Method, system, and non-transitory computer-readable recording medium for predicting crowd density risk

Abstract

According to one aspect of the present invention, a method for predicting the risk of crowd density comprises the steps of: acquiring flux information about a crowd included in a target area; and predicting the risk of crowd density in the target area by referring to information output by inputting the flux information to a voluntary threshold analysis model. The voluntary threshold analysis model is a model for simulating the risk to the crowd by referring to a propagation pattern in which due to a movement pattern of a first unit crowd having a density not smaller than a preset threshold level in the crowd, the density of a second unit crowd which was less than the threshold level is changed to be the threshold level or more.

Description

Method, system, and non-transient computer-readable recording medium for predicting crowd density risk

[0001] The present invention relates to a method, a system, and a non-transient computer-readable recording medium for predicting crowd density risk.

[0002] Recently, there has been an increase in safety accidents occurring when large numbers of people are densely packed in a limited space. As seen in cases such as the Itaewon tragedy in 2022, accidents do not occur simply because there are many people; rather, the risk increases rapidly when the flow of the crowd is not properly controlled. Such uncontrolled crowd movement leads to unpredictable dangers and spreads rapidly. Therefore, to prevent safety accidents in situations where crowds are dense, it is necessary to accurately analyze the level of risk in such circumstances.

[0003] However, existing crowd density risk analysis technologies are limited to evaluating risk primarily based on spatial area and the number of people within it, failing to adequately reflect the dynamic characteristics of crowds in risk prediction. To overcome this limitation, an analysis that meticulously considers crowd flow and movement patterns, rather than relying on simple numerical analysis, is required.

[0004] <Prior Art Literature>

[0005] <Patent Literature>

[0006] (Patent Document 1) Registered Patent Publication No. 10-2706119 (September 9, 2024)

[0007] (Patent Document 2) Published Patent Application No. 10-2025-0044605 (April 1, 2025)

[0008] (Patent Document 3) Registered Patent Publication No. 10-2674706 (June 10, 2024)

[0009] (Patent Document 4) Published Patent Application No. 10-2018-0094734 (Aug. 24, 2018)

[0010] (Patent Document 5) Registered Patent Publication No. 10-2674706 (June 10, 2024)

[0011] The present invention aims to solve all the problems of the aforementioned prior art.

[0012] In addition, the present invention has another objective of accurately predicting the risk of crowd density by acquiring information regarding not only crowd density but also movement and propagation patterns and analyzing this information in real time.

[0013] In addition, another objective of the present invention is to enable crowds and safety authorities to prevent safety accidents in advance by providing visual or auditory notification information based on risk prediction.

[0014] A representative configuration of the present invention for achieving the above objective is as follows.

[0015] According to one aspect of the present invention, a method for predicting crowd density risk is provided, comprising the steps of: acquiring flux information of a crowd included in a target area; and predicting crowd density risk of the target area by referring to information output by inputting the flux information into a spontaneous threshold analysis model, wherein the spontaneous threshold analysis model is a model that simulates the risk to the crowd by referring to a propagation pattern in which a second unit crowd, whose density was below the threshold level, changes to the threshold level or higher by means of a movement pattern of a first unit crowd whose density within the crowd is above a preset threshold level.

[0016] According to another aspect of the present invention, a system for predicting crowd density risk is provided, comprising: a data acquisition unit for acquiring flux information of a crowd included in a target area; and an analysis unit for predicting crowd density risk of the target area by referring to information output by inputting the flux information into a spontaneous threshold analysis model, wherein the spontaneous threshold analysis model is a model that simulates the risk to the crowd by referring to a propagation pattern in which a second unit crowd, whose density was below the threshold level, changes to the threshold level or higher by means of a movement pattern of a first unit crowd whose density within the crowd is above a preset threshold level.

[0017] In addition to this, other methods for implementing the present invention, other systems, and non-transient computer-readable recording media on which a computer program for executing said methods is recorded are further provided.

