Information processing program, information processing device and information processing method

Abstract

To solve the problem that while it is requested to take a plurality of evaluation indexes into consideration and then consider well-balanced measures against a complicated social problem from not a single point of view, but a wide point of view, important matters differs with stakeholders of measures while the plurality of evaluation indexes affect one another, and a stakeholder may not make his or her important point of view clear in advance.SOLUTION: An information processing program causes a computer to execute processing to: acquire a plurality of parameters for measures; execute a plurality of simulations for the measures in a virtual space based upon the plurality of acquired parameters; make relative evaluations based upon results of the plurality of simulations having been executed; output a combination of indexes of a plurality of important points of view of a stakeholder of the measures based upon results of the relative evaluations; and specify parts which are common among the stakeholders from the output combination.SELECTED DRAWING: Figure 6

Description

[Technical field]

[0001] The present invention relates to a policy search technique. [Background technology]

[0002] Complex social issues require consideration of multiple evaluation indicators from a broad perspective rather than a single one, and devise balanced measures. Here, for example, a social issue could be an issue related to urban transportation, and multiple evaluation indicators could be the reduction of CO2 (carbon dioxide) emissions, economic revitalization, and improved convenience that would be achieved through measures to address the issue. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2021-170187 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, as multiple evaluation indicators affect each other, what is important varies depending on the stakeholder, and it may not be possible to clarify in advance what is important to each stakeholder. Under these circumstances, it is necessary to have multiple stakeholders agree on the measures to be applied.

[0005] One aspect is that the aim is to make it easier for stakeholders to reach agreement on measures to address issues where multiple evaluation indicators affect each other. [Means for solving the problem]

[0006] In one embodiment, the information processing program causes a computer to execute a process of acquiring multiple parameters for a policy, running multiple simulations of the policy in a virtual space based on the acquired multiple parameters, performing a relative evaluation based on the results of the executed multiple simulations, outputting a combination of indicators of multiple perspectives that are important to stakeholders for the policy based on the results of the relative evaluation, and identifying commonalities between the stakeholders from the output combination. Effect of the Invention

[0007] On the one hand, it makes it easier for stakeholders to reach agreement on measures to address issues where multiple evaluation indicators affect each other. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of an information processing system 1 according to the present embodiment. [Diagram 2] FIG. 2 is a diagram showing an example of the configuration of the information processing device 10 according to the present embodiment. [Diagram 3] FIG. 3 is a diagram showing an example of policy parameters according to the present embodiment. [Figure 4] FIG. 4 is a diagram showing an example of a simulation result according to the present embodiment. [Diagram 5] FIG. 5 is a diagram showing an example of the relative evaluation according to the present embodiment. [Figure 6] FIG. 6 is a diagram showing an example of the policy search process according to the present embodiment. [Figure 7] FIG. 7 is a diagram showing an example of the Pareto frontier according to the present embodiment. [Figure 8] FIG. 8 is a diagram showing an example of a parallel coordinate plot according to this embodiment. [Figure 9] FIG. 9 is a diagram illustrating an example of a problem in consensus building. [Figure 10] FIG. 10 is a diagram showing an example of a goodness distribution according to the present embodiment. [Figure 11] FIG. 11 is a diagram showing an example of consensus formation according to the present embodiment. [Figure 12] FIG. 12 is a diagram showing an example of a problem in selecting a relative evaluation pair. [Figure 13] FIG. 13 is a diagram showing an example of relative evaluation pair selection according to this embodiment. [Figure 14] FIG. 14 is a diagram showing an example of global pair selection according to this embodiment. [Figure 15] FIG. 15 is a diagram showing an example of mid-range pair selection according to the present embodiment. [Figure 16] FIG. 16 is a diagram showing an example of local pair selection according to the present embodiment. [Figure 17] FIG. 17 is a flowchart showing an example of the flow of the policy search process according to this embodiment. [Figure 18] FIG. 18 is a diagram showing an example of the hardware configuration of the information processing device 10 according to the present embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, examples of the information processing program, the information processing device, and the information processing method according to the present embodiment will be described in detail with reference to the drawings. Note that the present embodiment is not limited to these examples. In addition, each example can be appropriately combined within a range that does not cause inconsistency.

[0010] First, an information processing system for carrying out this embodiment will be described. Fig. 1 is a diagram showing an example of the configuration of an information processing system 1 according to this embodiment. As shown in Fig. 1, 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 able to communicate with each other.

[0011] The network 50 may be any of a variety of communication networks, such as the Internet, whether wired or wireless. 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).

[0012] The information processing device 10 may be, for example, a desktop PC (Personal Computer), a notebook PC, or a server computer managed by a service provider that performs a policy search and presents a proposed agreement for the policy.

[0013] The information processing device 10, for example, acquires a plurality of parameters for a measure, and executes a plurality of simulations for the measure in a virtual space based on the acquired plurality of parameters. The simulations may be executed as a digital rehearsal of the measure on a digital twin, which is an existing technology, for example.

[0014] Furthermore, the information processing device 10 performs, for example, a relative evaluation based on the results of a plurality of executed simulations. The relative evaluation may be performed, for example, by presenting the simulation results of each measure to each stakeholder via the information processing terminal 100, and having each stakeholder input the evaluation result for each measure.

[0015] The information processing device 10 also outputs a combination of indices of multiple perspectives that are important to the policy among the stakeholders based on the results of the relative evaluation, and identifies commonalities between the stakeholders from the output combination. The information processing device 10 also presents the commonalities identified here to each stakeholder via the information processing terminal 100 as a proposed agreement on the policy.

