Information processing program, information processing method, and management device

Abstract

To solve the problem in which: in a digital twin, a technology called data assimilation is used, which can produce results closer to reality for avoiding errors between simulation results and a real world from occurring; however, because data assimilation cannot observe all and any data in the real world, there is a limit to observational data that can actually be observed and used; and therefore, the accuracy of the data assimilation cannot be said to be sufficiently high.SOLUTION: An information processing program causes a computer, a management device of a digital twin that reproduces a real world in a virtual space, to execute processing including: observing a first movement amount of an object that exists in the real world; specifying a second movement amount of an agent that corresponds to the object in the virtual space; and executing data assimilation processing of the digital twin based on the observed first movement amount and the specified second movement amount.SELECTED DRAWING: Figure 10

Description

[Technical field]

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

[0002] There is a technology called Digital Twin that can represent objects that exist in the physical space of the real world in a virtual space. For example, Digital Twin can utilize the Internet of Things (IoT) to collect the number of vehicles passing through actual roads in real time, run traffic simulations, and estimate people's traffic demand (OD: Origin-Destination Demand).

[0003] On the other hand, with such digital twins, for example, there is a certain amount of discrepancy (error) between the simulation results and the real world. For this reason, there is a technology called data assimilation, which compares the simulation results with actual observation data and corrects the trajectory of the simulation based on the observation data to produce results that are closer to reality. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2005-182383 A [Patent Document 2] JP 2018-101205 A [Patent Document 3] JP 2013-206406 A [Patent Document 4] US Patent Application Publication No. 2022 / 245462 Summary of the Invention [Problem to be solved by the invention]

[0005] However, data assimilation cannot observe all real-world data, so there are limitations to the observational data that can actually be observed and used, and the accuracy cannot be said to be sufficiently high.

[0006] In one aspect, the aim is to improve the accuracy of data assimilation in digital twins. [Means for solving the problem]

[0007] In one aspect, the information processing program causes a computer in a digital twin management device that reproduces the real world in a virtual space to observe a first movement amount of an object existing in the real world, identify a second movement amount of an agent corresponding to the object in the virtual space, and perform data assimilation processing of the digital twin based on the observed first movement amount and the identified second movement amount. Effect of the Invention

[0008] On one aspect, it can improve the accuracy of data assimilation in digital twins. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram showing an example of a road network. [Diagram 2] FIG. 2 is a diagram showing an example of observed link flow data. [Diagram 3] FIG. 3 is a diagram illustrating an example of the initial OD flow data. [Figure 4] FIG. 4 is a diagram showing an example of simulated link flow data. [Diagram 5] FIG. 5 is a diagram illustrating an example of an OD flow data update. [Figure 6] FIG. 6 is a flowchart showing an example of the flow of the OD flow estimation process. [Figure 7] FIG. 7 is a diagram for explaining an intersection branching flow according to this embodiment. [Figure 8] FIG. 8 is a diagram showing an example of the configuration of an information processing system 1 according to the present embodiment. [Figure 9] FIG. 9 is a diagram showing an example of the configuration of a digital twin management device 10 according to this embodiment. [Figure 10] FIG. 10 is a diagram for explaining the intersection branching ratio according to this embodiment. [Figure 11] FIG. 11 is a diagram showing an example of a differential equation for q of the link flow evaluation function L1. [Figure 12] FIG. 12 is a diagram showing an example of a differential equation for q of the incoming link flow evaluation function L2. [Figure 13] FIG. 13 is a diagram showing an example of initial setting values ​​for OD flow estimation according to this embodiment. [Figure 14] FIG. 14 is a diagram showing an example of calculation of each observation value according to this embodiment. [Figure 15] FIG. 15 is a diagram showing an example of updating the OD flow according to this embodiment. [Figure 16] FIG. 16 is a diagram (1) showing an example of the effect of this embodiment. [Figure 17] FIG. 17 is a diagram (2) showing an example of the effect of this embodiment. [Figure 18] FIG. 18 is a diagram illustrating an example of estimation error evaluation of the OD flow according to this embodiment. [Figure 19] FIG. 19 is a diagram illustrating an example of the hardware configuration of the digital twin management device 10.

[0010] Hereinafter, examples of the information processing program, the information processing method, and the management device 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.

[0011] First, we will explain the traffic demand estimation (OD estimation) technology performed on a digital twin. Figure 1 is a diagram showing an example of a road network. The example in Figure 1 shows roads as a network (hereinafter referred to as a "road network"), with intersections as nodes and roads between intersections as links.

[0012] In addition, in a road network, a route from an origin to a destination is shown as a path, as shown in Figure 1. For example, in Figure 1, A → C → D to travel from A to D is path 1. Although not shown, for example, A → X → D when traveling from A to D via point X is shown as a separate path.

[0013] In the OD estimation technology, for example, a link flow (data) is measured by a sensor installed on each road to measure vehicles, which is the number of vehicles that have passed through a certain link. To explain this in detail using the example of FIG. 1, the link flow is, for example, the number of vehicles that have passed through link1 (A → C). In the OD estimation technology, for example, a path flow (data) and an OD flow (data) are estimated based on the link flow. The path flow is, for example, the number of vehicles that have passed through a path, such as path1. In addition, the OD flow is, for example, the number of vehicles that have moved from an origin (origin) to a destination (destination), such as from A to D. In the example of FIG. 1, since there is only one path from A to D, path1, the "OD flow from A to D" = "path flow of path1", but if there are multiple paths, the sum of the path flows is the OD flow.

[0014] The OD estimation technology is a technology that estimates an OD flow from an observable link flow, for example. More specifically, if the path flow from A to D is path1=10 (vehicles) between the times 10:00 and 10:15, the OD flow is the sum of each path flow from A to D, so the OD flow is 10 (vehicles). However, usually, the path flow and the OD flow cannot be known directly. Therefore, for example, the path flow and the OD flow are estimated from the observable link flow using various technologies. Also, for example, if the number of passing vehicles on each road is observed and counted between the times 10:00 and 10:15, the link flow A → C (link1) was 25 vehicles, and the link flow C → D (link3) was 15 vehicles. In this way, for example, not all of the 35 vehicles that passed through link1 moved in the direction of D, and not all of the 15 vehicles on link3 came from the direction of A. Also, not all of the link flows can be observed. For example, under such various conditions, OD estimation is a problem of measuring link flows in advance using observation cameras installed on roads, and estimating OD flows based on the known link flows.

