Information generation system, information generation method, and program

Abstract

To provide an information generation system, an information generation method, and a program that can reflect a change in situation along with the lapse of time in a target space to an automatically generated scenario, and thereby improve the accuracy of generating the scenario.SOLUTION: An information generation system comprises: a simulation processing unit that, on the basis of first event information indicating a time-series change of a first event in a target real space, reproduces the first event in a virtual space that virtually reproduces the real space, and records a second event that is generated along with the time-series change of the first event in the virtual space; and a scenario generation unit that, on the basis of second event information indicating the second event, generates scenario information indicating a scenario for a user to cope with the second event that is generated in the first event.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an information generation system, an information generation method, and a program. [Background technology]

[0002] Conventionally, scenarios used in disaster prevention drills have been created manually. For example, in disaster prevention drills, scenarios are created manually based on static hazard maps, and the drills are carried out by providing trainees with fragmented information via telephone, fax, memos, etc. in accordance with the scenarios.

[0003] In order to reduce the workload involved in creating a scenario, various techniques for automatically generating a scenario have been proposed. For example, Patent Document 1 below discloses a technique for generating a scenario for a training simulation, in which an appropriate training exercise scenario is automatically generated according to the purpose of the training exercise by inputting several parameters as initial values. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2010-113105 Summary of the Invention [Problem to be solved by the invention]

[0005] However, the technology described in Patent Document 1 above was unable to automatically generate a scenario that reflected changes in the situation over time in the target space.

[0006] In view of the above-mentioned problems, an object of the present invention is to provide an information generation system, an information generation method, and a program that can reflect situational changes over time in a target space in an automatically generated scenario, thereby improving the accuracy of scenario generation. [Means for solving the problem]

[0007] In order to solve the above-mentioned problems, an information generation system according to one embodiment of the present invention is an information generation system comprising: a simulation processing unit that, based on first event information indicating a time series change of a first event in a target real space, reproduces the first event in a virtual space that virtually reproduces the real space, and records a second event that occurs in accordance with the time series change of the first event in the virtual space; and a scenario generation unit that, based on second event information indicating the second event, generates scenario information indicating a scenario for a user to respond to the second event that occurs in the first event.

[0008] An information generation method according to one embodiment of the present invention is an information generation method executed by a computer, including: a simulation processing step of recreating a first event in a virtual space that virtually recreates a real space based on first event information indicating a time series change of the first event in the target real space, and recording a second event that occurs in accordance with the time series change of the first event in the virtual space; and a scenario generation step of generating scenario information indicating a scenario for a user to respond to the second event that occurs in the first event, based on second event information indicating the second event.

[0009] A program according to one embodiment of the present invention causes a computer to function as: a simulation processing means that, based on first event information indicating the time series change of a first event in a target real space, recreates the first event in a virtual space that virtually recreates the real space, and records a second event that occurs in accordance with the time series change of the first event in the virtual space; and a scenario generation means that, based on second event information indicating the second event, generates scenario information indicating a scenario for a user to respond to the second event that occurs in the first event. [Effects of the Invention]

[0010] According to the present invention, it is possible to improve the accuracy of scenario generation by reflecting changes in the situation over time in a target space in an automatically generated scenario. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a diagram illustrating an example of the configuration of a training information generation system according to an embodiment of the present invention. [Figure 2] FIG. 2 is a block diagram showing an example of a functional configuration of a disaster reproduction server according to the present embodiment. [Figure 3] FIG. 2 is a block diagram illustrating an example of a functional configuration of a training server according to the present embodiment. [Figure 4] 1 is a flowchart showing an overview of the processing in the training information generation system according to this embodiment. [Figure 5] A sequence diagram showing an example of the flow of the training information generation process in the training information generation system of this embodiment. [Figure 6] FIG. 10 is a sequence diagram showing an example of the flow of disaster reproduction processing in the disaster reproduction server according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0012] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings. An information generating system according to this embodiment will be described below with reference to FIGS. In the following, the present embodiment will be described by taking as an example an information generation system that generates information used in training (hereinafter also referred to as "training information"). In the present embodiment, the training is, for example, a disaster prevention training for disasters and the damage caused by the disasters. The training information includes information indicating a scenario (hereinafter also referred to as "scenario information") for recreating a first event in a virtual space virtually recreated in a target real space (hereinafter also referred to as "target space") and for the user to respond to a second event that occurs in accordance with the chronological change of the first event in the virtual space. In this case, the first event is, for example, a disaster. The second event is, for example, damage caused by the disaster. The user is a trainee. The scenario information is information indicating, for example, a scenario for the trainee to conduct disaster prevention training for disasters and damage.

[0013] <1. Configuration of the training information generation system> The configuration of a training information generation system 1 according to this embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of the configuration of the training information generation system 1 according to this embodiment.

[0014] As shown in FIG. 1, the training information generation system 1 includes a scientific calculation device 10, a disaster reproduction server 20, a training server 30, a telephone 40, a text information output device 50, an image display device 60, an information compilation device 70, and an evaluation input device 80. Of the training information generation system 1, the scientific calculation device 10, disaster reproduction server 20, and training server 30 are used by the secretariat that implements the training (implementation secretariat). Also, of the training information generation system 1, the telephone 40, character information output device 50, image display device 60, information compilation device 70, and evaluation input device 80 are used at the venue where the training is implemented (training venue) by the person who implements the training (trainer) or the person who evaluates the results of the training (evaluator).

[0015] The networks NW (NW1, NW2) may be configured to transmit and receive information using, for example, a local area network (LAN), a wide area network (WAN), a telephone network (mobile phone network, landline telephone network, etc.), a regional Internet Protocol (IP) network, the Internet, etc. Communications in the training information generation system 1 include communications between multiple devices using the network NW and inter-process communications within the same device. As shown in Figure 1, network NW1 connects devices used in the implementation office so that they can communicate with each other. Network NW2 connects devices used in the implementation office and devices used at the training venue so that they can communicate with each other. Each device included in the training information generation system 1 can exchange data online between devices using network NW1 or network NW2.

