An Agent-Based Virtual Crowd Behavior Modeling and Parallel Simulation Method and System

Abstract

The present invention belongs to the technical field of computer simulation, and provides an agent-based virtual crowd behavior modeling and parallel simulation method and system. The method includes: obtaining a plurality of pairs of monitoring videos of historical group activities, extracting first group feature data therefrom, constructing training data according to the first group feature data, and training a group behavior analysis model; receiving a third video of real-time group activities captured by a drone, extracting second group feature data and type information of the group activities therefrom, and matching a number of abnormal events according to the type information; using the group behavior analysis model to deeply analyze the second group feature data and each abnormal event, obtaining a number of potential evacuation routes corresponding to each abnormal event, and performing parallel simulation on each potential evacuation route to screen out a target evacuation route; and outputting the target evacuation route to a management terminal. The present invention realizes the automatic generation of evacuation routes based on drone remote shooting technology.

Description

Technical Field

[0001] The present invention relates to the technical field of computer simulation, and more particularly, to an agent-based virtual crowd behavior modeling and parallel simulation method and system. Background Art

[0002] With the development of society, group activities are increasing day by day, such as large-scale concerts, sports events, commercial activities, etc. In these group activities, the population is dense. Once an abnormal event occurs, such as a fire, earthquake, etc., the evacuation of people becomes a crucial issue. In order to ensure that people can be safely evacuated in the shortest time, it is very necessary to plan a reasonable evacuation route in advance.

[0003] Currently, in the aspect of evacuation route planning for group activities, one way is that managers manually set evacuation routes based on videos taken by drones. However, this method has many drawbacks. On the one hand, manually setting evacuation routes requires managers to spend a lot of time and energy observing videos and analyzing the distribution and activities of the crowd, with extremely low efficiency. On the other hand, due to the subjective judgment and experience limitations of managers, the manually set evacuation routes may not be completely reasonable and cannot fully consider various complex situations, thus affecting the evacuation effect.

[0004] Therefore, there is an urgent need for a method that can efficiently and accurately plan evacuation routes for group activities to overcome the deficiencies of the prior art. Summary of the Invention

[0005] In view of the above technical problems, the present invention provides an agent-based virtual crowd behavior modeling and parallel simulation method, system, electronic device, computer storage medium, and computer program product.

[0006] The present invention discloses an agent-based virtual crowd behavior modeling and parallel simulation method, and the method comprises the following steps: obtaining a plurality of pairs of monitored videos of historical group activities, wherein each pair of monitored videos includes a first video and a second video, the first video is a video before the occurrence of an abnormal event, and the second video is a video from the occurrence of the same abnormal event until the evacuation is completed; extracting first group feature data from each pair of monitored videos, constructing training data according to the first group feature data, constructing a group behavior analysis model, and training the model using a plurality of pieces of the training data; receiving a third video of real-time group activities captured by a drone, extracting second group feature data and type information of the group activities from the third video, and matching a plurality of abnormal events according to the type information; deeply analyzing the second group feature data and each of the abnormal events using the group behavior analysis model to obtain a plurality of potential evacuation routes corresponding to each of the abnormal events, performing parallel simulation on each of the potential evacuation routes using simulation software, and screening out a target evacuation route according to the simulation results; and outputting the target evacuation route to a management terminal of the real-time group activities.

[0007] Optionally, the extracting first group feature data from each pair of monitored videos and constructing training data according to the first group feature data includes: extracting first human behavior features and building distribution information from the first video, extracting second human behavior features and abnormal event types from the second video, and obtaining an evacuation effect evaluation value corresponding to the pair of monitored videos; extracting evacuation passage distribution information and distribution information of the activity center area according to the building distribution information; using the abnormal event type as a first label and the evacuation effect evaluation value as a second label, and constructing the first human behavior features, the second human behavior features, the evacuation passage distribution information, the distribution information of the activity center area, the first label, and the second label into a piece of training data.

