Event optimization device, event optimization method, and computer program

Abstract

To provide an event optimization device for satisfying a plurality of objects related to an event, an event optimization method, and a computer program.SOLUTION: An event optimization device 100 includes an information reception part 101 for receiving a plurality of pieces of behavior information about behaviors executed by or for objects related to a town event and a plurality of pieces of target information about a target to evaluate each of a plurality of behaviors, an information acquisition part 102 for acquiring related information about the plurality of behaviors, a simulation part 103 for proposing behavior plans to be executed to achieve a plurality of targets on the basis of the behavior information and the target information acquired by the information reception means, and the related information acquired by the information acquisition means, and executing a simulation for optimizing the event, and an output part 104 for outputting the simulation results.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to an event optimization device, an event optimization method, a computer program, and the like. [Background technology]

[0002] There is a known method for finding an optimization method for a certain event through simulation.

[0003] For example, Patent Document 1 discloses a simulation method that uses a GIS (Geographic Information System) to estimate the trade area spatial structure of existing stores in competitive business types and formats, thereby improving the sales forecast and trade area spatial structure prediction accuracy for new stores. Patent Document 2 discloses a simulation method that uses a dynamic simulation model to generate information that enables improving the performance and sustainability of a local government, organization, or commercial entity. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2004-185539 [Patent Document 2] Japanese Patent Application Laid-Open No. 2016-504682 Summary of the Invention [Problem to be solved by the invention]

[0005] However, the invention described in Patent Document 1 is a simulation method for satisfying those opening new stores. The invention described in Patent Document 2 uses a dynamic simulation model that takes into account the effects of various factors, but is a simulation aimed at investors in the development project. Therefore, it is not a simulation that satisfies multiple parties involved in the event.

[0006] An example of an objective of the present disclosure is to provide an event optimizer that satisfies multiple objectives related to an event. [Means for solving the problem]

[0007] An event optimization device in one aspect of the present disclosure includes an information receiving means for receiving a plurality of pieces of action information related to actions performed by or against objects involved in city events, and a plurality of pieces of goal information related to goals for evaluating each of the plurality of actions; an information acquisition means for acquiring related information related to each of the plurality of actions; a simulation means for performing a simulation to optimize the event by proposing each of the action plans to be executed to achieve the multiple goals based on the action information and goal information acquired by the information receiving means and each of the related information acquired by the information acquisition means; and an output means for outputting each of the simulation results.

[0008] An event optimization method in one aspect of the present disclosure receives multiple pieces of action information related to actions performed by or against objects involved in a city event, as well as multiple pieces of goal information related to goals for evaluating each of the multiple actions, obtains related information for each of the multiple actions, proposes action plans to be executed to achieve the multiple goals based on the action information and goal information, and each related information, performs a simulation to optimize the event, and outputs each of the simulation results.

[0009] A program in one aspect of the present disclosure causes a computer to receive multiple pieces of action information related to actions taken by or against objects involved in city events, as well as multiple pieces of goal information related to goals for evaluating each of the multiple actions, obtain related information for each of the multiple actions, propose action plans to be executed to achieve the multiple goals based on the action information and goal information, and each related information, and perform a simulation to optimize the event, and output each of the simulation results. [Effects of the Invention]

[0010] One example of the effect of the present invention is that it is possible to carry out a simulation that satisfies multiple subjects involved in an event. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a block diagram showing the configuration of an event optimization device according to the first embodiment. [Figure 2] FIG. 2 is a diagram showing a hardware configuration in which the event optimization device according to the first embodiment is realized by a computer device and its peripheral devices. [Figure 3] FIG. 3 is a diagram illustrating an overview of a simulation for optimizing events by proposing an action plan to achieve multiple goals. [Figure 4] FIG. 4 is a diagram showing an example of an action plan proposed by the simulation unit in this embodiment for an event of movement in a city. [Figure 5] FIG. 5 is a flowchart showing the operation of the simulation in the first embodiment. [Figure 6] FIG. 6 is a diagram illustrating a modified example of the first embodiment. [Figure 7] FIG. 7 is a diagram illustrating another modified example of the first embodiment. [Figure 8] FIG. 8 is a block diagram showing the configuration of an event optimization device according to the second embodiment. [Figure 9] FIG. 9 is a diagram for explaining an outline of a simulation that proposes an action plan for achieving each goal of a plurality of processes. [Figure 10] FIG. 10 is a diagram illustrating how the actual evaluation is reflected in the action plan proposed by the simulation unit. [Figure 11] FIG. 11 is a diagram illustrating a hardware configuration of the simulation unit. [Figure 12] FIG. 12 is a flowchart showing the operation of the simulation in the second embodiment. [Figure 13] FIG. 13 is a flowchart showing the operation of the simulation in the modified example of the second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0012] Next, an embodiment will be described in detail with reference to the drawings.

[0013] [First embodiment] The event optimization device 100 in the first embodiment is a device that searches for a method for optimizing events by proposing action plans for multiple targets related to events that occur daily throughout a city, for example. FIG. 1 is a block diagram showing the configuration of the event optimization device 100 in the first embodiment. Referring to FIG. 1, the event optimization device 100 includes an information receiving unit 101, an information acquisition unit 102, a simulation unit 103, and an output unit 104. Next, the configuration of the event optimization device 100 in the first embodiment will be described in detail.

[0014] 2 is a diagram illustrating an example of a hardware configuration in which the event optimization device 100 according to the first embodiment of the present disclosure is realized by a computer device 500 including a processor. As shown in FIG. 2, the event optimization device 100 includes a central processing unit (CPU) 501, memories such as read-only memory (ROM) 502 and random access memory (RAM) 503, a storage device 505 such as a hard disk for storing a program 504, a communication interface (I / F) 508 for network connection, and an input / output interface 511 for inputting and outputting data. In the first embodiment, part of the information acquired by the information acquisition unit 102 is input to the event optimization device 100 via the communication I / F 508. The event optimization device 100 is also connected to an input device 509 and an output device 510 via a bus 512.