[0016] (1) Scientific computing equipment 10 The scientific computing device 10 is a device that performs a simulation assuming the occurrence of a disaster in real space (hereinafter also referred to as a "disaster simulation"). The scientific computing device 10 is a device that can perform large-scale numerical calculations and simulations, such as a supercomputer or a quantum computer. The scientific computing device 10 is communicably connected to a disaster reproduction server 20 via a network NW1.

[0017] Disasters include natural disasters such as earthquakes, tsunamis, and river flooding. In the case of earthquakes, disaster simulations involve analyses of, for example, the strength and magnitude of the earthquake, the speed and strength of seismic waves traveling through bedrock and the ground, and the seismic intensity at the ground surface. In the case of tsunamis, disaster simulations involve analyses of, for example, the time the tsunami will arrive, the maximum water level of the tsunami, the maximum water flow velocity, and the flooded areas. In the case of river flooding simulations, analyses include, for example, the location of the river's breach and the flooded areas depending on the location of the breach. The scientific computing device 10 generates information indicating the simulation results (hereinafter also referred to as "disaster information") through a disaster simulation. The disaster information is an example of event information (first event information) indicating a time-series change in the disaster in the target space. The scientific computing device 10 transmits the generated disaster information to the disaster reproduction server 20 via the network NW1.

[0018] When generating training information, the training information generation system may use disaster information generated in real time by the scientific computing device 10, or may reuse disaster information previously generated by the scientific computing device 10. For example, a local government may perform a disaster simulation using the scientific computing device 10 when creating a hazard map, and disaster information may already be generated. In this case, the training information generation system 1 can reuse the disaster information that has already been generated.

[0019] (2) Disaster Reconstruction Server 20 The disaster reproduction server 20 is a server for recreating a disaster in a virtual space, and is an example of a disaster reproduction device. The disaster reproduction server 20 is configured with one or more servers (for example, cloud servers). The disaster reproduction device may be a PC (Personal Computer). The disaster reenactment server 20 is communicably connected to the scientific computing device 10 and the training server 30 via a network NW1.

[0020] The disaster replay server 20 uses disaster information to replay a disaster in a virtual space and performs a simulation (hereinafter also referred to as a "disaster replay simulation") to detect the impact on objects placed in the virtual space. The disaster replay server 20 replays a disaster (a first event) in the virtual space and detects damage (a second event) that occurs to each object as the disaster changes over time. The disaster replay server 20 generates information (hereinafter also referred to as "disaster replay information") indicating the results of the disaster replay in the virtual space through the simulation. The disaster replay information is an example of event information (second event information) that indicates damage that occurs as the disaster changes over time in the virtual space. The disaster replay information includes, for example, information (hereinafter also referred to as "chronological log information") that chronologically shows a log of the damage detected by the disaster replay simulation. The disaster replay server 20 transmits the generated disaster replay information to the training server 30 via the network NW1.

[0021] The objects placed in the virtual space are objects that exist in the real space and are reproduced in the virtual space, and include static objects and dynamic objects. A static object is an object whose position in the virtual space is fixed. A static object is a reproduction of an immovable object in the real space, such as a building or natural object. Natural objects include plants and terrain. A dynamic object is an object whose position in the virtual space is not fixed, and is a reproduction of a movable object in the real space, such as a person or a car.

[0022] The type of damage varies depending on the type of disaster and the type of object. Disasters are divided into primary disasters and secondary disasters that occur as a result of primary disasters. Primary disasters include, for example, earthquakes, typhoons, heavy rain, heavy snow, and volcanic eruptions. Secondary disasters caused by earthquakes include, for example, fires, tsunamis, cracks in the ground, aftershocks, and landslides. Secondary disasters caused by typhoons and heavy rain include, for example, floods, inundation, landslides, and landslides. Secondary disasters caused by heavy snow include, for example, avalanches and traffic accidents. Secondary disasters caused by volcanic eruptions include, for example, volcanic rocks, pyroclastic flows, and volcanic mudflows. Damage to buildings caused by these disasters includes, for example, collapse, damage, breakage, flooding, burning, and subsidence or tilting due to liquefaction of the ground. The damage that people suffer from these disasters can be divided into damage that occurs directly to the human body (hereinafter also referred to as "direct damage") and damage that occurs indirectly to the human body (hereinafter also referred to as "indirect damage"). Direct damage includes, for example, injuries sustained when falling due to an earthquake, or being swept away by a tsunami or river flooding. Indirect damage includes, for example, being buried under a building that collapsed due to an earthquake, being left behind in a building flooded by a tsunami or river flooding, or being isolated due to a bridge collapse or landslide.

[0023] (3) Training Server 30 The training server 30 is a server for generating training information and is an example of a training device. The training server 30 is configured with one or more servers (for example, cloud servers). The training device may also be a PC. The training server 30 is communicatively connected to the disaster reproduction server 20 via a network NW1. The training server 30 is also communicatively connected to a text information output device 50, an image display device 60, an information compilation device 70, and an evaluation input device 80 via a network NW2.

[0024] The training information generated by the training server 30 includes scenario information, audio script, text information, and images. Scenario information is information that indicates scenarios used in role-playing training (tabletop training). For example, in a disaster prevention training exercise conducted by a local government, scenario information may include scenarios that indicate how to set up and operate a disaster response headquarters and evacuation shelters when a disaster occurs in the target space, scenarios that indicate how to respond to the disaster that has occurred, scenarios that indicate how to respond to damage caused by the disaster, and scenarios that indicate how to respond to recovery and reconstruction after the disaster has subsided. An audio script is a script that shows the text that an operator reads out loud to transmit disaster-related information to relevant parties by voice. Text information is information that is printed on paper in order to communicate disaster-related information to relevant parties in writing. The images are images showing the state of various locations in the target space in order to convey disaster information to relevant parties through images.

[0025] (4) Telephone 40 The telephone 40 is used by an operator to transmit information about the disaster to relevant parties by voice. The audio script generated by the training server 30 is printed on a medium such as paper and handed to the operator. The operator then reads the script over the phone. This allows trainees to understand disaster-related information through audio.

