavioral selection model to conduct a simulation regarding service usage by an agent corresponding to a target person, thereby generating information regarding the service usage experience of the target person; The process of setting information regarding intention to use the service includes: Using the generated information about the service usage experience, the information about the target person's usage intention stored in the storage unit is updated.

2. The information processing program according to claim 1, wherein:

3. the process of generating the behavioral selection model includes generating the behavioral selection model indicating whether or not a person will use a service using the updated information on the usage intention; The process of performing the simulation performs a simulation of the target person using the generated behavior selection model in the digital twin in which the real world and the virtual space are time-synchronized.

3. The information processing program according to claim 2, wherein:

4. Accepting information regarding conditions for measures in the service to be introduced into the real world; generating the digital twin that reproduces the real world in a virtual space based on information regarding the conditions of the received policy; The process of performing the simulation includes performing a simulation of the target person's use of a service using the generated behavioral selection model in the generated digital twin; Based on the results of the simulation, the state of the target for the introduction of the measures is identified; Based on the state of the target of the implementation of the measure, information regarding the verification result of the measure is displayed on a display screen.

4. The information processing program according to claim 3,

5. The process of identifying a state of a target for introducing the measure includes: In the digital twin, for each station where the service is introduced, the number of deployed mobile objects to which the service is to be introduced is obtained from the results of the simulation; In the digital twin, the number of people who intend to use the service is counted for each station; a process of calculating, for each station, the number of mobile objects that is insufficient based on the number of intending users and the number of deployed mobile objects; The process of displaying on the display screen includes: verifying the measure of moving the mobile units from a first station having a largest shortage of the mobile units to a second station having a small shortage of the mobile units, in order from a first station having a largest shortage of the mobile units to the first station; The number of mobile units deployed at each station is displayed on the display screen as a verification result of the policy.

5. The information processing program according to claim 4.

6. The process of performing the simulation includes: inputting information about the target person's intention to use into the behavioral selection model to obtain information indicating whether the target person will use a mobile object for which a service is to be introduced; and generating information about the target person's experience using the service by conducting a simulation regarding the use of the mobile object by an agent corresponding to the target person based on information indicating whether the target person will use the mobile object of the service and the number of the mobile objects deployed at each station where the service is introduced.

4. The information processing program according to claim 3,

7. The information regarding the intention to use and the information regarding the experience of use are expressed as graded numerical values ​​indicating intention to use for each item.

3. The information processing program according to claim 2, wherein:

8. The process of generating the behavioral selection model uses the person's attribute information and information about usage experience included in the information about usage intention as explanatory variables, and generates the behavioral selection model using information about whether or not the user wants to use the service included in the information about usage intention as an explained variable.

4. The information processing program according to claim 3,

9. In a digital twin that reproduces the real world in a virtual space, a simulation is carried out regarding the use of a service by an agent corresponding to a person existing in the real world, thereby generating an experience of using the service for the agent corresponding to the person; Based on the generated usage experience, information regarding the intention to use the service held by an agent corresponding to the person is set. An information processing method characterized in that the processing is executed by a computer.

10. a simulation unit that, in a digital twin that reproduces the real world in a virtual space, performs a simulation of the use of a service by an agent corresponding to a person existing in the real world, thereby generating an experience of using the service for the agent corresponding to the person; a setting unit that sets information about the intention to use the service held by an agent corresponding to the person based on the use experience generated by the simulation unit; An information processing device comprising:

Images