KR102665256B1 - Apparatus and method for managing flow of crowd - Google Patents

Abstract

The present invention relates to a crowd flow management device and method that efficiently manages the flow of crowds based on the risk calculated during crowd movement.
A crowd flow management method according to an embodiment of the present invention is a crowd flow management method performed by a processor of a crowd flow management device, comprising: generating 3D modeling information of an area of interest including one or more pedestrian paths, and 3D Based on the modeling information, setting the simulation environment, simulation conditions, and properties of objects included in the crowd and performing a first crowd simulation; and state change information about the objects generated according to the performance of the first crowd simulation. A step of calculating a first crowd simulation result based on a step of calculating a risk score for one or more pedestrian paths by applying a preset standard risk to the first crowd simulation result, and ranking the highest among the results of calculating the risk score. It may include generating crowd control information that determines whether to change the walking direction for a pedestrian path.

Description

Crowd flow management apparatus and method {APPARATUS AND METHOD FOR MANAGING FLOW OF CROWD}

The present invention relates to a crowd flow management device and method that efficiently manages the flow of crowds based on the level of risk on pedestrian paths.

In modern cities, the importance of crowd flow management is becoming more prominent due to population growth and urbanization. In particular, the crowding phenomenon that occurs on pedestrian paths and public facilities in the city increases the possibility of accidents due to collisions and risk factors between pedestrians. Therefore, technology is required to quantify and manage the flow of urban crowds and the risk of pedestrian paths.

The above-mentioned background technology is technical information that the inventor possessed for deriving the present invention or acquired in the process of deriving the present invention, and cannot necessarily be said to be known art disclosed to the general public before filing the application for the present invention.

Domestic Patent Publication No. 10-2013-0082635 (2013.07.22)

One object of the present invention is to analyze the crowd density and walking speed in a specific area, calculate the risk for each pedestrian path, and propose an effective crowd control method for dangerous pedestrian paths.

The problem to be solved by the present invention is not limited to the problems mentioned above, and other problems and advantages of the present invention that are not mentioned can be understood through the following description and can be understood more clearly through the embodiments of the present invention. It will be. In addition, it will be appreciated that the problems and advantages to be solved by the present invention can be realized by the means and combinations thereof indicated in the patent claims.

A crowd flow management device according to an embodiment of the present invention includes a processor and a memory operably connected to the processor and storing at least one code to be executed by the processor, and the memory, when executed through the processor, causes the processor to Generate 3D modeling information of the area of interest including the above pedestrian path, set the simulation environment, simulation conditions, and properties of objects included in the crowd based on the 3D modeling information, perform a first crowd simulation, and perform a first crowd simulation. Calculate a first crowd simulation result based on the state change information about the object generated as the crowd simulation is performed, and apply a preset standard risk to the first crowd simulation result to calculate a risk score for one or more pedestrian paths. , Among the results of calculating the risk score, a code that causes the creation of crowd control information that determines whether to change the walking direction for a specific walking path can be stored.

A crowd flow management method according to an embodiment of the present invention is a crowd flow management method performed by a processor of a crowd flow management device, comprising: generating 3D modeling information of an area of interest including one or more pedestrian paths, and 3D Based on the modeling information, setting the simulation environment, simulation conditions, and properties of objects included in the crowd and performing a first crowd simulation; and state change information about the objects generated according to the performance of the first crowd simulation. A step of calculating a first crowd simulation result based on a step of calculating a risk score for one or more pedestrian paths by applying a preset standard risk to the first crowd simulation result, and ranking the highest among the results of calculating the risk score. It may include generating crowd control information that determines whether to change the walking direction for a pedestrian path.

In addition, another method for implementing the present invention, another system, and a computer-readable recording medium storing a computer program for executing the method may be further provided.

Other aspects, features and advantages in addition to those described above will become apparent from the following drawings, claims and detailed description of the invention.

According to the present invention, it is possible to identify dangerous walking paths by calculating the risk for each walking path within a specific area and improve the safety of the crowd by controlling the crowd's walking on the dangerous walking path.

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

1 is an exemplary diagram of a crowd flow management environment according to this embodiment.
Figure 2 is a block diagram schematically illustrating the configuration of a crowd flow management device according to this embodiment.
FIG. 3 is a block diagram schematically illustrating the configuration of the crowd flow management unit of the crowd flow management device of FIG. 2.
4 to 11 are exemplary diagrams for explaining crowd flow management according to this embodiment.
Figure 12 is a block diagram schematically illustrating the configuration of a crowd flow management device according to another embodiment.
Figure 13 is a flowchart for explaining the crowd flow management method according to this embodiment.

The advantages and features of the present invention and 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 may be implemented in various different forms, and should be understood to include all conversions, equivalents, and substitutes included in the spirit and technical 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, if it is determined that a detailed description of related known technologies may obscure the gist of the present invention, the detailed description will be omitted.

The terms used in this application are only used to describe specific embodiments and are not intended to limit the invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, 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 the terms. The above terms are used only for the purpose of distinguishing one component from another.

Additionally, in this application, a “part” may be a hardware component, such as a processor or circuit, and/or a software component executed by the hardware component, such as a processor.

Hereinafter, embodiments according to the present invention will be described in detail with reference to the accompanying drawings. In the description with reference to the accompanying drawings, identical or corresponding components are assigned the same drawing numbers and overlapping descriptions thereof are omitted. I decided to do it.

In the following examples, the terms first, second, etc. are used not in a limiting sense but for the purpose of distinguishing one component from another component.

In the following examples, singular terms include plural terms unless the context clearly dictates otherwise.

In the following embodiments, terms such as include or have mean the presence of features or components described in the specification, and do not exclude in advance the possibility of adding one or more other features or components.

In cases where an embodiment can be implemented differently, a specific process sequence may be performed differently from the described sequence. For example, two processes described in succession may be performed substantially at the same time, or may be performed in an order opposite to that in which they are described.

1 is an exemplary diagram of a crowd flow management environment according to this embodiment. Referring to FIG. 1 , the crowd flow management environment 1 may include a crowd flow management device 100, a user terminal 200, and a network 300.

The crowd flow management device 100 may generate 3D modeling information of an area of interest including one or more pedestrian paths. The crowd flow management device 100 may generate 3D modeling information of the area of interest by applying the results of using the national information platform and the result of using a GIS (geographic information system) for the area of interest to 3D modeling software.

The crowd flow management device 100 may set the simulation environment, simulation conditions, and properties of objects included in the crowd based on 3D modeling information and perform a first crowd simulation. The crowd flow management device 100 can build a crowd simulation environment in which the shape of the pedestrian path included in the 3D modeling information is meshed. The crowd flow management device 100 may set crowd simulation conditions including the above-described characteristics of the crowd for a crowd walking on a pedestrian path made of mesh, and set properties for each object included in the crowd. The crowd flow management device 100 may perform a first crowd simulation in which an object walks a mesh by applying the results of setting the crowd simulation conditions and the properties of the object to the crowd simulation environment.