[0026] (5) Character information output device 50 The character information output device 50 is a device that outputs character information. The character information output device 50 is, for example, a printer, a FAX (facsimile), or the like, and is not particularly limited as long as it is a device that can output a medium (such as paper) on which character information is printed. The character information output device 50 is communicably connected to the training server 30 via the network NW2. In communication with the training server 30, the character information output device 50 receives character information generated by the training server 30. The character information output device 50 outputs paper on which the character information received from the training server 30 is printed. This allows trainees to obtain disaster-related information in writing.

[0027] (6) Image display device 60 The image display device 60 is a device for displaying images. The images may be either still images or moving images (video). The image display device 60 may be, for example, a display device, a PC, a smartphone, a tablet terminal, or the like, and is not particularly limited as long as it is a device equipped with a display device capable of displaying images. The image display device 60 is communicably connected to the training server 30 via the network NW2. In communication with the training server 30, the image display device 60 receives images generated by the training server 30. The image display device 60 displays the images received from the training server 30. This allows trainees to grasp information about disasters through images.

[0028] (7) Information collection device 70 The information compilation device 70 is a device for compiling information related to the training performed by the trainee. The information compilation device 70 may be a PC, a smartphone, a tablet terminal, or the like, and is not particularly limited as long as it is a device into which the trainee can input information. The information compilation device 70 is communicably connected to the training server 30 via the network NW2. In communication with the training server 30, the information compilation device 70 transmits information relating to the implementation of training input by the trainee (hereinafter also referred to as "training implementation information"). For example, the trainee inputs information indicating the actions actually taken based on the training information when implementing the training as the training implementation information.

[0029] (8) Evaluation input device 80 The evaluation input device 80 is a device for inputting an evaluation of the results of training by a trainee. The evaluation input device 80 may be a PC, smartphone, tablet terminal, or the like, and is not particularly limited as long as it is a device that allows the evaluator to input information. The evaluation input device 80 is communicably connected to the training server 30 via the network NW2. In communication with the training server 30, the evaluation input device 80 transmits information related to the evaluation input by the evaluator (hereinafter also referred to as "evaluation information").

[0030] <2. Functional Configuration of Disaster Reproduction Server 20> The configuration of the training information generation system 1 according to this embodiment has been described above. Next, the functional configuration of the disaster reenactment server 20 according to this embodiment will be described with reference to Fig. 2. Fig. 2 is a block diagram showing an example of the functional configuration of the disaster reenactment server 20 according to this embodiment. As shown in FIG. 2, the disaster reproduction server 20 includes a communication unit 210, a storage unit 220, and a control unit 230.

[0031] (1) Communications Unit 210 The communication unit 210 has a function of transmitting and receiving various types of information. The communication unit 210 is communicably connected to the scientific computing device 10 and the training server 30 via the network NW1, and transmits and receives various types of information to and from each device. In communication with the scientific computing device 10, the communication unit 210 receives, for example, disaster information. The communication unit 210 stores the received disaster information in the storage unit 220. In communication with the training server 30, the communication unit 210 transmits, for example, disaster reproduction information.

[0032] (2) Storage section 220 The storage unit 220 has a function of storing various types of information. The storage unit 220 is configured by a storage medium provided as hardware in the disaster reproduction server 20, such as a hard disk drive (HDD), a solid state drive (SSD), a flash memory, an electrically erasable programmable read-only memory (EEPROM), a random access read / write memory (RAM), a read-only memory (ROM), or any combination of these storage media.

[0033] The storage unit 220 stores, for example, disaster information, three-dimensional space map information, object information, characteristic information, and disaster reproduction information (time-series log information). The three-dimensional spatial map information is information that indicates a space (virtual space) in which a map of a target space is reproduced in three dimensions using CG (computer graphics). The object information is information that indicates an object to be placed in the virtual space. The characteristic information is information that indicates the characteristics of an object placed in a virtual space. The characteristic information of a static object is, for example, information that indicates position information (fixed position), damage occurrence logic, etc. The characteristic information of a dynamic object is, for example, information that indicates position information (initial position), damage occurrence logic, operation logic, etc.

[0034] (3) Control unit 230 The control unit 230 has a function of controlling the overall operation of the disaster reproduction server 20. The control unit 230 is realized, for example, by causing a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit) provided as hardware in the disaster reproduction server 20 to execute a program. As shown in FIG. 2, the control unit 230 includes a simulation processing unit 231, an object processing unit 232, and an interaction calculation unit 233.

[0035] (3-1) Simulation Processing Unit 231 The simulation processing unit 231 has a function of performing a disaster reproduction simulation. In the disaster reproduction simulation, the simulation processing unit 231 reproduces a disaster in a virtual space based on disaster information obtained from the scientific computing device 10, and records damage that occurs in accordance with time-series changes in the disaster in the virtual space. The simulation processing unit 231 generates disaster reproduction information by recording in chronological order a log of damage detected for each object in the disaster reproduction simulation and generating time-series log information. The simulation processing unit 231 stores the generated disaster reproduction information in the storage unit 220. The simulation processing unit 231 also transmits the generated disaster reproduction information to the training server 30 via the communication unit 210.

[0036] (3-2) Object processing unit 232 The object processing unit 232 has a function of executing processing related to objects, and places the object in the virtual space based on the object information and property information. When placing a static object in virtual space, the object processing unit 232 refers to the position information included in the characteristic information, and places the static object at the fixed position indicated by the position information. When placing a dynamic object in a virtual space, the object processing unit 232 refers to the position information included in the characteristic information and places the dynamic object at the initial position indicated by the position information. After placement, the object processing unit 232 causes the dynamic object to operate (for example, move) in accordance with the operation logic included in the characteristic information.