[0015] CPU 501 runs an operating system to control the entire event optimization device 100 according to the first embodiment of the present invention. CPU 501 also reads programs and data into memory from a recording medium 506 attached to, for example, a drive device 507. CPU 501 also functions as information receiving unit 101, information acquisition unit 102, simulation unit 103, and output unit 104 in the first embodiment, and as parts thereof, and executes processing or commands in the flowchart shown in FIG. 5, which will be described later, based on the program.

[0016] The recording medium 506 is, for example, an optical disk, a flexible disk, a magneto-optical disk, an external hard disk, or a semiconductor memory card. The semiconductor memory card, which is part of the recording medium, is a non-volatile storage device in which the program is recorded. The program may also be downloaded from an external computer (not shown) connected to a communication network.

[0017] The input device 509 is realized by, for example, a mouse, a keyboard, or built-in key buttons, and is used for input operations. The input device 509 is not limited to a mouse, a keyboard, or built-in key buttons, and may be, for example, a touch panel. In the first embodiment, information input to the information receiving unit 101 is input to the event optimization device 100 via the input device 509. The output device 510 is realized by, for example, a display, and is used to check the output.

[0018] As described above, the first embodiment shown in Fig. 1 is realized by the computer hardware shown in Fig. 2. However, the means for realizing each unit of the event optimization device 100 in Fig. 1 is not limited to the configuration described above. Furthermore, the event optimization device 100 may be realized by a single physically coupled device, or by two or more physically separated devices connected by wire or wirelessly. For example, the input device 509 and the output device 510 may be connected to the computer device 500 via a network.

[0019] The information receiving unit 101 is a means for receiving multiple pieces of behavioral information related to actions performed by or toward objects related to city events, as well as multiple goal information related to goals for evaluating each of the actions of the multiple objects. City events are a concept that includes events that can occur in daily life, such as the movement of objects in a city, the establishment of a large commercial facility, or the attraction of customers to a store. Objects related to city events include the people, objects, and events that make up a city and the city's environment, which are affected in some way by city events. Examples of people that make up a city include those who have some connection to the city, such as residents of the city, people who commute to work or school in the city, or visitors who come to shop or play in the city, as well as corporations such as businesses. Examples of things that make up a city include non-human objects that exist in the city, such as buildings (such as buildings and residences), tenant stores, parks, roads, vehicles (such as cars and bicycles), facilities (such as ports and airports), and infrastructure for water supply and sewerage, and energy (such as electricity and gas). The things that make up a city include, for example, events held in the city, such as sightseeing tours, sporting events, music events, and cultural events. The city environment includes, for example, the state of the city's environment, such as temperature, humidity, noise, light intensity, carbon dioxide concentration, PM2.5, photochemical smog, crime rate, and population density. Behavioral information is an action performed by an object or a plan scheduled for the object, and is information necessary for the event optimization device 100 to determine the action or plan to be optimized. Specific examples of behavioral information include, for example, when the event is movement within a city, if the object is a person, information such as the means of transportation, information on the departure point and destination, and departure time can be included. If the object is a transportation vehicle (thing), information such as the transportation vehicle's travel capacity, information on the departure point and destination of the transportation vehicle, and departure time can be included. If the object is a sightseeing tour (event), information such as the number of participants, attribute information of the participants, and tour schedule (information on the tour's departure point and destination or departure time) can be included. If the object is a city environment, it is an action to change the environmental state, such as plans for reducing carbon dioxide emissions or noise pollution.

[0020] The multiple behavioral information refers to behavioral information (related to the object) performed by or on the object, received by the event optimization device 100 when separate simulations are performed. The multiple objects have some kind of relationship with each other regarding the same event. Examples of the relationship include related behavioral information, human relationships (family / relatives / acquaintances, employment / business), ownership relationships (between a person and a person's car), and subordinate relationships (between a building owner and a tenant). In this embodiment, the multiple behaviors are actions performed by or on objects classified into the four categories of people, objects, events, and the city environment that make up the town described above. The objects performing or being performed on multiple behaviors may belong to the same category or different categories. For example, if the event is movement within a town, all the objects may be people, such as people commuting to work or school in the town, all the objects may be objects, such as vehicles, or all the objects may be events, such as sightseeing tours. When an event involves movement within a city, the objects that perform or are performed on belong to different categories. This includes not only people commuting to work or school in the city, but also objects classified as buildings (things) such as buildings and residences, events, or the city's environment. In this case, the simulation unit 103 (described later) proposes an action plan related to people commuting to work or school in the city, as well as an action plan related to buildings (things) such as buildings and residences, events, or the city's environment. In this embodiment, the objects may include all objects that belong to the people, objects, events, and city's environment that make up the city, and action plans related to each may be proposed to explore an optimization method for the event. The greater the number or variety of objects when performing a simulation, the more widely optimized action plans will be proposed for various objects related to city events.

[0021] The target information is information that defines a target value for the evaluation level of an action performed by or toward a target. The target value is, for example, represented by a numerical value of an evaluation parameter set for each target, and the evaluation parameter has a target value and a lower limit. If the target is a person making up a town, the evaluation parameter may be, for example, a numerical value indicating the degree of satisfaction obtained from a questionnaire answered by the target person, or a numerical value indicating the number or frequency of reactions appearing in the target person's appearance information. The reactions appearing in the appearance information are reactions that can be inferred from facial expressions and body states, and are inferred from information obtained by detecting signals from sensors installed in the town or analyzing images from cameras installed in the town. For example, if the camera image shows that the target person is smiling, the target can be evaluated as satisfied with the action. Conversely, if the camera image shows that the target person is angry, the target can be evaluated as dissatisfied with the action. If the target is an object, for example, an evaluation parameter based on information about the object obtained from a sensor or camera is used. If the target is an event, for example, a tallyable numerical value related to the event, such as the number of participants, is used as the evaluation parameter. If the target is the environment, the above-mentioned numerical values ​​indicating the state of the environment are used as evaluation parameters.