The crowd flow management device 100 may calculate the first crowd simulation result based on state change information about the entity generated as the first crowd simulation is performed. The crowd flow management device 100 may calculate one or more of crowd density, crowd walking speed, and crowd confluence flow as a result of the first crowd simulation.

The crowd flow management device 100 may calculate a risk score for one or more pedestrian paths by applying a preset standard risk level to the first crowd simulation result. The crowd flow management device 100 stores first to sixth standard risk levels for calculating a risk score. Different scores (e.g., different first scores to different sixth scores) may be assigned to the characteristics of pedestrian paths and crowds for the first to sixth standard risks and stored in the database (140 in FIG. 2). there is. The crowd flow management device 100 may calculate the sum of the first to sixth scores corresponding to the first crowd simulation result as a risk score.

The crowd flow management device 100 may generate crowd control information that determines whether to change the walking direction for a specific pedestrian path among the results of calculating the risk score. The crowd flow management device 100 may generate crowd control information that determines a walking direction different from the previous walking direction for the specific walking path described above.

The crowd flow management device 100 may perform a second crowd simulation by applying the crowd control information that determines the change in walking direction to one or more of the simulation environment, simulation conditions, and properties of objects included in the crowd. The crowd flow management device 100 may calculate a second crowd simulation result by integrating state change information for each entity created as the second crowd simulation is performed. The crowd flow management device 100 may provide the second crowd simulation result by displaying it on 3D modeling information.

In this embodiment, the crowd flow management device 100 exists independently in the form of a server, or calculates the risk level according to the crowd simulation results of the pedestrian path provided by the crowd flow management device 100, and the walking direction of the pedestrian path based on the risk degree. The function to change can be implemented in the form of an application and mounted on the user terminal 200.

The crowd flow management device 100 may be a database server that provides data necessary to apply various artificial intelligence algorithms.

Here, artificial intelligence (AI) is a field of computer science and information technology that studies ways to enable computers to do the thinking, learning, and self-development that can be done with human intelligence. This may mean enabling the imitation of intelligent behavior.

Additionally, artificial intelligence does not exist by itself, but is directly or indirectly related to other fields of computer science. In particular, in modern times, attempts are being made very actively to introduce artificial intelligence elements in various fields of information technology and use them to solve problems in those fields.

Machine learning is a branch of artificial intelligence that may include the field of study that gives computers the ability to learn without being explicitly programmed. Specifically, machine learning can be said to be a technology that studies and builds systems and algorithms that learn, make predictions, and improve their own performance based on empirical data. Rather than executing strictly fixed, static program instructions, machine learning algorithms can build a specific model to make predictions or decisions based on input data.

Both unsupervised learning and supervised learning can be used as machine learning methods for these artificial neural networks. In addition, deep learning technology, a type of machine learning, can learn at a multi-level, deep level based on data. Deep learning can represent a set of machine learning algorithms that extract key data from multiple pieces of data at higher levels.

The user terminal 200 may receive a crowd flow management service by accessing a crowd flow management application and/or a crowd flow management site provided by the crowd flow management device 100.

This user terminal 200 may include a communication terminal capable of performing the functions of a computing device (not shown), in addition to the desktop computer 201, smartphone 202, and laptop 203 operated by the user. , tablet PC, smart TV, mobile phone, PDA (personal digital assistant), media player, micro server, GPS (global positioning system) device, e-reader, digital broadcasting terminal, navigation, kiosk, MP3 player, digital camera, home appliances. and other mobile or non-mobile computing devices. Additionally, the user terminal 200 may be a wearable terminal such as a watch, glasses, hair band, or ring equipped with communication functions and data processing functions. This user terminal 200 is not limited to the above-described content, and any terminal capable of web browsing may be used without limitation.

The network 300 may serve to connect the crowd flow management device 100 and the user terminal 200. This network 300 may be, for example, a wired network such as a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), or an integrated service digital network (ISDN), a wireless LAN (WLAN), or a code division multiple access (CDMA) network. -division multiple access), and may encompass wireless networks such as satellite communication, but the scope of the present invention is not limited thereto. Additionally, the network 300 may transmit and receive information using short-range communication and/or long-distance communication. Here, short-range communication may include Bluetooth, radio frequency identification (RFID), infrared data association (IrDA), ultra-wideband (UWB), ZigBee, and Wi-Fi technology, and long-distance communication may include code-division multiple access (CDMA). ), frequency-division multiple access (FDMA), time-division multiple access (TDMA), orthogonal frequency-division multiple access (OFDMA), and single carrier frequency-division multiple access (SC-FDMA) technology.

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

Furthermore, the network 300 includes CAN (controller area network) communication, V2I (vehicle to infrastructure) communication, V2X (vehicle to everything) communication, wave (wireless access in vehicular environment) communication technology, objects, etc. It can support IoT (Internet of Things) networks and/or 5G communications that exchange and process information between distributed components.

Figure 2 is a block diagram schematically illustrating the configuration of a crowd flow management device according to this embodiment. In the following description, parts that overlap with the description of FIG. 1 will be omitted. Referring to Figure 2, the crowd flow management device 100 includes a communication unit 110, a storage medium 120, a program storage unit 130, a database 140, a crowd flow management unit 150, and a control unit 160. can do.

The communication unit 110 may work with the network 300 to provide a communication interface necessary to provide transmission and reception signals between the crowd flow management device 100 and the user terminal 200 in the form of packet data. Furthermore, the communication unit 110 may serve to receive a predetermined information request signal from the user terminal 200 and transmit the information processed by the crowd flow management unit 150 to the user terminal 200. there is. Here, the communication interface is a medium that serves to connect the crowd flow management device 100 and the user terminal 200, and the user terminal 200 receives information after accessing the crowd flow management device 100. It may include a path that provides a connection path to transmit and receive. 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.

The storage medium 120 functions to temporarily or permanently store 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. This storage medium 120 may include internal memory and/or external memory, volatile memory such as DRAM, SRAM, or SDRAM, one time programmable ROM (OTPROM), PROM, EPROM, EEPROM, mask ROM, flash ROM, etc. , non-volatile memory such as NAND flash memory, or NOR flash memory, SSD. It may include a flash drive such as a compact flash (CF) card, SD card, Micro-SD card, Mini-SD card, Xd card, or memory stick, or a storage device such as an HDD.

The program storage unit 130 generates 3D modeling information of an area of interest including one or more pedestrian paths, and sets and presents the simulation environment, simulation conditions, and properties of objects included in the crowd based on the 3D modeling information. 1 The task of performing a crowd simulation, the task of calculating the first crowd simulation result based on the state change information about the object created according to the performance of the first crowd simulation, and applying a preset standard risk level to the first crowd simulation result. The task of calculating a risk score for one or more pedestrian paths, the task of generating crowd control information that determines whether to change the walking direction for a specific pedestrian path among the results of calculating the risk score, and the crowd control information that determines the change in walking direction. , an operation of performing a second crowd simulation by applying it to one or more of the simulation environment, simulation conditions, and properties of objects included in the crowd, by integrating state change information for each of the objects created according to the performance of the second crowd simulation. It is equipped with control software that performs tasks such as calculating second crowd simulation results and displaying and providing second crowd simulation results on 3D modeling information.

