Apparatus and method for creating evacuation route based on artificial intelligence

Abstract

The present invention relates to an artificial intelligence-based evacuation route generation device and method. The artificial intelligence-based evacuation route generation method according to the present embodiment is an evacuation route generation method performed by a processor of an evacuation route generation device, and may include the steps of: generating a plurality of primary routes capable of moving from a starting point to a plurality of destinations; calculating a total sum of costs as a score added to an element that restricts movement, as there exists an element that restricts movement in at least one of the plurality of primary routes; and determining one of the plurality of primary routes as the optimal evacuation route based on the total sum of costs.

Description

Technology Field

[0001] The present invention relates to an artificial intelligence-based evacuation route generation device and method. Background Technology

[0002] Even with technological advancements, it is difficult for humans to accurately predict disaster situations such as fires or earthquakes. However, the extent of damage can vary depending on how accurately the disaster situation is assessed and responded to. Currently, when a disaster occurs, sirens and voice announcements are broadcast, and approximate evacuation routes to exits are displayed on guide signs. However, the process of people moving to find exits causes congestion as their paths cross, and there is a risk of secondary accidents caused by this congestion. Furthermore, since the route taken to find an exit may pass through the disaster site, this cannot be considered an effective method for presenting evacuation routes.

[0003] The aforementioned background technology is technical information that the inventor possessed for the derivation of the present invention or acquired during the process of deriving the present invention, and it cannot be considered as prior art disclosed to the general public prior to the filing of the present invention. Prior art literature

[0004] Korean Patent Publication No. 10-2004-0076396 (September 1, 2004) The problem to be solved

[0005] One objective of the present invention is to generate and provide an optimal evacuation route in the event of a disaster.

[0006] The problems that the present invention aims to solve are not limited to those mentioned above, and other problems and advantages of the present invention not mentioned can be understood from the following description and will be more clearly understood by the embodiments of the present invention. Furthermore, it will be understood that the problems and advantages that the present invention aims to solve can be realized by the means and combinations thereof set forth in the claims. means of solving the problem

[0007] The artificial intelligence-based evacuation route generation method according to the present embodiment is an evacuation route generation method performed by a processor of an evacuation route generation device, and may include the steps of generating a plurality of primary routes capable of moving from a starting point to a plurality of destinations, calculating a total sum of costs as a score added to an element that restricts movement, as there exists an element that restricts movement in at least one of the plurality of primary routes, and determining one of the plurality of primary routes as the optimal evacuation route based on the total sum of costs.

[0008] The artificial intelligence-based evacuation path generation device according to the present embodiment includes a processor and a memory that is operablely connected to the processor and stores at least one code executed by the processor. When the memory is executed through the processor, the processor generates multiple primary paths that can be moved from a starting point to multiple destinations, and, as there is an element that restricts movement in at least one of the multiple primary paths, calculates a total sum of costs as a score added to the element that restricts movement, and based on the total sum of costs, stores a code that causes one of the multiple primary paths to be determined as the optimal evacuation path.

[0009] In addition to this, other methods for implementing the present invention, other systems, and computer-readable recording media storing a computer program for executing said methods may be further provided.

[0010] Other aspects, features, and advantages other than those described above will become clear from the following drawings, claims, and detailed description of the invention. Effects of the invention

[0011] According to the present invention, by generating and providing an optimal evacuation route in the event of a disaster, it is possible to help evacuees evacuate quickly and accurately.

[0012] The effects of the present invention are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art from the description below. Brief explanation of the drawing

[0013] FIG. 1 is an example diagram of an artificial intelligence-based evacuation route generation environment according to one embodiment. FIG. 2 is a block diagram illustrating the configuration of an artificial intelligence-based evacuation path generation device according to one embodiment. Figure 3 is a block diagram illustrating the configuration of the evacuation route generation management unit among the artificial intelligence-based evacuation route generation device of Figure 2. FIGS. 4 to 12 are exemplary diagrams for explaining the generation of an artificial intelligence-based evacuation route according to one embodiment. FIG. 13 is a block diagram illustrating the configuration of an artificial intelligence-based evacuation path generation device according to another embodiment. FIG. 14 is a flowchart illustrating an artificial intelligence-based evacuation route generation method according to one embodiment. Specific details for implementing the invention

[0014] The advantages and features of the present invention, and the methods for achieving them, will become clear by referring to the embodiments described in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments presented below, but can be implemented in various different forms and should be understood to include all modifications, equivalents, and substitutions that fall within the spirit and scope of the present invention. The embodiments presented below are provided to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention. In describing the present invention, detailed descriptions of related known technologies are omitted if it is determined that such detailed descriptions may obscure the essence of the present invention.

[0015] The terms used in this application are used merely to describe specific embodiments and are not intended to limit the invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this application, terms such as “comprising” or “having” are intended to indicate the presence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof. Terms such as “first,” “second,” etc., may be used to describe various components, but the components should not be limited by these terms. These terms are used solely for the purpose of distinguishing one component from another.

[0016] Additionally, in this application, "part" may be a hardware component, such as a processor or circuit, and / or a software component executed by a hardware component, such as a processor.

[0017] Hereinafter, embodiments according to the present invention will be described in detail with reference to the attached drawings. In describing with reference to the attached drawings, identical or corresponding components are given the same reference numerals, and redundant descriptions thereof will be omitted.

[0018] In the following embodiments, the terms first, second, etc. are used not in a restrictive sense, but for the purpose of distinguishing one component from another component.

[0019] In the following embodiments, singular expressions include plural expressions unless the context clearly indicates otherwise.

[0020] In the following embodiments, terms such as "include" or "have" mean that the features or components described in the specification are present, and do not preclude the possibility that one or more other features or components may be added.

[0021] Where an embodiment can be implemented differently, a specific process sequence may be performed differently from the order described. For example, two processes described consecutively may be performed substantially simultaneously or proceed in the reverse order of the description.

[0023] FIG. 1 is an example diagram of an artificial intelligence-based evacuation route generation environment according to one embodiment. Referring to FIG. 1, the artificial intelligence-based evacuation route generation environment (1) may include an artificial intelligence-based evacuation route generation device (100, hereinafter referred to as the evacuation route generation device), a user terminal (200), and a network (300).

[0024] The evacuation route generation device (100) can collect one or more of disaster situation occurrence information, evacuation route request information from a user terminal (200), and user information when a disaster situation occurs.

[0025] In this embodiment, disaster situations may include urgent or crisis situations caused by humans or nature. Such disaster situations can pose a direct threat to people's health and safety and may also affect infrastructure and economic activities. Types of disaster situations may include natural disasters such as earthquakes, floods, storms, typhoons, tsunamis, landslides, heavy snowfall, and fires; man-made disasters such as war, terrorism, industrial accidents, fires, and crowd accidents caused by large crowds; and recently, infectious diseases such as the pandemic COVID-19 may also be included as disaster situations.