[0022] A specific example of goal information will be described. Assume that the behavioral information is a person's commute to work or school in a city, and the goal is to travel from home to work in the shortest time. For example, the goal information is received as a short delay time from the theoretical shortest required time calculated from the distance from home to work and the travel speed when using the selected means of transportation. Specifically, the target value is received as a delay time within 10% of the shortest required time, using the shortest required time as an evaluation parameter, and the lower limit is received as a delay time required to meet the travel deadline. The information receiving unit 101 receives input of behavioral information and goal information via the input device 509 or the like when the event optimization device 100 executes a simulation. When the information receiving unit 101 receives input of behavioral information and goal information from a user, it outputs the input behavioral information and goal information to the information acquiring unit 102 and the simulation unit 103.

[0023] The information acquisition unit 102 is a means for acquiring relevant information about each of a plurality of actions. The relevant information includes, for example, relevant information about the target, and people, objects, events, and the town environment that have some relationship with the target. The relevant information about people includes, for example, information obtained from the appearance of attributes, status, position, height, physique, actions, or action history (action history), as well as personal information (e.g., name, age, gender, address, occupation, hobbies, preferences, health status, income, savings, and family composition). The relevant information about objects includes, for example, the attributes, status, situation, position, size, action status, action history, shape, name, or price of the object. The relevant information about events includes the organizer, content of the event, event status, event location, size (area of ​​the event venue, number of participants), event history, or event name. Among the relevant information, information that can be automatically acquired from sensors or the like is acquired, for example, by detecting signals from sensors installed in the town or analyzing images from cameras installed in the town, and is stored in the storage device 505. Related information is acquired and updated via the network at predetermined intervals (e.g., every 10 minutes) in the storage device 505. Other information such as personal information is stored in the storage device 505 via the input device 509, for example, when the content of the information is updated.

[0024] When the behavioral information and goal information are input from the information receiving unit 101, the information acquiring unit 102 refers to the storage device 505 and acquires related information about the target and people, objects, events, and city environments that have some relationship with the target. The related information about the target's behavior is, specifically, information that is taken into consideration when the simulation unit 103 proposes an action plan. Specifically, for example, if the target is a person and the behavioral information is a trip to a home, the information acquiring unit 102 acquires information about the current locations of the target's family members. The information acquiring unit 102 outputs the acquired related information to the simulation unit 103.

[0025] The simulation unit 103 is a means for proposing each action plan to be executed to achieve multiple goals based on the multiple pieces of action information and multiple pieces of goal information received by the information receiving unit 101 and the multiple pieces of related information acquired by the information acquiring unit 102. When the multiple pieces of related information are input from the information acquiring unit 102, the simulation unit 103 calculates all possible action plans to achieve the multiple goals based on the multiple pieces of action information and multiple pieces of goal information input from the information receiving unit 101, and performs a brute-force verification of all calculated action plans. Specifically, during the learning process, the simulation unit 103 generates, for each combination, a trained model showing the relationship between one or more combinations (simulated events) of related information, action information, and target values ​​acquired as training data and an action plan (that achieves the goal) that indicates the correct label for the training data, using a neural network, graph AI (artificial intelligence), or other machine learning algorithm. During learning, the related information is input from the information acquiring unit 102, and the trained model is verified against evaluation parameters, target values, and lower limit values, thereby optimizing the model. Next, in the estimation process, when behavioral information and goal information for the input related information for an actual event are input from the information receiving unit 101, a trained model corresponding to the combination of the related information, behavioral information, and goal value is used to estimate a possible behavioral plan for achieving the goal. As described above, learning a model using a simulated event and estimating an behavioral plan is a simulation. At this time, the simulation unit 103 verifies all behavioral plans while executing the simulated event in consideration of the related information input from the information acquiring unit 102. For example, the information receiving unit 101 receives behavioral information from one of the subjects, such as shopping on the way home and goal information including a goal value of returning home by 6:00 PM. Furthermore, behavioral information from the subject's family, such as meeting the family on the way home from the store where they shopped, and goal information including a goal value of meeting the family by 6:00 PM, is also received.In this case, when the information acquisition unit 102 acquires information from current location information that one of the subjects is on his / her way home and that the subject's family is at a store near the home, the simulation unit 103 can propose to the subject a route to home that passes through the store where the subject's family is, and propose an action plan to the subject's family to wait at the store where they are currently located. Next, the simulation unit 103 extracts action plans that enable each subject to achieve the target value from the verification results. An achievable action plan is, for example, an action plan that does not fall below the target's lower limit. Then, the simulation unit 103 identifies, from the extracted action plans for each subject, the action plan with the highest degree of achievement. The plan with the highest degree of achievement is an achievable action plan that minimizes the difference from the target value. The simulation unit 103 outputs information about the identified action plans to the output unit 104.

[0026] FIG. 3 is a diagram illustrating an overview of a simulation for optimizing an event by proposing an action plan for achieving multiple goals. As shown in FIG. 3, a city event a[n] is divided into multiple target events a1[n], a2[n], and a3[n], each of which is executed in parallel. In this embodiment, the simulation is repeatedly performed under different conditions to explore an optimization method for a specific event. In FIG. 3, n indicates an arbitrary timing at which the simulation is performed. The simulation unit 103 simulates simulated events (d1[n+1], d2[n+1], and d3[n+1]) of action plans (c1[n], c2[n], and c3[n]) that achieve the target values ​​(b1[n], b2[n], and b3[n]) of the goal information received by the information receiving unit 101. The simulation unit 103 then executes a simulation to estimate an action plan that can achieve the goal using simulated events (d1[n+1], d2[n+1], and d3[n+1]) that combine the action plans (c1[n], c2[n], and c3[n]), and generates the action plan. The simulated event d[n+1] is an event that occurs when the action plan proposed by the results of a simulation executed at an arbitrary timing n is actually tried in real space for the city event a[n].

[0027] The output unit 104 is a means for outputting the action plan proposed (generated) by the simulation unit 103. When information about the action plan proposed by the simulation unit 103 is input to the output unit 104, the output unit 104 displays the information about the action plan via the output device 510 or the like so that the user who executed the simulation can confirm the information about the action plan.