Database 140 may include a management database that stores various information for crowd flow simulation. For example, 3D modeling software for generating 3D modeling information of an area of interest may be stored in the management database. A simulation program capable of performing a first crowd simulation and a second crowd simulation may be stored in the management database. The management database may store first to sixth standard risks that can calculate simulation results into risk scores. The management database may store an artificial intelligence algorithm that predicts the risk score of a pedestrian path by inputting the crowd simulation environment for the pedestrian path, crowd simulation conditions, and object properties.

Additionally, the database 140 may include a user database that stores information on users who will be provided with the crowd flow management service. Here, the user's information includes basic information about the user such as the user's name, affiliation, personal information, gender, age, contact information, email, address, and image, and the user's ID (or email) and password. It may include information related to the connection, such as information about authentication (login), country of connection, location of connection, information about the device used for connection, and the connected network environment.

In addition, the user database includes the user's unique information, information and/or category history provided by users who access the crowd flow management application or crowd flow management site, preference information set by the user, resource usage information used by the user, and user information. Billing and payment information corresponding to resource usage may be stored.

The crowd flow management unit 150 may generate 3D modeling information of an area of interest including one or more pedestrian paths. The crowd flow management unit 150 may set the simulation environment, simulation conditions, and properties of objects included in the crowd based on 3D modeling information and perform the first crowd simulation. The crowd flow management unit 150 may calculate the first crowd simulation result based on state change information about the entity generated as the first crowd simulation is performed. The crowd flow management unit 150 may calculate a risk score for one or more pedestrian paths by applying a preset standard risk level to the first crowd simulation result. The crowd flow management unit 150 may generate crowd control information that determines whether to change the walking direction for a specific pedestrian path among the results of calculating the risk score. The crowd flow management unit 150 may perform a second crowd simulation by applying the crowd control information that determines the change in walking direction to one or more of the simulation environment, simulation conditions, and properties of objects included in the crowd. The crowd flow management unit 150 integrates the state change information for each object created as the second crowd simulation is performed to calculate the second crowd simulation result, and displays the second crowd simulation result on the 3D modeling information. can be provided.

The control unit 160 is a type of central processing unit and can control the entire operation of the crowd flow management device 100 by running control software mounted on the program storage unit 130. The control unit 160 may include all types of devices that can process data, such as a processor. Here, 'processor' may mean, for example, a data processing device built into hardware that has a physically structured circuit to perform a function expressed by code or instructions included in a program. Examples of data processing devices built into hardware include a microprocessor, central processing unit (CPU), processor core, multiprocessor, and application-specific integrated (ASIC). circuit) and FPGA (field programmable gate array), etc., but the scope of the present invention is not limited thereto.

FIG. 3 is a block diagram schematically illustrating the configuration of the crowd flow management unit of the crowd flow management device of FIG. 2, and FIGS. 4 to 11 are exemplary diagrams for explaining crowd flow management according to the present embodiment. In the following description, parts that overlap with the description of FIGS. 1 and 2 will be omitted. 3 to 11, the crowd flow management unit 150 includes a first generating unit 151, a performing unit 152, a calculating unit 153, a providing unit 154, a second generating unit 155, and It may include a processing unit 156.

The first generator 151 may generate 3D modeling information of an area of interest including one or more pedestrian paths. The first generator 151 may access the national land information platform through the network 300 and load a digital topographic map of the area of interest in order to generate 3D modeling information of the area of interest. The national land information platform is an online platform built to efficiently collect, manage, and provide nationally important geographic information. It can support access to and utilize a variety of geographic information in one place by utilizing geographic information system (GIS) and database technology. Here, geographical information may include topographic maps, land use information, road networks, administrative districts, etc. Additionally, the digital topographic map may include elevation differences and topographical characteristics of the terrain for the area of interest.

The first generator 151 may acquire geometric data related to one or more of roads, towns, and buildings for an area of interest based on a geographic information system (GIS). For this purpose, the first generator 151 may utilize satellite images, map information, GPS data, etc. The first generator 151 can build a 3D model that reflects the actual terrain by aligning and connecting the structures of roads, roads, and buildings on a plane based on the digital topographic map. In this embodiment, 3D modeling software can be used when building a 3D model, and may include Autodesk Maya, Blender, Autodesk 3ds Max, Cinema 4D, SketchUp, etc.

The first generator 151 may construct a mesh of the shape of one or more pedestrian paths among the roads included in the 3D model. In general, a mesh is a structure used in 3D graphics, and can mean that polygons are connected to vertices to form a three-dimensional surface. A mesh is a network of these polygons and can be expressed primarily using triangles or squares. Mesh is used to define the shape and surface of 3D objects, and can be utilized to effectively model real-world objects or environments in computer graphics or simulation. In this embodiment, constructing a mesh may mean representing the shape of an actual road or pedestrian path as a polygon and implementing it in 3D space. Through this, you can accurately model the width, curve, and slope of a road or pedestrian path and obtain visual results similar to reality in a 3D simulation environment.

Figure 4 is an example diagram showing the creation of 3D model information of an area of interest according to this embodiment. Referring to FIG. 4, 401 represents a digital topographic map of an area of interest loaded by accessing a national land information platform, 402 represents geographic data about an area of interest created using a geographic information system (GIS), 402 and 403 represents 3D modeling information or 3D model created by applying 3D modeling software to 401 and 402.

The execution unit 152 sets the simulation environment, simulation conditions, and properties of objects included in the crowd based on the 3D model of one or more pedestrian paths generated by the first generation unit 151 and performs the first crowd simulation. can do.

The execution unit 152 creates a crowd simulation environment in which the shape of the pedestrian path is meshed, including one or more of the width of the pedestrian path, the width reduction ratio of the pedestrian path, and the slope of the pedestrian path for each of the one or more pedestrian paths included in the 3D model. It can be built. The width of a pedestrian path can represent the width of the space where pedestrians walk. The rate of decrease in the width of a pedestrian path can be an indicator of the degree to which the pedestrian path becomes narrower at a specific point. The width reduction ratio of the pedestrian path can be mainly used to evaluate crowding or movement inconveniences that occur in areas where traffic becomes narrow. The slope of a pedestrian path is an indicator of the inclination or inclination of the ground and can indicate the inclination of the ground with respect to the horizontal plane. The slope of a pedestrian path may be a factor that indicates how steeply a pedestrian will ascend or descend while moving.