[0016] 1, the information processing device 10 is shown as a single computer, but may be a distributed computing system consisting of multiple computers. The information processing device 10 may also be a cloud computer device managed by a service provider that provides cloud computing services.

[0017] The information processing terminal 100 may be, for example, a desktop PC or a notebook PC used by each stakeholder, or a mobile terminal such as a smartphone or a tablet PC. Each stakeholder, for example, inputs an evaluation result for each policy via the information processing terminal 100, and displays a simulation result for each policy and a proposed agreement for the policy provided by the information processing device 10.

[0018] Note that, for example, an application for inputting the evaluation results for each policy, displaying the simulation results for each policy, and a proposed agreement for each policy may be pre-installed in the information processing terminal 100. Alternatively, the information processing terminal 100 may access, for example, a website or application on the information processing device 10 to input the evaluation results for each policy. In this case, the information processing terminal 100 does not need to have an application for inputting the evaluation results for each policy installed.

[0019] [Functional configuration of information processing device 10] First, a functional configuration of the information processing device 10 which is the executing subject of this embodiment will be described. Fig. 2 is a diagram showing an example of the configuration of the information processing device 10 according to this embodiment. As shown in Fig. 2, the information processing device 10 has a communication unit 20, a storage unit 30, and a control unit 40.

[0020] The communication unit 20 is a processing unit that controls communication with other devices, and is, for example, a communication interface such as a network interface card or a Universal Serial Bus (USB) interface.

[0021] The storage unit 30 has a function of storing various data and programs executed by the control unit 40, and stores, for example, policy parameter data 31, simulation result data 32, relative evaluation data 33, and proposal agreement data .

[0022] For example, information on parameters for measures (hereinafter, referred to as "measure parameters") is stored in the measure parameter data 31. Here, an example of a measure will be described more specifically.

[0023] For example, a business operator plans a program called shared e-scooters as part of services for residents. In this program, for example, multiple e-scooters are deployed at each of multiple stations installed in a city. Note that e-scooters are also called electric kickboards, for example. Furthermore, the e-scooters are shared, for example, with the residents of the city. This allows, for example, residents to rent e-scooters at the nearest station for a fee. Furthermore, for example, residents can drop off or return the e-scooters at any station.

[0024] Also, for example, e-scooters are deployed at each of a number of stations in the early morning or late night. For example, a truck loaded with a number of e-scooters makes a round of each station, and the truck's occupant deploys the e-scooters at each station. Here, for example, the cost incurred by the operator and the income obtained by the operator change depending on the initial number of e-scooters deployed at the stations. Also, the cost includes, for example, fuel costs for the trucks that transport the e-scooters and labor costs for the occupants. Also, the income includes, for example, rental fees (rental fees) for the e-scooters. Also, since cars emit more CO2 than e-scooters, it is necessary to consider the number of e-scooters to be installed from the perspective of environmental issues such as global warming.

[0025] While such e-scooter policies can improve convenience for residents and revitalize local areas, for example, businesses and local governments must consider costs, income, CO2 emissions, etc. In other words, for example, e-scooter policies involve stakeholders such as residents, businesses, and local governments, and each stakeholder may place different priorities on different issues, or the issues that must be considered may not be clear.

[0026] In the case of such an e-scooter policy, the policy parameter is, for example, the initial deployment number of e-scooters to be deployed at each station in the early morning or late night, etc. The initial deployment number of such e-scooters may be, for example, data as shown in FIG.

[0027] Fig. 3 is a diagram showing an example of a policy parameter according to the present embodiment. The initial deployment number setting list shown in Fig. 3(a) is an example of a policy parameter, and is stored in the policy parameter data 31. In addition, the initial deployment number setting list may include, for example, the initial deployment number of e-scooters for each station uniquely identified by a station ID and for each policy, as shown in Fig. 3(a).

[0028] In addition, the policy parameter data 31 may store, for example, an OD table as shown in Fig. 3(b). The OD table represents the travel demand of e-scooters at each time, for example, with one point being the departure station of the e-scooter and the other point being the destination station.

[0029] For example, a simulation performed for each measure using the measure parameters and information on the results of the simulation are stored in the simulation result data 32. The simulation result data stored in the simulation result data 32 may be, for example, data as shown in FIG.

[0030] Fig. 4 is a diagram showing an example of a simulation result according to the present embodiment. As shown in Fig. 4, the simulation result data may include, for example, for each measure, a policy parameter used in the simulation and an evaluation result. In addition, the evaluation result may be, for example, a result for each evaluation index such as cost, income, and CO2 emissions when the measure is implemented, as shown in Fig. 4. Note that, although the example in Fig. 4 shows evaluation results based on three evaluation indexes, the number of evaluation indexes may be two or four or more.

[0031] The relative evaluation data 33 stores, for example, a relative evaluation for each stakeholder for the simulation result of each policy, information on the result, etc. The relative evaluation data stored in the relative evaluation data 33 may be input for each stakeholder via, for example, a user interface (UI) as shown in FIG.

[0032] FIG. 5 is a diagram showing an example of relative evaluation according to the present embodiment. The relative evaluation dashboard shown in FIG. 5 is a UI for displaying, for example, simulation results of two measures and for allowing a stakeholder to input which measure is better. The relative evaluation dashboard is presented for each stakeholder via the information processing terminal 100 from, for example, the information processing device 10. The stakeholder inputs which measure is better by selecting a radio button at the bottom of the relative evaluation dashboard, for example, as shown in FIG. 5. As a result, a relative evaluation is performed for each stakeholder for each measure, and the result is stored in the relative evaluation data 33. Note that the input method of the relative evaluation as shown in FIG. 5 is one example, and is not limited thereto.