[0037] (3-3) Interaction calculation section 233 The interaction calculation unit 233 has a function of detecting damage that occurs to objects. The interaction calculation unit 233 calculates the interaction between disasters and objects in the virtual space and detects damage that occurs to each object. In detecting damage, the interaction calculation unit 233 determines whether the impact of a time-series change in the disaster on an object corresponds to damage, based on the damage occurrence logic included in the object's characteristic information. The damage occurrence logic may, for example, have a reference value set for each type of damage. The interaction calculation unit 233 calculates the degree of impact that a time-series change in the disaster has on an object, and compares the calculated degree with the reference value indicated by the damage occurrence logic. The interaction calculation unit 233 determines whether damage has occurred depending on whether the calculated degree is above or below the reference value.

[0038] If the object is a static object, the interaction calculation unit 233 detects damage that occurs to the static object due to the interaction between the disaster and the static object, based on the damage occurrence logic included in the characteristic information of the static object.

[0039] If the object is a dynamic object, the interaction calculation unit 233 distinguishes and detects whether the damage that has occurred to the dynamic object is direct damage or indirect damage. When detecting direct damage, the interaction calculation unit 233 calculates the interaction between the disaster and the dynamic object based on the damage occurrence logic included in the characteristic information of the dynamic object, thereby enabling the interaction calculation unit 233 to detect direct damage that occurs to the dynamic object. When detecting indirect damage, the interaction calculation unit 233 first detects damage caused to a static object due to an interaction between a disaster and the static object, based on the damage occurrence logic included in the characteristic information of the static object. When damage caused to a static object is detected, the interaction calculation unit 233 calculates the interaction between the damage caused to the static object detected in the previous stage and the dynamic object, based on the damage occurrence logic included in the characteristic information of the dynamic object. This allows the interaction calculation unit 233 to detect indirect damage caused to the dynamic object.

[0040] <3. Functional configuration of the training server 30> The functional configuration of the disaster reenactment server 20 according to this embodiment has been described above. Next, the functional configuration of the training server 30 according to this embodiment will be described with reference to Fig. 3. Fig. 3 is a block diagram showing an example of the functional configuration of the training server 30 according to this embodiment. As shown in FIG. 3, the training server 30 includes a communication unit 310, a storage unit 320, and a control unit 330.

[0041] (1) Communications unit 310 The communication unit 310 has a function of transmitting and receiving various types of information. The communication unit 310 is communicably connected to the disaster reproduction server 20 via the network NW1, and transmits and receives various types of information. The communication unit 310 receives disaster reproduction information in communication with the disaster reproduction server 20. The communication unit 310 stores the received disaster reproduction information in the storage unit 320.

[0042] In addition, the communication unit 310 is communicatively connected to the text information output device 50, the image display device 60, the information compilation device 70, and the evaluation input device 80 via the network NW2, and transmits and receives various information to and from each device. In communication with the text information output device 50, the communication unit 310 transmits text information. In communication with the image display device 60, the communication unit 310 transmits images. In communication with the information compilation device 70, the communication unit 310 receives training implementation information. The communication unit 310 stores the received training implementation information in the memory unit 320. In communication with the evaluation input device 80, the communication unit 310 receives evaluation information. The communication unit 310 stores the received evaluation information in the memory unit 320.

[0043] (2) Storage section 320 The storage unit 320 has a function of storing various information. The storage unit 320 is configured by a storage medium provided as hardware in the training server 30, such as an HDD, SSD, flash memory, EEPROM, RAM, ROM, or any combination of these storage media.

[0044] The storage unit 320 stores, for example, disaster reproduction information, specification information, scenario information, audio script, text information, images, training implementation information, evaluation information, and a log related to the implementation of the training. The specification information is information indicating specifications regarding the intended use of the scenario, such as the purpose, phase, and level of the training.

[0045] (3) Control unit 330 The control unit 330 has a function of controlling the overall operation of the training server 30. The control unit 330 is realized, for example, by causing a CPU or GPU provided as hardware in the training server 30 to execute a program. As shown in FIG. 3, the control unit 330 includes a scenario generation unit 331, a natural language processing unit 332, an audio manuscript generation unit 333, a text information generation unit 334, a viewpoint calculation unit 335, an image generation unit 336, and a training log management unit 337.

[0046] (3-1) Scenario Generation Unit 331 The scenario generation unit 331 has a function of generating scenario information. The scenario generation unit 331 generates the scenario information based on the disaster reproduction information that the communication unit 310 receives from the disaster reproduction server 20. Based on the specification information stored in the storage unit 320, the scenario generation unit 331 extracts damage corresponding to the specifications indicated by the specification information from the damage indicated by the time-series log information recorded as disaster reproduction information. After extraction, the scenario generation unit 331 generates scenario information indicating a scenario for the trainee to respond to the extracted damage. During generation, the scenario generation unit 331 generates a scenario by synchronizing the time axis of the detected damage based on the log of damage indicated by the time-series log information. This allows the trainee to generate a scenario while ensuring temporal synchronization of the damage to be responded to during training. The scenario generation unit 331 stores the generated scenario information in the storage unit 320.

[0047] (3-2) Natural Language Processing Unit 332 The natural language processing unit 332 has a function of performing natural language processing. The natural language processing unit 332 performs natural language processing on the scenario information generated by the scenario generation unit 331. As a result, the natural language processing unit 332 converts the scenario information into information that can be used to generate various types of information.

[0048] (3-3) Audio manuscript generation unit 333 The audio manuscript generation unit 333 has a function of generating an audio manuscript. For example, the audio manuscript generation unit 333 generates an audio manuscript corresponding to a scenario based on scenario information generated by the scenario generation unit 331. Specifically, the audio manuscript generation unit 333 generates an audio manuscript from information obtained by natural language processing the scenario information generated by the scenario generation unit 331 by the natural language processing unit 332. The audio manuscript generating unit 333 stores the generated audio manuscript in the storage unit 320. The audio manuscript generated by the audio manuscript generating unit 333 is printed and handed to an operator.

[0049] (3-4) Character information generation section 334 The character information generation unit 334 has a function of generating character information. For example, the character information generation unit 334 generates character information corresponding to a scenario based on scenario information generated by the scenario generation unit 331. Specifically, the character information generation unit 334 generates character information from information obtained by natural language processing performed by the natural language processing unit 332 on the scenario information generated by the scenario generation unit 331. The character information generating unit 334 stores the generated character information in the storage unit 320. The character information generating unit 334 also transmits the generated character information to the character information output device 50 via the communication unit 310.