In this embodiment, the execution unit 152 may extract commercial areas excluding non-commercial areas and residential areas from areas of interest included in the 3D model. The execution unit 152 may construct a crowd simulation environment composed of a mesh of the shape of the pedestrian path including one or more of the width of the pedestrian path, the width reduction ratio of the pedestrian path, and the slope of the pedestrian path among the roads included in the commercial area. . Additionally, the execution unit 152 may include an event occurrence area that is included in the non-commercial area and the residential area but includes one or more of festivals and events in the commercial area.

The execution unit 152 may set crowd simulation conditions including one or more of the initial location of the crowd, walking direction, and walking speed. The execution unit 152 may set properties of objects, including physical radius, initial position, and walking speed for individually moving objects within the crowd simulation. Here, the physical radius of an object refers to the size of the actual space occupied by the object, and can mainly be expressed in length units such as radius or diameter. The physical radius of an object may contain information indicating the space required for the object to interact with or avoid collisions with other objects or the environment.

The execution unit 152 may apply the results of setting the crowd simulation conditions and the properties of the entity to the crowd simulation environment to perform a first crowd simulation that causes the entity to walk on the mesh.

Figure 5 is an exemplary diagram of an area of interest included in a commercial area and performing a first crowd simulation according to this embodiment. Referring to Figure 5, the area of interest included in the commercial area shows two subway stations, seven entrances (1 to 7), and 11 pedestrian paths (1 to 11). A different crowd simulation environment can be built for each pedestrian walkway. That is, for each pedestrian path, the shape of the pedestrian path may be composed of a mesh that includes one or more of the different walking path widths, walking path width reduction ratios, and walking path slopes. The execution unit 152 is. A first crowd simulation can be performed in which the crowd, applying the results of setting the crowd simulation conditions and the properties of the object, walks the mesh configured in each walking path (1 to 11).

The calculation unit 153 may calculate the first crowd simulation result based on state change information about the entity generated as the first crowd simulation is performed.

Figure 6 is an exemplary diagram of the first crowd simulation result. Referring to FIG. 6, 601 represents the first crowd simulation result for the area of interest shown in FIG. 5. 602 to 604 show first crowd simulation results for different areas of interest including one or more different pedestrian paths. The dots displayed on the walking path 601 to 604 may represent each entity included in the crowd, and the more dots there are, the more complex the walking path may be.

The calculation unit 153 may collect changes in the properties of an object over time, which are generated as the object walks the mesh, as state change information for the object. The calculation unit 153 may collect changes in the initial position and walking speed of objects that individually move over time within the mesh as state change information for the objects.

Based on the state change information about the object, the calculation unit 153 determines the crowd density, which integrates the density of objects walking on the walking path, the walking speed of the crowd, which integrates the walking speed of objects walking on the walking path, and the walking speed of the crowd at different locations. A first crowd simulation result may be produced that includes one or more of the converging flows of the crowd indicating the degree to which the entities in the crowd are converging on the pedestrian path. Here, the density of the crowd, the walking speed of the crowd, and the converging flow of the crowd can represent average values.

The calculation unit 153 may calculate a risk score for one or more pedestrian paths by applying a preset standard risk level to the first crowd simulation result. The calculation unit 153 may load the first to sixth standard risk levels from the database 140 to calculate a risk score for the pedestrian path.

The calculation unit 153 may apply the first to sixth standard risks to the first crowd simulation result and calculate the sum of the first to sixth scores corresponding to the first crowd simulation result as a risk score. there is.

Figure 7 is an exemplary diagram showing the first to sixth standard risk levels and the risk level of the pedestrian path stored in the database 140 according to this embodiment. Referring to FIG. 7, the first standard risk may be stored in the database 140 by assigning different first scores depending on the width of the pedestrian path. For example, if the width of the pedestrian path is 5m or more, 1-1 points (e.g., 1 point) are allocated, and if the width of the pedestrian path is less than 5m, 1-2 points (e.g., 2 points) are allocated. If the width of the walkway is less than 4m, points 1-3 (e.g., 3 points) are allocated, and if the width of the walkway is less than 3m, points 1-4 (e.g., 4 points) are allocated and stored. It can be. In this embodiment, the width of the pedestrian path and the corresponding score are not limited to the above-described example and may be changed.

The second standard risk may be stored in a database (140 in FIG. 2) by assigning different second scores according to the rate of reduction in the width of the pedestrian path. For example, if the width reduction ratio of the pedestrian path is 10% or less, a 2-1 score (e.g., 1 point) is assigned, and if the width reduction ratio of the pedestrian path is 25% or less, a 2-2 score is assigned (e.g., , 2 points) are allocated, and if the reduction ratio of the width of the pedestrian path is 50% or less, 2-3 points (e.g., 3 points) are allocated, and if the reduction ratio of the width of the pedestrian path is 50% or more, 2-4 points are allocated. (For example, 4 points) may be assigned and stored. In this embodiment, the width reduction ratio of the pedestrian path and the resulting score are not limited to the above-described example and may be changed.

The third standard risk may be stored in a database (140 in FIG. 2) by assigning different third scores depending on the slope of the walking path. For example, if the slope of the walking path is 3 degrees or less, 3-1 points (e.g., 1 point) are assigned, and if the slope of the walking path is 5 degrees or less, 3-2 points (e.g., 2 points) are assigned. If the slope of the walking path is 10 degrees or less, 3-3 points (e.g., 3 points) are allocated, and if the slope of the walking path is 10 degrees or more, 3-4 points (e.g., 4 points) are allocated. can be assigned and stored. In this embodiment, the slope of the pedestrian path and the corresponding score are not limited to the above-described example and may be changed.

The fourth standard risk can be stored in a database (140 in FIG. 2) by assigning different fourth scores according to the convergence flow, which is the degree to which individuals walking at different locations gather on a walking path. For example, if the converging flow is smooth, 4-1 points (e.g., 1 point) are allocated, and if the converging flow is normal, 4-2 points (e.g., 2 points) are allocated, If the merging flow is congested, a 4-3 score (e.g., 3 points) may be assigned, and if the merging flow is very congested, a 4-4 score (e.g., 4 points) may be assigned and stored. . In this embodiment, the criteria for determining whether the merging flow is smooth, normal, crowded, or very crowded may be determined in proportion to one or more of the width of the walking path, the rate of reduction in the width of the walking path, the slope of the walking path, and the crowd density and walking speed described later. You can. For example, if the crowd density of one pedestrian path is 7 or more and the walking speed is less than 0.5 m/s, the merging flow may be judged to be very crowded and a score of 4-4 may be assigned. In this embodiment, the merging flow of pedestrian paths and the resulting score are not limited to the above-described example and may be changed.

The fifth standard risk may be stored in a database (140 in FIG. 2) by assigning different fifth scores according to crowd density, which is the degree to which objects are concentrated on a pedestrian path. Here, crowd density can be expressed as the number of objects divided by the area of the pedestrian path (number of objects/square meter). For example, if the crowd density is 1 to 2, the 5-1 score (e.g., 1 point) is assigned, and if the crowd density is 3 to 4, the 5-2 score (e.g., 2 points) is assigned. is allocated, and if the crowd density is 5 to 6, 5-3 points (e.g., 3 points) are allocated, and if the crowd density is 7 or more, 5-4 points (e.g., 4 points) are allocated. and can be saved. In this embodiment, the crowd density and the resulting score are not limited to the above-described example and may be changed.