[0015] In the OD estimation technique, the OD flow is estimated so as to minimize the evaluation function shown in the following equation (1), for example.

[0016]

number

[0017] In formula (1), for example, i indicates a means of transportation (for example, general car: i=0, truck: i=1). Also, q i For example, w indicates the OD flow. i For example, y′ denotes the weighting of link flow loss. For example, y′ denotes the observed data of link flows. For example, D denotes the set of transportation modes={1,2}. For example, Li denotes the aggregation matrix that aggregates the simulated link flows to compare with the observed data. For example, x iFor example, denotes the simulated link flow. Also, w2 denotes, for example, the weighting of the travel time loss. Also, z′ denotes, for example, the observed data of the travel time passing through the link. Also, M i denotes a summary matrix that summarizes the time to pass through a simulated link, for example, to compare with observed data. Also, t i For example, c indicates the time it takes to pass a link. i For example, ρ indicates the time required to travel a path from a starting point O to a destination D. i For example, f indicates the dynamic traffic distribution rate. i For example, p indicates a path flow from a starting point O to a destination D. i For example, indicates the path selection probability from the origin O to the destination D. Also, Ψ i For example, L denotes a dynamic user equilibrium matrix. For example, L denotes loss, and the first term L1 in formula (1) denotes link flow loss, and the second term L2 in formula (1) denotes travel time loss.

[0018] The evaluation function shown in formula (1) is composed of, for example, the weighted sum of the error in the cumulative traffic volume observed and estimated for each link within a certain period of time, and the error between the observed and estimated travel time to pass through the link. After the OD is set, each traffic volume is calculated using a traffic simulation, which is an existing technology, and the gradient is calculated from the error between the traffic volume and the actual observed value, and the OD is updated.

[0019] In addition, in Fig. 1, a road network is shown as an example, and as an explanation of the OD estimation technology, for example, a technology for estimating OD flow, which is the number of vehicles moving from an origin (Origin) on a road network to a destination (Destination), has been explained. In the following explanation of the OD estimation technology, estimation of the number of vehicles moving on a road will be explained, but the OD estimation technology is not limited to estimation of the number of vehicles moving on a road, and may be, for example, estimation of the number of people moving on a passage.

[0020] The OD estimation technology will be described in more detail. For example, in the example of the road network shown in Fig. 1, the number of vehicles (OD flow) departing from node 1 and heading to node 4 is estimated every 30 minutes between 6:00 and 7:00. In this case, for example, in order to estimate the OD flow every 30 minutes, the time between 6:00 and 7:00 is divided into two time frames, and the OD flow between 6:00 and 6:30 and between 6:30 and 7:00 is estimated.

[0021] As advance preparations, data tables such as a road network, OD combinations, and a route selection probability table between ODs are prepared. Also, actually observed link flow data is prepared, for example, as shown in Fig. 2. Fig. 2 is a diagram showing an example of observed link flow data. As shown in Fig. 2, for example, the observed link flow data is denoted as y, and the observed link flow data for each time frame and link flow is denoted as y1 to y4.

[0022] As a forward process, for example, a traffic simulation is performed with a given OD flow as shown in FIG. 3, and link flows are tallied. FIG. 3 is a diagram showing an example of initial OD flow data. As shown in FIG. 3, for example, random numbers q1 to q6 (or a fixed value) are given to the initial OD. Then, for example, a traffic simulation is performed using the OD as shown in FIG. 3, the number of vehicles (link flows) passing through each link on the simulator is counted, and after the simulation, the traffic volume as shown in FIG. 4 is tallied (the tallied traffic volume is taken as ρ). FIG. 4 is a diagram showing an example of simulated link flow data.

[0023] In addition, as a backward process, for example, the OD flow is updated based on the error of the link flow. The error Δy between the simulated link flow and the observed link flow is calculated, for example, by the formula "Δy=y-Lρpq" (L is the observation matrix, and p is the route selection probability). Then, when the error Δy is smaller than, for example, a predetermined threshold, the OD estimation is terminated. Also, the error Δq is calculated by the formula "Δq=wp T ρ TL T The amount of OD correction is calculated using "Δy" (w is a weight, usually a decimal between 0 and 1). Then, as shown in FIG. 5, for example, each of the OD flows q1 to q6 is updated using the formula "q=q+Δq". FIG. 5 is a diagram showing an example of OD flow data update. Then, as an iterative process, a traffic simulation is performed using the updated OD flows, and link flows are tallied as shown in FIG. 4. The process is repeated, for example, until the error Δy becomes smaller than a predetermined threshold.

[0024] The flow of the OD flow estimation process is summarized in Fig. 6. Fig. 6 is a flowchart showing an example of the flow of the OD estimation process. In the OD estimation process shown in Fig. 6, for example, it is assumed that the link flow is measured every 15 minutes between the times of 6:00 and 11:00, and the OD flow every 15 minutes between the times of 6:00 and 11:00 is estimated using the link flow every 15 minutes.

[0025] First, as shown in FIG. 6, the digital twin management device 10, for example, initializes the OD flow (step S1). The initial setting of the OD flow is, for example, a random number setting as shown in FIG. 3. Next, the digital twin management device 10, for example, selects a route for the OD flow to be estimated (step S2). Next, the digital twin management device 10 executes a traffic simulation using, for example, a path flow calculated using the link flow of the selected route (step S3). Note that, for example, if there are multiple path flows for the OD flow to be estimated, the processes of steps S3 to S7 may be executed for each path flow.

[0026] Next, the digital twin management device 10, for example, tallies and records the link flows in each time slot as shown in Fig. 4 (step S4). Then, the digital twin management device 10 calculates the error between the simulated link flow and the observed link flow using, for example, an evaluation function, and determines whether or not the error is smaller than a predetermined threshold and the OD flow estimation process is terminated (step S5).

[0027] For example, if the error is equal to or greater than a predetermined threshold (step S5: No), the digital twin management device 10 calculates the amount of correction to the path flow based on the error (step S6) and updates and corrects the path flow (step S7), as shown in Fig. 5. Then, the digital twin management device 10 executes a traffic simulation using the corrected path flow (step S3), for example, and repeats the process until the error becomes smaller than the predetermined threshold, optimizing the path flow while correcting it (steps S3 to S7).