[0018] According to the present invention, information regarding not only crowd density but also movement patterns and propagation patterns is obtained and analyzed in real time, thereby accurately predicting the risk of crowd density.

[0019] In addition, according to the present invention, visual or auditory notification information is provided based on risk prediction, allowing crowds and safety authorities to prevent safety accidents in advance.

[0020] FIG. 1 is a diagram showing the schematic configuration of an overall system for predicting crowd density risk according to one embodiment of the present invention.

[0021] FIG. 2 is a drawing illustrating in detail the internal configuration of a risk prediction system according to one embodiment of the present invention.

[0022] FIG. 3 is a diagram exemplarily illustrating a process for predicting crowd density risk according to one embodiment of the present invention.

[0023] <Explanation of Symbols>

[0024] 100: Communication network

[0025] 200: Flow information sensor module

[0026] 300: Risk Prediction System

[0027] 310: Data Acquisition Unit

[0028] 320: Analysis Department

[0029] 330: Notification Information Provider

[0030] 340: Communications Department

[0031] 350: Control unit

[0032] 400: Device

[0033] The following detailed description of the invention refers to the accompanying drawings, which illustrate specific embodiments in which the invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention. It should be understood that various embodiments of the invention are different but need not be mutually exclusive. For example, specific shapes, structures, and characteristics described herein may be modified from one embodiment to another without departing from the spirit and scope of the invention. It should also be understood that the location or arrangement of individual components within each embodiment may be modified without departing from the spirit and scope of the invention. Accordingly, the following detailed description is not meant to be limiting, and the scope of the invention should be understood to encompass the scope claimed by the claims and all equivalents thereof. Similar reference numerals in the drawings indicate identical or similar components across various aspects.

[0034] Additionally, terms including ordinal numbers, such as first, second, etc., may be used to describe various components, but said components are not limited by said terms. Such terms are used solely to distinguish one component from another. For example, without departing from the scope of the present invention, the first component may be named the second component, and similarly, the second component may be named the first component. The term "and / or" includes a combination of a plurality of related described items or any of a plurality of related described items.

[0035] Hereinafter, in order to enable a person skilled in the art to easily practice the present invention, various preferred embodiments of the present invention will be described in detail with reference to the attached drawings.

[0036] Configuration of the entire system

[0037] FIG. 1 is a diagram showing the schematic configuration of an overall system for predicting crowd density risk according to one embodiment of the present invention.

[0038] As illustrated in FIG. 1, the entire system according to one embodiment of the present invention may include a communication network (100), a flux information sensor module (200), a risk prediction system (300), and a device (400).

[0039] First, a communication network (100) according to one embodiment of the present invention can be configured regardless of the mode of communication, such as wired communication or wireless communication, and can be configured as various communication networks such as a Local Area Network (LAN), a Metropolitan Area Network (MAN), or a Wide Area Network (WAN). Preferably, the communication network (100) referred to in this specification may be the known Internet or the World Wide Web (WWW). However, the communication network (100) may include, in at least a part thereof, a known wired / wireless data communication network, a known telephone network (e.g., a Public Switched Telephone Network (PSTN)), or a known wired / wireless television communication network, without being limited thereto.

[0040] For example, the communication network (100) may be a wireless data communication network and may implement conventional communication methods such as WiFi communication, WiFi-Direct communication, Long Term Evolution (LTE) communication, 5G communication, Bluetooth communication (including Bluetooth Low Energy (BLE) communication), infrared communication, ultrasonic communication, etc., in at least a part thereof.

[0041] Next, a flow information sensor module (200) according to one embodiment of the present invention is a module for measuring and detecting crowd flow (flux) information in real time and can communicate with a risk prediction system (300) through a communication network (100).