[0028] FIG. 4 is a diagram illustrating an example of an action plan proposed by the simulation unit 103 in this embodiment for a movement event in a city. FIG. 4 illustrates an example of an action plan proposed by the simulation unit 103 based on the behavior information and goal information (evaluation parameters, target values, and lower limit values) received by the information receiving unit 101 and the related information acquired by the information acquiring unit 102. As illustrated in FIG. 4, the target is a human commuter or student. One piece of behavior information is movement from point A to point B while walking, and the other piece of behavior information is movement from point B to point A while walking. For both, the evaluation parameter is, for example, the delay time from the shortest required time. The information acquiring unit 102 acquires attribute information such as the age and gender of multiple targets as related information to take into account the walking speed of the targets. In this case, the simulation unit 103 can present multiple targets with a route to a destination and the accurate time to reach the destination by, for example, providing one target with the time required to move around point A and another with information required to move around point B. In this case, if the multiple targets have different ages or genders, the time required to reach the destination is presented taking these differences into consideration. In another example, the target is a transportation vehicle, which is a good, and one piece of behavioral information is the transportation of mistakenly loaded luggage to destination A, and the other piece of behavioral information is the transportation of luggage to be transported to destination A. In both cases, for example, the delay time from the shortest required time is used as the evaluation parameter. The information acquisition unit 102 acquires, as related information, the type of luggage (fragile, etc.), movement history, movement schedule, etc. of the transportation vehicle belonging to the same transportation company as the target. In this case, the simulation unit 103 can, for example, drive to destination A for the mistakenly loaded luggage so that it can be transported to the actual destination A, and present the location and time for handing over the luggage to a transportation vehicle that can load it. In another example, if the target is a sightseeing tour, which is an event, and the behavioral information is merging with another tour, for example, the time required for merging is used as the evaluation parameter. The information acquisition unit 102 acquires, as related information, sightseeing tour information (number of participants, participant attribute information, tour schedule) operated by the same operating company as the target.In this case, the simulation unit 103 can present, for example, the location and time of meeting with other tours, the route and travel schedule for visiting tourist spots, etc. However, the example shown in FIG. 4 is an example of an action plan proposed by the simulation unit 103, and the action plan proposed by the simulation unit 103 in this embodiment is not limited to this. In the three examples described above, examples were shown in which the targets were the same type, i.e., people, objects, or events (the targets belong to the same category), but simulations may also be performed for action plans in which the targets include different types of targets, i.e., people, objects, events, and environments (the targets belong to different categories). Also, in the example of FIG. 4, the same evaluation parameter is used for multiple pieces of destination information, but different evaluation parameters may also be used. Also, in the example in which the target is a transportation vehicle, the delay time from the shortest required time is used as the evaluation parameter, but the minimum fuel cost when transporting using the transportation vehicle currently being driven may also be used as the evaluation parameter.

[0029] The operation of the event optimization device 100 configured as above will be described with reference to the flowchart in Fig. 5. Fig. 5 is a flowchart showing an outline of the operation of the event optimization device 100 in the first embodiment. Note that the processing according to this flowchart may be executed based on program control by the processor described above.

[0030] 5, first, the information receiving unit 101 receives behavior information relating to behaviors performed by or against objects related to events in the city, as well as multiple pieces of goal information relating to goals for evaluating each of the multiple behaviors, and outputs the multiple pieces of behavior information and the multiple pieces of goal information to the information acquiring unit 102 and the simulation unit 103 (step S101). Next, the information acquisition unit 102 acquires related information relating to a plurality of actions, and outputs the acquired related information to the simulation unit 103 (step S102). Next, the simulation unit 103 performs a simulation to propose each action plan to be executed to achieve the goal and optimize the event based on the multiple pieces of behavioral information and goal information received by the information receiving unit 101 and the multiple pieces of related information acquired by the information acquiring unit 102 (step S103). Finally, the output unit 104 outputs each of the results of the simulation performed by the simulation unit 103 (step S104). This is how the event optimization device 100 completes the simulation operation.

[0031] Next, the effects of the first embodiment of the present disclosure will be described. The event optimization device 100 in the above-described embodiment can perform a simulation in which multiple targets related to an event are satisfied. This is because the simulation unit 103 proposes an action plan for achieving each goal related to multiple targets. Conventional simulations have performed simulations in which only a single target is satisfied. Furthermore, the event optimization device 100 in this embodiment performs a simulation by taking into account related information input by the simulation unit 103 from the information acquisition unit 102. This makes it possible to propose a more detailed action plan for achieving the goal.

[0032] A modified example of the first embodiment will be described. FIG. 6 is a diagram showing an example of an action plan proposed by the simulation unit 103 of this embodiment in the event of the establishment of a large commercial facility. In the first embodiment, the example in FIG. 4 was described using the case where multiple targets have the same position. However, in this modified example, as shown in FIG. 6, multiple targets have different positions and different goals for the same event, i.e., the establishment of a large commercial facility. In this case, when proposing each action plan to be executed to achieve multiple goals, the simulation unit 103 proposes each action plan such that the evaluation parameters of the targets associated with each target do not fall below their lower limit values ​​and the sum of the differences from the target values ​​is minimized. For example, in the example of FIG. 6, assume that the behavioral information received from the large commercial facility operator is an increase in the number of visitors, and from nearby residents is a reduction in the number of complaints, including noise and traffic congestion. However, if the number of visitors to the large commercial facility increases, there is a possibility that nearby residents will complain due to the occurrence of noise and traffic congestion. Therefore, the simulation unit 103 proposes an action plan that satisfies both targets to a certain extent. In addition, the establishment of a large commercial facility also affects sales at surrounding commercial facilities by changing the flow of people. Therefore, people involved with surrounding commercial facilities can also be included in the example of Figure 6. As described above, a modification of the first embodiment has been described. According to this modification, it is possible to propose an action plan for each of the targets affected by the establishment of a large commercial facility, minimizing the sum of the differences between the target values ​​and the targets. This makes it possible to obtain an optimal solution for each target related to multiple targets. Conventional simulations have mainly predicted only changes in the flow of shoppers to determine the economic impact on the town, and therefore do not satisfy the multiple targets related to the establishment of a large commercial facility.