[0026] The evacuation route generation device (100) can collect information on the occurrence of such disaster situations from external devices (e.g., a disaster management agency server, a weather agency server, a Ministry of the Interior server, a server providing media or news, a fire department server, etc., not shown). Additionally, the evacuation route generation device (100) may collect information on the occurrence of disasters from a user terminal (200). For example, in the event of a crowd accident caused by the concentration of a large crowd, information on the occurrence of disasters can be collected from a user terminal (200) equipped by a user at the scene.

[0027] The evacuation route generation device (100) can collect evacuation route request information and user information from a user terminal (200). To do this, an evacuation route generation application provided by the evacuation route generation device (100) may be installed on the user terminal (200), or the user terminal (200) may access an evacuation route generation site provided by the route generation device (100). The user may execute the evacuation route generation application installed on the user terminal (200) or access the evacuation route generation site via the user terminal (200) to transmit evacuation route request information to the evacuation route generation device (100), and may transmit user information including one or more of the user's speed, direction, and location to the evacuation route generation device (100). Here, the user information may be measured from an accelerometer (not shown), a gyroscope (not shown), a GPS sensor (not shown), etc., equipped in the user terminal (200) and transmitted to the evacuation route generation device (100). An accelerometer is a sensor that detects changes in velocity and can detect magnitude information measured from three vectors having x, y, and z axes. A gyroscope is a sensor that detects angular velocity and can detect data regarding the user's rotation angle information, that is, the user's direction of movement. A GPS sensor can receive location information indicating the user's current location from satellites.

[0028] When the evacuation route generation device (100) collects one or more of disaster situation occurrence information, evacuation route request information, and user information, it can load prior information from a database (140 in FIG. 2). In this embodiment, the prior information may include 3D modeling information of a place including walkable areas and not walkable areas based on the starting point, i.e., the place where the user is located based on user information, multiple destination information on the 3D modeling information, location information of fire sensors on the 3D modeling information, and setting information for costs on the 3D modeling information. Here, the cost may include a score added to an element that restricts movement on the path generated by the evacuation route generation device (100) based on the 3D modeling information.

[0029] The evacuation route generation device (100) can generate multiple primary routes that can be traveled from a starting point to multiple destinations based on one or more of disaster situation occurrence information, evacuation route request information, and user information, and prior information loaded from a database (140 in FIG. 2). Here, the starting point includes the user's current location, and the multiple destinations may include one or more of multiple exit locations, rooftops, or safety zones.

[0030] In this embodiment, the evacuation path generation device (100) can generate a primary path using the ASTAR algorithm. The ASTAR algorithm is a graph search algorithm and can be used to solve the shortest path problem. The ASTAR algorithm can be used to efficiently search for a path in the problem of finding the shortest path from a starting point to a destination.

[0031] The ASTAR algorithm can explore a path by comprehensively considering actual costs and predicted costs. The actual cost for each node represents the actual travel cost from the starting node, which corresponds to the source information, to the current node. This can refer to the cost accumulated along the path from the starting node to the current node. The predicted cost represents the estimated cost from the current node to the target node, which corresponds to the destination information. This can be calculated by a heuristic function representing the estimated shortest distance between the current node and the target node. By combining these two costs, the priority of the nodes can be determined, and the node with the highest priority can be explored. Here, high priority may include having the shortest distance from the starting node to the target node.

[0032] The evacuation path generation device (100) can generate a primary path by connecting intermediate nodes that have the shortest path from the starting node to the target node as a result of the search. In this embodiment, as there are multiple destinations, there may be multiple primary paths (first path to Nth path) from the starting point to the destination.

[0033] In this embodiment, the evacuation path generation device (100) may apply an AI-based ASTAR algorithm. Here, applying an AI-based ASTAR algorithm may include improving a heuristic function using AI. In one embodiment, machine learning may be utilized to improve the heuristic function. To this end, training data may be collected, and the relationship between the input state and the actual cost may be learned to improve the heuristic function. In addition, various machine learning algorithms such as supervised learning, unsupervised learning, and reinforcement learning may be applied to improve the heuristic function. In another embodiment, deep learning may be utilized to improve the heuristic function. Deep learning has a powerful ability to learn complex patterns and make predictions. A heuristic function that estimates the expected cost based on the input state can be improved by using a deep learning neural network. A deep learning model can be designed and trained to improve the heuristic function so that it predicts more accurately. By improving the heuristic function using such AI, more accurate and efficient path search may be possible.

[0034] When the evacuation path generation device (100) completes the generation of multiple primary paths, it determines whether there is an element that restricts movement for each of the multiple primary paths, and if there is an element that restricts movement, it can calculate the total sum of the cost as a score added to the element that restricts movement.

[0035] The evacuation route generation device (100) can determine one of a plurality of primary routes as the optimal evacuation route based on the total sum of costs. In this embodiment, the evacuation route generation device (100) can determine the primary route with the highest total sum of costs among the plurality of primary routes as the optimal evacuation route.

[0036] As an optional embodiment, the evacuation path generating device (100) may determine whether the fire sensor is operating and, upon detecting the operation of the fire sensor, set a movable area located around the fire sensor as an immovable area. The evacuation path generating device (100) may exclude one or more primary paths that include a movable area located around the fire sensor from a plurality of primary paths. Here, the area around the fire sensor may include an area within a preset distance (e.g., 2m) from where the fire sensor is located.

[0037] As an optional embodiment, the evacuation path generating device (100) may, upon detecting the operation of a fire sensor located in the primary path with the highest total cost among a plurality of primary paths, i.e., the optimal evacuation path, cancel the determination of the optimal evacuation path and exclude the said primary path from the plurality of primary paths. The evacuation path generating device (100) may redetermine or update the primary path with the next highest total cost among the remaining plurality of primary paths excluded from the said primary path as the optimal evacuation path.

[0038] As an optional embodiment, the evacuation path generation device (100) may exclude one or more primary paths where the operating fire sensor is located from the results of generating multiple primary paths by detecting the operation of one or more fire sensors located in one or more of the multiple primary paths during the primary path generation process prior to determining the optimal evacuation path.

[0039] In this embodiment, the evacuation route generation device (100) may exist independently in the form of a server, or the evacuation route generation function provided by the evacuation route generation device (100) may be implemented in the form of an application and installed on a user terminal (200).

[0040] The user terminal (200) can access an evacuation route generation application and / or an evacuation route generation site provided by the evacuation route generation device (100) to receive an evacuation route generation service. The user terminal (200) can transmit evacuation route request information and user information to the evacuation route generation device (100).

[0041] Such user terminals (200) may include communication terminals capable of performing the functions of computing devices (not shown), and in addition to desktop computers (201), smartphones (202), and laptops (203) operated by the user, they may be tablet PCs, smart TVs, mobile phones, PDAs (personal digital assistants), media players, micro servers, GPS (global positioning system) devices, e-book readers, digital broadcasting terminals, navigation devices, kiosks, MP3 players, digital cameras, home appliances, and other mobile or non-mobile computing devices, but are not limited thereto. Additionally, user terminals (200) may be wearable terminals such as watches, glasses, hair bands, and rings equipped with communication functions and data processing functions. Such user terminals (200) are not limited to the above descriptions, and any terminal capable of web browsing may be used without restriction.