The sixth standard risk may be stored in a database (140 in FIG. 2) by assigning different sixth scores depending on the walking speed of objects on the walking path. In this embodiment, the walking speed of the individuals may be the same as the average walking speed of the crowd. For example, if the walking speed of the objects is 1m/s or more, score 6-1 (e.g., 1 point) is assigned, and if the walking speed of the objects is between 0.8m/s and 1m/s, score 6-2 is assigned. A score (e.g., 2 points) is allocated, and if the walking speed of the objects is 0.5 m/s to 0.8 m/s, a 6-3 score (e.g., 3 points) is allocated, and the walking speed of the objects is If is less than 0.5 m/s, the 6-4 score (for example, 4 points) may be assigned and stored. In this embodiment, the walking speed of the entities and the resulting score are not limited to the above-described examples and may be changed.

The calculation unit 153 may determine the risk level of the pedestrian path as one of concern, caution, caution, and seriousness by comparing the result calculated from the risk score and the preset seventh standard rating score.

As shown in FIG. 7, the risk level of the pedestrian path may be further stored in the database 140. The hazard level of a pedestrian walkway can indicate one of the following: Concern, Caution, Alert, or Severe. Additionally, the 7th standard grade score for determining the hazard grade of the pedestrian path is stored. For example, if the sum of the first to sixth scores is less than or equal to the 7-1 standard grade score (eg, 10 points), the risk grade of the pedestrian path may be determined as interest. In addition, if the sum of the first to sixth scores is a 7-2 standard grade score (for example, 11 to 14 points), the risk grade of the pedestrian path may be determined as caution. In addition, if the sum of the first to sixth scores is a 7-3 standard grade score (for example, 11 to 16 points), the risk grade of the pedestrian path may be determined by interest. Additionally, if the sum of the first to sixth scores is greater than or equal to the 7-4 standard grade score (for example, 19 points), the risk grade of the pedestrian path may be determined to be serious. In this embodiment, the seventh standard grade score is not limited to the above-described example and may be changed.

For example, the width of the walking path is less than 4 m, the width reduction ratio of the walking path is less than 25%, the slope of the walking path is less than 3 degrees, the merging flow of the walking path is congested, the crowd density is 5 to 6, and the walking speed is When is 0.5 to 0.8 m/s, applying the standard risk stored in the database 140 results in 1st-3rd scores (e.g., 3 points), 2nd-2nd scores (e.g., 2 points), and 3-1 score (e.g., 1 point), 4-3 score (e.g., 3 points), 5-3 score (e.g., 3 points), 6-3 score (e.g. , 3 points) are assigned, and the sum of the first to sixth scores becomes 15 points, so the risk level of the corresponding pedestrian path can be determined as a boundary.

FIG. 8 shows an example of calculating a risk score using the first crowd simulation result for the pedestrian paths 1 to 11 of FIG. 5. Referring to FIG. 8, the calculation unit 153 determines the risk level of pedestrian path 6 based on the result of calculating the risk score, and determines the grades of pedestrian path 2 to 6, 7, and 11. The risk level for pedestrian routes 1 and 8 can be determined as Caution, and the risk levels for pedestrian routes 9 and 10 can be determined as Severe.

In an optional embodiment, the calculation unit 153 generates a risk rating prediction result for the pedestrian path using a deep neural network model pre-trained to predict the risk rating for the pedestrian path based on the crowd simulation environment, crowd simulation conditions, and object properties. can do. In this embodiment, the deep neural network model may be a model trained in a supervised learning method using training data that uses the crowd simulation environment, crowd simulation conditions, and object properties as input, and the risk level for the pedestrian road as a label.

The calculation unit 153 may train an initially set deep neural network model using labeled training data using a supervised learning method. Here, the initially set deep neural network model is an initial model designed to construct a model that can predict the risk level of the pedestrian path, and the parameter values are set to arbitrary initial values. As the initial model is trained using the above-mentioned training data, the parameter values are optimized and completed as a prediction model that can accurately predict the risk level for the pedestrian path.

The providing unit 154 may display the risk level of the pedestrian path corresponding to the risk score of one or more pedestrian paths included in the 3D modeling information by displaying them in different colors. For example, the provision unit 154 displays blue on a pedestrian path whose risk level is determined to be of interest, displays yellow on a pedestrian path whose risk level of the pedestrian path is determined to be caution, and displays yellow on a pedestrian path whose risk level of the pedestrian path is determined to be caution. Orange can be displayed, and red can be provided for pedestrians whose risk level is determined to be serious.

Figure 9 is an example diagram showing risk levels for one or more pedestrian paths included in an area of interest in different colors. 902 to 904 are enlarged views of a portion of 901. From Figure 9, it is possible to intuitively check whether the risk level of a pedestrian path is Interest, Caution, Warning, or Serious.

The second generator 155 may generate crowd control information that determines whether to change the walking direction for a specific pedestrian path among the results of calculating the risk score. Here, a specific pedestrian path may include a pedestrian path whose risk level is determined to be serious. The second generator 155 may generate crowd control information that determines a walking direction different from the previous walking direction for a pedestrian path whose risk level is determined to be serious. Here, other walking directions may include one-way walking directions. For example, if the previous walking direction for a pedestrian path whose risk level was determined to be serious was two-way, crowd control information determined to be a one-way walking direction can be generated thereafter.

Figure 10 is an example diagram of a target area of interest in which crowd control information is reflected according to this embodiment. Referring to FIG. 10, as a result of performing the first crowd simulation on pedestrian paths 1 to 11 shown in FIG. 5, the risk score calculation result as shown in FIG. 8 was generated, of which for pedestrian paths 9 and 10. As the pedestrian level is determined to be serious, the walking direction for pedestrian routes 9 and 10 is determined to be one-way and marked as one-way.

The processing unit 156 performs a second crowd simulation by applying the crowd control information that determines the change in walking direction to one or more of the simulation environment, simulation conditions, and properties of objects included in the crowd applied when performing the first crowd simulation. can do. The processing unit 156 may calculate a second crowd simulation result by integrating state change information for each entity created as the second crowd simulation is performed. The processing unit 156 may provide the second crowd simulation result by displaying it on 3D modeling information.

Figure 11 is an example diagram of the first crowd simulation result and the second crowd simulation result according to this embodiment. Referring to FIG. 11, 1101 shows the first crowd simulation result for the area of interest shown in FIG. 5, that is, the same drawing as 601 in FIG. 6. 1102 shows the results of performing the second crowd simulation after performing the first crowd simulation and changing the walking direction for pedestrian path 9 1110, where the risk level of the pedestrian path was determined to be serious, to one-way. Comparing the results of performing the first crowd simulation and the second crowd simulation based on pedestrian path No. 9 (1110), when the walking direction is changed to one-way, the complexity of pedestrian path No. 9 (1110) is significantly lowered. , it can be seen that the stability of the crowd is improved.