[0033] Another variation of the first embodiment will be described. FIG. 7 is a diagram showing an example of an action plan proposed by the simulation unit 103 of this embodiment for the event of attracting customers to a restaurant. In the example of FIG. 7, for example, the behavioral information may include an increase in sales as a goal for the restaurant and an increase in satisfaction with working conditions for employees. However, improving the restaurant's sales will affect the working conditions of the employees. Therefore, the simulation unit 103 proposes an action plan that satisfies both targets to a certain extent. That is, when proposing each action plan to be executed to achieve multiple goals, the simulation unit 103 proposes each action plan that does not fall below the lower limit value of the evaluation parameter for the target associated with each target and minimizes the sum of the differences from each target value. This makes it possible to obtain an optimal solution for each goal associated with multiple targets affected by the event of attracting customers to the restaurant.

[0034] [Second embodiment] Next, a second embodiment of the present disclosure will be described in detail with reference to the drawings. Below, explanations of the contents that overlap with the above explanation will be omitted to the extent that the explanation of this embodiment is not unclear. As with the computer device shown in FIG. 2, the functions of each component in each embodiment of the present disclosure can be realized not only by hardware but also by a computer device or firmware based on program control.

[0035] Fig. 8 is a block diagram showing the configuration of an event optimization device 110 according to a second embodiment of the present disclosure. With reference to Fig. 8, the event optimization device 110 according to the second embodiment will be described, focusing on the parts that differ from the event optimization device 100 according to the first embodiment. The event optimization device 110 according to the second embodiment includes an evaluation receiving unit 111, an information receiving unit 112, an information acquisition unit 113, a simulation unit 114, and an output unit 115.

[0036] The second embodiment differs from the first embodiment in that events in a city are divided into multiple processes, action information and goal information for the multiple processes are received, and action plans for achieving the goals for each of the multiple processes are proposed. That is, the information receiving unit 112 receives action information and goal information for each of the multiple processes, the information acquisition unit 113 acquires related information about the actions of each of the multiple processes, and the simulation unit 114 proposes action plans to be executed for each of the multiple processes and performs a simulation to optimize the event.

[0037] 9 is a diagram illustrating an overview of a simulation that proposes an action plan for achieving each goal of multiple processes. As shown in FIG. 9, the simulation unit 114 of this embodiment is configured to divide multiple target events a[n] in a city in real space into a1[n], a2[n], and a3[n] in chronological order, and execute each event serially. The simulation unit 114 executes simulated events (d1[n+1], d2[n+1], and d3[n+1]) of action plans (c1[n], c2[n], and c3[n]) that achieve the target values ​​(b1[n], b2[n], and b3[n]) of the goal information received by the information receiving unit 112 for each event. The simulation unit 103 then generates an action plan by performing a simulation to estimate an action plan that can achieve the goal using simulated events (d1[n+1], d2[n+1], and d3[n+1]) that combine the action plans (c1[n], c2[n], and c3[n]). The simulated city event d[n+1] is an event that occurs when an action plan proposed based on the results of a simulation performed at an arbitrary timing n is actually tested in real space for the city event a[n]. In the simulation unit 114 of this embodiment, the information receiving unit 112 also receives multiple pieces of target information and multiple pieces of goal information, the information acquisition unit 113 acquires each piece of related information, and the simulation unit 114 proposes multiple action plans. For this reason, the simulation unit 114 has a configuration that combines the configuration shown in FIG. 3 and the configuration shown in FIG. 9. In this embodiment, the plurality of target information, the plurality of goal information, the plurality of (each) related information, or the plurality of action plans may be simply referred to as target information, goal information, related information, or action plan, respectively, in order to clearly indicate the difference from the first embodiment. Also, the second embodiment is significantly different from the first embodiment in that it includes an evaluation receiving unit 111. Each configuration of the second embodiment will be described below, taking into account the above differences from the first embodiment.

[0038] The evaluation receiving unit 111 is a means for receiving actual evaluations of action plans previously proposed by the event optimization device 110. The actual evaluation indicates, for example, the difference between the target value of an evaluation parameter when the action plan is executed in real space. If the value of the evaluation parameter in real space is a parameter calculated based on information acquired by a sensor or a camera, it is input via the communication I / F 508, and the value of other parameters is input via, for example, the input device 509. The evaluation receiving unit 111 calculates the difference between the input parameter and the target value, and stores the difference between the input parameter and the target value as a simulation result with a higher priority in ascending order of difference from the target value, together with the simulation model, in the storage device 505. The evaluation receiving unit 111 also stores, from among the simulation models stored in the storage device 505, simulation models with a higher actual evaluation (higher priority) in the information accumulation unit 602, which will be described later.

[0039] The information receiving unit 112 receives behavior information and goal information for each of the multiple processes. As an example of the multiple processes, in the case of a person's movement, the processes can be divided into an outbound journey from a departure point to a destination point, a rest at the destination, and a return journey from the destination point to the departure point. The information receiving unit 112 receives behavior information for determining behavior such as a means of transportation and travel time for each of the multiple processes, and goal information regarding a goal for evaluating behavior in each process, and outputs the input behavior information and goal information to the information acquisition unit 113 and the simulation unit 114. The specific operation of the information receiving unit 112 for receiving behavior information and goal information is the same as that of the information receiving unit 101, and therefore will not be described here.

[0040] The information acquisition unit 113 acquires related information about actions in multiple processes. When the information acquisition unit 113 receives action information and goal information about multiple processes from the information receiving unit 112, it refers to the storage device 505 and acquires related information about each of the multiple processes. In the case of the above-mentioned human movement from the information receiving unit 112, for example, the information may be the behavioral history of a person traveling by the same means of transportation for each of the outbound journey, the rest period at the destination, and the return journey. When the information receiving unit 112 acquires the related information, it outputs the acquired related information to the simulation unit 114. The specific operation of the information acquisition unit 113 to acquire the related information is the same as that of the information acquisition unit 102, and therefore will not be described here.