[0042] The network (300) can perform the role of connecting the evacuation path generating device (100) and the user terminal (200). This network (300) may include wired networks such as LAN (local area network), WAN (wide area network), MAN (metropolitan area network), ISDN (integrated service digital network), etc., or wireless networks such as WLAN (wireless LAN), CDMA (code-division multiple access), and satellite communication, but the scope of the present invention is not limited thereto. In addition, the network (300) can transmit and receive information using short-range communication and / or long-range communication. Here, short-range communication may include Bluetooth, RFID (radio frequency identification), IrDA (infrared data association), UWB (ultra-wideband), ZigBee, and Wi-Fi technologies, and long-range communication may include CDMA (code-division multiple access), FDMA (frequency-division multiple access), TDMA (time-division multiple access), OFDMA (orthogonal frequency-division multiple access), and SC-FDMA (single carrier frequency-division multiple access) technologies.

[0043] The network (300) may include connections of network elements such as hubs, bridges, routers, and switches. The network (300) may include one or more connected networks, such as a multi-network environment, including a public network such as the Internet and a private network such as a secure corporate private network. Access to the network (300) may be provided through one or more wired or wireless access networks.

[0044] Furthermore, the network (300) can support CAN (controller area network) communication, V2I (vehicle to infrastructure) communication, V2X (vehicle to everything) communication, WAVE (wireless access in vehicular environment) communication technology, and IoT (Internet of Things) network and / or 5G communication that exchanges and processes information between distributed components such as objects.

[0046] FIG. 2 is a block diagram illustrating the configuration of a vibration energy amplifier design device according to the present embodiment. In the following description, parts that overlap with the description of FIG. 1 will be omitted. Referring to FIG. 2, the evacuation path generation device (100) may include a communication unit (110), a storage medium (120), a program storage unit (130), a database (140), an evacuation path generation management unit (150), and a control unit (160).

[0047] The communication unit (110) may provide a communication interface necessary to provide transmission and reception signals between the evacuation route generation device (100) and the user terminal (200) in the form of packet data in conjunction with the network (300). Furthermore, the communication unit (110) may perform the role of receiving a predetermined information request signal from the user terminal (200) and may perform the role of transmitting information on the evacuation route generated by the evacuation route generation management unit (150) to the user terminal (200). Here, the communication interface is a medium that performs the role of connecting the evacuation route generation device (100) and the user terminal (200), and may include a path that provides a connection path so that the user terminal (200) can transmit and receive information after connecting to the evacuation route generation device (100). Additionally, the communication unit (110) may be a device that includes hardware and software necessary to transmit and receive signals, such as control signals or data signals, through wired or wireless connections with other network devices.

[0048] The storage medium (120) performs the function of temporarily or permanently storing data processed by the control unit (160). Here, the storage medium (120) may include magnetic storage media or flash storage media, but the scope of the present invention is not limited thereto. Such storage medium (120) may include internal memory and / or external memory, and may include volatile memory such as DRAM, SRAM, or SDRAM, non-volatile memory such as OTPROM (one time programmable ROM), PROM, EPROM, EEPROM, mask ROM, flash ROM, NAND flash memory, or NOR flash memory, flash drives such as SSD, CF (compact flash) card, SD card, Micro-SD card, Mini-SD card, Xd card, or memory stick, or storage devices such as HDD.

[0049] The program storage unit (130) is equipped with control software that performs tasks such as collecting disaster situation occurrence information from one or more of an external device and a user terminal (200), collecting one or more of evacuation route request information and user information from the user terminal (200), loading prior information from a database (140), creating multiple primary routes that can move from a starting point to multiple destinations by loading an A-Star algorithm from the database (140), calculating a total sum of costs for each of the multiple primary routes, determining one of the multiple primary routes as the optimal evacuation route based on the total sum of costs, and providing the determined optimal evacuation route to the user terminal (200).

[0050] The database (140) may include a management database that stores preliminary information for generating an evacuation route. In one embodiment, the management database may store 3D modeling information for a place, such as a building, a station, a subway station, an underpass, a public facility, an amusement park, etc. Additionally, the management database may include multiple destination information on the 3D modeling information. Here, the destination information may include one or more location information among an exit, a rooftop, and a safety zone on the 3D modeling information. Additionally, the management database may include location information of a fire sensor on the 3D modeling information. Additionally, the management database may include setting information for a cost on the 3D modeling information. Here, the cost may include a score added to an element that restricts movement on the route generated by the evacuation route generation management unit (150) based on the 3D modeling information. Detailed information regarding the setting information for the cost stored in the management database will be described later. In addition, the management database may store an ASTAR algorithm for generating a primary path, and one or more machine learning algorithms and deep learning algorithms for improving heuristic functions.

[0051] Additionally, the database (140) may include a user database that stores unique information about a user who will receive the evacuation route generation service. Here, the unique information about the user may include basic information about the user, such as the user's name, affiliation, personal details, gender, age, contact information, email, address, and image; information about user authentication (login), such as ID (or email) and password; information related to the connection, such as the country of connection, location of connection, information about the device used for connection, and the connected network environment.

[0052] In addition, the user database may store user information including changes in the user's speed detected by the accelerometer, the user's direction of movement detected by the gyroscope, and the user's current location detected by the GPS sensor.

[0053] In addition, the user database may store information and / or category history provided to users who access the evacuation route generation application or evacuation route generation site, environment setting information set by the user, resource usage information used by the user, and billing and payment information corresponding to the user's resource usage.

[0054] The evacuation route generation management unit (150) can collect disaster situation occurrence information from an external device and collect one or more of evacuation route request information and user information from a user terminal (200). The evacuation route generation management unit (150) can load prior information and an ASTAR algorithm from a database (140). The evacuation route generation management unit (150) can generate multiple primary routes that can move from a starting point to multiple destinations using prior information and an ASTAR algorithm. The evacuation route generation management unit (150) can calculate the total sum of costs for each of the multiple primary routes. Based on the total sum of costs, the evacuation route generation management unit (150) can determine one of the multiple primary routes as the optimal evacuation route and provide the determined optimal evacuation route to the user terminal (200).

[0055] The control unit (160) is a type of central processing unit and can control the operation of the entire evacuation path generation device (100) by running control software installed in the program storage unit (130). The control unit (160) may include all types of devices capable of processing data, such as a processor. Here, 'processor' may refer to a data processing device embedded in hardware that has a physically structured circuit to perform functions expressed by code or instructions included in a program, for example. Examples of such data processing devices embedded in hardware may include microprocessors, central processing units (CPUs), processor cores, multiprocessors, ASICs (application-specific integrated circuits), and FPGAs (field programmable gate arrays), but the scope of the present invention is not limited thereto.