[0028] On the other hand, for example, if the error is smaller than a predetermined threshold (step S5: Yes), the digital twin management device 10 calculates the OD flow based on the simulated link flow (step S8). As described above, if there are multiple path flows, steps S3 to S7 may be executed for each path flow, and if the condition of step S5 is satisfied for all of the multiple path flows, the process may proceed to step S8. After executing step S8, the OD flow estimation process shown in FIG. 6 ends.

[0029] The OD flow estimation process has been described above. For example, the evaluation function used in this process, such as that shown in formula (1), has the error between the simulated link flow and the observed link flow as an evaluation target. Therefore, in this evaluation function, for example, depending on the structure of the road network, the same link flow can be reproduced even with different OD flows, and there is a possibility that there are multiple local solutions that minimize the evaluation function. For example, when applying to a large-scale road network, this leads to a decrease in the estimation accuracy of the OD flow, and also leads to a decrease in the accuracy of data assimilation in the digital twin.

[0030] Therefore, in this embodiment, for example, the branch flow of vehicles to each road estimated by traffic simulation at each observation time period and each observation intersection, and the branch flow actually observed at the intersection at the time period are used as the estimated value and observed value of the link flow. Here, the (intersection) branch flow refers to, for example, the number of vehicles that branch off to each destination road by turning right or left, going straight, etc., among the vehicles flowing out from a certain road (= link) at each intersection.

[0031] Fig. 7 is a diagram for explaining an intersection branch flow according to this embodiment. As shown in Fig. 7, for example, a vehicle exiting from link1 branches off at intersection X to a road heading for B, C, or another destination. In this manner, in this embodiment, for example, a link flow, which is the number of vehicles exiting from a certain link, is further considered as the sum of branch flows, which are the number of vehicles on each branching road, and the branch flows are used to estimate the OD flow.

[0032] [Configuration of Information Processing System 1] Next, an information processing system 1 for implementing this embodiment will be described. Fig. 8 is a diagram showing an example of the configuration of the information processing system 1 according to this embodiment. As shown in Fig. 8, in the information processing system 1, for example, a digital twin management device 10 and camera devices 100-1 to 100-n (n is an arbitrary natural number; hereinafter, collectively referred to as "camera devices 100") are connected to each other via a network 50 so as to be able to communicate with each other.

[0033] 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 combining the Internet and an intranet via a network device such as a gateway or other device (not shown).

[0034] The digital twin management device 10 is, for example, an information processing device such as a desktop PC (Personal Computer), a notebook PC, or a server computer that reproduces the real world in a virtual space.

[0035] For example, in order to collect real-world information in real time, the digital twin management device 10 receives video captured by the camera device 100 from the camera device 100. Note that the video captured by the camera device 100 is, strictly speaking, a plurality of captured images captured by the camera device 100, that is, a series of frames of a video.

[0036] Furthermore, the digital twin management device 10 detects objects such as vehicles and people from the video using, for example, existing object detection technology. Note that detection of objects such as vehicles from the video may involve detecting a predetermined area on the video for each object, such as a bounding box that is a rectangular area surrounding an object such as a vehicle. Furthermore, the digital twin management device 10 may detect, in addition to vehicles and people, for example, roads, passageways, intersections, etc. from the video.

[0037] The digital twin management device 10 also constructs a digital twin that reproduces the real world in a virtual space. The digital twin management device 10 then observes a first movement amount of an object that exists in the real world. The digital twin management device 10 also identifies a second movement amount of an agent corresponding to the object in the virtual space of the digital twin. For example, the digital twin management device 10 identifies a road or passage in the virtual space that reproduces a road or passage in the real world, and identifies a second movement amount of an agent corresponding to the object that moves along the identified road or passage in the virtual space.

[0038] Next, the digital twin management device 10 executes data assimilation processing of the digital twin based on the observed first movement amount and the second movement amount of the agent corresponding to the object in the virtual space. For example, the digital twin management device 10 executes data assimilation processing of the digital twin so as to match the first movement amount and the second movement amount based on the error between the first movement amount of each vehicle or the like in the real world and the simulated second movement amount of each agent.

[0039] More specifically, the digital twin management device 10, for example, places agents corresponding to each vehicle and each person detected from the captured image on the digital twin, and simulates the movement of each agent using existing simulation technology such as traffic simulation. The digital twin management device 10 also identifies an error between a first movement amount of each vehicle in the real world and a second movement amount of each simulated agent, and dynamically changes the movement demand of the agent based on the error. Then, the digital twin management device 10 executes data assimilation processing of the digital twin between the first movement amount and the second movement amount based on the changed movement demand. The digital twin management device 10 matches the first movement amount and the second movement amount based on the changed movement demand, and performs data assimilation.

[0040] 8, the digital twin management device 10 is shown as a single computer, but it may be a distributed computing system made up of multiple computers. The digital twin management device 10 may also be a cloud computer device managed by a service provider that offers cloud computing services.

[0041] The camera device 100 is, for example, a surveillance camera installed on a road or a passage. The camera device 100 captures, for example, vehicles and people passing through the road or passage. The video captured by the camera device 100 is transmitted to the digital twin management device 10.

[0042] [Functional configuration of the digital twin management device 10] Next, a description will be given of the functional configuration of the digital twin management device 10. Fig. 9 is a diagram showing an example of the configuration of the digital twin management device 10 according to this embodiment. As shown in Fig. 9, the digital twin management device 10 has a communication unit 20, a storage unit 30, and a control unit 40.

[0043] The communication unit 20 is a processing unit that controls communication with other devices such as the camera device 100, and is, for example, a communication interface such as a network interface card or a Universal Serial Bus (USB) interface.

[0044] The storage unit 30 has a function of storing various data and programs executed by the control unit 40, and is realized by a storage device such as a memory or a hard disk. The storage unit 30 stores, for example, video information 31, real world information 32, and digital twin information 33.

[0045] The video information 31 stores, for example, video captured by the camera device 100. The video stored in the video information 31 is video captured by the camera device 100 and transmitted to the digital twin management device 10, and the video information 31 may also store, for example, an identifier for uniquely identifying the camera device 100 that captured the video, the date and time of capture, and the like.

[0046] The real world information 32 stores, for example, information about the real world obtained from images captured by the camera device 100. The real world information is, for example, information such as the number of vehicles and people that have passed through each road or passage (= link), and the number and ratio of vehicles and people that have branched off onto each road at an intersection.

[0047] Digital twin information 33 stores information about the digital twin, such as agents corresponding to vehicles and people in the real world, and areas on the digital twin corresponding to roads, passageways, intersections, etc. in the real world. Digital twin information 33 may also store information derived by simulation on the digital twin, such as the number of agents that passed through each road or passageway (= link), and the number and percentage of agents that branched off onto each road at an intersection.