[0042] A flow information sensor module (200) according to one embodiment of the present invention may include an image module such as a CCTV, a LiDAR sensor module, a radar sensor module, an infrared (IR) sensor module, an ultrasonic sensor module, etc. However, the flow information sensor module (200) according to the present invention is not necessarily limited to those listed above, and may be configured to include or combine a thermal imaging sensor module, an environmental sensor module (e.g., a temperature, humidity, carbon dioxide concentration measuring sensor), an IMU (Inertial Measurement Unit) sensor module, etc., in order to more precisely measure the flux information of a crowd, such as the location, direction of movement, speed of movement, and density of the crowd, within the scope of achieving the purpose of the present invention.

[0043] Meanwhile, the flow information sensor module (200) according to the present invention can measure or detect crowd flow information based on a sensor module installed at a single point, but can also measure or detect crowd flow information with higher accuracy based on sensor modules installed at multiple points (e.g., in combination).

[0044] Next, a risk prediction system (300) according to one embodiment of the present invention can communicate with a flow information sensor module (200) and a device (400) through a communication network (100), acquire crowd flux information received from the flow information sensor module (200), and predict the risk of crowd density in a target area by referring to the information output by inputting the flux information into a voluntary threshold analysis model. Here, the voluntary threshold analysis model may be a model that simulates the risk to the crowd by referring to a propagation pattern in which a second unit crowd, whose density was below the threshold level, changes to a threshold level or higher due to the movement pattern of a first unit crowd whose density within the crowd is above a preset threshold level. Such a risk prediction system (300) may be a system that runs on a server equipped with memory means and equipped with a microprocessor to have computational capabilities.

[0045] In addition, the voluntary threshold analysis model according to one embodiment of the present invention may be a model that predicts the risk affecting a crowd by performing a simulation that reflects the non-linear propagation characteristics of a crowd (e.g., a characteristic in which risk is amplified or spread in a non-proportional or difficult-to-predict manner within the entire crowd set by affecting other adjacent or related units of a crowd, as a result of behavioral changes in some units of a crowd (e.g., density, movement, congestion, etc.) within the crowd) in conjunction with an agent-based model (ABM) or a feedback loop. Here, an agent-based model may refer to a model that analyzes how collective system behavior manifests as individual agents act and interact according to defined rules.

[0046] In addition, the risk prediction system (300) may input simulation results based on a voluntary threshold analysis model into a supervised learning-based prediction model (e.g., logistic regression, decision tree, random forest, etc.) to improve the accuracy of crowd density and risk prediction, and predict the risk affecting the crowd by referring to the output results from the prediction model. In this case, the prediction model may be a model that undergoes supervised learning using simulation results based on a voluntary threshold analysis model and the risk determined in response thereto (e.g., risk calculated or determined by a risk expert) as training data.

[0047] The configuration and function of the risk prediction system (300) according to the present invention will be examined in detail through the following detailed description.

[0048] Next, the device (400) according to one embodiment of the present invention is a digital device that includes a function to communicate with the risk prediction system (300), and any digital device equipped with memory means and equipped with a microprocessor to have computational capabilities, such as a fax machine, smartphone, tablet, smart watch, smart band, smart glasses, desktop computer, laptop computer, workstation, PDA, web pad, mobile phone, etc., can be adopted as the device (400) according to the present invention.

[0049] In addition, in one embodiment of the present invention, the device (400) may include not only digital devices carried by individuals but also various communication means such as digital displays, electronic display boards, and speaker systems installed for crowd management and safety response. Here, in cases where a crowd is concentrated in a specific area, such as during a rally or large-scale event, the device (400) may include a broadcasting system or guidance system operated by the organizer of the rally, or communication means exclusively used by public safety authorities such as fire departments or police stations. For example, an emergency disaster text message system, a wireless broadcasting system, a dedicated radio system, and digital signage operated by a public safety agency may be utilized as the device (400) according to the present invention, thereby providing notification information to the crowd in real time to alert them to dangerous situations.