[0057] FIG. 3 is a block diagram illustrating the configuration of the evacuation path generation management unit of the AI-based evacuation path generation device of FIG. 2, and FIG. 4 to 12 are example diagrams illustrating AI-based evacuation path generation according to an embodiment. In the following description, parts that overlap with the description of FIG. 1 and FIG. 2 will be omitted. Referring to FIG. 3 to 12, the evacuation path generation management unit (150) may include a collection unit (151), a loading unit (152), a generation unit (153), a calculation unit (154), a determination unit (155), and a provision unit (156).

[0058] The collection unit (151) can collect disaster situation occurrence information from one or more of an external device and a user terminal (200). The collection unit (151) can collect user information including evacuation route request information, changes in the user's speed, the user's direction of movement, and the user's current location from the user terminal (200).

[0059] When the loading unit (152) collects one or more of disaster situation occurrence information, evacuation route request information and user information, it can load prior information from the database (140).

[0060] In this embodiment, the prior information may include 3D modeling information of the location where the user is situated, based on user information. In this embodiment, the database (140) stores various 3D modeling information for locations, such as buildings, historical sites, subway stations, underpasses, public facilities, amusement parks, etc. The loading unit (152) can load 3D modeling information of the location where the user is situated from the database (140). This 3D modeling information may include walkable areas and non-walkable areas. Walkable areas may include passageways, exits, stairs, floors, etc. Non-walkable areas may include walls, pillars, partitions, obstacles, ceilings, roofs, etc. For example, if the location where the user is situated is Building XX, the loading unit (152) can load 3D modeling information for Building XX from the database (140). Also, if the location where the user is situated is Amusement Park YY, the loading unit (152) can load 3D modeling information for Amusement Park YY from the database (140).

[0061] FIG. 4 is an example of 3D modeling information of Building XX loaded from a database (140) as the location of the user is Building XX. Referring to FIG. 4 (a), an obstacle (410) included in an immovable area is shown on the 3D modeling information of Building XX. Referring to FIG. 4 (b), a passageway (420) and stairs (430) included in an movable area are shown on the 3D modeling information of Building XX. In FIG. 4 (b), the light blue area excluding the obstacle (410) is a movable area that can be generated as a navigation mesh and used to calculate the shortest distance from the starting point to the destination. At this time, the shortest distance may include the shortest distance on the actual path, rather than the shortest distance on the coordinates.

[0062] FIG. 5 is a diagram illustrating an example of calculating the shortest distance from a starting point to a destination using a navigation mesh. Referring to FIG. 5, the user's current location (510), a first destination (520), and a second destination (530) are shown. In FIG. 5, it can be seen that the first destination (520) is closer to the user's current location (510) in terms of coordinates, but the second destination (530) is closer to the user's current location (510) in terms of path. This is because there is a wall included in an impassable area between the user's current location (510) and the first destination (520), so a detour is required to move from the user's current location (510) to the first destination (520). The A-Star algorithm described later can also calculate the shortest distance along the path rather than the shortest distance in terms of coordinates.

[0063] Additionally, the prior information may include multiple destination information on the 3D modeling information. Here, the starting point information may be the same as the location information included in the user information, and the destination information may be the same as one or more location information among the exit, rooftop, and safety zone, which are destinations of the evacuation route. The loading unit (152) can load multiple destination information from the 3D modeling information of the place where the user is located.

[0064] Additionally, the prior information may include location information of the fire sensor on the 3D modeling information. The loading unit (152) may load location information of the fire sensor from the 3D modeling information of the location where the user is located. In one embodiment, if the location information of the fire sensor does not exist on the 3D modeling information, the loading unit (152) may extract the location coordinates of the fire sensor from a drawing in which the location information of the fire sensor is shown, and input the location coordinates of the fire sensor onto the 3D modeling information to indicate that the fire sensor exists at the corresponding coordinates.

[0065] Additionally, the prior information may include setting information for the cost on the 3D modeling information. Here, the cost may include a score added to an element that restricts movement on a path generated based on the 3D modeling information. The loading unit (152) can load setting information for the cost from the 3D modeling information of the location where the user is located.

[0066] In this embodiment, the cost setting information may include information in which a lower cost is set for stairs between flat ground and stairs on the 3D modeling information. For example, a default value, for example, 1 point, may be set as the cost for flat ground, and a cost, for example, -1 point, may be set for stairs.

[0067] In addition, the cost setting information may include information in which a lower cost is set for points where the crowd density is greater than or equal to the first threshold value, among points where the crowd density is less than or equal to the first threshold value in the 3D modeling information. For example, among Exits 1 through 8 included in the 3D modeling information of the subway <Express Bus Terminal Station>, the crowd density (total number of people (persons) / unit area (m²) 2 For Exit 1, Exit 3, and Exit 5, where the crowd density is greater than or equal to the first threshold value (e.g., 5 people), -1 point may be set as the cost for each, and for Exit 2, Exit 4, Exit 6, Exit 7, and Exit 8, where the crowd density is less than the first threshold value, a default value may be set as the cost.

[0068] Additionally, the cost setting information may include information in which a lower cost is set at the point where the width of the movement space is less than the second threshold value during crowd movement, among the points where the width of the movement space is greater than or equal to the second threshold value during crowd movement on the 3D modeling information. For example, among the multiple pedestrian passages included in the 3D modeling information of the Gangnam Station underground shopping mall, a cost of -1 point may be set as the width of the pedestrian passage in the direction of Teheran-ro is less than the second threshold value (e.g., 5m), and a default cost value may be set as the width of the pedestrian passage in the direction of Gangnam-daero on the Nonhyeon-dong side is greater than or equal to the second threshold value.

[0069] In addition, regarding the cost setting information, among points where the crowd density relative to time is greater than or equal to the third threshold value (e.g., 10 people) and points where the crowd density relative to time is less than the third threshold value on the 3D modeling information, a lower cost may be set for points where the crowd density relative to time is greater than or equal to the third threshold value. For example, assuming that Exit 1 of the Gangnam Station underground shopping mall has a crowd density greater than or equal to the third threshold value during rush hour, i.e., between 8:00 AM and 10:00 AM and between 5:00 PM and 8:00 PM, and a crowd density less than the third threshold value during non-rush hour, if a fire occurs at 7:00 PM, which falls within rush hour, the cost for Exit 1 may be set to -1 point.

[0070] Regarding the cost setting information, among points where the probability of a secondary accident occurring during movement on the 3D modeling information is greater than or equal to the fourth threshold value (e.g., 50%) and points where the probability of a secondary accident occurring during movement is less than the fourth threshold value, a lower cost may be set for points where the probability of a secondary accident occurring during movement is greater than or equal to the fourth threshold value. For example, points where the probability of a secondary accident occurring during movement is greater than or equal to the fourth threshold value may include one or more of entrances, stairs, corridors, emergency exits, obstacles, and safety zones where many people gather, and accordingly, a cost of -1 point may be set. In this embodiment, a default cost value may be set for points where the probability of a secondary accident occurring during movement is less than the fourth threshold value.