Figure 12 is a block diagram schematically illustrating the configuration of a crowd flow management device according to another embodiment. In the following description, parts that overlap with the description of FIGS. 1 to 11 will be omitted. Referring to FIG. 12, a crowd flow management device 100 according to another embodiment may include a processor 170 and a memory 180.

In this embodiment, the processor 170 includes the communication unit 110, storage medium 120, program storage unit 130, database 140, crowd flow management unit 150, and control unit 160 disclosed in FIGS. 2 and 3. It can process the functions performed by .

This processor 170 can control the entire operation of the crowd flow management device 100. Here, 'processor' may mean, for example, a data processing device built into hardware that has a physically structured circuit to perform a function expressed by code or instructions included in a program. Examples of data processing devices built into hardware include processing devices such as microprocessors, central processing units, processor cores, multiprocessors, ASICs, and FPGAs, but the scope of the present invention is not limited thereto. .

The memory 180 is operatively connected to the processor 170 and can store at least one code in association with an operation performed by the processor 170.

Additionally, the memory 180 may perform a function of temporarily or permanently storing data processed by the processor 170 and may include data established as 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, such as volatile memory such as DRAM, SRAM, or SDRAM, OTPROM, PROM, EPROM, EEPROM, mask ROM, flash ROM, NAND flash memory, or NOR. It may include non-volatile memory such as 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.

Figure 13 is a flowchart for explaining the crowd flow management method according to this embodiment. In the following description, parts that overlap with the description of FIGS. 1 to 12 will be omitted. The crowd flow management method according to this embodiment will be described assuming that the crowd flow management device 100 is performed by the processor 170 with the help of peripheral components.

Referring to FIG. 13, in step S1310, the processor 170 may generate 3D modeling information of an area of interest including one or more pedestrian paths. When generating 3D modeling information, the processor 170 may access a national land information platform and load a digital topographic map for the area of interest. The processor 170 may acquire geographic data related to one or more of roads, roads, and buildings for an area of interest based on a geographic information system (GIS). The processor 170 can build a 3D model that reflects the actual terrain by aligning and connecting the structures of roads, roads, and buildings on a plane based on the digital topographic map. The processor 170 may configure the shape of one or more pedestrian paths among roads included in the 3D model into a mesh.

In step S1310, the processor 170 may set the simulation environment, simulation conditions, and properties of objects included in the crowd based on the 3D modeling information and perform the first crowd simulation. When performing the first crowd simulation, the processor 170 constructs a mesh of the shape of the pedestrian path including one or more of the width of the pedestrian path, the width reduction ratio of the pedestrian path, and the slope of the pedestrian path among the roads included in the 3D model. A crowd simulation environment can be built. When building a crowd simulation environment, the processor 170 may extract commercial areas excluding non-commercial areas and residential areas from areas of interest included in the 3D model. The processor 170 may include an event occurrence area that is included in the non-commercial area and the residential area but includes one or more of festivals and events in the commercial area. The processor 170 may construct a crowd simulation environment in which the shape of the pedestrian path including one or more of the width of the pedestrian path, the width reduction ratio of the pedestrian path, and the slope of the pedestrian path among the roads included in the commercial area are meshed. After building the crowd simulation environment, the processor 170 may set crowd simulation conditions including one or more of the initial location of the crowd, walking direction, and walking speed. Processor 170 may set properties of objects, including physical radius, initial position, and walking speed for individual moving objects within a crowd simulation. The processor 170 may apply the results of setting the crowd simulation conditions and the properties of the object to the crowd simulation environment to perform a first crowd simulation that causes the object to walk on the mesh.

In step S1330, the processor 170 may calculate a first crowd simulation result based on state change information about the entity generated as the first crowd simulation is performed. When calculating the first crowd simulation result, the processor 170 may collect changes in the properties of the object over time, which are generated as the object walks the mesh, as state change information for the object. Based on the state change information about the object, the processor 170 determines the crowd density, which integrates the density of objects walking on the walking path, the walking speed of the crowd, which integrates the walking speed of objects walking on the walking path, and the crowd walking speed at different locations. A first crowd simulation result may be produced that includes one or more of the converging flows of the crowd indicating the degree to which entities are converging on the pedestrian path.

In step S1340, the processor 170 may calculate a risk score for one or more pedestrian paths by applying a preset standard risk level to the first crowd simulation result. When calculating the risk score, the processor 170 provides a first standard risk score in which different first scores are assigned according to the width of a pedestrian path included in a random target area, and a second standard risk score that is different depending on the rate of reduction in the width of the pedestrian path. A second standard risk level in which scores are assigned, a third standard risk level in which different scores are assigned according to the slope of the walking path, and a converging flow as the degree to which individuals walking in different locations gather on the walking path. A fourth standard risk level to which different fourth scores are assigned, a fifth standard risk level to which different fifth scores are assigned according to the crowd density as the degree to which objects are concentrated on the walking path, and a different risk rating according to the walking speed of objects in the walking path. The standard risk including the sixth standard risk to which 6 points are assigned can be loaded from the database 140. The processor 170 may apply the standard risk to the first crowd simulation result and calculate the sum of the first to sixth scores corresponding to the first crowd simulation result as a risk score. The processor 170 may determine the risk level of the pedestrian path as one of concern, caution, caution, and serious by comparing the result calculated from the risk score and the seventh standard rating score. The processor 170 may provide the risk level of the pedestrian path corresponding to the risk score to one or more pedestrian paths included in the 3D modeling information by displaying different colors.

In step S1350, the processor 170 may generate crowd control information that determines whether to change the walking direction for a specific pedestrian path among the results of calculating the risk score. The processor 170 may generate crowd control information that determines a walking direction different from the previous walking direction for a specific walking path. Here, the other walking direction may be a one-way walking direction.

In an optional embodiment, processor 170 may generate a risk rating prediction result for a pedestrian path using a deep neural network model pre-trained to predict a risk rating for a pedestrian path based on the crowd simulation environment, crowd simulation conditions, and properties of objects. You can. In this embodiment, the deep neural network model may be a model trained in a supervised learning method using training data that uses the crowd simulation environment, crowd simulation conditions, and object properties as input, and the risk level for the pedestrian road as a label.

In an optional embodiment, after generating the crowd control information, the processor 170 applies the crowd control information that determines the change in walking direction to one or more of the simulation environment, simulation conditions, and properties of objects included in the crowd to create a second Crowd simulation can be performed. The processor 170 may calculate a second crowd simulation result by integrating state change information for each object created as the second crowd simulation is performed. The processor 170 may provide the second crowd simulation result by displaying it on the 3D modeling information.

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. At this time, the media includes magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and ROM. , RAM, flash memory, etc., may include hardware devices specifically configured to store and execute program instructions.