[0008] Optionally, the extracting second group feature data from the third video includes: receiving a fourth video of real-time group activities captured by a drone, extracting appearance feature information and motion feature information of each person from the fourth video, and comprehensively evaluating a crowd diversity index according to the appearance feature information and the motion feature information; determining a shooting duration according to the crowd diversity index, controlling and receiving the third video of the real-time group activities captured by the drone according to the shooting duration; and extracting the second group feature data from the third video.

[0009] Optionally, the method further includes: grouping each of the potential evacuation routes to obtain a plurality of evacuation route groups, determining an execution time for each potential evacuation route in the evacuation route groups; performing parallel simulation on each of the evacuation route groups using simulation software, and during the process of simulating each evacuation route group, sequentially and overlappingly adding the potential evacuation routes according to the execution time, and evaluating the overall evacuation efficiency of each evacuation route group; determining the evacuation route group with the highest overall evacuation efficiency as the target evacuation route group.

[0010] Optionally, after outputting the target evacuation route to the management terminal of the real-time group activity, the method further includes: the management terminal determines the control devices and guiding devices corresponding to the target evacuation route, and after an abnormal event occurs, the management terminal controls each of the control devices and the guiding devices to be turned on together to perform the evacuation guiding operation.

[0011] The present invention also discloses an agent-based virtual crowd behavior modeling and parallel simulation system, the system includes a processing device and a storage device, and the computer program code stored in the storage device is executed by the processing device to achieve: obtaining a plurality of pairs of monitoring videos of historical group activities, the pair of monitoring videos includes a first video and a second video, the first video is the video before the occurrence of an abnormal event, and the second video is the video from the occurrence of the same abnormal event until the evacuation is completed; extracting first group feature data from each pair of monitoring videos, constructing training data according to the first group feature data, constructing a group behavior analysis model and training it using a plurality of the training data; receiving a third video of the real-time group activity captured by a drone, extracting second group feature data and the type information of the group activity from the third video, and matching a plurality of abnormal events according to the type information; using the group behavior analysis model to deeply analyze the second group feature data and each of the abnormal events, obtaining a plurality of potential evacuation routes corresponding to each of the abnormal events, performing parallel simulation on each of the potential evacuation routes using simulation software, and screening out the target evacuation route according to the simulation results; outputting the target evacuation route to the management terminal of the real-time group activity.

[0012] The present invention also discloses an electronic device, including: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, and the processor executes the computer program to implement the method as described in any one of the foregoing.

[0013] The present invention also discloses a computer storage medium, the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method as described in any one of the foregoing.

[0014] The present invention also discloses a computer program product, which contains computer code that, when executed by a processor of an electronic device, implements the method described in any of the previous items.

[0015] Compared with the traditional method of manually setting evacuation routes based on drone videos, the present invention greatly improves the planning efficiency and avoids the time-consuming and laborious nature of manual observation and analysis. At the same time, based on the analysis of models and simulations, it effectively overcomes subjective judgments and empirical limitations, can more comprehensively consider complex situations, makes the evacuation routes more scientific and reasonable, significantly improves the evacuation efficiency and safety, and can provide strong support for the safety guarantee of group activities. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0017] Figure 1 is a schematic flowchart of a method for virtual crowd behavior modeling and parallel simulation based on agents according to an embodiment of the present invention.

[0018] Figure 2 is a schematic structural diagram of a system for virtual crowd behavior modeling and parallel simulation based on agents according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] The following specific embodiments illustrate the implementation manners of the present application. Those skilled in this technology can easily understand the other advantages and effects of the present application from the content disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of them. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope protected by the present application.

[0020] In addition, the technical features involved in different implementation manners of the present application described below can be combined with each other as long as they do not conflict with each other.

[0021] For the above technical problems, as Figure 1As shown in the figure, an agent-based virtual crowd behavior modeling and parallel simulation method is disclosed in an embodiment of the present invention. The method includes the following steps: S101, obtaining a plurality of pairs of monitoring videos of historical group activities. Each pair of monitoring videos includes a first video and a second video. The first video is a video before the occurrence of an abnormal event, and the second video is a video from the occurrence of the same abnormal event until the evacuation is completed.