[0050] Meanwhile, the device (400) may further include an application program for performing functions according to the present invention. Such an application may exist in the form of a program module within the device (400). The nature of such a program module may generally be similar to the components of the risk prediction system (300) described below (i.e., data acquisition unit (310), analysis unit (320), notification information provision unit (330), communication unit (340), and control unit (350)). Here, at least a part of the application may be replaced with a hardware device or firmware device capable of performing substantially the same or equivalent functions as needed.

[0051] Configuration of the risk prediction system

[0052] Below, we will examine the internal configuration of the risk prediction system (300) that performs important functions for the implementation of the present invention and the functions of each component.

[0053] FIG. 2 is a drawing illustrating in detail the internal configuration of a risk prediction system (300) according to one embodiment of the present invention.

[0054] As illustrated in FIG. 2, according to one embodiment of the present invention, a risk prediction system (300) may include a data acquisition unit (310), an analysis unit (320), a notification information provision unit (330), a communication unit (340), and a control unit (350). According to one embodiment of the present invention, the data acquisition unit (310), the analysis unit (320), the notification information provision unit (330), the communication unit (340), and the control unit (350) of the risk prediction system (300) may be program modules, at least some of which communicate with an external system (not shown). Such program modules may be included in the risk prediction system (300) in the form of an operating system, an application program module, and other program modules, and may be physically stored in various known storage devices. Additionally, such program modules may be stored in a remote storage device capable of communicating with the risk prediction system (300). Meanwhile, such program modules include, but are not limited to, routines, subroutines, programs, objects, components, data structures, etc. that perform specific tasks or execute specific abstract data types as described below according to the present invention.

[0055] Meanwhile, although the risk prediction system (300) has been described as above, this description is exemplary, and it is obvious to those skilled in the art that at least some of the components or functions of the risk prediction system (300) may be implemented within a device (400) or server (not shown) or included within an external system (not shown) as needed.

[0056] First, a data acquisition unit (310) according to one embodiment of the present invention can perform the function of acquiring flow information of a crowd included in a target area. Here, the target area may refer to an area subject to risk prediction, and the flow information may include crowd density (e.g., number of crowds relative to area), location, direction of movement, speed of movement, movement path, distance between crowds, etc.

[0057] Specifically, the data acquisition unit (310) can acquire information regarding the number, location, direction of movement, speed of movement, etc. of a crowd specified from a camera image module (e.g., CCTV) of a target area, information regarding the location, direction of movement, speed of movement, shape of a crowd specified from a lidar sensor module of a target area, or information regarding the location, direction of movement, speed of movement, etc. of a crowd (specifically, an object) specified from a Bluetooth module (or WIFI module) of a target area as crowd flow information.

[0058] Meanwhile, the data acquisition unit (310) according to the present invention can improve analysis efficiency by performing preprocessing and filtering of the acquired information to provide more reliable information. For example, the data acquisition unit (310) can perform a preprocessing process for flow information containing noise or flow information that is falsely detected, convert data formats that differ by flow information sensor module (200) into a preset format, and perform a time synchronization process to sort information collected from different flow information sensor modules (200) according to the same standard.

[0059] Meanwhile, it should be noted that the types of information acquired by the data acquisition unit (310) according to the present invention and the methods of preprocessing the information are not necessarily limited to those listed above, and can be varied within the scope of achieving the purpose of the present invention. For example, if the flow information is acquired in the form of point cloud data, the data may be converted into distance information, and if the flow information is acquired in the form of image data, preprocessing such as filtering metadata may be performed.

[0060] Next, an analysis unit (320) according to one embodiment of the present invention can predict the risk of crowd density in a target area by inputting flow information obtained from a data acquisition unit (310) into a voluntary threshold analysis model and referring to the output information. Here, the voluntary threshold analysis model may be a model that simulates the risk to a crowd by referring to a propagation pattern in which a second unit crowd, whose density was below the threshold level, changes to a threshold level or higher due to the movement pattern of a first unit crowd, whose density within the crowd is above a preset threshold level.