[0071] In addition, regarding the cost setting information, if the movement path in the 3D modeling information is determined to be a complex path based on whether non-straight lines and curves are repeated more than a preset number or the number of obstacles in the movement path is more than a preset number, a lower cost (e.g., -1 point) may be set compared to a simple path where non-straight lines and curves are repeated less than a preset number or the number of obstacles in the movement path is less than a preset number. In this embodiment, a default value may be set as the cost for a simple path where non-straight lines and curves are repeated less than a preset number or the number of obstacles in the movement path is less than a preset number.

[0072] In addition, the cost setting information may include information in which a lower cost is set for the location where hazardous materials are present, among the locations where hazardous materials are present and locations where hazardous materials are not present in the 3D modeling information. For example, as a radiation therapy room equipped with radioactive materials exists on the first basement floor included in the 3D modeling information of AA General Hospital, a cost of -1 point may be set for the radiation therapy room on the first basement floor, and a default cost value may be set for the remaining locations where hazardous materials are not present.

[0073] The setting information for such costs may be set differently depending on the design, use, and safety regulations of the building or place, and the loading unit (152) may load the setting information for costs from the database (140) to create an evacuation path.

[0074] The generating unit (153) can generate multiple primary paths that can be traveled from a starting point to multiple destinations based on one or more of disaster situation occurrence information, evacuation route request information, and user information, and prior information loaded from a database (140 in FIG. 2). Here, the starting point includes the user's current location, and the destinations may include one or more of an exit, a rooftop, and a safe zone.

[0075] In this embodiment, the generating unit (153) can generate a primary path using the A-Star algorithm. The generating unit (153) can generate a primary path by connecting intermediate nodes that have the shortest path from a starting node corresponding to a starting point to a target node corresponding to a destination. In this embodiment, as there are multiple destinations, there may be multiple primary paths (first path to Nth path) from the starting point to the destination.

[0076] Figure 6 illustrates C# code for searching for the shortest path by applying the ASTAR algorithm to a starting point and multiple destinations. Referring to Figure 6, an example is given where there are 10 destinations, and C# code is illustrated for searching for 10 primary paths, namely the first path to the tenth path, which have the shortest path from the starting point to each of the 10 destinations by the ASTAR algorithm.

[0077] In Fig. 6, transform.position can represent the user's current position. In Fig. 6, Exit.gameObject.transform.position can represent the destination position, and it can be seen that there are 10 destinations. Using the NavMesh.CalculatePath function, distance information along the path, rather than the coordinate distance, can be calculated and stored in Route_N.

[0078] The generating unit (153) can calculate the travel distance by the cumulative result of an edge connecting at least one intermediate node found between a starting node, a target node, and each of the starting node and the target node for each of the multiple primary paths, namely the first path to the Nth path. Here, the intermediate node may include one or more of the following cases: the case where the edge connecting the current node and the next node is a straight line based on the edge connecting the previous node and the current node, and the case where the edge connecting the current node and the next node is a curve requiring rotational movement based on the edge connecting the previous node and the current node.

[0079] FIG. 7 illustrates C# code for calculating the travel distance for each of the multiple primary paths generated through the ASTAR algorithm of FIG. 6. FIG. 7 illustrates C# code for calculating the travel distance for the first path and the travel distance for the second path among the first to ten paths. In FIG. 7, i can represent the coordinates of a node, and lengths can represent the travel distance. To calculate the travel distance, the cumulative result of the edges connecting the start node, the target node, and at least one intermediate node explored between each of the start node and the target node can be calculated as the travel distance.

[0080] In this embodiment, one or more intermediate nodes located between the start node and the target node may include one or more of the following cases: a case where the edge connecting the current node and the next node is a straight line based on the edge connecting the previous node and the current node, and a case where the edge connecting the current node and the next node is a curve requiring rotational movement based on the edge connecting the previous node and the current node.

[0081] In one embodiment, the generating unit (153) can search for one starting node, ten target nodes, and a plurality of intermediate nodes searched between the starting node and the ten target nodes when there are ten destinations. For example, for the first destination, the cumulative result of the edge connecting the starting node, the first target node, and at least one intermediate node searched between the starting node and the first target node can be calculated as the travel distance of the first path. Additionally, for the seventh destination, the cumulative result of the edge connecting the starting node, the seventh target node, and at least one intermediate node searched between the starting node and the seventh target node can be calculated as the travel distance of the seventh path.

[0082] The generating unit (153) can determine the first to Nth paths, each reflecting a different travel distance, as multiple primary paths. In one embodiment, if there are 10 destinations, the generating unit (153) can determine the first path, which reflects the travel distance of the first path, to the 10th path, which reflects the travel distance of the 10th path, as 10 primary paths.

[0083] Generally, in the A-Star algorithm, as shown in Fig. 8, the first to Nth paths are determined as the evacuation path by comparing the travel distances of multiple primary paths and selecting the path with the minimum value. However, this cannot be considered an effective method for presenting an evacuation path because, in the process of moving to find an exit, people's paths intersect, causing congestion, and there may be a risk of secondary accidents due to the congestion, and the path taken to find an exit may pass through the disaster site.

[0084] In this embodiment, when the generating unit (153) determines the first to Nth paths, which reflect different travel distances, as multiple primary paths, the calculation unit (154) determines whether there is an element that restricts movement for each of the multiple primary paths, and can calculate the total sum of the cost as a score added to the element that restricts movement as there is an element that restricts movement.

[0085] The calculation unit (154) can calculate the total sum of costs for each of the multiple primary paths using the cost setting information loaded from the database (140).

[0086] Here, the cost setting information may include information that a lower cost is set for stairs among flat ground and stairs. The cost setting information may include information that a lower cost is set for points where the crowd density is greater than or equal to the first threshold value, among points where the crowd density is less than or equal to the first threshold value and points where the crowd density is greater than or equal to the first threshold value. The cost setting information may include information that a lower cost is set for points where the width of the movement space during crowd movement is less than the second threshold value, among points where the width of the movement space during crowd movement is greater than or equal to the second threshold value. The cost setting information may include information that a lower cost is set for points where the crowd density relative to time is greater than or equal to the third threshold value, among points where the crowd density relative to time is greater than or equal to the third threshold value and points where the crowd density relative to time is less than the third threshold value. The cost setting information may include information that a lower cost is set for a point where the probability of a secondary accident occurring during movement is greater than or equal to the fourth threshold value, among a point where the probability of a secondary accident occurring during movement is less than or equal to the fourth threshold value. The cost setting information may include information that a path is determined to be complex based on whether non-straight lines and curves are repeated more than a preset number of times in the path of movement, or whether the number of obstacles in the path of movement is greater than or equal to the preset number, and that a lower cost is set for a path of complexity than a simple path where non-straight lines and curves are repeated less than a preset number of times in the path of movement, or where the number of obstacles in the path of movement is less than a preset number. The cost setting information may include information that a lower cost is set for a point where hazardous materials are present, among a point where hazardous materials are not present and a point where hazardous materials are present.