[0048] 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.

[0049] The control unit 40 is a processing unit that controls the entire digital twin management device 10, and is, for example, a processor. The control unit 40 includes an acquisition unit 41, a simulation unit 42, a calculation unit 43, and an estimation unit 44. Each processing unit is an example of an electronic circuit that the processor has or an example of a process that the processor executes.

[0050] The acquisition unit 41 acquires, for example, a video of a vehicle or a person passing through a road or a passage. For example, the video is captured by the camera device 100, transmitted from the camera device 100 at any time, and stored in the video information 31, so that the acquisition unit 41 acquires the video from the video information 31. In addition, the acquisition unit 41 acquires real-world information contained in the video by analyzing the video captured by the camera device 100 using existing technology. The real-world information is, for example, information such as the number of vehicles and people passing through each road or passage (= link) (= link flow), the number of vehicles and people branching off to each road at an intersection (= branch flow) and the ratio. That is, the acquisition unit 41 observes and acquires, for example, a first movement amount of an object such as a vehicle or a person that exists in the real world. Therefore, the process of observing the first movement amount includes a process of detecting an object using an image captured by the camera device 100 and identifying the first movement amount of the detected object. In addition, the process of observing and obtaining the first amount of movement includes, for example, a process of observing and obtaining a first number of objects that have moved on a road or passage between specified intersections on a road or passage in the real world as the first amount of movement.

[0051] The ratio of vehicles branching out to each road at an intersection (branch ratio) will be described more specifically. FIG. 10 is a diagram for explaining the intersection branch ratio according to this embodiment. As shown on the left side of FIG. 10, for example, a vehicle that flows out from link1 and enters from branch A of intersection X will exit from one of branches B to D. The acquisition unit 41 acquires the branch ratios (0.6, 0.2, and 0.2, respectively) of vehicles that enter from branch A to branches B to D by analyzing an image captured by a camera device 100 installed at intersection X. Then, the acquisition unit 41 records the branch ratios to each branch as observation data in a turn rate table, for example, as shown on the right side of FIG. 10, with each branch at intersection X as an entrance. Note that, for example, in FIG. 10, the number of vehicles that flows out from link1 and enters from branch A of intersection X becomes the link flow of link1, and the link flow is the total value of the number of vehicles that branch out to branches B to D (= each branch flow). That is, the above-mentioned process of observing the first movement amount executed by the acquisition unit 41 includes a process of observing and acquiring, as the first movement amount, a first ratio of objects such as vehicles or people that have moved to each branch at a specified intersection on a road or passage in the real world.

[0052] In addition, the branching rate data at each intersection may be obtained by, for example, obtaining a movement trajectory of a probe vehicle from a provider that provides probe vehicle data, linking the GPS (Global Positioning System) position with a road, and then directly calculating a turn rate table at each intersection. Alternatively, as the branching rate data at each intersection, for example, a turn rate table may be obtained from a provider that provides an API (Application Programming Interface) that analyzes traffic flow at an intersection. Alternatively, as the branching rate data at each intersection, for example, data on the number of vehicles turning right or left and going straight at each time may be purchased and obtained from a provider.

[0053] The simulation unit 42, for example, uses the observed first movement amount to simulate and calculate a second movement amount of an agent corresponding to an object such as a vehicle or a person in the real world in the digital twin using an existing simulation technique such as traffic simulation. In addition, the process of executing the simulation may include, for example, a process of placing an agent corresponding to each vehicle or person in the real world in the virtual space of the digital twin.

[0054] The calculation unit 43, for example, specifies an error between a first movement amount observed and acquired by the acquisition unit 41 and a second movement amount of an agent corresponding to an object such as a vehicle or a person in the virtual space. The process of specifying the error includes a process of calculating a first error between a first number of objects that have moved on a road or passage between predetermined intersections in the real world and a second number of agents that have moved on a road or passage between predetermined intersections in the road or passage in the virtual space as the error. The process of specifying the error also includes a process of calculating a second error between a first ratio of objects that have moved to each branch at a predetermined intersection in the real world and a second ratio of agents that have moved to each branch at a predetermined intersection in the road or passage in the virtual space as the error. That is, in this embodiment, the branch flow is taken into consideration, and in the OD estimation process in this embodiment, the OD flow is estimated so as to minimize the following formula (2) in which the evaluation function shown in formula (1) is modified to take the branch flow into consideration.

[0055]

number

[0056] In formula (2), for example, the first term including w1 is the same as formula (1). w2, for example, indicates a weight for the loss of the branch flow. η, for example, indicates observed data of the link branch flow. K, for example, indicates a matrix that aggregates the simulated link branch flow to compare with the observed data. φ, for example, indicates the simulated branch flow. τ, for example, indicates the dynamic distribution rate of the branch flow.

[0057] In addition, by setting "x = ρpq" (from equation (1)) and "φ = τpq" in equation (2), the following equation (3) is obtained by converting equation (2).

[0058]

number

[0059] In addition, if the evaluation function is L (cursive), the first term in equations (2) and (3) is the link flow loss L1 (cursive), and the second term is the branch flow loss L2 (cursive), the following equation (4) is obtained.

[0060]

number

[0061] In addition, in formula (4), L1 (cursive) and L2 (cursive) are expressed, for example, by the following formulas (5) and (6), respectively.

[0062]

number

[0063] In equation (5), for example, y=Lx, x=pf, and f=pq.

[0064]

number

[0065] In equation (6), for example, η=Kφ, φ=τf, and f=pq.

[0066] Moreover, a differential equation for q of the evaluation function L (cursive) is expressed, for example, by the following equation (7).

[0067]

number

[0068] Moreover, the differential equations for q of the link flow evaluation function L1 (cursive) and the branch flow evaluation function L2 (cursive) can be calculated, for example, as shown in Fig. 11 and Fig. 12. Fig. 11 is a diagram showing an example of the differential equation for q of the link flow evaluation function L1. Fig. 12 is a diagram showing an example of the differential equation for q of the incoming link flow evaluation function L2.

[0069] The calculation unit 43 also dynamically changes the movement demand of the agent in the virtual space based on, for example, the error between the identified first movement amount and the second movement amount, and executes a data assimilation process to match the first movement amount and the second movement amount based on the changed movement demand. More specifically, for example, the calculation unit 43 executes an update value of the OD flow q "Δq=-2p T (wρ T L T (y′-y)+w2τ T K T (η'-η)" and update the OD flow q as "q←max(0,q-γΔq)".