[0061] Specifically, the analysis unit (320) can set a threshold level of crowd density based on the crowd (e.g., the number of crowds) distributed within an area of ​​a specific size. For example, if the number of crowds distributed within an area of ​​a specific size is greater than a predetermined level, the analysis unit (320) can determine that the area has exceeded the threshold level. Based on this criterion, the analysis unit (320) can define the crowds distributed within the area exceeding the threshold level as a first unit crowd and analyze their movement patterns.

[0062] Additionally, the analysis unit (320) can predict whether there will be a change in crowd density by analyzing whether the movement pattern of the first unit crowd affects the crowd density of an adjacent area or another area when the crowd density of the area where the first unit crowd is located exceeds a threshold level. At this time, the crowd distributed in the adjacent or other area that is affected (or whose crowd density changes) (specifically, the crowd distributed within an area of ​​a predetermined size) can be defined as the second unit crowd, and the analysis unit (320) can simulate and predict the risk of crowd density in the target area by referring to the propagation pattern in which the second unit crowd, whose crowd density was below the threshold level, changes to above the threshold level.

[0063] To perform the above prediction more precisely, the analysis unit (320) can model individual crowds as independent simulation units (agents). Additionally, the analysis unit (320) can simulate movement paths and interactions over time by referring to factors such as the movement speed, direction of movement, surrounding density, and tendency to maintain psychological distance of each crowd agent. Through this simulation, the analysis unit (320) can predict a change in which the density of the second unit crowd increases, by having a ripple effect that causes a density-inducing effect or an increase in density in adjacent areas, when a first unit crowd exceeding a threshold level exhibits a specific movement pattern (e.g., a unidirectional concentration pattern, a radial diffusion pattern, a sudden change in direction pattern, etc.).

[0064] For example, the analysis unit (320) can simulate a situation in which a large crowd is waiting in front of a specific theater entrance (first area) and is in a dense state (the crowd within a designated area may be defined as the first unit crowd), and they begin to move all at once upon the opening of the theater. At this time, the analysis unit (320) can analyze how their movement affects the internal passageway or surrounding area (second area) of the theater by reflecting the direction of movement, speed, and narrowness of the adjacent pedestrian space of the first unit crowd. As a result of the simulation, if the first unit crowd moves along the narrow passageway at a fast speed, a situation can be predicted in which a large crowd temporarily gathers in the second area located at the end of the passageway, and the density of the second unit crowd also increases rapidly.

[0065] More specifically, the analysis unit (320) can pre-set a crowd density threshold level. For example, the crowd density threshold level is the number of first unit crowds or the number of second unit crowds m 2 There can be 5 people per person. That is, m 2 If the number of people exceeds 5, it may be determined that the threshold level has been exceeded. According to one embodiment of the present invention, the risk level can be divided into stages as the area where the crowd exceeding the threshold level is distributed increases, and the notification provided by the notification information providing unit (330) may be different for each stage. The stages according to the risk level can be divided into 4 stages, and the configuration and function of the notification provided by the notification information providing unit (330) according to the present invention, which differ for each stage, will be examined in detail through the following detailed description.

[0066] Meanwhile, it should be noted that the threshold level of crowd density pre-set in the analysis unit (320) according to the present invention is not necessarily limited only to the level presented above, and may be modified in various ways within the range that can achieve the purpose of the present invention. For example, m 2If the threshold level set to 5 people per party is based on a simple flat area, the threshold level set may differ depending on factors such as the terrain or weather of the densely populated area.

[0067] In addition, according to one embodiment of the present invention, the analysis unit (320) can simulate a propagation pattern in which the density of the second unit crowd changes above a critical level due to the movement pattern of the first unit crowd.

[0068] For example, crowd movement patterns can be influenced by interactions among the crowd. Specifically, in cases of high crowd density, individual movement speeds may decrease or movement in certain directions may be restricted, and individuals may adjust their movement paths to avoid collisions with one another. Furthermore, when a crowd moves intensively in a specific direction, other individuals tend to follow that flow more strongly, which can cause bottlenecks at entrances or narrow passages. In addition, the crowd's movement patterns can change abruptly if a specific individual takes the lead in the direction of movement. Moreover, in high-density situations, the crowd's direction of movement may be determined to head toward open spaces or exits.