[0087] In this embodiment, the cost may be lowered if one or more of the following are included in each of the multiple primary paths: stairs, a point where the crowd density is greater than or equal to a first threshold value, a point where the width of the movement space is less than a second threshold value when the crowd moves, a point where the crowd density relative to time is greater than or equal to a third threshold value, a point where the probability of a secondary accident occurring during movement is greater than or equal to a fourth threshold value, a complex path where straight lines and curves that are not straight are repeated more than a preset number of times in the movement path, or a point where the number of obstacles in the movement path is greater than or equal to a preset number, a point where hazardous materials are present, a point where a secondary accident may occur during movement, or a complex movement path.

[0088] The decision unit (155) can determine one of the multiple primary paths as the optimal evacuation path based on the total sum of the costs. The decision unit (155) can determine the primary path with the highest total sum of costs among the multiple primary paths as the optimal evacuation path.

[0089] The decision unit (155) detects the operation of the fire sensor, and when the fire sensor operates, sets the movable area located around the fire sensor as an unmovable area, and can exclude one or more primary paths including the movable area located around the fire sensor from a plurality of primary paths.

[0090] For example, assuming that multiple primary paths are the first to ten paths, and that a fire sensor operates in the first and second paths and the movable area located around the fire sensor is treated as an immovable area, the determining unit (155) can exclude the first and second paths from the first to ten paths. The determining unit (155) can determine the third to ten paths as multiple primary paths, and determine the primary path with the highest total cost among the third to ten paths as the optimal evacuation path.

[0091] FIG. 9 is a diagram illustrating an example in which a movable area is set as an immovable area. Referring to FIG. 9, FIG. 9 (a) illustrates normal 3D modeling information, and FIG. 9 (b) illustrates an example in which a fire sensor located near a staircase is activated, and the entrance, stairs, and passageway, which are movable areas around the fire sensor, are blocked as immovable areas.

[0092] In such a case, the decision unit (155) can exclude a path that includes an entrance, stairs, and passageways, which are movable areas around the fire sensor, and determine another path that does not include an entrance, stairs, and passageways, which are movable areas around the fire sensor, even if the travel distance becomes longer.

[0093] As an optional embodiment, the decision unit (155) may detect the operation of a fire sensor located in the primary path with the highest total cost among a plurality of primary paths, i.e., the optimal evacuation path, set a movable area located around the fire sensor as an immovable area, and cancel the determination of the optimal evacuation path for the primary path with the highest total cost. The decision unit (155) may exclude the primary path with the highest total cost from the plurality of primary paths. The decision unit (155) may update the primary path with the next highest total cost among the plurality of primary paths excluded from the primary path with the highest total cost as the optimal evacuation path.

[0094] For example, if multiple primary paths are the first to ten paths, and the primary path with the highest total cost, i.e., the optimal evacuation path, is determined as the fifth path, and assuming that a fire sensor located in the fifth path operates and a movable area located around the fire sensor is treated as an unmovable area, the determination unit (155) can cancel the fifth path, which is the optimal evacuation path, and update any one of the first to fourth paths and the sixth to ten paths, which has the next highest total cost, as the optimal evacuation path.

[0095] FIG. 10 is a diagram illustrating the determination of an optimal evacuation route according to one embodiment. Referring to FIG. 10, a user's current location (1011), a first destination (1012), and a second destination (1013) are shown. A generating unit (153) can generate a first path (1021) from the user's current location (1011) to the first destination (1012) and a second path (1022) from the user's current location (1011) to the second destination (1013). A determining unit (155) may determine the first path (1021), which is the shortest path, as the optimal evacuation route, but may block the first destination (1012) by causing a fire to occur near the first destination (1012) on the first path (1021), cancel the first path (1021), and then re-determine the second path (1022) as the optimal evacuation route.

[0096] FIG. 11 is a drawing illustrating the determination of an optimal evacuation route according to another embodiment. Referring to FIG. 11, a user's current location (1111), a first destination (1112), and a second destination (1113) are shown. A generating unit (153) can generate a first path (1121) from the user's current location (1111) to the first destination (1112), a second path (1122) from the user's current location (1111) to the first destination (1112), and a third path (1123) from the user's current location (1111) to the second destination (1113). The decision unit (155) may determine the first path (1121), which is the shortest path, as the optimal evacuation path, but if a fire occurs near the first destination (1112) on the first path (1121), the first destination (1112) may be blocked and the first path (1121) canceled, and then the second shortest path, the third path (1123), may be re-determined as the optimal evacuation path. However, if a fire also occurs near the second destination (1113), the decision unit (155) may block the second destination (1113) and cancel the third path (1123), and then the third shortest path, the second path (1122), may be re-determined as the optimal evacuation path.

[0097] FIG. 12 is a diagram illustrating the determination of an optimal evacuation route according to another embodiment. In FIG. 12, parts with the same color may represent a primary route generated by the total sum of costs, and may include a blue primary route and a purple primary route. The determination unit (155) determined the blue primary route as the optimal evacuation route because going straight down from the blue cylinder (column) via the stairs in FIG. 12 is the fastest. However, if the total sum of costs for the purple primary route is higher, the optimal evacuation route for the blue primary route may be canceled, and the purple primary route may be re-determined as the optimal evacuation route. Extending this further, by reflecting the time of day, the route can be determined as the optimal evacuation route to prevent stampede accidents by avoiding evacuation to a point with high crowd density at a specific time, and to allow for safe and fast evacuation even if it takes a slightly longer route.

[0098] As another example, if a fire breaks out on the 7th floor of a 15-story building, it may be safer for people on floors 8 through 15 to evacuate to the rooftop rather than descending unconditionally. This is because there is a risk of suffocation while going down. Additionally, it may be safer for people on floors 7 and below to exit through the first floor. This is because smoke spreads upward due to air density.

[0099] In this case, the decision unit (155) can set the destination to the rooftop for users on floors 8 through 15 and determine the shortest path from the starting point to the rooftop as the optimal evacuation path, and for users on floors 7 or lower, set the destination to the 1st floor entrance and determine the shortest path from the starting point to the 1st floor entrance as the optimal evacuation path. Here, when determining the evacuation path, the setting information regarding the cost described above is reflected so that the path with the highest cost can be determined as the evacuation path.

[0100] The providing unit (156) can provide the evacuation route determined by the determining unit (155) to the user terminal (200). The providing unit (156) can provide the evacuation route that is updated in real time to the user terminal (200).

[0102] FIG. 13 is a block diagram illustrating the configuration of an artificial intelligence-based evacuation path generation device according to another embodiment. In the following description, parts that overlap with the description of FIG. 1 to FIG. 12 will be omitted. Referring to FIG. 12, an evacuation path generation device (100) according to another embodiment may include a processor (170) and a memory (180).

[0103] In this embodiment, the processor (170) can process the functions performed by the communication unit (110), storage medium (120), program storage unit (130), database (140), evacuation path generation management unit (150), and control unit (160) disclosed in FIGS. 2 and 3.

[0104] Such a processor (170) can control the operation of the entire evacuation path generation device (100). Here, 'processor' may refer to a data processing device embedded in hardware having a physically structured circuit to perform a function expressed by code or instructions included in a program, for example. Examples of such data processing devices embedded in hardware may include microprocessors, central processing units, processor cores, multiprocessors, ASICs, FPGAs, etc., but the scope of the present invention is not limited thereto.