[0070] The estimation unit 44 estimates the amount of movement of objects such as vehicles and people from a predetermined starting point in the real world to a destination so as to minimize, for example, a weighted sum of a first error and a second error. The first error is, for example, an error between a first number of objects that have moved on a road or passage between predetermined intersections in the real world calculated by the calculation unit 43, and a second number of agents that have moved on a road or passage between predetermined intersections in a road or passage in the virtual space. The second error is, for example, an error between a first ratio of objects that have moved to each branch at a predetermined intersection in the real world calculated by the calculation unit 43, and a second ratio of agents that have moved to each branch at a predetermined intersection in a road or passage in the virtual space.

[0071] Next, the OD flow estimation according to this embodiment will be described in more detail. FIG. 13 is a diagram showing an example of initial setting values ​​of the OD flow estimation according to this embodiment. In the OD flow estimation according to this embodiment, for example, pseudo observed values ​​of the traffic flow are used to estimate the OD flow. FIG. 13 is a diagram showing an example of initial setting values ​​of the OD flow estimation according to this embodiment. As shown in the dashed line part in FIG. 13, for example, pseudo observed values ​​of the link flow and the branch flow are set as initial setting values ​​of the observed values ​​of the traffic flow. Also, as shown in the lower part of FIG. 13, an initial value q0 of the OD flow is set.

[0072] Next, the digital twin management device 10 executes a traffic simulation using each observation value and OD flow that are initially set as shown in Fig. 13, and calculates the link flow observation value y and the branch flow observation value η as shown in Fig. 14. Fig. 14 is a diagram showing an example of calculation of each observation value according to this embodiment.

[0073] Next, the digital twin management device 10 calculates update values ​​Δq1 and Δq2 of the OD flow from the errors of the link flow and the branch flow, as shown in Fig. 15, using y and η calculated by simulation as shown in Fig. 14, for example. Then, the digital twin management device 10 calculates an update value Δq of the OD flow using the calculated update values ​​Δq1 and Δq2 of the OD flow, as shown in Fig. 15, for example, and updates the OD flow q using the update value Δq as "q←q-γΔq). Fig. 15 is a diagram showing an example of updating the OD flow according to this embodiment.

[0074] Then, the digital twin management device 10 repeats the optimization process, for example, as follows. For example, the digital twin management device 10 performs forward processing with the OD flow updated in backward as a known OD flow, and calculates link flows and branch flows. In addition, the digital twin management device 10 compares the link flows and branch flows calculated in forward with the actually observed values, and updates the OD flow.

[0075] [effect] The digital twin management device 10 can reflect the situation in the real world, and can improve the accuracy of data assimilation in the digital twin in the virtual space. FIG. 16 is a diagram (1) showing an example of the effect of this embodiment. FIG. 17 is a diagram (2) showing an example of the effect of this embodiment. FIG. 18 is a diagram showing an example of estimation error evaluation of the OD flow according to this embodiment. As shown in FIGS. 16 to 18, in the OD estimation according to this embodiment taking into account the branch flow, the estimation error is smaller and the data assimilation accuracy and estimation accuracy are improved compared to the conventional method using the evaluation function as shown in formula (1).

[0076] Furthermore, as described above, the digital twin management device 10, which reproduces the real world in a virtual space, observes a first movement amount of an object existing in the real world, identifies a second movement amount of an agent corresponding to the object in the virtual space, and performs data assimilation processing of the digital twin based on the observed first movement amount and the identified second movement amount.

[0077] In this way, the digital twin management device 10 assimilates the amount of movement of an object observed in the real world and the amount of movement of an agent simulated on a digital twin based on the error between the two amounts of movement. This enables the digital twin management device 10 to improve the accuracy of data assimilation in a digital twin.

[0078] The digital twin management device 10 identifies an error between an observed first movement amount and a second movement amount of an agent corresponding to an object in the virtual space, and dynamically changes the movement demand of the agent in the virtual space based on the identified error, and the process of performing data assimilation processing executed by the digital twin management device 10 includes a process of performing data assimilation processing of the digital twin between the first movement amount and the second movement amount based on the changed movement demand.

[0079] This enables the digital twin management device 10 to improve the accuracy of data assimilation in the digital twin.

[0080] In addition, the process of observing the first movement amount performed by the digital twin management device 10 includes a process of observing the first movement amount of an object on a road or passage in the real world, the process of identifying the error includes a process of identifying the error between the observed first movement amount and a second movement amount of an agent corresponding to the object on the road or passage in the virtual space, and the process of performing the data assimilation process includes a process of performing the data assimilation process so as to match the first movement amount and the second movement amount.

[0081] This enables the digital twin management device 10 to improve the accuracy of data assimilation in the digital twin.

[0082] In addition, the process of observing the first movement amount executed by the digital twin management device 10 includes a process of detecting an object using an image captured by a camera and identifying the first movement amount of the detected object, and the digital twin management device 10 uses the observed first movement amount to simulate and calculate the second movement amount in the digital twin.

[0083] This enables the digital twin management device 10 to improve the accuracy of data assimilation in the digital twin.

[0084] In addition, the process of observing a first amount of movement performed by the digital twin management device 10 includes a process of observing a first number of objects that have moved on a road or passage between specified intersections on a road or passage in the real world as the first amount of movement, and the process of identifying an error includes a process of calculating, as an error, a first error between the first number and a second number of agents that have moved on a road or passage between specified intersections on a road or passage in the virtual space.

[0085] This enables the digital twin management device 10 to improve the accuracy of data assimilation in the digital twin.

[0086] In addition, the process of observing a first amount of movement executed by the digital twin management device 10 includes a process of observing a first proportion of objects that have moved to each branch at a specified intersection on a road or passage in the real world as the first amount of movement, and the process of identifying an error includes a process of calculating, as an error, a second error between the first proportion and a second proportion of agents that have moved to each branch at a specified intersection on a road or passage in the virtual space.

[0087] This enables the digital twin management device 10 to further improve the accuracy of data assimilation in digital twins.

[0088] In addition, the digital twin management device 10 estimates the amount of movement of an object from a specified starting point in the real world to the destination so as to minimize the weighted sum of the first error and the second error.

[0089] This enables the digital twin management device 10 to improve the accuracy of data assimilation in the digital twin.