[0033] The agreement proposal data 34 stores, for example, information on the agreement proposal for the measures based on the relative evaluation of each measure by each stakeholder. Note that the agreement proposal data stored in the agreement proposal data 34 is generated by the information processing device 10 based on the result data of the relative evaluation of each measure by each stakeholder stored in the relative evaluation data 33, which will be described in detail later.

[0034] The above information stored in the storage unit 30 is merely an example, and the storage unit 30 can store various information other than the above information.

[0035] The control unit 40 is a processing unit, such as a processor, that controls the entire information processing device 10. The control unit 40 includes an acquisition unit 41, a simulation unit 42, an evaluation unit 43, an output unit 44, and an identification unit 45. Each processing unit is an example of an electronic circuit included in the processor or an example of a process executed by the processor.

[0036] The acquiring unit 41 acquires, for example, a plurality of parameters for the measures, that is, a plurality of measure parameters. Since the parameters for the measures are, for example, set and stored in advance in the measure parameter data 31, the acquiring unit 41 acquires the measure parameters corresponding to the measures to be simulated from the measure parameter data 31. Here, the overall flow of the measure search process executed by the information processing device 10 is shown with reference to FIG. 6.

[0037] Fig. 6 is a diagram showing an example of a policy search process according to this embodiment. As shown in "(1) Policy Point Determination" in Fig. 6, the acquisition unit 41, for example, determines a policy parameter to be used in a simulation (strictly speaking, a policy point in a policy parameter space) and acquires the policy point. The policy point is used by the simulation unit 42 to execute a simulation. The policy point to be used in the simulation may be determined in advance and stored in the policy parameter data 31, or may be determined randomly and acquired from the policy parameter data 31.

[0038] The simulation unit 42 executes a plurality of simulations for the measures in a virtual space, for example, based on a plurality of parameters acquired by the acquisition unit 41. The simulation may be executed, for example, by constructing a digital twin, which is an existing technology, and executing the simulation for each measure as a digital rehearsal of each measure on the digital twin. Note that, as shown in "(2) Calculation of evaluation value and additional information" in FIG. 6, the simulation unit 42 executes a simulation for each measure, for example, to calculate an evaluation value for each evaluation index and other additional information. Then, the simulation unit 42 generates, for example, a relative evaluation dashboard as shown in FIG. 5 as a simulation result, and stores it in the simulation result data 32.

[0039] The evaluation unit 43 performs a relative evaluation based on the results of a plurality of simulations executed by the simulation unit 42, for example. The relative evaluation may be, for example, as shown in "(3) Human Evaluation" in Fig. 6, in which each stakeholder looks at a relative evaluation dashboard generated as a simulation result and evaluates which measure is better. In addition, the evaluation unit 43 stores, for example, the relative evaluation of each stakeholder for the simulation result in the relative evaluation data 33.

[0040] The process of performing the relative evaluation executed by the evaluation unit 43 may include, for example, a process of generating a Pareto frontier based on the results of multiple simulations executed by the simulation unit 42. Then, for example, a relative evaluation based on the results of multiple simulations on the Pareto frontier is executed for each stakeholder. The Pareto frontier is an existing technology, but will be described more specifically with reference to FIG. 7.

[0041] Fig. 7 is a diagram showing an example of the Pareto frontier according to this embodiment. The example in Fig. 7 shows the Pareto frontier in an evaluation value space in which evaluation index 1 is represented by the x-axis and evaluation index 2 is represented by the y-axis. In the Pareto frontier, for example, for evaluation result x=(x1,...,xn), if all evaluation results y=(y1,...,yn) different from x do not satisfy yi≦xi(i=1,...,n), then x is said to be an optimal solution. Also, it is shown that there is no better solution than the Pareto frontier shown by the curve in Fig. 7.

[0042] The output unit 44 outputs a combination of indicators from multiple perspectives that are considered important by stakeholders of a policy, for example, based on the result of the relative evaluation executed by the evaluation unit 43. The process of outputting the combination may include, for example, a process of outputting the combination using a parallel coordinate plot in which points on the Pareto frontier are plotted with each of the indicators as an axis. The parallel coordinate plot is an existing technology, but will be described more specifically with reference to FIG. 8.

[0043] FIG. 8 is a diagram showing an example of a parallel coordinate plot according to this embodiment. The example of FIG. 8 is a parallel coordinate plot that expresses points in a three-dimensional Euclidean space in two dimensions, where each evaluation index is represented by three axes, i.e., x, y, and z. In the parallel coordinate plot, for example, it is possible to narrow down any points by narrowing down the width of the axes. In the policy search process of this embodiment, for example, points on the Pareto frontier are output in a parallel coordinate plot. Note that the parallel coordinate plot shown in FIG. 8 is an example of a three-dimensional space representing three evaluation indexes expressed in two dimensions, but in the parallel coordinate plot, it is also possible to express, for example, a four-dimensional or more space, that is, points of four or more evaluation indexes in two dimensions.

[0044] The identification unit 45 identifies a common part (hereinafter referred to as a "common part") between the stakeholders from, for example, a combination of indicators of multiple perspectives that the stakeholders regard as important for the policy output by the output unit 44. The process of identifying the common part may be, for example, a process of identifying, as the common part, a common part of all the stakeholders' parallel coordinate plots where each of the indicators is equal to or greater than a respective predetermined threshold value. Note that, for example, a parallel coordinate plot in which the common part is visually identifiable is stored in the proposed agreement data 34 as proposed agreement data for the policy and presented to each stakeholder.