[0050] (3-5) Viewpoint calculation unit 335 The viewpoint calculation unit 335 has a function of calculating the viewpoint in the virtual space. For each scenario indicated by the scenario information, the viewpoint calculation unit 335 acquires viewpoint information (location of damage occurrence) from, for example, time-series log information corresponding to each scenario. The viewpoint calculation unit 335 calculates a path of viewpoint movement based on the acquired viewpoint information of each scenario. The path of viewpoint movement is, in other words, information indicating how the viewpoint in the virtual space changes.

[0051] (3-6) Image generation unit 336 The image generation unit 336 has a function of generating images showing the state of the virtual space. For example, the image generation unit 336 generates an image corresponding to a scenario, reflecting the effects of damage, based on scenario information generated by the scenario generation unit 331. Specifically, the image generation unit 336 generates images showing the state of the virtual space from each viewpoint, based on a path of viewpoint movement calculated by the viewpoint calculation unit 335 from the scenario information generated by the scenario generation unit 331. Note that the image generation unit 336 may generate images using a separately set path of viewpoint movement instead of the path of viewpoint movement calculated by the viewpoint calculation unit 335. The separately set path of viewpoint movement may be, for example, a path based on the viewpoint of a fixed observation camera installed in real space, a path set to patrol a certain range, or a path based on the flight path of a drone in real space. The image generation unit 336 stores the generated image in the storage unit 320. The image generation unit 336 also transmits the generated image to the image display device 60 via the communication unit 310.

[0052] (3-7) Training Log Management Department 337 The training log management unit 337 has a function of managing logs related to the implementation of training. For example, the training log management unit 337 generates a log related to the implementation of training based on the training implementation information received by the communication unit 310 from the information compilation device 70 and the evaluation information received by the communication unit 310 from the evaluation input device 80, and stores the log in the storage unit 320.

[0053] The above-mentioned audio manuscript generation unit 333, character information generation unit 334, and image generation unit 336 all generate various types of information based on the scenario information generated by the scenario generation unit 331. The scenario information is generated by the scenario generation unit 331 in a state where temporal synchronization of the damage is ensured. Therefore, the audio manuscript generation unit 333, character information generation unit 334, and image generation unit 336 can generate information in a state where temporal synchronization between the scenario and other information is ensured.

[0054] <4. Processing flow> The functional configuration of the training server 30 according to this embodiment has been described above. Next, the processing flow in the training information generation system 1 according to this embodiment will be described with reference to Figs.

[0055] (1) Overview of the processing in the training information generation system First, an overview of the processing in the training information generation system 1 according to this embodiment will be described with reference to Fig. 4. Fig. 4 is a flowchart showing an overview of the processing in the training information generation system 1 according to this embodiment. In the example shown in Fig. 4, the explanation will be given assuming that the implementation office, the trainee, or the evaluator is the subject of each process.

[0056] 4, first, the implementation office carries out a disaster simulation (step S101). The implementation office carries out the disaster simulation using the scientific computing device 10. The implementation office uploads disaster information obtained by carrying out the disaster simulation to the disaster reproduction server 20.

[0057] Next, the implementation office prepares information for disaster reproduction (step S102). The implementation office prepares three-dimensional map space information indicating the virtual space, object information indicating each object to be placed in the virtual space, and characteristic information indicating the characteristics of each object, and uploads each of the prepared information to the disaster reproduction server 20.

[0058] Next, the implementation office conducts a disaster re-enactment simulation (step S103). The implementation office conducts the disaster re-enactment simulation using the disaster re-enactment server 20 based on the disaster information, 3D map space information, object information, and characteristic information prepared in advance. The implementation office uploads the disaster re-enactment information obtained by conducting the disaster re-enactment simulation to the training server 30.

[0059] Next, the implementation office prepares a training scenario (step S104). The implementation office uses the training server 30 to prepare scenario information from the disaster reproduction information.

[0060] Next, the implementation office prepares an audio script, text information, and images (step S105). The implementation office uses the training server 30 to prepare an audio script, text information, and images from the scenario information.

[0061] The trainee conducts the training (step S106). The trainee conducts the training using the audio script, text information, and images prepared by the training office. The trainee or evaluator inputs training implementation information about the training that was conducted from the information compilation device 70.

[0062] After the training is completed, the trainee and the evaluator review the training and carry out improvement activities (step S107). The evaluator inputs evaluation information from the evaluation input device 80 regarding the training implementation information entered by the trainee or evaluator. The trainee and the evaluator review the training and carry out improvement activities based on the training implementation information and evaluation information.

[0063] (2) Training information generation process flow in the training information generation system Next, the flow of the training information generation process in the training information generation system 1 according to this embodiment will be described with reference to Fig. 5. Fig. 5 is a sequence diagram showing an example of the flow of the training information generation process in the training information generation system 1 according to this embodiment.

[0064] 5, first, the scientific computing device 10 performs a disaster simulation (step S201). By performing the disaster simulation, the scientific computing device 10 generates disaster information indicating the results. After the disaster simulation is performed, the scientific computing device 10 transmits the generated disaster information to the disaster reproduction server 20 (step S202).

[0065] The disaster reproduction server 20 executes disaster reproduction processing (step S203). Details of the disaster reproduction processing will be described later. After the disaster reproduction process, the disaster reproduction server 20 transmits disaster reproduction information to the training server 30 (step S204).

[0066] The scenario generation unit 331 of the training server 30 extracts disaster reproduction information (step S205). The scenario generation unit 331 extracts disaster reproduction information corresponding to the specification information stored in the storage unit 320 from the disaster reproduction information received by the communication unit 310 from the disaster reproduction server 20.

[0067] Next, the scenario generating unit 331 generates scenario information (step S206). The scenario generating unit 331 generates scenario information indicating a scenario corresponding to the extracted disaster reproduction information.