[0105] The memory (180) is operably connected to the processor (170) and can store at least one code associated with an operation performed by the processor (170).

[0106] Additionally, the memory (180) may perform the function of temporarily or permanently storing data processed by the processor (170) and may include data built into the database (140). Here, the memory (180) may include a magnetic storage medium or a flash storage medium, but the scope of the present invention is not limited thereto. Such memory (180) may include internal memory and / or external memory, and may include volatile memory such as DRAM, SRAM, or SDRAM, non-volatile memory such as OTPROM, PROM, EPROM, EEPROM, mask ROM, flash ROM, NAND flash memory, or NOR flash memory, flash drives such as SSD, CF card, SD card, Micro-SD card, Mini-SD card, xD card, or Memory Stick, or storage devices such as HDD.

[0108] FIG. 14 is a flowchart illustrating an artificial intelligence-based evacuation path generation method according to one embodiment. In the following description, parts that overlap with the descriptions of FIG. 1 to FIG. 13 will be omitted. The amplifier design method according to this embodiment will be described under the assumption that the evacuation path generation device (100) performs the task at the processor (170) with the help of surrounding components.

[0109] Referring to FIG. 14, in step S1410, the processor (170) can generate multiple primary paths that can be traveled from a starting point to multiple destinations.

[0110] In this embodiment, prior to the step of generating a plurality of primary paths, the processor (170) may load prior information including 3D modeling information of a place including a walkable area and a not walkable area based on a starting point, a plurality of destination information on the 3D modeling information, location information of a fire sensor on the 3D modeling information, and setting information for a cost on the 3D modeling information.

[0111] In this embodiment, when generating multiple primary paths, the processor (170) can generate a first path to the Nth path having the shortest path from a source to multiple destinations by applying source information and multiple destination information on 3D modeling information to the A-Star algorithm. For each of the first path to the Nth path, the processor (170) can calculate the travel distance by the cumulative result of an edge connecting a start node corresponding to source information, a target node corresponding to destination information, and at least one intermediate node found between each of the start node and the target node. The processor (170) can determine the first path to the Nth path, which reflect different travel distances, as multiple primary paths.

[0112] In step S1420, when the processor (170) completes the generation of multiple primary paths, it determines whether there is an element that restricts movement for each of the multiple primary paths, and if there is an element that restricts movement, it can calculate the total sum of the cost as a score added to the element that restricts movement.

[0113] In this embodiment, the cost setting information is such that, on the 3D modeling information, a lower cost is set for stairs among flat ground and stairs; a lower cost is set for points where the crowd density is greater than or equal to the first threshold value among points where the crowd density is less than or equal to the first threshold value and points where the crowd density is greater than or equal to the first threshold value; a lower cost is set for points where the width of the movement space during crowd movement is less than the second threshold value among points where the width of the movement space during crowd movement is greater than or equal to the second threshold value and points where the width of the movement space during crowd movement is greater than or equal to the second threshold value; a lower cost is set for points where the crowd density relative to time is greater than or equal to the third threshold value among points where the crowd density relative to time is less than or equal to the third threshold value and points where the crowd density relative to time is greater than or equal to the third threshold value; a lower cost is set for points where the probability of a secondary accident occurring during movement is greater than or equal to the fourth threshold value among points where the probability of a secondary accident occurring during movement is less than the fourth threshold value and points where the probability of a secondary accident occurring during movement is greater than or equal to the fourth threshold value; and on the movement path Information may be included such as determining that a path is complex because non-straight lines and curves are repeated more than a preset number, or the number of obstacles in the path is more than a preset number, and setting a lower cost for a complex path than for a simple path where non-straight lines and curves are repeated less than a preset number, or the number of obstacles in the path is less than a preset number, and setting a lower cost for a point where hazardous materials exist among a point where hazardous materials do not exist and a point where hazardous materials exist. The processor (170) can calculate the total sum of costs for each of the multiple primary paths by reflecting the cost setting information for each of the multiple primary paths.

[0114] In step S1430, the processor (170) may determine one of the multiple primary paths as the optimal evacuation path based on the total sum of the costs. The processor (170) may determine the primary path with the highest total sum of costs among the multiple primary paths as the optimal evacuation path.

[0115] In this embodiment, when determining the optimal evacuation path, the processor (170) detects the operation of a fire sensor located in the primary path with the highest total cost among a plurality of primary paths, sets a movable area located around the fire sensor as an immovable area, and can cancel the determination of the optimal evacuation path for the primary path with the highest total cost. The processor (170) can exclude the primary path with the highest total cost from the plurality of primary paths. The processor (170) can update the primary path with the next highest total cost among the plurality of primary paths excluded from the primary path with the highest total cost as the optimal evacuation path. Here, "updating" may include canceling the previous evacuation path determination and re-determining a new evacuation path.

[0116] In this embodiment, when determining the optimal evacuation path, the processor (170) detects the operation of the fire sensor and, as the fire sensor operates, sets the movable area located around the fire sensor as an immovable area, and can exclude one or more primary paths that include the movable area located around the fire sensor from a plurality of primary paths. The processor (170) can determine the optimal evacuation path by selecting one primary path with the highest total cost from the remaining primary paths from which one or more primary paths including the movable area located around the fire sensor have been excluded.

[0118] The embodiments according to the present invention described above may be implemented in the form of a computer program that can be executed through various components on a computer, and such a computer program may be recorded on a computer-readable medium. In this case, the medium may include a magnetic medium such as a hard disk, a floppy disk, and a magnetic tape, an optical recording medium such as a CD-ROM and a DVD, a magneto-optical medium such as a floptical disk, and a hardware device specifically configured to store and execute program instructions, such as a ROM, RAM, or flash memory.

[0119] Meanwhile, the above-mentioned computer program may be one specifically designed and configured for the present invention, or one known and available to those skilled in the art of computer software. Examples of computer programs may include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

[0120] In the specification of the present invention (particularly in the claims), the use of the term "above" and similar descriptive terms may be in both singular and plural. Furthermore, where a range is described in the present invention, it is to include an invention to which individual values ​​belonging to said range are applied (unless otherwise stated), and this is equivalent to describing each individual value constituting said range in the detailed description of the invention.

[0121] Unless explicitly stated or contrary to the order of the steps constituting the method according to the present invention, said steps may be performed in a suitable order. The present invention is not necessarily limited by the order in which said steps are described. The use of all examples or exemplary terms (e.g., etc.) in the present invention is merely for the purpose of describing the present invention in detail, and the scope of the present invention is not limited by said examples or exemplary terms unless limited by the claims. Furthermore, those skilled in the art will understand that various modifications, combinations, and changes may be made according to design conditions and factors within the scope of the claims or equivalents to which they are added.

