Evacuation prediction device and evacuation prediction method

Abstract

In an evacuation prediction device (10), an acquisition unit (15a) acquires information representing characteristics of residents to be processed and information about the current evacuation shelter. A prediction unit (15b) uses the information representing the characteristics of the residents and the information about the current evacuation shelter to predict the evacuation behavior of each resident when an evacuation instruction is received.

Description

Evacuation prediction device and evacuation prediction method

[0001] The present invention relates to an evacuation prediction device and an evacuation prediction method.

[0002] A conventional technology for predicting the evacuation status of residents is known, which uses a 3D city model that reflects the flooding situation over time to simulate and predict events that will occur based on scenarios such as the timing of when residents will start evacuating, the evacuation method, and the evacuation destination (see Non-Patent Document 1). For example, the technology predicts events such as the occurrence of traffic congestion, the time required for evacuation, the number of evacuees at each evacuation site, and the situation of people being late in evacuating.

[0003] “Time-series simulation of flood evacuation behavior by foot and car,” [online], 2023, Lightech Co., Ltd. [Retrieved October 20, 2023], Internet<URL:https: / / www.mlit.go.jp / plateau / use case / uc22-039 / >

[0004] However, with conventional technology, it is difficult to make evacuation predictions that incorporate current information, such as the location and status of evacuation shelters, as well as the characteristics and judgments of each resident. For example, residents do not immediately follow evacuation orders issued by local governments. Instead, they decide whether to evacuate based on their individual characteristics and evacuation shelter information, such as the location and congestion of evacuation shelters. Only when they decide to evacuate do they select a shelter and begin evacuation action. Therefore, the evacuation rates and damage rates calculated using conventional technology may differ significantly from reality.

[0005] Furthermore, evacuation shelters will be opened one by one once local governments have made them available for use in the event of an emergency. The evacuation rate and number of victims will change depending on the opening status of evacuation shelters, the timing of evacuation orders issued by local governments, and road conditions such as flooding. Therefore, with conventional technology, evacuation destinations and evacuation timing are fixed, making it difficult to perform evacuation simulations that take into account actual operations.

[0006] The present invention has been made in consideration of the above, and aims to make evacuation predictions that incorporate current information such as the location and situation of evacuation shelters, as well as the characteristics and judgments of each resident.

[0007] In order to solve the above-mentioned problems and achieve the objectives, the evacuation prediction device of the present invention is characterized by having an acquisition unit that acquires information representing the characteristics of the residents to be processed and information about evacuation shelters, and a prediction unit that uses the information representing the characteristics of the residents and the information about the evacuation shelters to predict the evacuation behavior of each resident when an evacuation order is received.

[0008] According to the present invention, it is possible to make evacuation predictions that incorporate current information such as the location and status of evacuation shelters, as well as the characteristics and judgments of each resident.

[0009] FIG. 1 is a schematic diagram illustrating the overall configuration of an evacuation prediction device according to this embodiment. FIG. 2 is a diagram illustrating person information. FIG. 3 is a diagram illustrating evacuation shelter information. FIG. 4 is a diagram illustrating evacuation tally information. FIG. 5 is a diagram illustrating scenario information. FIG. 6 is a diagram illustrating detailed scenario information. FIG. 7 is a diagram illustrating disaster area information. FIG. 8 is a diagram illustrating road map information. FIG. 9 is a diagram illustrating evacuation prediction processing. FIG. 10 is a flowchart illustrating the evacuation prediction processing procedure. FIG. 11 is a flowchart illustrating the evacuation prediction processing procedure. FIG. 12 is a diagram illustrating an example of a computer that executes an evacuation prediction program.

[0010] Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings. Note that the present invention is not limited to this embodiment. In addition, in the description of the drawings, the same parts are designated by the same reference numerals.

[0011] [Configuration of the evacuation prediction device] Fig. 1 is a schematic diagram illustrating the general configuration of the evacuation prediction device of this embodiment. As illustrated in Fig. 1, the evacuation prediction device 10 of this embodiment is realized by a general-purpose computer such as a personal computer, and includes an input unit 11, an output unit 12, a communication control unit 13, a storage unit 14, and a control unit 15.

[0012] The input unit 11 is realized using input devices such as a keyboard and a mouse, and inputs various instruction information such as a command to start processing to the control unit 15 in response to input operations by an operator. The output unit 12 is realized by a display device such as a liquid crystal display, a printing device such as a printer, etc. For example, the output unit 12 displays the results of the evacuation prediction processing described below.