[0090] In addition, the process of identifying the second movement amount executed by the digital twin management device 10 includes a process of identifying a road or passage in a virtual space that reproduces a road or passage in the real world, and identifying a second movement amount of an agent corresponding to an object that moves along the identified road or passage in the virtual space.

[0091] This enables the digital twin management device 10 to improve the accuracy of data assimilation in the digital twin.

[0092] In addition, during the period from after the data assimilation process of the digital twin is completed until the next data assimilation process is executed, the digital twin management device 10 uses an agent in the virtual space to conduct a simulation in the virtual space of the digital twin to predict whether or not there is an abnormality in the amount of movement of objects in the real world, and when an abnormality is predicted, identifies the road or passage on which the abnormality is predicted, and executes a process on the digital twin management device to display an image on a display device in which the identified road or passage is highlighted.

[0093] This enables the digital twin management device 10 to improve the accuracy of data assimilation in the digital twin.

[0094] [Apply Processing] Here, the application process of the digital twin after the data assimilation process of the digital twin is completed will be described. The digital twin management device 10 repeatedly executes the data assimilation process of the digital twin and the application process in the digital twin.

[0095] First, during the period from when the data assimilation process of the digital twin is completed until the next data assimilation process is executed, the digital twin management device 10 uses an agent in the virtual space to perform a simulation in the virtual space. More specifically, after the data assimilation process of the digital twin is completed, the digital twin management device 10 uses an agent in the virtual space to perform a simulation in the virtual space to predict the presence or absence of an abnormality in an object existing in the real world. For example, based on the second movement amount, the digital twin management device 10 predicts the presence or absence of an abnormal change in the movement amount of a person or a car depending on the traffic situation due to the occurrence of an accident or the like. More specifically, the digital twin management device 10 predicts the presence or absence of an abnormality in the movement amount of an object existing in the real world by inputting the second movement amount into a machine learning model in which the second movement amount and the presence or absence of an abnormality have been learned.

[0096] Next, when an abnormality is predicted, the digital twin management device 10 identifies the road or passage on which the abnormality is predicted. For example, when an abnormality is predicted, the digital twin management device 10 identifies the road or passage on which an object predicted to have an abnormal amount of movement is located. Then, the digital twin management device 10 causes the display device to display information on a map in which the identified road or passage is highlighted. For example, the digital twin management device 10 causes the display to display a screen in which the identified road is highlighted from among the multiple roads on the map.

[0097] [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.

[0098] Furthermore, the specific form of distribution or integration of the components of each device is not limited to that shown in the figures. In other words, all or part of the components may be functionally or physically distributed or integrated in any unit depending on various loads, usage conditions, etc. Furthermore, all or any part of the processing functions of each device may be realized by a CPU (Central Processing Unit) and a program analyzed and executed by the CPU, or may be realized as hardware using wired logic.

[0099] [Hardware] Fig. 19 is a diagram illustrating an example of the hardware configuration of the digital twin management device 10. As shown in Fig. 19, the digital twin management device 10 has a communication interface 10a, a HDD (Hard Disk Drive) 10b, a memory 10c, and a processor 10d. Moreover, each unit shown in Fig. 19 is connected to each other via a bus or the like.

[0100] The communication interface 10a is a network interface card or the like, and communicates with other servers. The HDD 10b stores programs and data for operating the functions shown in FIG.

[0101] The processor 10d is a hardware circuit that operates a process that executes each function described in FIG. 9 and the like by reading a program that executes the same processing as each processing unit shown in FIG. 9 from the HDD 10b or the like and expanding it in the memory 10c. That is, this process executes functions similar to those of each processing unit possessed by the digital twin management device 10. Specifically, the processor 10d reads a program having functions similar to those of the acquisition unit 41, the simulation unit 42, the calculation unit 43, and the estimation unit 44 from the HDD 10b or the like. Then, the processor 10d executes a process that executes processes similar to those of the acquisition unit 41, the simulation unit 42, the calculation unit 43, and the estimation unit 44.

[0102] In this way, the digital twin management device 10 operates as an information processing device that executes operational control processing by reading and executing a program that executes the same processing as each processing unit shown in FIG. 9. The digital twin management device 10 can also realize functions similar to those of the above-mentioned embodiment by reading a program from a recording medium using a media reading device and executing the read program. Note that the program in this other embodiment is not limited to being executed by the digital twin management device 10. For example, this embodiment may also be applied in a similar manner to cases where another information processing device executes a program or where the digital twin management device 10 and another information processing device cooperate to execute a program.

[0103] A program that executes the same processes as those of each processing unit shown in Fig. 9 can be distributed via a network such as the Internet. This program can be recorded on a computer-readable recording medium such as a hard disk, a flexible disk (FD), a CD-ROM, a magneto-optical disk (MO), or a digital versatile disk (DVD), and can be executed by being read out from the recording medium by a computer.

[0104] The following supplementary notes are further disclosed regarding the embodiments including the above examples.

[0105] (Note 1) A management device for digital twins that reproduce the real world in a virtual space. Observing a first amount of movement of an object existing in the real world; determining a second amount of movement of the agent corresponding to the object in the virtual space; Executing a data assimilation process of the digital twin based on the observed first movement amount and the identified second movement amount. An information processing program that causes a process to be executed.

[0106] (Appendix 2) Identifying an error between the observed first movement amount and a second movement amount of an agent corresponding to the object in the virtual space; Dynamically changing a movement demand of the agent in the virtual space based on the identified error; The process of performing the data assimilation process includes: Based on the changed travel demand, data assimilation processing of the digital twin is performed between the first travel amount and the second travel amount. 2. The information processing program according to claim 1, further comprising:

[0107] (Additional Note 3) The process of observing the first movement amount includes: Observing a first amount of movement of an object along the real world road or passageway. Including processing, The process of identifying the error includes: Identifying an error between the observed first movement amount and a second movement amount of an agent corresponding to the object on a road or passage in the virtual space. Processing The process of performing the data assimilation process includes: The data assimilation process is performed so that the first movement amount and the second movement amount coincide with each other. 3. The information processing program according to claim 2, further comprising:

[0108] (Appendix 4) The process of observing the first movement amount includes: The object is detected using an image captured by the camera, and a first amount of movement of the detected object is identified. Including processing, The second movement amount is calculated by simulating the second movement amount in the digital twin using the observed first movement amount. An information processing program as described in Appendix 2, characterized in that the processing is executed by a management device for the digital twin.