[0041] Before executing a simulation, the simulation unit 114 first determines a simulation model to be applied based on the similarity of events for multiple processes and actual evaluations. The similarity of events is determined, for example, based on the similarity of object and behavior information. In the case of movement within a city, the similarity is determined taking into consideration information about the moving object, the movement route such as the starting point and destination, and the attributes of the target person or object.

[0042] 10 is a diagram illustrating how actual evaluations are reflected in the action plan proposed by the simulation unit 114. As shown in FIG. 10, the evaluation receiving unit 111 receives an actual evaluation for an action (time series [n-1]) proposed by a past simulation, and stores the evaluation information in, for example, the storage device 505 in association with the event, goal information, and action plan. As described above, the evaluation receiving unit 111 also stores, among the simulation models stored in the storage device 505, simulation models with high actual evaluations (high priority) in the information accumulation unit 602. Therefore, when a simulation is subsequently performed (time series [n] and time series [n-1]), the information accumulation unit 602 is referenced and a simulation model with a high evaluation in the simulation results for similar events is applied.

[0043] The simulation unit 114 also executes a simulation of a system constructed using digital twin technology in a virtual space. A digital twin is a solution for predicting what will happen in real space by collecting information acquired in real time and using technologies such as AI (Artificial Intelligence) to recreate and simulate situations that could actually occur in a virtual space on a computer. When simulating in virtual space, a dynamic map is created by overlaying time-series information and future prediction information acquired through sensor terminals installed in various locations on data representing map information, and the actual situation is recreated as a twin in the virtual space. To represent real-space events on the dynamic map, the information used in the simulation is accumulated in layers categorized by purpose. In this embodiment, a simulation is executed by recreating in virtual space what could happen when an action plan proposed by the simulation unit 114 is executed in real space.

[0044] FIG. 11 is a diagram illustrating an example of a hardware configuration when a simulation using a digital twin is executed by the simulation unit 114 according to the second embodiment of the present disclosure. As illustrated in FIG. 11 , the input / output interface 601 inputs signal information acquired by devices installed in the real space, such as sensors, and device setting information to the information storage unit 602. In addition to the information from the input / output interface 601, the information storage unit 602 stores the simulation model used in the simulation, criteria for determining whether the simulation results are normal, and past simulation results. In this embodiment, behavior information and goal information input from the information receiving unit 112 and related information input from the information acquisition unit 113 are stored in the information storage unit 602 via the input / output interface 601. The input / output device 603 receives input settings corresponding to the situation in the real space from the user. The simulation execution unit 604 selects a model to be used in the simulation from the information storage unit 602 and executes a simulation while reproducing the situation in the real space in a virtual space based on the information input from the information receiving unit 112 and the information acquisition unit 113 and the setting conditions input from the input / output device 603. The evaluation unit 605 evaluates whether the simulation results are normal based on the results output from the simulation execution unit 604. The user can arbitrarily set the criteria for determining whether the simulation results stored in the information accumulation unit 602 are normal, but examples include the following: in multiple processes, the value of the evaluation parameter for the action does not fall below a lower limit value, and the sum of the differences from the target values ​​in multiple processes is smallest. If the evaluation unit 605 evaluates the simulation results as abnormal, the simulation execution unit 604 changes the simulation model and setting conditions and repeats the simulation until the evaluation unit 605 evaluates the simulation results as normal. If the evaluation unit 605 determines that the simulation results are normal, the simulation application unit 606 outputs the evaluation result to the output unit 115 and displays it via the output device 510 or the like so that the user who executed the simulation can confirm information about the action plan.Furthermore, the simulation execution unit 604 may start controlling devices such as actuators to be reflected in the system in the real space based on the action plan proposed by the simulation.

[0045] When the simulation unit 114 evaluates the simulation results as normal, the output unit 115 displays information about the action plan via the output device 510 or the like so that the user who executed the simulation can confirm the information.

[0046] Next, the operation of the event optimizer 110 will be described with reference to the flowchart shown in Fig. 12. The processing according to this flowchart may also be executed based on program control by the CPU described above.

[0047] 12, first, the information receiving unit 112 receives, as the behavioral information, a plurality of pieces of behavioral information for each of a plurality of processes, and receives, as the goal information, a plurality of pieces of goal information for each of the plurality of processes, and outputs the received plurality of pieces of behavioral information and goal information to the simulation unit 114 (step S201). Next, the information acquisition unit 113 acquires related information about a plurality of actions for each of the plurality of processes, and outputs the acquired related information to the simulation unit 114 (step S202). Next, the simulation unit 114 determines the simulation model to be applied to each of the past simulations based on the similarity and priority information (step 203). Next, the simulation unit 114 executes a simulation in a virtual space to propose a plurality of action plans for each of the plurality of processes and optimize the event based on the plurality of pieces of behavioral information and plurality of pieces of goal information received by the information receiving unit 112 and the plurality of pieces of related information acquired by the information acquiring unit 113 (step S204). If the simulation result is evaluated as normal (step S205; Yes), the simulation unit 114 outputs the simulation result to the output unit 115. If the simulation result is not evaluated as normal (step S205; No), the simulation is repeated until the simulation result is evaluated as normal. Finally, the output unit 115 outputs the results of the simulation performed by the simulation unit 114 (step S206). This completes the simulation operation of the event optimizer 110. However, the step of evaluating the simulation result as normal in step S205 may be omitted in this embodiment.

[0048] Next, the effects of the second embodiment of the present disclosure will be described. In the event optimization device 110 in the second embodiment described above, the information receiving unit 112 receives action information and goal information for each of a plurality of processes, the information acquisition unit 113 acquires related information necessary to evaluate each of the plurality of processes, and the simulation unit 114 proposes a plurality of action plans for each of the plurality of processes and executes a simulation to optimize the event. Thus, the event optimization device 110 can propose an action plan optimized for each process of the event, thereby proposing an action plan that is more optimized for the event as a whole. Furthermore, the simulation unit 114 applies a simulation model that has been highly evaluated in real space in the past for similar events. Therefore, the simulation unit 114 can propose an action plan that has been highly evaluated in real space.

[0049] According to the simulation using the digital twin by the simulation unit 114 in this embodiment, the simulation can be performed by reproducing the situation in the real space using information acquired in real time, so that highly accurate simulation results can be applied to the real space.