[0013] The communication control unit 13 is realized by a NIC (Network Interface Card) or the like, and controls communication between the control unit 15 and external devices via telecommunication lines such as a LAN (Local Area Network) or the Internet. For example, the communication control unit 13 controls communication between the control unit 15 and a management device that manages various types of information such as evacuation shelter information and scenario information, a people flow / traffic flow simulator, etc.

[0014] The storage unit 14 is realized by a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 14 stores in advance the processing program that operates the evacuation prediction device 10, data used during execution of the processing program, and the like, or temporarily stores the data each time processing is performed. The storage unit 14 may be configured to communicate with the control unit 15 via the communication control unit 13.

[0015] In this embodiment, the storage unit 14 stores person information 14a including information representing the characteristics of the resident to be processed, and evacuation shelter information 14b including information on available evacuation shelters. Specifically, the resident characteristics include aversion to crowding and aversion to evacuation. The evacuation shelter information includes whether the evacuation shelter is open, its maximum capacity, and the current number of evacuees.

[0016] The storage unit 14 also stores evacuation compilation information 14c, scenario information 14d, detailed scenario information 14e, disaster area information 14f, and road map information 14g.

[0017] The acquiring unit 15a, which will be described later, acquires this information from a management device or the like in advance of the evacuation prediction process, which will be described later, and stores it in the storage unit 14. Note that this information is not necessarily limited to being stored in the storage unit 14, and may be acquired by the acquiring unit 15a, for example, when the evacuation prediction process, which will be described later, is executed.

[0018] 2 is a diagram for explaining the person information. The person information 14a is information about the resident to be processed, and includes information such as a person ID, disaster status, evacuation status, current location, characteristics, evacuation shelter information, and date and time, as exemplified in FIG. 2.

[0019] The person ID is an identifier that identifies a resident, i.e., a person. The damage status indicates whether the resident has been affected by a disaster, i.e., whether it is "affected" or "not affected." The evacuation status indicates whether the resident has evacuated, i.e., whether it is "completed" or "not yet evacuated." The current location indicates the resident's current location, for example, using latitude and longitude.

[0020] The characteristic is a characteristic for determining the psychological state of the resident, and may include multiple characteristics, for example, characteristic 1 is set to a value between 0 and 1.0 representing the degree of aversion to crowding, and characteristic 2 is set to a value between 0 and 1.0 representing the degree of aversion to evacuation. In both cases, the larger the value, the stronger the degree of aversion.

[0021] The evacuation shelter information includes information such as the evacuation shelter ID of available evacuation shelters notified by local governments, the number of evacuees, and the maximum capacity, and no values ​​are entered as the initial values. The date and time indicate the logical date and time (logical time from the start) when the simulation is performed.

[0022] 3 is a diagram illustrating the evacuation shelter information. The evacuation shelter information 14b is information about available evacuation shelters, and includes information such as the evacuation shelter ID, location, opening status, number of evacuees, maximum capacity, date and time, as illustrated in FIG.

[0023] The shelter ID is an identifier that identifies the shelter. The location indicates the location of the shelter, for example, using latitude and longitude. The opening status indicates whether the shelter is open or not, i.e., whether it is "open" or "closed." The number of evacuees indicates the number of residents who have evacuated to the shelter. The maximum capacity indicates the maximum capacity of the shelter. The date and time indicates the logical date and time (logical time from the start) when the simulation is performed.

[0024] Fig. 4 is a diagram for explaining the evacuation compilation information. As illustrated in Fig. 4, the evacuation compilation information 14c includes information such as the number of evacuees, the number of victims, and the date and time. The number of evacuees indicates the total number of evacuees. The number of victims indicates the total number of victims. The date and time indicate the logical date and time (logical time from the start) when the simulation is performed.

[0025] 5 is a diagram for explaining scenario information. As shown in the example of Fig. 5, the scenario information 14d includes information such as a scenario ID, a logical start time, a total number of execution turns, and a logical time / turn.

[0026] The scenario ID is an identifier for identifying a scenario that indicates the conditions of the simulation. The logical start time indicates the logical start time of the simulation. The total number of execution turns indicates the total number of execution turns when performing the simulation. The logical time / turn indicates the logical time per turn of the repeated processing.