[0109] (Additional Note 5) The process of observing the first movement amount includes: A first number of the objects that have moved on a road or passage between predetermined intersections in the road or passage in the real world is observed as the first movement amount. Processing The process of identifying the error includes: A first error between the first number and a second number of the agents who have moved along a road or passage between predetermined intersections in the road or passage in the virtual space is calculated as the error. 4. The information processing program according to claim 3, further comprising:

[0110] (Additional Note 6) The process of observing the first movement amount includes: Observe, as the first movement amount, a first ratio of the object that has moved to each branch at a predetermined intersection on the road or passage in the real world. Processing The process of identifying the error includes: A second error between the first ratio and a second ratio of the agents who move to each branch at a predetermined intersection on a road or passage in the virtual space is calculated as the error. 6. The information processing program according to claim 5, further comprising:

[0111] (Appendix 7) Estimating the amount of movement of the object from a predetermined starting point in the real world to a destination so as to minimize a weighted sum of the first error and the second error. An information processing program as described in Appendix 6, characterized in that the processing is executed by a management device for the digital twin.

[0112] (Additional Note 8) The process of determining the second movement amount includes: identifying a road or passage in a virtual space that reproduces the road or passage in the real world, and moving along the identified road or passage in the virtual space; and identifying a second movement amount of the agent corresponding to the object; 4. The information processing program according to claim 3, further comprising:

[0113] (Appendix 9) During the period from when the data assimilation process of the digital twin is completed to when the next data assimilation process is executed, a simulation is performed in the virtual space of the digital twin using an agent in the virtual space to predict the presence or absence of an abnormality in the amount of movement of an object existing in the real world; When the abnormality is predicted, a road or a passage on which the abnormality is predicted is identified; Displaying an image in which the identified road or passage is highlighted on a display device An information processing program as described in Appendix 3, characterized in that the processing is executed by a management device for the digital twin.

[0114] (Appendix 10) A management device for digital twins that reproduces the real world in a virtual space, Observing a first amount of movement of an object existing in the real world; determining a second amount of movement of the agent corresponding to the object in the virtual space; Executing a data assimilation process of the digital twin based on the observed first movement amount and the identified second movement amount. 2. An information processing method comprising:

[0115] (Appendix 11) Identifying an error between the observed first movement amount and a second movement amount of an agent corresponding to the object in the virtual space; Dynamically changing a movement demand of the agent in the virtual space based on the identified error; The process of performing the data assimilation process includes: Based on the changed travel demand, data assimilation processing of the digital twin is performed between the first travel amount and the second travel amount. 11. The information processing method according to claim 10, further comprising:

[0116] (Additional Note 12) The process of observing the first movement amount includes: Observing a first amount of movement of an object along the real world road or passageway. Including processing, The process of identifying the error includes: Identifying an error between the observed first movement amount and a second movement amount of an agent corresponding to the object on a road or passage in the virtual space. Including processing, The process of performing the data assimilation process includes: The data assimilation process is performed so that the first movement amount and the second movement amount coincide with each other. 12. The information processing method according to claim 11, further comprising the steps of:

[0117] (Additional Note 13) The process of observing the first movement amount includes: The object is detected using an image captured by the camera, and a first amount of movement of the detected object is identified. Including processing, The second movement amount is calculated by simulating the second movement amount in the digital twin using the observed first movement amount. An information processing method as described in Appendix 11, characterized in that the processing is performed by a management device for the digital twin.

[0118] (Additional Note 14) The process of observing the first movement amount includes: A first number of the objects that have moved on a road or passage between predetermined intersections in the road or passage in the real world is observed as the first movement amount. Processing The process of identifying the error includes: A first error between the first number and a second number of the agents who have moved along a road or passage between predetermined intersections in the road or passage in the virtual space is calculated as the error. 13. The information processing method according to claim 12, further comprising the steps of:

[0119] (Additional Note 15) The process of observing the first movement amount includes: Observe, as the first movement amount, a first ratio of the object that has moved to each branch at a predetermined intersection on the road or passage in the real world. Processing The process of identifying the error includes: A second error between the first ratio and a second ratio of the agents who move to each branch at a predetermined intersection on a road or passage in the virtual space is calculated as the error. 15. The information processing method according to claim 14, further comprising the steps of:

[0120] (Appendix 16) Estimating the amount of movement of the object from a predetermined starting point in the real world to a destination so as to minimize a weighted sum of the first error and the second error. An information processing method as described in Appendix 15, characterized in that the processing is performed by a management device for the digital twin.

[0121] (Additional Note 17) The process of determining the second movement amount includes: identifying a road or passage in a virtual space that reproduces the road or passage in the real world, and moving along the identified road or passage in the virtual space; and identifying a second movement amount of the agent corresponding to the object; 13. The information processing method according to claim 12, further comprising the steps of:

[0122] (Appendix 18) During the period from when the data assimilation process of the digital twin is completed to when the next data assimilation process is executed, a simulation is performed in the virtual space of the digital twin using an agent in the virtual space to predict the presence or absence of an abnormality in the amount of movement of an object existing in the real world; When the abnormality is predicted, a road or a passage on which the abnormality is predicted is identified; Displaying an image in which the identified road or passage is highlighted on a display device An information processing method as described in Appendix 12, characterized in that the processing is performed by a management device for the digital twin.

[0123] (Appendix 19) A management device for a digital twin that reproduces the real world in a virtual space, Observing a first amount of movement of an object existing in the real world; determining a second amount of movement of the agent corresponding to the object in the virtual space; Executing a data assimilation process of the digital twin based on the observed first movement amount and the identified second movement amount. A management device comprising a control unit for executing processing.

[0124] (Appendix 20) Identifying an error between the observed first movement amount and a second movement amount of an agent corresponding to the object in the virtual space; Dynamically changing a movement demand of the agent in the virtual space based on the identified error; The process of performing the data assimilation process includes: Based on the changed travel demand, data assimilation processing of the digital twin is performed between the first travel amount and the second travel amount. 20. The management device according to claim 19, further comprising a control unit for executing processing.

[0125] (Additional Note 21) The process of observing the first movement amount includes: Observing a first amount of movement of an object along the real world road or passageway. Including processing, The process of identifying the error includes: Identifying an error between the observed first movement amount and a second movement amount of an agent corresponding to the object on a road or passage in the virtual space. Including processing, The process of performing the data assimilation process includes: The data assimilation process is performed so that the first movement amount and the second movement amount coincide with each other. 21. The management device according to claim 20, further comprising a process.