Meanwhile, the computer program may be designed and configured specifically for the present invention, or may be known and available to those skilled in the art of computer software. Examples of computer programs may include not only machine language code such as that created by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like.

In the specification (particularly in the claims) of the present invention, the use of the term “above” and similar referential terms may refer to both the singular and the plural. In addition, when a range is described in the present invention, it includes the invention to which individual values within the range are applied (unless there is a statement to the contrary), and each individual value constituting the range is described in the detailed description of the invention. It's the same.

Unless there is an explicit order or statement to the contrary regarding the steps constituting the method according to the invention, the steps may be performed in any suitable order. The present invention is not necessarily limited by the order of description of the above steps. The use of any examples or illustrative terms (e.g., etc.) in the present invention is merely to describe the present invention in detail, and unless limited by the claims, the scope of the present invention is limited by the examples or illustrative terms. It doesn't work. Additionally, those skilled in the art will recognize that various modifications, combinations and changes may be made depending on design conditions and factors within the scope of the appended claims or their equivalents.

Accordingly, the spirit of the present invention should not be limited to the above-described embodiments, and the scope of the patent claims described below as well as all scopes equivalent to or equivalently changed from the scope of the claims are within the scope of the spirit of the present invention. It will be said to belong to

100: Crowd flow management device
200: user terminal
300: Network

Claims (11)