[0045] However, there are problems with forming consensus proposal data by identifying common parts from parallel coordinate plots (hereinafter, referred to as "consensus formation"). FIG. 9 is a diagram showing an example of a problem with consensus formation. FIG. 9 is a parallel coordinate plot in which each evaluation index of a parallel coordinate plot for three stakeholders, namely, a local government, a business operator, and a resident, is color-coded with the threshold of each evaluation index as a boundary. More specifically, for example, in FIG. 9, the "above threshold" part and the "below threshold" part are color-coded with the threshold of each evaluation index as a boundary. Note that the threshold is set for each evaluation index, and the scale intervals of each axis are not the same, so that the "above threshold" part and the "below threshold" part do not necessarily form a horizontal straight line, as shown in FIG. 9.

[0046] For example, the common parts of the parallel coordinate plot of all stakeholders, where each evaluation indicator is above its respective threshold, can be adopted as the proposed agreement. However, as shown in Figure 9, while there are common parts between the business department and residents, when the local government is included, there are no common parts between all stakeholders, creating the problem that consensus cannot be reached. With conventional methods, each stakeholder could only select the part they considered most important, and even if there was a second most important part, this would be left out, making it impossible to find common parts. Therefore, we made it possible to extract multiple parts that each stakeholder considered important, thereby increasing the common parts.

[0047] To achieve this, in this embodiment, a distribution of the goodness of evaluation values ​​(hereinafter referred to as "Goodness distribution"), such as a heat map, is created based on the relative evaluation results of each stakeholder, as shown in "(4) Creating a Goodness Distribution" in Fig. 6. The Goodness distribution will be specifically described with reference to Fig. 10.

[0048] FIG. 10 is a diagram showing an example of a Goodness distribution according to this embodiment. In the example of FIG. 10, a Goodness distribution is created for a Pareto frontier on an evaluation value space in which evaluation indexes 1 to 3 are represented by three axes, i.e., x, y, and z. In FIG. 10, a part that is partially curved but has a triangular shape is the Pareto frontier. For example, the Goodness distribution is a display of the parts on the Pareto frontier where each evaluation value is equal to or greater than a predetermined threshold (parts shown as "parts with high Goodness values" in FIG. 10) in shading based on the magnitude of the evaluation value. Note that there may be multiple "parts with high Goodness values" as shown as value 1 and value 2 in FIG. 10. In this embodiment, for example, in order to solve the problem of consensus building as shown in FIG. 9, a parallel coordinate plot of each stakeholder is created using the Goodness distribution, as shown in "(5) Consensus Building" in FIG. 6, and consensus building is performed.

[0049] FIG. 11 is a diagram showing an example of consensus formation according to this embodiment. As in FIG. 9, FIG. 11 is a parallel coordinate plot in which the evaluation indexes of the parallel coordinate plots for three stakeholders, namely, the local government, the business operator, and the resident, are color-coded with the threshold value of each evaluation index as a boundary. Each parallel coordinate plot in FIG. 11 is created by narrowing down to the "part with high Goodness value" using, for example, the Goodness distribution. In this way, by creating each parallel coordinate plot by narrowing down to the "part with high Goodness value" using the Goodness distribution, as shown in FIG. 11, the common part among all stakeholders can be increased and the part can be adopted as the proposed agreement. Note that, as shown in FIG. 11, the part that can be adopted as the proposed agreement may include, for example, the common part among all stakeholders and the surrounding part. The final consensus decision is made among all stakeholders to whom the proposed agreement is presented.

[0050] Although the policy search process of this embodiment has been described above, there may be problems with the part that selects pairs of policies for relative evaluation shown in "(3) Human evaluation" in Fig. 6. The problem will be specifically described with reference to Fig. 12.

[0051] Fig. 12 is a diagram showing an example of a problem in selecting a relative evaluation pair. In Fig. 12, the triangular part is assumed to be a Pareto frontier on an evaluation value space in which evaluation indexes 1 to 3 are represented by three axes, x, y, and z. A pair of two points on the Pareto frontier is selected, for example, at random, as a pair of measures for which a relative evaluation is performed.

[0052] However, depending on the method of selecting pairs on the Pareto frontier, as shown on the left side of FIG. 12, the selected sample points may be sparse or dense, and for example, if there is a peak in the Goodness distribution in the area indicated by the dashed line, it may not be possible to capture it. Also, as shown on the right side of FIG. 12, for example, if the selected pairs are local, it may not be possible to capture a large peak in the Goodness distribution in the entire Pareto frontier. In this way, depending on the method of selecting pairs on the Pareto frontier, there is a problem that the multi-peaked peak of the Goodness distribution that should be captured may be overlooked. If such a problem occurs, for example, visualization of multiple perspectives such as the best policy and second best policy of the stakeholder may not be performed correctly. Therefore, in this embodiment, in order to comprehensively capture the tendency of the Goodness distribution from local to global, the selection of pairs of measures to be subjected to relative evaluation is performed based on a policy that selects in stages, for example, global → mid-range → local, rather than randomly. The selection of relative evaluation pairs based on the policy will be specifically described with reference to FIG. 13 to FIG. 16.

[0053] Fig. 13 is a diagram showing an example of relative evaluation pair selection according to this embodiment. As shown in Fig. 13, in this embodiment, when selecting pairs for performing relative evaluation from points on the Pareto frontier, a pair for capturing a global tendency of Goodness distribution, a pair for a mid-range tendency, and a pair for a local tendency are selected in stages.