[0122] Accordingly, the scope of the present invention should not be limited to the embodiments described above, and all scopes equivalent to or equivalently modified from the claims set forth below, as well as the claims set forth below, shall be considered to fall within the scope of the concept of the present invention. Explanation of the symbols

[0123] 100: Evacuation route generation device 200: User terminal 300: Network

Claims

Claim 1 A method for generating an evacuation path performed by a processor of an evacuation path generating device, comprising: a step of generating a plurality of primary paths capable of moving from a starting point to a plurality of destinations; and a step of calculating a total sum of costs as points added to an element restricting movement, wherein, as there exists an element restricting movement in at least one of the plurality of primary paths. and includes a step of determining one of the plurality of primary paths as the optimal evacuation path based on the total sum of the above costs, and further includes, prior to the step of generating the plurality of primary paths, a step of loading prior information including 3D modeling information of a place including a walkable area and a not walkable area based on the starting point, a plurality of destination information on the 3D modeling information, location information of a fire sensor on the 3D modeling information, and setting information for the above costs on the 3D modeling information, wherein, on the 3D modeling information, a lower cost is set for the stairs among flat ground and stairs, on the 3D modeling information, a lower cost is set for the point where the crowd density is greater than or equal to the first reference value among a point where the crowd density is greater than or equal to the first reference value and a point where the crowd density is less than the first reference value, and on the 3D modeling information, a point where the width of the movement space during crowd movement is less than the second reference value and a point where the width of the movement space during crowd movement Among points greater than or equal to the second threshold value, a lower cost is set at points where the width of the movement space is less than the second threshold value during the crowd movement, and on the 3D modeling information, among points where the crowd density relative to time is greater than or equal to the third threshold value and points where the crowd density relative to time is less than the third threshold value, a lower cost is set at points where the crowd density relative to time is greater than or equal to the third threshold value, and on the 3D modeling information,Among a point where the probability of a secondary accident occurring during movement is greater than or equal to a fourth threshold value and a point where the probability of a secondary accident occurring during movement is less than or equal to the fourth threshold value, a lower cost is set at the point where the probability of a secondary accident occurring during movement is greater than or equal to the fourth threshold value; on the 3D modeling information, a path is determined to be complex based on whether non-straight lines and curves are repeated more than a preset number in the movement path or the number of obstacles in the movement path is greater than a preset number; a lower cost is set at the complex path compared to a simple path where non-straight lines and curves are repeated less than a preset number or the number of obstacles in the movement path is less than a preset number; and on the 3D modeling information, among a point where hazardous materials are not present and a point where hazardous materials are present, a lower cost is set at the point where hazardous materials are present; and the step of calculating the total sum of the costs includes the step of calculating the total sum of costs for each of the plurality of primary paths by reflecting the cost setting information to each of the plurality of primary paths. AI-based evacuation route generation method including Claim 2 delete Claim 3 In claim 1, the step of generating the plurality of primary paths comprises: a step of generating a first path to the Nth path having the shortest path from the starting point to the plurality of destinations by applying the starting point information and the plurality of destination information on the 3D modeling information to the A-Star algorithm; a step of calculating the cumulative result of an edge connecting a starting node corresponding to the starting point information, a target node corresponding to the destination information, and at least one intermediate node searched between each of the starting node and the target node as the travel distance for each of the first path to the Nth paths; and a step of determining the first path to the Nth paths, each reflecting different travel distances, as the plurality of primary paths, an artificial intelligence-based evacuation path generation method. Claim 4 delete Claim 5 In claim 1, the step of determining the optimal evacuation route includes the step of determining the primary route with the highest total cost among the plurality of primary routes as the optimal evacuation route, an artificial intelligence-based evacuation route generation method. Claim 6 In claim 5, the step of determining the optimal evacuation path comprises: a step of detecting the operation of the fire sensor located in the primary path with the highest total cost among the plurality of primary paths, setting a movable area located around the fire sensor as an immovable area, and canceling the determination of the optimal evacuation path for the primary path with the highest total cost; a step of excluding the primary path with the highest total cost from the plurality of primary paths; and a step of re-determining the primary path with the next highest total cost among the plurality of primary paths excluded from the primary path with the highest total cost as the optimal evacuation path, an artificial intelligence-based evacuation path generation method. Claim 7 An artificial intelligence-based evacuation path generation method according to claim 1, further comprising, prior to the step of determining the optimal evacuation path, the step of setting a movable area located around the fire sensor as an immovable area upon detecting the operation of the fire sensor, and excluding one or more primary paths including the movable area located around the fire sensor from the plurality of primary paths. Claim 8 A computer-readable recording medium storing a computer program for executing any one of the methods of claims 1, 3, and 5 through 7 using a computer. Claim 9 As an evacuation route generating device, a processor; The system includes a memory operably connected to the processor and storing at least one code executed on the processor, wherein the memory stores code that, when executed through the processor, causes the processor to generate multiple primary paths movable from a starting point to multiple destinations, determine whether there is an element restricting movement for each of the multiple primary paths, calculate a total sum of costs as a score added to the element restricting movement if the element restricting movement exists, and determine one of the multiple primary paths as the optimal evacuation path based on the total sum of costs, wherein the processor causes the memory to load prior information including 3D modeling information of a place including a walkable area and a not walkable area based on the starting point, information on multiple destinations on the 3D modeling information, location information of fire sensors on the 3D modeling information, and setting information for the costs on the 3D modeling information, prior to generating the multiple primary paths. Saved, and the setting information for the above cost is such that, on the 3D modeling information, a lower cost is set for the stairs among flat ground and stairs, on the 3D modeling information, a lower cost is set for the point where the crowd density is greater than or equal to the first reference value among the point where the crowd density is less than the first reference value and the point where the crowd density is less than the first reference value, on the 3D modeling information, a lower cost is set for the point where the width of the movement space during crowd movement is less than the second reference value among the point where the width of the movement space during crowd movement is less than the second reference value and the point where the width of the movement space during crowd movement is greater than or equal to the second reference value, and on the 3D modeling information,Among a point where the crowd density relative to time is greater than or equal to the third threshold value and a point where the crowd density relative to time is less than the third threshold value, a lower cost is set to the point where the crowd density relative to time is greater than or equal to the third threshold value; on the 3D modeling information, among a point where the probability of a secondary accident occurring during movement is greater than or equal to the fourth threshold value and a point where the probability of a secondary accident occurring during movement is less than the fourth threshold value, a lower cost is set to the point where the probability of a secondary accident occurring during movement is greater than or equal to the fourth threshold value; on the 3D modeling information, a path is determined to be complex if non-straight lines and curves are repeated more than a preset number in the movement path or if the number of obstacles in the movement path is greater than a preset number; a lower cost is set to the complex path than to a simple path where non-straight lines and curves are repeated less than a preset number or if the number of obstacles in the movement path is less than a preset number; and on the 3D modeling information, among a point where hazardous materials do not exist and a point where hazardous materials exist, the hazardous materials An artificial intelligence-based evacuation path generation device comprising: including information in which a lower cost is set at an existing point; and a processor storing a code that causes the memory to calculate the total sum of costs for each of the plurality of primary paths by reflecting the cost setting information for each of the plurality of primary paths when calculating the total sum of the costs.

Images