[0027] 6 is a diagram for explaining the detailed scenario information. As illustrated in FIG. 6, the detailed scenario information 14e includes information such as a scenario ID, the number of turns, the evacuation shelters to be opened, the information transmission method, the details of the information transmission, disaster area information, and road map information.

[0028] The scenario ID is information for linking with the scenario information 14d, and an identifier for identifying the scenario is set. The number of turns indicates the number of turns. The opened evacuation shelter indicates the evacuation shelter ID of the evacuation shelter to be opened. The information transmission method indicates, for example, either SNS (default) or broadcast communication. The information transmission details indicate the number of times the information is transmitted and the number of people to whom it is transmitted when the information transmission method is SNS, or the transmission area information when the information transmission method is broadcast communication. The disaster area information is information for linking with the disaster area information 14f, and an evacuation area ID for identifying the disaster area is set. If there is no disaster area, there is no data. The road map information is information for association with the road map information 14g, and a road map ID for identifying the road map is set.

[0029] 7 is a diagram illustrating disaster area information. As illustrated in FIG. 7, disaster area information 14f includes a disaster area ID and a polygon. The disaster area ID is an identifier that identifies the disaster area, and the polygon represents the disaster area as a polygon of latitude and longitude.

[0030] 8 is a diagram for explaining road map information. As shown in FIG. 8, the road map information 14g includes a road map ID and a road map. The road map ID is an identifier for identifying the road map, and the road map indicates the storage location and file name of the road map.

[0031] Returning to the explanation of FIG. 1 , the control unit 15 is realized using a CPU (Central Processing Unit), an NP (Network Processor), an FPGA (Field Programmable Gate Array), or the like, and executes a processing program stored in memory. As a result, the control unit 15 functions as an acquisition unit 15a and a prediction unit 15b, as exemplified in FIG. 1 , and executes evacuation prediction processing. Note that these functional units may be implemented in different hardware. The control unit 15 may also include other functional units.

[0032] The acquisition unit 15a acquires information about the resident (person) to be processed and information about the current evacuation shelter. Specifically, the acquisition unit 15a acquires, as the resident's characteristics, aversion to crowding and aversion to evacuation. Furthermore, the acquisition unit 15a acquires, as the evacuation shelter information, whether the evacuation shelter is open, its maximum capacity, and the current number of evacuees.

[0033] For example, the acquisition unit 15a acquires information on evacuation shelters that are open at the time an evacuation order is issued from a management device or the like, and updates the evacuation shelter information 14b with the acquired information. Then, the prediction unit 15b acquires information on evacuation shelters whose opening status is "open" from the evacuation shelter information 14b, and information on residents in the person information 14a whose current location is within the disaster area information 14f and whose disaster status is "not affected" and whose evacuation status is "not yet affected." In addition, the acquisition unit 15a updates the disaster status of residents who are unable to evacuate to "affected" and excludes them from the residents to be processed.

[0034] The prediction unit 15b predicts the evacuation behavior of each resident when an evacuation instruction is received, using information representing the characteristics of the residents and information about the current evacuation shelter.

[0035] Specifically, when an evacuation order is issued, the prediction unit 15b calculates a point P that represents each resident's feelings toward evacuation using the aversion of each resident within the disaster area information 14f to crowding and aversion to evacuation, as well as whether or not an evacuation shelter is open, its maximum capacity, and the current number of evacuees.

[0036] For example, the characteristics of residents in human information 14a are set as a value between 0 and 1.0 (characteristic 1) representing the degree of aversion to crowding, and a value between 0 and 1.0 (characteristic 2) representing the degree of aversion to evacuation (in both cases, the larger the number, the stronger the degree of aversion).

[0037] If the shelter information in the person information 14a does not contain a value indicating an available shelter, the prediction unit 15b sets the psychological score P for evacuation of the resident to 0.

[0038] On the other hand, if the shelter information in the person information 14a contains a value for the shelter to which evacuation is possible, a value representing the strength of the desire to move to that shelter (0 to 1.0, the larger the value, the stronger the desire) is calculated for each shelter, as shown in the following formula (1).

[0039] Strength of desire to move = (1 - current capacity / maximum capacity) * (1 - aversion to crowding) ... (1)

[0040] Then, the prediction unit 15b calculates a psychological point P for each evacuation shelter as shown in the following formula (2), and predicts the decision on whether to evacuate or not and the evacuation shelter if it is decided to evacuate.