[0050] Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

[0051] For example, although multiple operations are described in a sequence in the form of a flowchart, the sequence does not limit the order in which the multiple operations are performed. Therefore, when implementing each embodiment, the sequence of the multiple operations can be changed within the scope that does not affect the content.

[0052] In the first embodiment, the information accepting unit 101 accepts goal information input by a user. However, the means for accepting the input of goal information is not limited to this. For example, if a city administrator has published a policy regarding city events in advance, the policy may be used as goal information. In this case, the information accepting unit 101 accepts the input of goal information by searching for information regarding goal information, such as a policy regarding city events, via a network and receiving the information. Furthermore, in the first embodiment, the goal information accepted by the information accepting unit 101 may be updated as the simulation is repeatedly performed based on information received by the information accepting unit 101 via a network. In this way, if goal information is accepted and updated without user intervention and related information can be automatically acquired by the information acquiring unit 102 from sensors, cameras, etc., a user only needs to input behavioral information related to the targets once, and action plans for multiple targets can be automatically proposed by simulation without human intervention, thereby enabling the exploration of methods for optimizing city events.

[0053] Furthermore, in the second embodiment, when the simulation execution unit 604 executes an action plan proposed by simulation in the real space and starts controlling devices such as actuators in the real space, the evaluation receiving unit 111 receives an actual evaluation of the executed action plan. If the actual evaluation does not reach the lower limit of the target value even after a certain period of time (e.g., one month) has elapsed and the goal has not been achieved, the simulation unit 114 can change the simulation model to be applied and execute the simulation again. In this case, the flow of proposing an action plan by the simulation unit 114, executing the action plan in the real space, and receiving an evaluation of the execution in the real space by the evaluation receiving unit 111 can be automatically repeated until the evaluation receiving unit 111 receives notification that the goal has been achieved.

[0054] Fig. 13 is a flowchart showing the operation of a simulation in a modified example of the second embodiment. The flow from step S301 to step S305 in Fig. 13 is the same as the flow from step S201 to step S205 in Fig. 12. In the modified example of the second embodiment, in step S306, the action plan proposed in the simulation is executed in real space, and control of devices such as actuators is started. Next, the evaluation receiving unit 111 receives an actual evaluation of the executed action plan (step S307). If the evaluation receiving unit 111 receives an evaluation that the goal has been achieved (step S307; Yes), the flow proceeds to step S308. If the evaluation receiving unit 111 does not receive an evaluation that the goal has been achieved (step S307; No), the flow returns to step S303, the simulation unit 114 changes the simulation model to be applied, and the flow from S303 to S307 is repeated until the evaluation receiving unit 111 receives an evaluation that the goal has been achieved. Next, if the information receiving unit 112 detects that the target information has been updated via the network (step S308; Yes), the process returns to step S302 and repeats the flow. On the other hand, if the information receiving unit 112 does not detect that the target information has been updated via the network (step S308; No), the simulation operation ends. However, steps S307 and S308 do not have to be executed in this order.

[0055] Furthermore, in the second embodiment, the simulation unit 114 executes a simulation in a virtual space using digital twin technology, but the simulation means is not limited to this. The simulation unit 114 may execute a simulation using a simulation technology that does not use digital twin technology. Furthermore, the event optimization method using digital twin technology is not limited to the above-described method, and any method applicable to the present invention can be used.

[0056] Some or all of the above-described embodiments can be described as follows: However, some or all of the above-described embodiments are not limited to the following.

[0057] (Appendix 1) an information receiving means for receiving a plurality of pieces of action information relating to actions performed by an object related to an event in the town or actions performed on the object, and a plurality of pieces of goal information relating to goals for evaluating each of the plurality of actions; information acquisition means for acquiring information related to each of the plurality of actions; a simulation means for proposing each of the action plans to be executed in order to achieve the plurality of goals and executing a simulation to optimize the event, based on the plurality of pieces of action information and the plurality of pieces of goal information acquired by the information accepting means, and the respective related information acquired by the information acquiring means; an event optimizer comprising output means for outputting each of the results of said simulations;

[0058] (Appendix 2) the plurality of pieces of target information received by the information receiving means include information on target values ​​and lower limit values ​​indicated by evaluation parameters, 2. The event optimization device according to claim 1, wherein the simulation means, when proposing each of the action plans to be executed to achieve the plurality of goals, optimizes the events by creating each action plan such that the evaluation parameter does not fall below the lower limit value and the sum of differences from the target value is minimized.

[0059] (Appendix 3) further comprising an evaluation receiving means for receiving an actual evaluation of each of the action plans proposed by the simulation means; 3. The event optimization device according to claim 1, wherein the simulation means determines a simulation model to be applied based on the similarity of the events and the actual evaluation before executing the simulation, and then executes the simulation.

[0060] (Appendix 4) The event is divided into multiple processes, the information receiving means receives, as the behavior information, the plurality of pieces of behavior information for each of the plurality of processes, and receives, as the goal information, the plurality of pieces of goal information for each of the plurality of processes; the information acquisition means acquires relevant information about the behavior for each of the plurality of processes; The event optimization device according to any one of appendices 1 to 3, wherein the simulation means proposes each of the action plans to be executed to achieve the plurality of goals and performs a simulation to optimize the event.

[0061] (Appendix 5) 5. An event optimization device according to any one of appendices 1 to 4, wherein the city event is an event related to movement of an object in the city.

[0062] (Appendix 6) 5. The event optimization device according to any one of appendices 1 to 4, wherein the city event is an event related to the installation of a large commercial facility.

[0063] (Appendix 7) 5. The event optimization device according to any one of appendices 1 to 4, wherein the town event is an event related to attracting customers to a store.

[0064] (Appendix 8) 8. The event optimization device according to any one of appendices 1 to 7, wherein the simulation means executes a simulation in a virtual space using digital twin technology.

[0065] (Appendix 9) 9. An event optimization device according to any one of appendices 1 to 8, which starts controlling equipment installed in the real space in order to implement each of the action plans proposed by the simulation means in the real space.