[0069] As another example, the analysis unit (320) can determine the movement pattern of the crowd by referring to environmental information. For example, the environmental information may include factors such as topographical factors and weather conditions around the area where the crowd is dense.

[0070] Specifically, the analysis unit (320) may include terrain factors such as slope, obstacles, and the size of open spaces, and accordingly, the movement speed of crowds decreases on steep terrain and movement paths change depending on the direction of the slope, which can be reflected in the simulation process. In addition, narrow passages or structures with one side blocked restrict the direction of movement, thereby increasing density, whereas in open spaces, there is no restriction on the direction of movement of crowds, so density can be relatively lower.

[0071] As another example, the analysis unit (320) can reflect that, in the case of weather conditions, when it rains, the road surface becomes slippery, reducing the stability of movement of the crowd and decreasing the speed of movement. On the other hand, in clear weather, the speed of movement may relatively increase, and there may be a tendency for the crowd to disperse in open spaces. Additionally, in hot weather, the crowd may decide to move toward shaded paths or indoor spaces, and in cold weather, the crowd may decide to move toward the direction of the wind or avoid snow-covered areas.

[0072] According to one embodiment of the present invention, the risk to a crowd can be determined by referring to the change in density to a threshold level or higher in a second unit crowd of a predetermined number or more per unit time. Specifically, as the density of a first unit crowd increases, adjacent second unit crowds are also likely to be affected and their density exceeding the threshold level; therefore, the risk may reflect not only the density of individual zones but also the extent to which the influence spreads to the surroundings. The greater the number of second unit crowds that have exceeded (or are expected to exceed) the threshold density, the greater the risk may be.

[0073] In addition, the risk to the crowd can be determined by referring to the occurrence of propagation patterns more than a predetermined number of times per unit time. Specifically, to predict the risk due to crowd density, the risk can be calculated by assigning weights to spatial diffusion (e.g., the number of second-unit crowds exceeding the critical density = number of excess zones), temporal change (e.g., the time taken to exceed the critical density = excess time), and cascading diffusion (e.g., the frequency with which the same change occurs in surrounding second-unit crowds after the density in the first-unit crowd exceeds the critical level = number of propagations). The risk may increase as the number of excess zones increases, as the excess time becomes shorter, and as the frequency of the same change occurring in adjacent zones within a certain time (i.e., number of propagations) increases. For example, if the process of calculating the predicted risk by reflecting the above factors is expressed as a relationship, [Risk = (Number of Excess Zones) Weight 1) + (Reference time) Overtime Weight 2) + (number of propagations) It can be expressed as [weight 3)]. As another example, the analysis unit (320) can calculate the predicted risk level according to the above relationship in stages and classify it as shown in Table 1.

[0074] Risk Level Exceeded, Number Exceeded, Time Propagation Count Level 1: 530 seconds, 2 times Level 2: 1020 seconds, 3 times Level 3: 1515 seconds, 4 times Level 4: 2010 seconds, 5 times

[0075] For example, it can be classified into a level 1 if the number of second unit crowds whose density exceeds the threshold level (e.g., the number of excesses in Table 1) is 5 or less and the same change is expected to occur 2 or less times within 1 minute; a level 2 if the time during which the density of the first unit crowd (or second unit crowd) exceeds the threshold level (e.g., the excess time in Table 1) is shortened to 20 seconds or less and the same change is expected to occur 3 or more times within 1 minute; a level 3 if the time during which the density of the first unit crowd (or second unit crowd) exceeds the threshold level is shortened to 15 seconds or less and the same change is expected to occur 4 or more times within 1 minute; and a level 4 if the time during which the density of the first unit crowd exceeds the threshold level is shortened to 10 seconds or less and the same change is expected to occur 5 or more times within 1 minute. According to one embodiment of the present invention, the analysis unit (320) can calculate the predicted risk level at the level of each stage, and accordingly, the notification information providing unit (330) can provide notification information.