[0041] P = (strength of desire to move) - (dislike of evacuation) ... (2)

[0042] For example, the prediction unit 15b predicts that the resident will move to the shelter if the calculated psychological point P > 0. If psychological points P > 0 are calculated for multiple shelters, the prediction unit 15b predicts that the resident will select the shelter with the largest P as the evacuation (relocation) destination, and if the P values ​​are the same, the prediction unit 15b predicts that the resident will select the shelter closest to the resident's current location as the evacuation (relocation) destination.

[0043] On the other hand, if P≦0, the prediction unit 15b predicts that the resident will wait and not evacuate.

[0044] The prediction unit 15b updates the current location of the resident in the person information 14a with the location of the shelter predicted as the destination, and sets the evacuation status to "complete." The prediction unit 15b also updates the number of evacuees in the shelter information 14b.

[0045] For example, the prediction unit 15b calculates the shortest route to a shelter using a pedestrian and traffic flow simulator based on the road map information 14g. Then, the prediction unit 15b sets the location of the shelter as a destination, and uses the pedestrian and traffic flow simulator to move residents along the logical time of one turn and the route to the destination. The location after the movement is set as each resident's current location after the logical time. This enables the prediction unit 15b to predict the evacuation behavior of each resident, reflecting their judgment based on their characteristics, such as their aversion to evacuation and crowding, in response to the constantly changing situation at the shelter.

[0046] The prediction unit 15b repeats the above one-turn process for all residents who are subject to evacuation orders. Then, the prediction unit 15b tallies the number of residents whose disaster status is "disaster" and the number of residents whose evacuation status is "completed," and updates the evacuation tallied information 14c in the storage unit 14. Therefore, it becomes possible to effectively execute a simulation of evacuation behavior of residents in the disaster area according to a scenario that specifies the timing of opening evacuation shelters and issuing evacuation orders, etc.

[0047] [Evacuation Prediction Processing] Next, the evacuation prediction processing performed by the evacuation prediction device 10 according to this embodiment will be described with reference to Fig. 9 to Fig. 11. Fig. 9 is a diagram for explaining the evacuation prediction processing. As illustrated in Fig. 9, the evacuation prediction processing includes a scenario execution processing and a simulation execution processing.

[0048] Here, the scenario execution process executes a simulation of the evacuation behavior of residents in the disaster area in accordance with a scenario that specifies the timing of opening evacuation shelters, issuing evacuation orders, etc. During the scenario execution process, the simulation execution process executes a simulation that predicts the evacuation behavior of each resident, reflecting the judgment of each resident based on their characteristics, such as their aversion to evacuation and crowding, in response to the ever-changing situation at the evacuation shelter.

[0049] 10 and 11 are flowcharts showing the evacuation prediction processing procedure. Fig. 10 shows an example of the scenario execution processing procedure. Fig. 11 shows an example of the simulation execution processing procedure.

[0050] 10 starts, for example, when a user performs an operation input to specify a scenario ID. The acquisition unit 15a acquires the logical start time, the total number of execution turns, and the logical time per turn from the scenario information 14d using the specified scenario ID (step S1). The acquisition unit 15a also sets the number of turns n to an initial value of 1 (step S2). The acquisition unit 15a also acquires the establishment evacuation information, information transmission method, information transmission details, disaster area information, and road map information from the detailed scenario information 14e using the scenario ID and the number of turns n (step S3).

[0051] If there is an open evacuation shelter (step S4, Yes), the acquisition unit 15a updates the open status of the corresponding evacuation shelter ID in the evacuation shelter information to "open" (step S5), and proceeds to step S6. On the other hand, if there is no open evacuation shelter (step S4, No), the acquisition unit 15a proceeds to step S6.

[0052] If there is disaster area information (step S6, Yes), the acquisition unit 15a acquires the current locations of residents whose disaster status in the person information 14a is "not affected" and identifies residents who are in the disaster area identified by the disaster area information 14f. Then, the acquisition unit 15a updates the disaster status in the person information 14a for those residents who cannot evacuate to "affected" (step S7), and the process proceeds to step S8. On the other hand, if there is no disaster area information (step S6, No), the acquisition unit 15a proceeds to step S8.

[0053] Next, the acquisition unit 15a acquires information on residents whose disaster status is "not present" and whose evacuation status is "not yet" in the person information 14a, and information on evacuation shelters whose opening status is "open" in the evacuation shelter information 14b. Using this information and the information transmission method, information transmission details, logical time per turn, and road map information acquired in step S3, the prediction unit 15b performs a simulation execution process to predict the evacuation behavior of each resident (step S8).