[0068] Next, the natural language processing unit 332 of the training server 30 performs natural language processing on the scenario information generated by the scenario generation unit 331 (step S207).

[0069] Next, the audio manuscript generating unit 333 of the training server 30 generates an audio manuscript (step S208). The audio manuscript generating unit 333 generates an audio manuscript from information obtained by natural language processing of the scenario information.

[0070] Next, the character information generating unit 334 of the training server 30 generates character information (step S209). The character information generating unit 334 generates character information from information obtained by natural language processing of the scenario information.

[0071] Next, the viewpoint calculation unit 335 of the training server 30 performs viewpoint calculation (step S210). The viewpoint calculation unit 335 performs viewpoint calculation based on the scenario information generated by the scenario generation unit 331. Note that the viewpoint calculation unit 335 may perform viewpoint calculation based on separately defined route information (for example, the flight path of a drone).

[0072] Next, the image generation unit 336 of the training server 30 generates an image (step S211). The image generation unit 336 generates an image based on the result of viewpoint calculation by the viewpoint calculation unit 335. Note that the image generation unit 336 may generate an image based on separately defined route information (for example, a flight path of a drone).

[0073] (3) Flow of disaster reproduction process on the disaster reproduction server Next, the flow of disaster reproduction processing in the disaster reproduction server 20 according to this embodiment will be described with reference to Fig. 6. Fig. 6 is a sequence diagram showing an example of the flow of disaster reproduction processing in the disaster reproduction server 20 according to this embodiment.

[0074] As shown in FIG. 6, first, the disaster reproduction server 20 performs an initial setting process (step S301). For static objects, the object processing unit 232 of the disaster reproduction server 20 performs initial placement based on characteristic information (step S301-1). For dynamic objects, the object processing unit 232 performs initial placement based on characteristic information (step S301-2). For time-series log information, the simulation processing unit 231 performs initialization (step S301-3). For three-dimensional map space information, the object processing unit 232 performs initialization (step S301-4).

[0075] Next, the object processing unit 232 determines terrain effect information for the dynamic object (step S302). The terrain effect information is information that indicates the characteristics of the terrain and the effect that the characteristics have on the dynamic object. For example, the terrain effect information indicates a decrease in movement speed due to an uphill slope, an increase in movement speed due to a downhill slope, a decrease in movement speed due to mud, etc. This allows the object processing unit 232 to cause the dynamic object to move in a way that takes the terrain into consideration.

[0076] Next, the object processing unit 232 calculates the current position of the dynamic object (step S303). After the calculation, the object processing unit 232 updates the current position of the dynamic object (step S304).

[0077] Next, the object processing unit 232 reflects the disaster information in chronological order in the static objects (step S305). The interaction calculation unit 233 determines whether or not damage will occur to the static object based on the disaster information reflected in the static object (step S306). If it is determined that damage will occur to a static object, the simulation processing unit 231 records a log (that is, time-series log information) indicating the damage (step S307). Furthermore, if it is determined that damage will occur to a static object, the object processing unit 232 reflects update information of the static object according to the type of damage in the three-dimensional map space information (step S308). Furthermore, if it is determined that damage will occur to a static object, the interaction calculation unit 233 determines whether or not indirect damage will occur to a dynamic object based on the time-series log information of the damage (steps S309 and S310).

[0078] Next, the object processing unit 232 reflects the disaster information in chronological order on the dynamic object (step S311). The interaction calculation unit 233 determines whether or not direct damage will occur to the dynamic object based on the disaster information reflected in the dynamic object (step S312). If it is determined that direct damage will occur to the dynamic object, the simulation processing unit 231 records a log (i.e., time-series log information) indicating the damage (step S313). At this time, if it is determined in step S310 that indirect damage will occur, the time-series log information is also recorded. Furthermore, if it is determined that direct or indirect damage will occur to the dynamic object, the object processing unit 232 reflects update information of the dynamic object according to the type of damage in the three-dimensional map space information (step S314).

[0079] The disaster reproduction server 20 performs an update process (step S315). For static objects, the object processing unit 232 of the disaster reproduction server 20 updates the status etc. in accordance with the damage assessment result (step S315-1). For dynamic objects, the object processing unit 232 updates the status etc. in accordance with the damage assessment result (step S315-2). For time-series log information, the simulation processing unit 231 adds newly obtained time-series log information (step S315-3). For three-dimensional map space information, the object processing unit 232 updates the states of static objects and dynamic objects to the latest states (step S315-4).

[0080] The disaster re-enactment server 20 repeatedly performs the processes from step S302 to step S315 within the dashed-line box in Fig. 6 according to the simulation interval. For example, the disaster re-enactment server 20 repeats the processes until the disaster that occurred in the virtual space subsides. Alternatively, the disaster re-enactment server 20 may repeat the processes until the state of a specific object converges to a certain condition, such as "stable" or "disappeared."

[0081] The processing flow in the training information generation system 1 is not limited to the processing flow described with reference to Figures 4 to 6, and the processing order may be different. For example, the processing order of generating an audio manuscript in step S208 and the processing order of generating text information in step S209 may be reversed.

[0082] The processing flow according to this embodiment has been described above. As described above, the training information generation system 1 (information generation system) according to this embodiment comprises a simulation processing unit 231 that recreates a disaster in a virtual space that virtually recreates the real space based on disaster information (first event information) that indicates the time series changes of the disaster (first event) in the target real space, and records the damage (second event) that occurs in accordance with the time series changes of the disaster in the virtual space, and a scenario generation unit 331 that generates scenario information that indicates a scenario for the user to respond to damage that occurs in a disaster based on the disaster reproduction information (second event information) that indicates the damage. With this configuration, the training information generation system 1 automatically generates a scenario that reflects changes in the situation over time in the target space. Therefore, the training information generation system 1 according to this embodiment reflects situation changes over time in the target space in the automatically generated scenario, thereby making it possible to improve the accuracy of scenario generation.