[0076] Meanwhile, it should be noted that the criteria for determining the level of risk to the crowd and the level of notification information provided according to the present invention are not necessarily limited to the manner presented above, and may be modified in various ways within the scope of achieving the purpose of the present invention.

[0077] Next, the notification information providing unit (330) according to one embodiment of the present invention can perform the role of generating notification information corresponding to crowd density and movement patterns based on information regarding risk levels output from the analysis unit (320), and providing this to the device (400). The notification information providing unit (330) can provide an optimized notification according to the output risk level so as to respond to situations that fluctuate in real time in a target area where crowds are dense.

[0078] Specifically, the notification information provider (330) can provide a notification to a target area or crowd in a visual or auditory manner when the risk level is assessed to be above a predetermined level.

[0079] For example, if the risk level corresponds to level 1, a medium that provides only visual information (e.g., an electronic display or digital signage) can be used as the device (400) to output guidance messages. In addition, push notifications using individual users' smartphone applications, SMS text messages, and SNS message transmissions can be performed together. Furthermore, if the risk level corresponds to level 2, in addition to the notification means of level 1, a broadcasting system accompanied by an auditory signal (e.g., an emergency warning broadcast accompanied by an alarm sound) can be used as the device (400) to output guidance and warning messages. Furthermore, if the risk level corresponds to level 3, a high-output and wide-area warning system (e.g., a siren, a public loudspeaker) higher than the notification of level 2 can be used as the device (400) to induce the immediate movement of the crowd. In the highest level, level 4, a forced evacuation order can be executed simultaneously with the level 3 notification through a dedicated device (400) by safety authorities (e.g., fire department or police station) and relevant authorities (e.g., event organizer or local public institution), or rapid and widespread warning measures can be taken using drones, etc.

[0080] As another example, the notification information provider (330) can support real-time information sharing and response processes with safety authorities.

[0081] For example, in a situation where a risk level of 2 or higher is predicted in a crowded situation such as an event, the device (400) according to the present invention may be the event organizer's monitoring system and integrated control center. Through this, the event organizer can receive notifications regarding the risk level or changes therein in real time, and if necessary, can receive information regarding temporary measures such as alternative movement routes through the integrated control system. In addition, if a situation of level 3 or higher is detected in a specific area where a crowd gathers, the information is transmitted through the integrated control center to a device (400) dedicated to police stations and fire departments, etc., so that they can be prepared in advance for safety accidents.

[0082] Next, a communication unit (340) according to one embodiment of the present invention can perform the function of enabling data transmission and reception from / to a data acquisition unit (310), an analysis unit (320), and a notification information providing unit (330).

[0083] Finally, a control unit (350) according to one embodiment of the present invention can perform the function of controlling the flow of data between a data acquisition unit (310), an analysis unit (320), a notification information provision unit (330), and a communication unit (340). That is, by controlling the data flow from / to / from the outside of the risk prediction system (300) or the data flow between each component of the risk prediction system (300), the control unit (350) according to the present invention can control the data acquisition unit (310), the analysis unit (320), the notification information provision unit (330), and the communication unit (340) to perform their respective unique functions.

[0084] FIG. 3 is a diagram exemplarily illustrating a process for predicting crowd density risk according to one embodiment of the present invention.

[0085] A camera image module (e.g., CCTV) that illuminates a target area may be a flow information sensor module (200), and a situation in which crowd flow information is monitored and received through the camera image module.

[0086] First, referring to FIG. 3, according to one embodiment of the present invention, crowd density, location, direction of movement, speed of movement, movement path, distance between crowds, etc. can be obtained from a camera image module as crowd flow information (S310).

[0087] Next, based on the crowd flux information above, the movement pattern of the crowd can be analyzed (S320).