[0054] Then, the prediction unit 15b uses the output of the simulation execution process, logical time, human information 14a, and evacuation shelter information 14b to tally the number of residents whose disaster status in the human information 14a is "disaster" and the number of residents whose evacuation status is "completed," and updates the evacuation summary information 14c (step S9).

[0055] The prediction unit 15b sets the number of turns n to n+1 (step S10), and if n has not reached the total number of execution turns (step S11, No), the process returns to step S3. On the other hand, if n has reached the total number of execution turns (step S11, Yes), the prediction unit 15b ends the series of scenario execution processes.

[0056] 11 illustrates a detailed procedure for the simulation execution process in step S8. Specifically, the prediction unit 15b calculates, for each resident, a psychological score P for evacuating to the evacuation shelter in accordance with the above formula (2) using information representing the resident's characteristics and information on current evacuation shelters to which evacuation is possible (step S21).

[0057] If there is no shelter with a psychological point P>0 (No at step S22), the prediction unit 15b proceeds to step S31.

[0058] On the other hand, if there is a shelter with a psychological score P>0 (Yes at step S22), the prediction unit 15b lists the w shelters in descending order of the psychological score P (step S23) and sets k=1 (step S24).The prediction unit 15b then calculates the shortest route to the k-th shelter from the road map information 14g using a pedestrian and traffic flow simulator (step S25).

[0059] If there is no route to the evacuation shelter (No at Step S26), k is set to k+1 (Step S27), and if k has not reached w (Yes at Step S28), the prediction unit 15b returns the process to Step S25. On the other hand, if k has reached w (No at Step S28), the process proceeds to Step S31.

[0060] On the other hand, if there is a route to the evacuation shelter (step S26, Yes), the prediction unit 15b sets the location of the evacuation shelter as the destination, and moves the residents along the route to the destination using the logical time of one turn using a people flow / traffic flow simulator (step S29).The prediction unit 15b then updates the location after the movement as the current location of each resident after the logical time (step S30).

[0061] The prediction unit 15b then identifies the residents who have arrived at each evacuation shelter based on the residents' current locations and the evacuation shelter information, and updates the evacuation status to "complete." The prediction unit 15b also tallies the number of evacuees at each evacuation shelter and outputs the person information and the evacuation shelter information (step S31 → S9 in Figure 10). This completes the series of simulation execution processes.

[0062] If the information transmission method is SNS (step S41, Yes), the initial value of m is set to 1 (step S42). Then, the prediction unit 15b uses the number of transmissions and the number of recipients in the information transmission details to select, for each evacuation shelter, residents in the people information 14a whose disaster status is "none" and for whom the number of recipients is "none," and updates the evacuation shelter information associated with the residents in memory (step S43).

[0063] Then, the prediction unit 15b sets m to m+1 (step S44), and if m is equal to or less than the number of propagations (step S45, Yes), the process returns to step S43. On the other hand, if m is greater than the number of propagations (step S45, No), the prediction unit 15b outputs the evacuation shelter information (step S46 → S9 in FIG. 10). This completes the series of simulation execution processes.

[0064] Also, if the information transmission method is not SNS (step S41, No), the prediction unit 15b extracts residents who are present in the transmission area from the information on the transmission area and the current location of the person information 14a (step S47).

[0065] The prediction unit 15b also updates the evacuation shelter information associated with the extracted residents in the program memory and outputs it (step S48 → S9 in FIG. 10), thereby completing a series of simulation execution processes.

[0066] As described above, in the evacuation prediction device 10 of this embodiment, the acquisition unit 15a acquires information representing the characteristics of the resident to be processed and information about the current evacuation shelter. The prediction unit 15b predicts the evacuation behavior of each resident when an evacuation order is received, using the information representing the characteristics of the resident and the information about the current evacuation shelter.

[0067] Specifically, the acquiring unit 15a acquires, as the resident characteristics, aversion to crowding and aversion to evacuation. In addition, the acquiring unit 15a acquires, as the evacuation shelter information, whether the evacuation shelter is open, its maximum capacity, and the current number of evacuees.