[0054] Here, the Pareto frontier is, for example, a continuous space having vertices and boundaries, and the goodness distribution is a continuous distribution in that space. Therefore, as shown in FIG. 13, for example, the distance between any two points on the Pareto frontier and the concepts of global, mid-range, and local can be defined, and the tendency of the goodness distribution can be comprehensively grasped. For example, if the tendency at the vertices and the center of gravity of the triangular Pareto frontier is known, the global tendency of the goodness distribution can be grasped. Also, for example, by dividing the area of ​​the Pareto frontier and determining in which divided area the peak of the goodness distribution is located, the mid-range tendency of the goodness distribution can be grasped. Also, for example, by determining where in the divided area the peak of the goodness distribution is located, the local tendency of the goodness distribution can be grasped. Therefore, a method of selecting pairs for each tendency of global, mid-range, and local will be described in more detail.

[0055] Fig. 14 is a diagram showing an example of global pair selection according to this embodiment. As shown in Fig. 14, the sample points used for pairs for the global trend are, for example, three vertices of a triangular Pareto frontier and their centroids. As shown by the double-headed arrow in Fig. 14, for pairs for the global trend, for example, four pairs are selected by pairing three vertices in a brute-force manner and pairing the vertex farthest from the centroid with the centroid.

[0056] That is, for example, each combination of the vertices of each index on the Pareto frontier and the combination of the center of gravity of each vertex and the vertex farthest from the center of gravity are selected as pairs of measures to be relatively evaluated.

[0057] FIG. 15 is a diagram showing an example of mid-range pair selection according to the present embodiment. In FIG. 15, for example, as shown by dashed lines, the region of the Pareto frontier is divided by triangles formed by the three vertices and the center of gravity of the Pareto frontier selected as sample points to be used for pairs for the global trend in FIG. 14. Also, for example, as shown in FIG. 15, each of the triangles shown by dashed lines is further divided into three triangular regions by the center of gravity of the vertices of each divided triangle and each vertex. Then, for example, the center of gravity of each of the three triangles in the triangle shown by dashed lines is set as a sample point to be used for pairs for the mid-range trend. Furthermore, for example, as shown by double-headed arrows in FIG. 15, sample points with different dashed triangles are selected as pairs for the mid-range trend. Note that, for sample points with different dashed triangles, pairs with the points farther apart are selected, for example, as shown in FIG. 15.

[0058] That is, for example, the Pareto frontier is divided into a plurality of triangles formed by each of the vertices of each index in the Pareto frontier and the center of gravity of the vertices.Furthermore, for example, the triangle is divided into a plurality of second triangles formed by each of the second vertices of the triangle and the second center of gravity of the triangle.Then, for example, from among the third centers of gravity of the second triangles, combinations of the third centers of gravity that belong to different second triangles and are separated by a predetermined distance or more are selected as pairs of measures to be subjected to relative evaluation.

[0059] Fig. 16 is a diagram showing an example of local pair selection according to this embodiment. For example, as shown in Fig. 16, within a triangle shown by a dashed line, sample points to be used as pairs for a local tendency are selected in consideration of uniformity in the evaluation value space. Then, for example, as shown in Fig. 16, each sample point is sorted by distance from the origin of the evaluation value space, and as shown by the double-headed arrow in Fig. 16, sample points are selected as pairs for a local tendency such that the distance between all pairs of sample points is large.

[0060] That is, for example, a pair of measures to be relatively evaluated is selected from the combination of the second points in the second triangle based on the distance from the origin of the Pareto frontier.

[0061] [Processing flow] Next, the flow of the policy search process according to this embodiment will be described with reference to Fig. 17. Fig. 17 is a flowchart showing an example of the flow of the policy search process according to this embodiment.

[0062] First, as shown in FIG. 17, the information processing device 10 acquires, for example, a plurality of policy parameters used in a simulation for a policy from the policy parameter data 31 (step S101).

[0063] Next, the information processing device 10 executes a plurality of simulations for each measure as a digital rehearsal on a digital twin, which is an existing technology, using, for example, the measure parameters acquired in step S101 (step S102).

[0064] Next, the information processing device 10 performs, for example, a relative evaluation for each stakeholder based on the results of the multiple simulations performed in step S102 (step S103).

[0065] Next, the information processing device 10 outputs a combination of indices of a plurality of viewpoints that are considered important by the stakeholders for the policy, for example, based on the result of the relative evaluation executed in step S103 (step S104).

[0066] Next, the information processing device 10 forms a proposal for agreement by identifying commonalities among all stakeholders from a combination of indices of multiple perspectives that the stakeholders consider important for the policy output in step S104 (step S105). After step S105 is executed, the policy search process shown in Fig. 17 ends, but for example, the proposal for agreement formed in step S105 is presented to each stakeholder via the information processing terminal 100, and a final agreement is reached.

[0067] [effect] As described above, the information processing device 10 acquires multiple parameters for a policy, performs multiple simulations for the policy in a virtual space based on the acquired multiple parameters, performs a relative evaluation based on the results of the performed multiple simulations, outputs a combination of indicators of multiple perspectives that are important to stakeholders for the policy based on the results of the relative evaluation, and identifies commonalities between the stakeholders from the output combination.

[0068] In this way, a relative evaluation is performed based on multiple simulation results for the policy, and a consensus proposal is formed by identifying common points in the indicators that are important to the stakeholders based on the relative evaluation results. This makes it easier for the information processing device 10 to reach an agreement among the stakeholders on the policy for the issue in which multiple evaluation indicators mutually affect the policy.