[0066] (Appendix 10) 10. The event optimization device according to claim 9, wherein the evaluation receiving means receives the actual evaluation for each of the action plans implemented in the real space, and when the simulation means does not receive an evaluation from the evaluation receiving means that the goal has been achieved, the simulation means changes each of the applied simulation models and runs the simulation again.

[0067] (Appendix 11) receiving a plurality of pieces of action information relating to actions performed by an object related to an event in the city or actions performed on the object, and a plurality of pieces of goal information relating to goals for evaluating each of the plurality of actions; acquiring relevant information about each of the plurality of actions; Based on the action information, the goal information, and each of the related information, a simulation is performed to propose each of the action plans to be executed in order to achieve the plurality of goals and to optimize the event; An event optimization method that outputs each of the results of said simulations.

[0068] (Appendix 12) receiving a plurality of pieces of action information relating to actions performed by an object related to an event in the city or actions performed on the object, and a plurality of pieces of goal information relating to goals for evaluating each of the plurality of actions; acquiring relevant information about each of the plurality of actions; Based on the action information, the goal information, and each of the related information, a simulation is performed to propose each of the action plans to be executed in order to achieve the plurality of goals and to optimize the event; A program that causes a computer to output each of the results of the simulation. [Explanation of symbols]

[0069] 100, 110 Event Optimizer 101, 112 Information Reception Department 102, 113 Information acquisition section 103, 114 Simulation Section 104, 115 Output section 111 Evaluation Reception Department

Claims

1. An information receiving means for receiving a plurality of pieces of action information relating to actions performed by or against an object related to an event in a town, and a plurality of pieces of goal information relating to goals for evaluating each of the plurality of actions; information acquisition means for acquiring information related to each of the plurality of actions; a simulation means for proposing each of the action plans to be executed in order to achieve the plurality of goals and executing a simulation to optimize the event, based on the plurality of pieces of action information and the plurality of pieces of goal information acquired by the information receiving means, and related information on each of the objects, and people, things, matters, and the town environment that have some kind of relationship with the objects acquired by the information acquiring means; and an output means for outputting each of the simulation results; the plurality of pieces of target information received by the information receiving means include information on target values ​​and lower limit values ​​indicated by evaluation parameters, the simulation means, when proposing each of the action plans to be executed in order to achieve the plurality of goals, proposes each of the action plans such that the evaluation parameters do not fall below the lower limit values ​​and the sum of the differences from the target values ​​is minimized, thereby optimizing the events; The evaluation parameters include a degree of satisfaction obtained from the results of a questionnaire answered by the subject, a numerical value indicating the number or frequency of reactions appearing in the subject's appearance information, an evaluation based on information about an object obtained from at least one of a sensor and a camera, or a numerical value that can be aggregated related to the event.

2. further comprising an evaluation receiving means for receiving an actual evaluation of each of the action plans proposed by the simulation means; 2. The event optimization device according to claim 1, wherein the simulation means determines a simulation model to be applied based on the similarity of the events and the actual evaluation before executing the simulation, and then executes the simulation.

3. The event is divided into multiple processes, the information receiving means receives, as the behavior information, the plurality of pieces of behavior information for each of the plurality of processes, and receives, as the goal information, the plurality of pieces of goal information for each of the plurality of processes; the information acquisition means acquires relevant information about the behavior for each of the plurality of processes; 3. The event optimization device according to claim 1, wherein the simulation means performs a simulation to optimize the event by proposing each of the action plans to be executed to achieve the plurality of goals.

4. 4. The event optimization device according to claim 1, wherein the town events are events related to the movement of objects in the town.

5. 4. The event optimization device according to claim 1, wherein the city event is an event related to the establishment of a large commercial facility.

6. The event optimization device according to any one of claims 1 to 3, wherein the town event is an event related to attracting customers to a store.

7. The event optimization device according to any one of claims 1 to 6, wherein the simulation means executes a simulation in a virtual space using digital twin technology.

8. The computer receiving a plurality of pieces of action information relating to actions performed by an object related to an event in the city or actions performed on the object, and a plurality of pieces of goal information relating to goals for evaluating each of the plurality of actions; A process of acquiring information related to each of the plurality of actions; A process of proposing each action plan to be executed to achieve the multiple goals and executing a simulation to optimize the event, based on the action information, the goal information, and each of the objects, and related information on people, things, events, and the city environment that have some relationship with the objects; and outputting each of the simulation results. the plurality of pieces of target information to be received include information on target values ​​and lower limit values ​​indicated by evaluation parameters, the process of executing a simulation is a process of optimizing the event by proposing each action plan to be executed in order to achieve the plurality of goals, such that the evaluation parameter does not fall below the lower limit value and the sum of the differences from the target value is minimized, An event optimization method in which the evaluation parameters include satisfaction obtained from the results of a questionnaire answered by the subject, a numerical value indicating the number or frequency of reactions appearing in the subject's appearance information, an evaluation based on information about an object obtained from at least one of a sensor and a camera, or a computable numerical value related to the event.

9. receiving a plurality of pieces of action information relating to actions performed by an object related to an event in the city or actions performed on the object, and a plurality of pieces of goal information relating to goals for evaluating each of the plurality of actions; A process of acquiring information related to each of the plurality of actions; A process of proposing each action plan to be executed to achieve the multiple goals and executing a simulation to optimize the event, based on the action information, the goal information, and each of the objects, and related information on people, things, events, and the city environment that have some relationship with the objects; and a process of outputting each of the results of the simulation, the plurality of pieces of target information to be received include information on target values ​​and lower limit values ​​indicated by evaluation parameters, the process of executing a simulation is a process of optimizing the event by proposing each action plan to be executed in order to achieve the plurality of goals, such that the evaluation parameter does not fall below the lower limit value and the sum of the differences from the target value is minimized, The program includes the evaluation parameters including a degree of satisfaction obtained from the results of a questionnaire answered by the subject, a numerical value indicating the number or frequency of reactions appearing in the subject's appearance information, an evaluation based on information about an object obtained from at least one of a sensor and a camera, or a tallyable numerical value related to an event.

Images