[0068] This allows the evacuation prediction device 10 to predict the evacuation behavior of each resident, reflecting their judgment based on their characteristics in response to the ever-changing situation at the evacuation shelter. This makes it possible to execute highly effective simulations of scenarios for the opening of evacuation shelters and the timing of evacuation orders.

[0069] [Program] A program written in a computer-executable language may be created to execute the processes performed by the evacuation prediction device 10 according to the above embodiment. In one embodiment, the evacuation prediction device 10 can be implemented by installing an evacuation prediction program that executes the evacuation prediction process as package software or online software on a desired computer. For example, by executing the evacuation prediction program on an information processing device, the information processing device can function as the evacuation prediction device 10. The information processing device referred to here includes desktop and notebook personal computers. Other examples of information processing devices include mobile communication devices such as smartphones, mobile phones, and PHS (Personal Handyphone Systems), as well as slate devices such as PDAs (Personal Digital Assistants). The functions of the evacuation prediction device 10 may also be implemented on a cloud server.

[0070] 12 is a diagram showing an example of a computer that executes an evacuation prediction program. The computer 1000 includes, for example, a memory 1010, a CPU 1020, a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These components are connected by a bus 1080.

[0071] The memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM 1012. The ROM 1011 stores a boot program such as a BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to a hard disk drive 1031. The disk drive interface 1040 is connected to a disk drive 1041. A removable storage medium such as a magnetic disk or optical disk is inserted into the disk drive 1041. The serial port interface 1050 is connected to a mouse 1051 and a keyboard 1052, for example. The video adapter 1060 is connected to a display 1061, for example.

[0072] Here, the hard disk drive 1031 stores, for example, an OS (Operating System) 1091, an application program 1092, a program module 1093, and program data 1094. The various pieces of information described in the above embodiments are stored in the hard disk drive 1031 or the memory 1010, for example.

[0073] The evacuation prediction program is stored in the hard disk drive 1031 as, for example, a program module 1093 in which instructions to be executed by the computer 1000 are written. Specifically, the program module 1093 in which each process executed by the evacuation prediction device 10 described in the above embodiment is written is stored in the hard disk drive 1031.

[0074] Furthermore, data used for information processing by the evacuation prediction program is stored as program data 1094, for example, in the hard disk drive 1031. Then, the CPU 1020 reads the program module 1093 and the program data 1094 stored in the hard disk drive 1031 into the RAM 1012 as necessary, and executes each of the above-described procedures.

[0075] The program module 1093 and program data 1094 related to the evacuation prediction program are not limited to being stored in the hard disk drive 1031, and may be stored in, for example, a removable storage medium and read by the CPU 1020 via the disk drive 1041. Alternatively, the program module 1093 and program data 1094 related to the evacuation prediction program may be stored in another computer connected via a network such as a LAN or a WAN (Wide Area Network), and read by the CPU 1020 via the network interface 1070.

[0076] Although the present invention has been described above as an embodiment, the present invention is not limited to the description and drawings that form part of the disclosure of the present invention. In other words, other embodiments, examples, and operational techniques that can be made by those skilled in the art based on the present invention are all included in the scope of the present invention.

[0077] REFERENCE SIGNS LIST 10 Evacuation prediction device 11 Input unit 12 Output unit 13 Communication control unit 14 Storage unit 14a Person information 14b Evacuation shelter information 14c Evacuation summary information 14d Scenario information 14e Detailed scenario information 14f Disaster area information 14g Road map information 15 Control unit 15a Acquisition unit 15b Prediction unit

Claims

1. An evacuation prediction device comprising: an acquisition unit that acquires information representing the characteristics of the residents to be processed and information about evacuation shelters; and a prediction unit that uses the information representing the characteristics of the residents and the information about the evacuation shelters to predict the evacuation behavior of each resident when an evacuation order is received.

2. The evacuation prediction device according to claim 1, characterized in that the acquisition unit acquires, as the resident's characteristics, an aversion to crowding and an aversion to evacuation.

3. The evacuation prediction device according to claim 1, characterized in that the acquisition unit acquires, as information about the evacuation shelter, whether the evacuation shelter is open, its maximum capacity, and the current number of evacuees.

4. An evacuation prediction method executed by an evacuation prediction device, comprising: an acquisition step of acquiring information representing the characteristics of the residents to be processed and information on evacuation shelters; and a prediction step of predicting the evacuation behavior of each resident when an evacuation order is received, using the information representing the characteristics of the residents and the information on the evacuation shelters.

Images