[0069] In addition, the process of performing relative evaluation executed by the information processing device 10 includes a process of generating a Pareto frontier based on the results of multiple simulations, and performing a relative evaluation for each stakeholder based on the results of multiple simulations on the Pareto frontier.

[0070] This enables the information processing device 10 to make it easier for stakeholders to reach an agreement on measures for issues where multiple evaluation indexes mutually affect each other.

[0071] In addition, the process of performing a relative evaluation based on the results of multiple simulations on the Pareto frontier, which is executed by the information processing device 10, includes a process of selecting pairs of points on the Pareto frontier based on each vertex of an index on the Pareto frontier, and performing a relative evaluation on the pairs.

[0072] This allows the information processing device 10 to grasp the tendency of the goodness distribution comprehensively from local to global.

[0073] Furthermore, the process of selecting pairs executed by the information processing device 10 includes a process of selecting each combination of vertices, and a combination of the center of gravity of a vertex and the vertex farthest from the center of gravity as pairs.

[0074] This allows the information processing device 10 to grasp the tendency of the goodness distribution comprehensively from local to global.

[0075] In addition, the process of selecting pairs executed by the information processing device 10 includes a process of dividing the Pareto frontier into multiple triangles formed by each of the vertices and the center of gravity, dividing the triangle into multiple second triangles formed by each of the second vertices of the triangle and the second center of gravity of the triangle, and selecting, as pairs, combinations of third centroids that belong to different second triangles and are separated by a predetermined distance or more from the third centroids of the second triangles.

[0076] This allows the information processing device 10 to grasp the tendency of the goodness distribution comprehensively from local to global.

[0077] Furthermore, the process of selecting a pair executed by the information processing device 10 includes a process of selecting a pair from a combination of second points in a second triangle based on the distance from the origin of the Pareto frontier.

[0078] This allows the information processing device 10 to grasp the tendency of the goodness distribution comprehensively from local to global.

[0079] Furthermore, the process of outputting the combinations, which is executed by the information processing device 10, includes a process of outputting the combinations using a parallel coordinate plot in which points on the Pareto frontier are plotted with each of the indexes as an axis.

[0080] This enables the information processing device 10 to make it easier for stakeholders to agree on measures for issues where multiple evaluation indexes mutually affect each other.

[0081] In addition, the process of identifying common parts executed by the information processing device 10 includes a process of selecting and identifying common parts from the parts in which each of the indicators is equal to or greater than a respective predetermined threshold in the parallel coordinate plots of all the stakeholders.

[0082] This enables the information processing device 10 to make it easier for stakeholders to agree on measures for issues where multiple evaluation indexes mutually affect each other.

[0083] [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 arbitrarily unless otherwise specified. In addition, the specific examples, distributions, numerical values, etc. described in the embodiments are merely examples and may be changed arbitrarily.

[0084] Furthermore, the specific form of distribution or integration of the components of the information processing device 10 is not limited to that shown in the figure. For example, the simulation unit 42 of the information processing device 10 may be distributed to multiple processing units, or the acquisition unit 41 and the simulation unit 42 of the information processing device 10 may be integrated into one processing unit. In other words, all or a part of the components may be functionally or physically distributed or integrated in any unit depending on various loads and usage conditions. Furthermore, all or any part of the processing functions of each device may be realized by a CPU or a program analyzed and executed by the CPU (Central Processing Unit), or may be realized as hardware using wired logic.

[0085] Fig. 18 is a diagram showing an example of a hardware configuration of an information processing device 10 according to this embodiment. As shown in Fig. 18, 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. 18 are connected to each other via a bus or the like.

[0086] The communication interface 10a is a network interface card or the like, and communicates with other information processing devices. For example, when the information processing device 10 is the information processing device 10, the HDD 10b stores programs and data for operating each function shown in FIG.

[0087] The processor 10d is a CPU, a micro processing unit (MPU), a graphics processing unit (GPU), etc. The processor 10d may also be realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA). The processor 10d reads out a program that executes the same processes as the processing units shown in FIG. 2, etc. from the HDD 10b, etc., and loads it in the memory 10c. This allows the processor 10d to operate as a hardware circuit that executes a process that realizes each function described in FIG. 2, etc.

[0088] Furthermore, the information processing device 10 can also realize the same functions as those of the above embodiment by reading the above program from a recording medium using a medium reading device and executing the read program. Note that the program in this other embodiment is not limited to being executed by the information processing device 10. For example, the above embodiment may be similarly applied to a case where an information processing device other than the information processing device 10 executes a program, or a case where the information processing device 10 and another information processing device cooperate to execute a program.

[0089] The program may be distributed via a network such as the Internet. The program may be recorded in a computer-readable storage medium such as a hard disk, a flexible disk (FD), a CD-ROM, a magneto-optical disk (MO), or a digital versatile disk (DVD). The program may be executed by being read from the storage medium by the information processing device 10 or the like.

[0090] The following supplementary notes are further disclosed regarding the embodiments including the above examples.

[0091] (Appendix 1) Obtain multiple parameters for the measures, Executing a plurality of simulations for the measures in a virtual space based on the plurality of acquired parameters; Carrying out a relative evaluation based on the results of the plurality of simulations carried out; outputting a combination of indicators of multiple perspectives that are considered important by stakeholders for the policy based on the result of the relative evaluation; From the output combinations, commonalities between the stakeholders are identified. An information processing program that causes a computer to execute a process.