[0088] Specifically, the risk prediction system (300) (specifically, the analysis unit (320)) can obtain the movement pattern of the crowd or the change therefrom based on factors such as the influence of crowd interaction, terrain factors, and weather conditions.

[0089] Next, the propagation pattern according to changes in crowd density can be analyzed (S330).

[0090] Specifically, the risk prediction system (300) (specifically, the analysis unit (320)) can simulate the risk to the crowd by referring to the propagation pattern in which the second unit crowd, which was previously less than the threshold level, changes to a threshold level or higher by the movement pattern of the first unit crowd, which is more than the threshold level within the crowd.

[0091] For example, the risk prediction system (300) (specifically, the analysis unit (320)) can determine the risk to the crowd by referring to the occurrence of a propagation pattern more than a predetermined number of times per unit time through simulation, and can predict that the risk will increase as the frequency of the same change occurring in the surrounding second unit crowd increases after the density in the first unit crowd exceeds a threshold level.

[0092] Then, the risk of crowd density is predicted (S340), and notification information can be provided to the device (400) according to the level of the predicted risk (S350).

[0093] For example, the risk prediction system (300) (specifically, the notification information provider (330)) can predict the risk level by dividing it into stages (e.g., 4 stages) and can provide notification information to the device (400) in real time for crowd management and safety response.

[0094] The embodiments according to the present invention described above may be implemented in the form of program instructions that can be executed through various computer components and recorded on a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc., either individually or in combination. The program instructions recorded on the computer-readable recording medium may be those specifically designed and configured for the present invention or those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include 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 hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions 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. Hardware devices may be modified into one or more software modules to perform processing according to the present invention, and vice versa.

[0095] Although the present invention has been described above with reference to specific details such as specific components, limited embodiments, and drawings, this is provided only to aid in a more comprehensive understanding of the invention, and the invention is not limited to the above embodiments, and a person skilled in the art to which the invention belongs can make various modifications and changes from this description.

[0096] 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.

Claims

1. As a method for predicting the risk of crowd density, A step of acquiring information on the flux of a crowd included in a target area, and The method includes the step of predicting the risk of crowd density in the target area by inputting the above flow information into a spontaneous threshold analysis model and referring to the output information. The above voluntary threshold analysis model is a model that simulates the risk to the crowd by referring to a propagation pattern in which a second unit crowd, whose density was below the threshold level, changes to above the threshold level due to the movement pattern of a first unit crowd, whose density within the crowd is above a preset threshold level. method.

2. In Paragraph 1, The risk to the above crowd is determined by referring to the change in density above a critical level in a second unit crowd of a predetermined number or more per unit time. method.

3. In Paragraph 1, The risk to the crowd is determined by referring to the fact that the propagation pattern occurs more than a predetermined number of times per unit time. method.

4. In Paragraph 1, The above-mentioned second unit crowd is adjacent to the above-mentioned first unit crowd method.

5. In Paragraph 1, The above threshold level is determined by referring to environmental information of the target area. method.

6. In Paragraph 1, The above movement pattern is determined by referring to the interaction information between people within the crowd. method.

7. In Paragraph 1, In response to the above risk level being above a predetermined level, visual or auditory notification information is provided to the target area or the crowd. method.

8. In Paragraph 7, Depending on the level of the above risk, the means of providing the above notification information is different. method.

9. In Paragraph 7, The above notification information is provided to the above target area or to institutions associated with the above crowd method.

10. A non-transient computer-readable recording medium for recording a computer program for executing the method according to paragraph 1.

11. As a system for predicting the risk of crowd density, A data acquisition unit for acquiring flux information of crowds included in a target area, and It includes an analysis unit that predicts the risk of crowd density in the target area by inputting the above flow information into a voluntary critical analysis model and referring to the output information. The above voluntary threshold analysis model is a model that simulates the risk to the crowd by referring to a propagation pattern in which a second unit crowd, whose density was below the threshold level, changes to above the threshold level due to the movement pattern of a first unit crowd, whose density within the crowd is above a preset threshold level. System.

Images