[0126] (Additional Note 22) The process of observing the first movement amount includes: Observing a first amount of movement of an object along the real world road or passageway. Including processing, The process of identifying the error includes: Identifying an error between the observed first movement amount and a second movement amount of an agent corresponding to the object on a road or passage in the virtual space. Including processing, The process of performing the data assimilation process includes: The data assimilation process is performed so that the first movement amount and the second movement amount coincide with each other. 21. The management device according to claim 20, further comprising a process.

[0127] (Additional Note 23) The process of observing the first movement amount includes: The object is detected using an image captured by the camera, and a first amount of movement of the detected object is identified. Including processing, The second movement amount is calculated by simulating the second movement amount in the digital twin using the observed first movement amount. The management device according to claim 21, characterized in that the control unit executes the processing.

[0128] (Additional Note 24) The process of observing the first movement amount includes: A first number of the objects that have moved on a road or passage between predetermined intersections in the road or passage in the real world is observed as the first movement amount. Including processing, The process of identifying the error includes: A first error between the first number and a second number of the agents who have moved along a road or passage between predetermined intersections in the road or passage in the virtual space is calculated as the error. 24. The management device according to claim 23, further comprising a process.

[0129] (Appendix 25) Estimating the amount of movement of the object from a predetermined starting point in the real world to a destination so as to minimize a weighted sum of the first error and the second error. The management device according to claim 24, wherein the control unit executes the processing.

[0130] (Additional Note 26) The process of determining the second movement amount includes: identifying a road or passage in a virtual space that reproduces the road or passage in the real world, and moving along the identified road or passage in the virtual space; and identifying a second movement amount of the agent corresponding to the object; 22. The management device according to claim 21, further comprising a process.

[0131] (Appendix 27) During the period from when the data assimilation process of the digital twin is completed to when the next data assimilation process is executed, a simulation is performed in the virtual space of the digital twin using the second movement amount to predict the presence or absence of an abnormality in the movement amount of an object existing in the real world; When the abnormality is predicted, a road or a passage on which the abnormality is predicted is identified; Displaying an image in which the identified road or passage is highlighted on a display device The management device according to claim 21, characterized in that the control unit executes the processing.

[0132] (Appendix 28) A processor; a memory operatively connected to the processor; A management device for a digital twin that reproduces the real world in a virtual space, comprising: Observing a first amount of movement of an object existing in the real world; determining a second amount of movement of the agent corresponding to the object in the virtual space; Executing a data assimilation process of the digital twin based on the observed first movement amount and the identified second movement amount. A management device that executes a process. [Explanation of symbols]

[0133] 1. Information Processing Systems 10 Digital Twin Management Device 10a Communication Interface 10b HDD 10c Memory 10d Processor 20 Communications Department 30 Storage section 31 Video information 32 Real World Information 33 Digital Twin Information 40 Control section 41 Acquisition Department 42 Simulation Department 43 Arithmetic section 44 Estimation part 50 Network 100 Camera Equipment

Claims

1. A digital twin management device that recreates the real world in a virtual space. Observing a first amount of movement of an object existing in the real world; determining a second amount of movement of the agent corresponding to the object in the virtual space; Executing a data assimilation process of the digital twin based on the observed first movement amount and the identified second movement amount. An information processing program that causes a process to be executed.

2. determining an error between the observed first movement amount and a second movement amount of an agent corresponding to the object in the virtual space; Dynamically changing a movement demand of the agent in the virtual space based on the identified error; The process of performing the data assimilation process includes: Based on the changed travel demand, data assimilation processing of the digital twin is performed between the first travel amount and the second travel amount.

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

3. The process of observing the first movement amount includes: Observing a first amount of movement of an object along the real world road or passageway. Processing The process of identifying the error includes: Identifying an error between the observed first movement amount and a second movement amount of an agent corresponding to the object on a road or a passage in the virtual space. Processing The process of performing the data assimilation process includes: The data assimilation process is performed so that the first movement amount and the second movement amount coincide with each other.

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

4. The process of observing the first movement amount includes: The object is detected using an image captured by the camera, and a first amount of movement of the detected object is identified. Processing Using the observed first movement amount, the second movement amount is simulated and calculated in the digital twin. The information processing program according to claim 2, characterized in that the processing is executed by a management device for the digital twin.

5. The process of observing the first movement amount includes: A first number of the objects that have moved on a road or passage between predetermined intersections in the road or passage in the real world is observed as the first movement amount. Processing The process of identifying the error includes: A first error between the first number and a second number of the agents who have moved along a road or a passage between predetermined intersections in the road or passage in the virtual space is calculated as the error.

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

6. The process of observing the first movement amount includes: Observe a first ratio of the object that has moved to each branch at a predetermined intersection on a road or passage in the real world as the first movement amount. Processing The process of identifying the error includes: A second error between the first ratio and a second ratio of the agents who move to each branch at a predetermined intersection on a road or passage in the virtual space is calculated as the error.

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

7. A movement amount of the object from a given origin in the real world to a destination is estimated so as to minimize a weighted sum of the first error and the second error. The information processing program according to claim 6, characterized in that the processing is executed by a management device for the digital twin.

8. The process of determining the second movement amount includes: identifying a road or passage in a virtual space that reproduces the road or passage in the real world, and moving along the identified road or passage in the virtual space; and identifying a second movement amount of the agent corresponding to the object.

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

9. During the period from when the data assimilation process of the digital twin is completed until the next data assimilation process is executed, a simulation is performed in the virtual space of the digital twin using an agent in the virtual space to predict the presence or absence of an abnormality in the amount of movement of an object existing in the real world; When the abnormality is predicted, a road or a passage on which the abnormality is predicted is identified; Displaying an image in which the identified road or passage is highlighted on a display device The information processing program according to claim 3, characterized in that the processing is executed by a management device for the digital twin.

10. A digital twin management device that reproduces the real world in a virtual space Observing a first amount of movement of an object existing in the real world; determining a second amount of movement of the agent corresponding to the object in the virtual space; Executing a data assimilation process of the digital twin based on the observed first movement amount and the identified second movement amount.

2. An information processing method comprising:

11. A management device for digital twins that reproduce the real world in a virtual space, Observing a first amount of movement of an object existing in the real world; determining a second amount of movement of the agent corresponding to the object in the virtual space; Executing a data assimilation process of the digital twin based on the observed first movement amount and the identified second movement amount. A management device comprising a control unit for executing processing.

Images