[0092] (Appendix 2) The process of performing the relative evaluation is generating a Pareto Frontier based on the results of the plurality of simulations; The relative evaluation based on the results of the plurality of simulations on the Pareto frontier is performed for each of the stakeholders. 2. The information processing program according to claim 1, further comprising:

[0093] (Appendix 3) The process of performing the relative evaluation based on the results of the plurality of simulations on the Pareto frontier includes: selecting pairs of points on the Pareto Frontier based on the vertices of each of the indices on the Pareto Frontier; Performing said relative evaluation on said pairs 3. The information processing program according to claim 2, further comprising:

[0094] (Appendix 4) The process of selecting the pair includes: Each combination of the vertices and the combination of the center of gravity of the vertex and the vertex farthest from the center of gravity are selected as the pair. 4. The information processing program according to claim 3, further comprising:

[0095] (Appendix 5) The process of selecting the pair includes: Dividing the Pareto Frontier into a plurality of triangles formed by each of the vertices and the centroid; Dividing the triangle into a plurality of second triangles formed by each of the second vertices of the triangle and a second centroid of the triangle; Among the third centroids of the second triangles, a combination of the third centroids that belong to different second triangles and are separated by a predetermined distance or more is selected as the pair. 5. The information processing program according to claim 4, further comprising:

[0096] (Appendix 6) The process of selecting the pair includes: Selecting the pair from a combination of second points in the second triangle based on their distance from the origin of the Pareto frontier. 6. The information processing program according to claim 5, further comprising:

[0097] (Appendix 7) The process of outputting the combination includes: The combinations are output using a parallel coordinate plot in which points on the Pareto frontier are plotted with each of the indices as an axis. 7. The information processing program according to claim 2, further comprising:

[0098] (Appendix 8) The process of identifying the common part includes: Select and identify the common portion from among the portions of the parallel coordinate plots of all the stakeholders where each of the indicators is equal to or greater than a respective predetermined threshold value. 8. The information processing program according to claim 7, further comprising:

[0099] (Appendix 9) Obtain multiple parameters for the measures, Executing a plurality of simulations for the measures in a virtual space based on the plurality of acquired parameters; Carrying out a relative evaluation based on the results of the plurality of simulations carried out; outputting a combination of indicators of multiple perspectives that are considered important by stakeholders for the policy based on the result of the relative evaluation; From the output combinations, commonalities between the stakeholders are identified. An information processing device including a control unit that executes processing.

[0100] (Appendix 10) The process of performing the relative evaluation includes: generating a Pareto Frontier based on the results of the plurality of simulations; The relative evaluation based on the results of the plurality of simulations on the Pareto frontier is performed for each of the stakeholders. 10. The information processing device according to claim 9, further comprising:

[0101] (Appendix 11) The process of performing the relative evaluation based on the results of the plurality of simulations on the Pareto frontier includes: selecting pairs of points on the Pareto Frontier based on the vertices of each of the indices on the Pareto Frontier; Performing said relative evaluation on said pairs 11. The information processing device according to claim 10, further comprising:

[0102] (Appendix 12) The process of selecting the pair includes: Each combination of the vertices and the combination of the center of gravity of the vertex and the vertex farthest from the center of gravity are selected as the pair. 12. The information processing device according to claim 11, further comprising:

[0103] (Appendix 13) The process of selecting the pair includes: Dividing the Pareto Frontier into a plurality of triangles formed by each of the vertices and the centroid; Dividing the triangle into a plurality of second triangles formed by each of the second vertices of the triangle and a second centroid of the triangle; Among the third centroids of the second triangles, a combination of the third centroids that belong to different second triangles and are separated by a predetermined distance or more is selected as the pair. 13. The information processing device according to claim 12, further comprising:

[0104] (Appendix 14) The process of selecting the pair includes: Selecting the pair from a combination of second points in the second triangle based on their distance from the origin of the Pareto frontier. 14. The information processing device according to claim 13, further comprising:

[0105] (Appendix 15) The process of outputting the combination includes: The combinations are output using a parallel coordinate plot in which points on the Pareto frontier are plotted with each of the indices as an axis. 15. The information processing device according to claim 10, further comprising:

[0106] (Appendix 16) The process of identifying the common part includes: Select and identify the common portion from among the portions of the parallel coordinate plots of all the stakeholders where each of the indicators is equal to or greater than a respective predetermined threshold value. 16. The information processing device according to claim 15, further comprising:

[0107] (Appendix 17) Obtain multiple parameters for the measures, Executing a plurality of simulations for the measures in a virtual space based on the plurality of acquired parameters; Carrying out a relative evaluation based on the results of the plurality of simulations carried out; outputting a combination of indicators of multiple perspectives that are considered important by stakeholders for the policy based on the result of the relative evaluation; From the output combinations, commonalities between the stakeholders are identified. An information processing method in which processing is performed by a computer.