[0083] In addition, the training information generation system 1 according to this embodiment further includes an object processing unit 232 that places objects in the virtual space, and an interaction calculation unit 233 that calculates the interaction between disasters in the virtual space and objects and detects damage that occurs to each object. With this configuration, the training information generation system 1 can generate a scenario that reflects situation changes in which factors (disasters) and multiple elements (objects) are synchronized over time. Therefore, the training information generation system 1 can further improve the accuracy of generating scenarios compared to when simply reflecting changes in the situation over time.

[0084] In addition, in the training information generation system 1 according to this embodiment, the objects include static objects whose positions in the virtual space are fixed and dynamic objects whose positions are not fixed, and the interaction calculation unit 233 detects damage caused to the static objects due to the interaction between the disaster and the static objects, and detects damage caused to the dynamic objects due to the interaction between the damage caused to the static objects and the dynamic objects. With this configuration, the training information generation system 1 can detect not only direct damage that an object receives from a disaster, but also indirect damage that an object receives from other objects, and reflect this in the scenario. Therefore, the training information generation system 1 can further improve the accuracy of scenario generation compared to when simply reflecting direct damage.

[0085] In addition, the training information generation system 1 according to this embodiment further includes an audio manuscript generation unit 333 that generates an audio manuscript corresponding to the scenario based on the generated scenario information, a text information generation unit 334 that generates text information corresponding to the scenario based on the generated scenario information, and an image generation unit 336 that generates an image corresponding to the scenario based on the generated scenario information, with the impact of the damage reflected. With this configuration, the training information generation system 1 can generate a scenario in which audio, text, and image (video) information is synchronized and linked with the original scientific calculation results. Therefore, the training information generation system 1 enables trainees to use the various generated information to conduct practical training based on objective scenarios that reflect the damage situation as it changes over time. Furthermore, by generating images, the training information generation system 1 also makes it possible to enhance the sense of realism by using video linked to the training progress. Furthermore, by generating images, the training information generation system 1 also makes it possible to visually review the results of the training and extract causal relationships for improvement.

[0086] In addition, the audio manuscript generation unit 333, the text information generation unit 334, and the image generation unit 336 all generate various types of information based on the scenario information generated by the scenario generation unit 331 while ensuring temporal synchronization of the damage. Therefore, the training information generation system 1 can generate a scenario while ensuring the temporal synchronization of various pieces of information that the trainee uses during training.

[0087] <5. Variations> The above describes the embodiments. Next, modifications of the above-described embodiments will be described. Note that each modification described below may be applied to the embodiments alone or in combination with each other. Furthermore, each modification may be applied in place of the configuration described in the embodiments, or may be applied in addition to the configuration described in the embodiments.

[0088] In the above-described embodiment, the training information generation system 1 includes the scientific calculation device 10, the disaster reproduction server 20, the training server 30, the telephone 40, the text information output device 50, the image display device 60, the information compilation device 70, and the evaluation input device 80. However, the present invention is not limited to this example. For example, some of the above-described devices may not be used, the number of devices may be reduced by combining the functions of multiple devices into one device, or the functions of one or more devices may be divided and a new device may be added. As an example, an embodiment may also be possible in which the evaluation input device 80 is not used. Furthermore, the functions of each device may be provided by installing an application on each device (i.e., a native application), or may be provided by a web system (i.e., a web application). In the case of a web application, the application functions are managed by a server and are provided via a web browser.

[0089] In the above-described embodiment, an example has been described in which devices used in the implementation office are communicatively connected to each other via network NW1, and devices used in the implementation office and devices used at the training venue are communicatively connected to each other via network NW2, and data is exchanged between the devices online. However, this is not a limitation. The devices included in the training information generation system 1 may be capable of exchanging data offline without using the network NW. For example, data may be exchanged offline between the devices using a computer-readable recording medium (such as a USB memory, HDD, CD-R, or DVD-R) or a wired connection (such as a connection via an HDMI (registered trademark) cable).

[0090] For example, assume that the scientific computing device 10, the disaster re-creation server 20, and the training server 30 on the implementation secretariat side are constructed as separate devices, as in the configuration of the training information generation system 1 described with reference to Fig. 1. In this case, the scientific computing device 10, the disaster re-creation server 20, and the training server 30 may share data offline using a recording medium, rather than via the network NW1. For example, the scientific computing device 10 links the generated disaster information to the disaster replay server 20 via a recording medium. The disaster replay server 20 links the generated disaster replay information to the training server 30 via a recording medium.

[0091] In addition, in the configuration of the training information generation system 1 described with reference to Fig. 1, it is assumed that the disaster re-creation server 20 and the training server 30 on the implementation secretariat side are constructed as the same device (a server for both disaster re-creation and training). In this case, the scientific computing device 10 and the server for both disaster re-creation and training may share data offline using a recording medium, rather than via the network NW1. For example, the scientific computing device 10 links the generated disaster information to a disaster reproduction and training server via a recording medium.

[0092] 1, the scientific computing device 10 on the implementation secretariat side and the disaster re-creation and training server are configured to share data via a recording medium. In this case, the disaster re-creation and training server may share data with the device on the training venue side via the network NW2, or may share data without going through the network NW2. For example, if the image display device 60 at the training venue is a device (such as a smartphone) that can share data via the network NW2, the disaster reenactment and training server will share data with the image display device 60 via the network NW2. On the other hand, if the image display device 60 at the training venue is a device (such as a display device) that can share data via a wired connection, the disaster reenactment and training server will share data directly with the image display device 60 without going through the network NW2.

[0093] 1, the scientific computing device 10, the disaster reproduction server 20, and the training server 30 on the implementation secretariat side share data offline using a recording medium. In this case, the training server 30 may share data with the device on the training site side without going through the network NW2. For example, suppose that the text information output device 50 and image display device 60 at the training venue are devices that can link data with the training server 30 via a wired connection, and the information compilation device 70 and evaluation input device 80 are configured to output input information on paper without linking to the training server 30. In this case, the network NW2 between the training server 30 and the training venue is not required.