A crowd flow management method performed by a processor of a crowd flow management device, comprising:
Generating 3D modeling information of an area of interest including one or more pedestrian paths;
Based on the 3D modeling information, setting a simulation environment, simulation conditions, and properties of objects included in the crowd and performing a first crowd simulation;
calculating a first crowd simulation result based on state change information about the entity generated as the first crowd simulation is performed;
calculating a risk score for the one or more pedestrian paths by applying a preset standard risk level to the first crowd simulation result; and
A step of generating crowd control information that determines whether to change the walking direction for a specific pedestrian path among the results of calculating the risk score,
The step of performing the first crowd simulation is:
A crowd simulation environment composed of a mesh of the shape of the pedestrian path including one or more of the width of the pedestrian path, the width reduction ratio of the pedestrian path, and the slope of the pedestrian path among the roads included in the 3D model based on the 3D modeling information. steps to build;
Setting crowd simulation conditions including one or more of the initial location, walking direction, and walking speed of the crowd;
setting properties of objects, including physical radius, initial position, and walking speed for the objects individually moving within the crowd simulation;
Applying a result of setting the crowd simulation conditions and a result of setting properties of the entity to the crowd simulation environment, performing a first crowd simulation to have the entity walk on the mesh,
The step of calculating the first crowd simulation result is,
collecting changes in the properties of the object over time generated by the object walking the mesh as state change information for the object; and
Based on the state change information about the object, the density of the crowd that integrates the density of the objects walking on the walking path, the walking speed of the crowd that integrates the walking speed of the objects walking on the walking path, and the walking speed of the crowd walking at different locations. Producing a first crowd simulation result comprising one or more of a converging flow of crowds indicative of the extent to which entities are converging on the pedestrian walkway;
The step of calculating the risk score is,
A first standard risk in which different first scores are assigned according to the width of the pedestrian path included in a random target area, and a second standard risk in which different second scores are assigned according to the rate of reduction in the width of the pedestrian path, A third standard risk level in which different third scores are assigned according to the slope of the walking path, and a different fourth score is assigned according to the converging flow as the degree to which individuals walking at different locations gather on the walking path. A fourth standard risk, a fifth standard risk in which different scores are assigned according to the crowd density, which is the degree to which objects are concentrated in the walking path, and a sixth standard in which different scores are assigned according to the walking speed of objects in the walking path. loading a standard risk including a sixth standard risk;
Applying the reference risk to the first crowd simulation result and calculating a sum of first to sixth scores corresponding to the first crowd simulation result as a risk score; and
Comprising the step of comparing the result calculated from the risk score and a preset seventh standard rating score to determine the risk rating of the pedestrian path as one of concern, caution, caution, and seriousness,
In the step of loading the standard risk,
The first standard risk level is assigned a point of 1-1 when the width of the pedestrian path is 5 m or more, a point 1-2 is assigned when the width of the pedestrian path is 4 m or more but less than 5 m, and a score of 1-2 is assigned when the width of the pedestrian path is 3 m or more but less than 4 m. In this case, points 1 to 3 are allocated, and if the width of the pedestrian path is less than 3 m, points 1 to 4 are allocated,
The second standard risk is assigned a 2-1 score when the width reduction rate of the pedestrian path is 10% or less, and a 2-2 score is assigned when the width reduction rate of the pedestrian path is more than 10% and 25% or less, If the width reduction ratio of the pedestrian path is more than 15% and less than 50%, 2-3 points are allocated, and if the width reduction ratio of the pedestrian path is more than 50%, 2-4 points are allocated,
The third standard risk is assigned a score of 3-1 when the slope of the walking path is 3 degrees or less, and a score of 3-2 is assigned when the slope of the walking path is more than 3 degrees and less than or equal to 5 degrees, and the slope of the walking path is If the slope of the pedestrian path exceeds 5 degrees but is less than 10 degrees, 3-3 points are allocated, and if the slope of the pedestrian path exceeds 10 degrees, 3-4 points are allocated,
The fourth standard risk is assigned a 4-1 score when the merging flow is smooth, a 4-2 score when the merging flow is normal, and a 4-3 score when the merging flow is congested. is assigned, and if the merging flow is very congested, 4-4 points are assigned, and the criteria for determining whether the merging flow is smooth, normal, congested, or very congested are the width of the pedestrian path and the rate of reduction in the width of the pedestrian path. , determined in proportion to one or more of the slope of the pedestrian path, the crowd density, and the walking speed,
The fifth standard risk is calculated by dividing the number of objects by the area of the pedestrian path. If the crowd density is 1 to 2, a score of 5-1 is assigned, and if the crowd density is 3 to 4, a score of 5-2 is assigned. Points are allocated, and if the crowd density is 5 to 6, 5-3 points are allocated, and if the crowd density is 7 or more, 5-4 points are allocated,
The sixth standard risk is assigned a score of 6-1 when the walking speed of the entities is 1 m/s or more, and a score of 6-2 is assigned when the walking speed of the entities is more than 0.8 m/s and less than 1 m/s. If the walking speed of the objects is more than 0.5 m/s and less than 0.8 m/s, 6-3 points are allocated, and if the walking speeds of the objects are 0.5 m/s or less, 6-4 points are allocated,
How to manage crowd flow. According to claim 1,
The step of generating the 3D modeling information is,
Accessing a national land information platform and loading a digital topographic map for an area of interest;
Obtaining geographic data related to one or more of roads, roads, and buildings for the area of interest based on a geographic information system (GIS);
Building a 3D model reflecting the actual terrain by aligning and connecting the structures of the roads, roads, and buildings on a plane based on the digital topographic map; and
Comprising the step of configuring the shape of one or more pedestrian paths among the roads included in the 3D model as a mesh,
How to manage crowd flow. delete According to claim 1,
The step of building the crowd simulation environment is,
extracting commercial areas excluding non-commercial areas and residential areas from the area of interest included in the 3D model; and
including an event occurrence area that is included in the non-commercial area and the residential area but includes one or more of festivals and events in the commercial area; and
Constructing a crowd simulation environment composed of a mesh of the shape of the pedestrian path including one or more of the width of the pedestrian path, the width reduction ratio of the pedestrian path, and the slope of the pedestrian path among the roads included in the commercial area. ,
How to manage crowd flow. delete delete According to claim 1,
After calculating the risk score,
Further comprising providing a risk level of the pedestrian path corresponding to the risk score to the one or more pedestrian paths included in the 3D modeling information by displaying different colors,
How to manage crowd flow. According to claim 1,
The step of generating the crowd control information is,
Comprising the step of generating crowd control information that determines a walking direction different from the previous walking direction for the specific walking path,
How to manage crowd flow. According to claim 1,
After generating the crowd control information,
performing a second crowd simulation by applying the crowd control information that determines the change in walking direction to one or more of the simulation environment, the simulation conditions, and attributes of objects included in the crowd;
calculating a second crowd simulation result by integrating state change information for each of the entities generated as the second crowd simulation is performed; and
Comprising the step of displaying and providing the second crowd simulation result on the 3D modeling information,
How to manage crowd flow. A computer-readable recording medium storing a computer program for executing the method of any one of claims 1, 2, 4, and 7 to 9 using a computer. As a crowd flow management device,
processor; and
a memory operably connected to the processor and storing at least one code to be executed by the processor;
When the memory is executed through the processor, the processor generates 3D modeling information of an area of interest including one or more pedestrian paths, and
Based on the 3D modeling information, set the simulation environment, simulation conditions, and properties of objects included in the crowd and perform a first crowd simulation,
Calculating a first crowd simulation result based on state change information about the entity generated as the first crowd simulation is performed,
Calculate a risk score for the one or more pedestrian paths by applying a preset standard risk level to the first crowd simulation result,
Among the results of calculating the risk score, a code is stored that generates crowd control information that determines whether to change the walking direction for a specific pedestrian path,
The memory allows the processor to:
When performing the first crowd simulation, the shape of the pedestrian path including one or more of the width of the pedestrian path, the width reduction ratio of the pedestrian path, and the slope of the pedestrian path among roads included in the 3D model based on the 3D modeling information. Build a crowd simulation environment composed of a mesh,
Set crowd simulation conditions including one or more of the initial position, walking direction, and walking speed of the crowd,
set properties of objects, including physical radius, initial position, and walking speed for the objects individually moving within the crowd simulation;
storing code that causes a first crowd simulation to be performed by causing the entity to walk on the mesh by applying a result of setting the crowd simulation conditions and a result of setting properties of the entity to the crowd simulation environment;
The memory allows the processor to:
When calculating the first crowd simulation result, changes in the properties of the entity over time generated by the entity walking the mesh are collected as state change information for the entity,
Based on the state change information about the object, the density of the crowd that integrates the density of the objects walking on the walking path, the walking speed of the crowd that integrates the walking speed of the objects walking on the walking path, and the walking speed of the crowd walking at different locations storing code that causes to produce a first crowd simulation result comprising one or more of a converging flow of crowds indicative of the extent to which entities are converging on said walkway;
The memory allows the processor to:
When calculating the risk score, a first standard risk level in which different first scores are assigned according to the width of a pedestrian path included in an arbitrary target area, and a different second score is assigned according to the rate of reduction in the width of the pedestrian path. a second standard risk level, a third standard risk level in which different scores are assigned according to the slope of the walking path, and a converging flow as the degree to which individuals walking at different locations gather on the walking path. A fourth standard risk to which different fourth scores are assigned, a fifth standard risk to which different fifth scores are assigned according to crowd density as the degree to which individuals are concentrated in the pedestrian path, and a fifth standard risk to which different fourth scores are assigned according to the walking speed of individuals in the pedestrian path. Loading the reference risk including the sixth reference risk with different sixth scores assigned,
Applying the reference risk to the first crowd simulation result, calculating the sum of the first to sixth scores corresponding to the first crowd simulation result as a risk score,
Storing a code that causes the risk level of the pedestrian path to be determined as one of concern, caution, caution, and serious by comparing the result calculated from the risk score and a preset seventh standard rating score,
The memory allows the processor to:
When loading the standard risk, the first standard risk is assigned a 1-1 point when the width of the pedestrian path is 5 m or more, and a 1-2 point is assigned when the width of the pedestrian path is 4 m or more and less than 5 m, and If the width of the pedestrian path is 3m or more but less than 4m, points 1 to 3 are allocated, and if the width of the pedestrian path is less than 3m, points 1 to 4 are allocated,
The second standard risk is assigned a score of 2-1 when the width reduction ratio of the pedestrian path is 10% or less, and a score 2-2 is assigned when the width reduction ratio of the pedestrian path is greater than 10% and less than 25%, If the width reduction ratio of the pedestrian path is more than 15% and less than 50%, 2-3 points are allocated, and if the width reduction ratio of the pedestrian path is more than 50%, 2-4 points are allocated,
The third standard risk is assigned a score of 3-1 when the slope of the walking path is 3 degrees or less, and a score of 3-2 is assigned when the slope of the walking path is more than 3 degrees and less than or equal to 5 degrees, and the slope of the walking path is If the slope of the pedestrian path exceeds 5 degrees but is less than 10 degrees, 3-3 points are allocated, and if the slope of the pedestrian path exceeds 10 degrees, 3-4 points are allocated,
The fourth standard risk is assigned a 4-1 score when the merging flow is smooth, a 4-2 score when the merging flow is normal, and a 4-3 score when the merging flow is congested. is assigned, and if the merging flow is very congested, 4-4 points are assigned, and the criteria for determining whether the merging flow is smooth, normal, congested, or very congested are the width of the pedestrian path and the rate of reduction in the width of the pedestrian path. , determined in proportion to one or more of the slope of the pedestrian path, the crowd density, and the walking speed,
The fifth standard risk is calculated by dividing the number of objects by the area of the pedestrian path. If the crowd density is 1 to 2, a score of 5-1 is assigned, and if the crowd density is 3 to 4, a score of 5-2 is assigned. Points are allocated, and if the crowd density is 5 to 6, 5-3 points are allocated, and if the crowd density is 7 or more, 5-4 points are allocated,
The sixth standard risk is assigned a score of 6-1 when the walking speed of the entities is 1 m/s or more, and a score of 6-2 is assigned when the walking speed of the entities is more than 0.8 m/s and less than 1 m/s. If the walking speed of the objects is more than 0.5 m/s and less than 0.8 m/s, the 6-3 score is assigned, and if the walking speed of the objects is less than 0.5 m/s, the 6-4 score is assigned. saving code,
Crowd flow management device.

Images