[0108] (Appendix 18) The process of performing the relative evaluation includes: generating a Pareto Frontier based on the results of the plurality of simulations; The relative evaluation based on the results of the plurality of simulations on the Pareto frontier is performed for each of the stakeholders. 18. The information processing method according to claim 17, further comprising the steps of:

[0109] (Supplementary Note 19) The process of performing the relative evaluation based on the results of the plurality of simulations on the Pareto frontier includes: selecting pairs of points on the Pareto Frontier based on the vertices of each of the indices on the Pareto Frontier; Performing said relative evaluation on said pairs 19. The information processing method according to claim 18, further comprising the steps of:

[0110] (Supplementary Note 20) The process of selecting the pair includes: Each combination of the vertices and the combination of the center of gravity of the vertex and the vertex farthest from the center of gravity are selected as the pair. 20. The information processing method according to claim 19, further comprising the steps of:

[0111] (Supplementary Note 21) The process of selecting the pair includes: Dividing the Pareto Frontier into a plurality of triangles formed by each of the vertices and the centroid; Dividing the triangle into a plurality of second triangles formed by each of the second vertices of the triangle and a second centroid of the triangle; Among the third centroids of the second triangles, a combination of the third centroids that belong to different second triangles and are separated by a predetermined distance or more is selected as the pair. 21. The information processing method according to claim 20, further comprising the steps of:

[0112] (Appendix 22) The process of selecting the pair includes: Selecting the pair from a combination of second points in the second triangle based on their distance from the origin of the Pareto frontier. 22. The information processing method according to claim 21, further comprising the steps of:

[0113] (Appendix 23) The process of outputting the combination includes: The combinations are output using a parallel coordinate plot in which points on the Pareto frontier are plotted with each of the indices as an axis. 23. The information processing method according to any one of claims 18 to 22, further comprising the step of:

[0114] (Appendix 24) The process of identifying the common part includes: Select and identify the common portion from among the portions of the parallel coordinate plots of all the stakeholders where each of the indicators is equal to or greater than a respective predetermined threshold value. 24. The information processing method according to claim 23, further comprising the steps of:

[0115] (Appendix 25) A processor; a memory operatively connected to the processor; An information processing device comprising: Obtain multiple parameters for the measures, Executing a plurality of simulations for the measures in a virtual space based on the plurality of acquired parameters; Carrying out a relative evaluation based on the results of the plurality of simulations carried out; outputting a combination of indicators of multiple perspectives that are considered important by stakeholders for the policy based on the result of the relative evaluation; From the output combinations, commonalities between the stakeholders are identified. 23. An information processing apparatus comprising: [Explanation of symbols]

[0116] 10. Information processing device 10a Communication Interface 10b HDD 10c Memory 10d Processor 20 Communications Department 30 Storage section 31 Policy parameter data 32 Simulation result data 33 Relative Evaluation Data 34 Proposed Agreement Data 40 Control section 41 Acquisition Department 42 Simulation Department 43 Evaluation Department 44 Output section 45 Specific part 100 Information processing terminal

Claims

1. Obtain multiple parameters for the measures, Executing a plurality of simulations for the measures in a virtual space based on the plurality of acquired parameters; Carrying out a relative evaluation based on the results of the plurality of simulations carried out; outputting a combination of indicators of multiple perspectives that are considered important by stakeholders for the policy based on the result of the relative evaluation; From the output combinations, commonalities between the stakeholders are identified. An information processing program that causes a computer to execute a process.

2. The process of performing the relative evaluation includes: generating a Pareto Frontier based on the results of the plurality of simulations; The relative evaluation based on the results of the plurality of simulations on the Pareto frontier is performed for each of the stakeholders.

2. The information processing program according to claim 1, further comprising a process for:

3. The process of performing the relative evaluation based on the results of the plurality of simulations on the Pareto frontier includes: selecting pairs of points on the Pareto Frontier based on the vertices of each of the indices on the Pareto Frontier; Performing said relative evaluation on said pairs 3. The information processing program according to claim 2, further comprising a process for:

4. The process of selecting the pair includes: Each combination of the vertices and the combination of the center of gravity of the vertex and the vertex farthest from the center of gravity are selected as the pair.

4. The information processing program according to claim 3, further comprising a process for:

5. The process of selecting the pair includes: Dividing the Pareto Frontier into a plurality of triangles formed by each of the vertices and the centroid; Dividing the triangle into a plurality of second triangles formed by each of the second vertices of the triangle and a second centroid of the triangle; Among the third centroids of the second triangles, a combination of the third centroids which belong to different second triangles and are separated by a predetermined distance or more is selected as the pair.

5. The information processing program according to claim 4, further comprising a process for:

6. The process of selecting the pair includes: Selecting the pair from a combination of second points in the second triangle based on their distance from the origin of the Pareto frontier.

6. The information processing program according to claim 5, further comprising a process for:

7. The process of outputting the combination includes: The combinations are output using a parallel coordinate plot in which points on the Pareto frontier are plotted with each of the indices as an axis.

7. The information processing program according to claim 2, further comprising a process for:

8. The process of identifying the common portion includes: Select and identify the common portion from among the portions of the parallel coordinate plots of all the stakeholders where each of the indicators is equal to or greater than a respective predetermined threshold value.

8. The information processing program according to claim 7, further comprising a process for:

9. Obtain multiple parameters for the measures, Executing a plurality of simulations for the measures in a virtual space based on the plurality of acquired parameters; Carrying out a relative evaluation based on the results of the plurality of simulations carried out; outputting a combination of indicators of multiple perspectives that are considered important by stakeholders for the policy based on the result of the relative evaluation; From the output combinations, commonalities between the stakeholders are identified. An information processing device including a control unit that executes processing.

10. Obtain multiple parameters for the measures, Executing a plurality of simulations for the measures in a virtual space based on the plurality of acquired parameters; Carrying out a relative evaluation based on the results of the plurality of simulations carried out; outputting a combination of indicators of multiple perspectives that are considered important by stakeholders for the policy based on the result of the relative evaluation; From the output combinations, commonalities between the stakeholders are identified. An information processing method in which processing is performed by a computer.

Images