[0094] Although the above-described embodiment describes an example in which the contents of the audio manuscript are communicated to the trainee by an operator reading them aloud, the present invention is not limited to such an example. For example, the contents of the audio manuscript may be communicated to the trainee by being read aloud using Text-To-Speech (TTS). For this purpose, the training information generation system 1 further includes an automatic voice conversion device with TTS functionality. In this case, the audio manuscript generation unit 333 of the training server 30 transmits the generated audio manuscript from the communication unit 310 to the automatic voice conversion device via the network NW2. The automatic voice conversion device converts the audio manuscript received from the training server 30 into audio information using the TTS function. The automatic voice conversion device transmits the converted audio information data via the network NW2 to a device capable of audio output at the training venue. The device capable of audio output communicates the contents of the audio manuscript to the trainee by playing the converted audio information data. The device capable of audio output may be, for example, a telephone 40, a speaker, a PC, a smartphone, or a tablet terminal.

[0095] In the above-described embodiment, an example in which the information generation system is applied to the field of disaster prevention has been described, but the invention is not limited to such an example. For example, the information generation system may be applied to fields such as the metaverse, traffic (people flow), and the environment.

[0096] In the above-described embodiment, an example has been described in which a dynamic object is moved according to the operation logic included in the characteristic information in order to reproduce a movable object in real space, such as a person or a car, but the present invention is not limited to such an example. For example, a movable object existing in real space may be reproduced using data obtained by a person's movement in a metaverse space that reproduces real space.

[0097] The above describes the modified examples of the embodiment of the present invention. Note that some or all of the functions of the training information generation system 1, the scientific computing device 10, the disaster reproduction server 20, and the training server 30 in the above-described embodiment may be implemented by a computer. In this case, a program for implementing these functions may be recorded on a computer-readable recording medium, and the program recorded on the recording medium may be read into and executed by a computer system. Note that the term "computer system" as used herein includes hardware such as an OS and peripheral devices. Additionally, "computer-readable recording media" refers to portable media such as flexible disks, optical magnetic disks, ROMs, CD-ROMs, etc., and storage devices such as hard disks built into computer systems. Furthermore, "computer-readable recording media" may also include devices that dynamically store programs for a short period of time, such as communication lines when transmitting programs via networks such as the Internet or communication lines such as telephone lines, and devices that store programs for a certain period of time, such as volatile memory within computer systems that serve as servers or clients in such cases. Furthermore, the above program may be one that realizes part of the above-mentioned functions, or may be one that can realize the above-mentioned functions in combination with a program already recorded in a computer system, or may be one that is realized using a programmable logic device such as an FPGA (Field Programmable Gate Array).

[0098] The embodiments of the present invention have been described in detail above with reference to the drawings, but the specific configuration is not limited to that described above, and various design changes can be made within the scope of the gist of the present invention. [Explanation of symbols]

[0099] 1...Training information generation system, 10...Scientific calculation device, 20...Disaster reproduction server, 30...Training server, 40...Telephone, 50...Text information output device, 60...Image display device, 70...Information compilation device, 80...Evaluation input device, 210...Communication unit, 220...Memory unit, 230...Control unit, 231...Simulation processing unit, 232...Object processing unit, 233...Interaction calculation unit, 310...Communication unit, 320...Memory unit, 330...Control unit, 331...Scenario generation unit, 332...Natural language processing unit, 333...Audio manuscript generation unit, 334...Text information generation unit, 335...Viewpoint calculation unit, 336...Image generation unit, 337...Training log management unit, NW (NW1, NW2)...Network

Claims

1. a simulation processing unit that reproduces a first event in a virtual space that virtually reproduces a real space based on first event information indicating a time-series change of the first event in the target real space, and records a second event that occurs in accordance with the time-series change of the first event in the virtual space; a scenario generation unit that generates, based on second event information indicating the second event, scenario information indicating a scenario for a user to respond to the second event occurring during the first event; An information generation system comprising:

2. an object processing unit that places objects in the virtual space; an interaction calculation unit that calculates an interaction between the first event and the object in the virtual space and detects the second event occurring with respect to the object for each of the objects; The information generating system of claim 1 further comprising:

3. the objects include static objects whose positions in the virtual space are fixed and dynamic objects whose positions are not fixed; the interaction calculation unit detects the second event occurring on the static object due to an interaction between the first event and the static object, and detects the second event occurring on the dynamic object due to an interaction between the second event occurring on the static object and the dynamic object; The information generating system according to claim 2 .

4. the scenario generation unit extracts the second event corresponding to the specification from the recorded second events based on specification information indicating specifications related to the usage of the scenario, and generates the scenario information for the user to respond to the extracted second event. The information generating system according to claim 1 .

5. an audio manuscript generating unit that generates an audio manuscript corresponding to the scenario based on the generated scenario information; The information generating system of claim 1 further comprising:

6. a character information generating unit that generates character information corresponding to the scenario based on the generated scenario information; The information generating system of claim 1 further comprising:

7. an image generation unit that generates an image corresponding to the scenario based on the generated scenario information, in a state where an influence of the second event is reflected; The information generating system of claim 1 further comprising:

8. the first event is a disaster; the second event is damage caused by the disaster, the user is a trainee; The scenario information is information indicating a scenario for the trainee to conduct a disaster prevention training for the disaster and the damage. The information generating system according to claim 1 .

9. a simulation process of reproducing a first event in a virtual space that virtually reproduces a real space based on first event information indicating a time-series change of the first event in the target real space, and recording a second event that occurs in accordance with the time-series change of the first event in the virtual space; a scenario generation step of generating, based on second event information indicating the second event, scenario information indicating a scenario for a user to respond to the second event occurring during the first event; 1. A computer-implemented information generation method comprising:

10. Computer, a simulation processing means for reproducing a first event in a virtual space that virtually reproduces a real space based on first event information indicating a time series change of the first event in the target real space, and for recording a second event that occurs in accordance with the time series change of the first event in the virtual space; a scenario generating means for generating, based on second event information indicating the second event, scenario information indicating a scenario for a user to respond to the second event occurring during the first event; A program to function as a

Images