[0022] In this step, a plurality of pairs of monitoring videos of historical group activities are obtained. Each pair of monitoring videos includes two parts: the first video is a video (for example, 3 minutes) before the occurrence of an abnormal event (such as a fire, earthquake, etc.). This part of the video records information such as the state of normal group activities, the distribution of people, and activity patterns; the second video is a video from the occurrence of the abnormal event until the evacuation is completed, which records how the crowd evacuates and their behavior during the evacuation process.

[0023] S102, extracting first group feature data from each pair of monitoring videos, constructing training data based on the first group feature data, constructing a group behavior analysis model, and training the model using a plurality of the training data.

[0024] In this step, for each pair of monitoring videos, first group feature data can be extracted from the first video and the second video. The first group feature data includes the crowd behavior characteristics before and after the occurrence of an abnormal event. Training data is constructed based on the extracted group feature data, and using these training data can realize the training of the group behavior analysis model. The group behavior analysis model can be a model based on machine learning or deep learning, such as a neural network. The trained group behavior analysis model learns the behavior patterns and rules of the crowd in different states (normal and abnormal).

[0025] S103, receiving a third video of real-time group activities captured by a drone, extracting second group feature data and type information of the group activities from the third video, and matching a plurality of abnormal events according to the type information.

[0026] In this step, the real-time group activities are the targets to be monitored in the present invention. The deployed drone takes videos of the real-time group activities to obtain the third video. Second group feature data can be extracted from the third video, and the second group feature data contains similar content to the first group feature data.

[0027] At the same time, the type information of the group activities is extracted, such as a concert, a sports event, an exhibition, etc. Different types of group activities may face different potential risks. For example, a concert may face risks such as fires and stampedes, and a sports event may face risks such as riots. According to the extracted type information, a plurality of possible abnormal events can be matched.

[0028] S104. Use the group behavior analysis model to deeply analyze the second group feature data and each of the abnormal events, obtain a number of potential evacuation routes corresponding to each of the abnormal events, use simulation software to perform parallel simulations on each of the potential evacuation routes, and screen out the target evacuation route according to the simulation results.

[0029] In this step, use the trained group behavior analysis model to deeply analyze the second group feature data, predict the possible evacuation behaviors that the crowd may take corresponding to each abnormal event, so as to obtain a number of potential evacuation routes corresponding to each abnormal event. Then, use simulation software (such as SUMO) to perform parallel simulations on these potential evacuation routes. During the simulation process, simulate the crowd evacuating according to different potential evacuation routes, consider various factors such as the passage capacity of the passage and the congestion of the crowd, obtain the simulation results with corresponding evacuation efficiency evaluation information, and screen out the potential evacuation route with the highest evacuation efficiency in various situations as the target evacuation route.

[0030] S105. Output the target evacuation route to the management terminal of the real-time group activity.

[0031] In this step, output the finally screened target evacuation route to the management terminal of the real-time group activity. The management terminal can be the command center at the activity site, etc. Managers can formulate corresponding evacuation plans according to this target evacuation route. Once a certain abnormal event occurs, they can guide the crowd to evacuate more efficiently and accurately, thereby improving the evacuation effect and safety.

[0032] Compared with the traditional method of manually setting evacuation routes based on drone videos, the present invention greatly improves the planning efficiency and avoids the time-consuming and laborious manual observation and analysis. At the same time, based on the analysis of the model and simulation, it effectively overcomes the subjective judgment and empirical limitations, can consider complex situations more comprehensively, makes the evacuation route more scientific and reasonable, significantly improves the evacuation efficiency and safety, and can provide strong support for the safety guarantee of group activities.

[0033] An intelligent agent is a program or system with certain intelligence, which can autonomously sense, make decisions and take actions in a specific environment. The above solution of the present invention can be executed by an intelligent agent. The intelligent agent can be embedded in a drone or deployed in a management terminal. The present invention does not make specific limitations on this.

[0034] Optionally, the extracting the first group feature data from each pair of monitoring videos and constructing the training data according to the first group feature data includes:

[0035] Extract the first crowd behavior characteristics and building distribution information from the first video, extract the second crowd behavior characteristics and abnormal event type from the second video, and obtain the evacuation effect evaluation value corresponding to the monitoring video pair; extract the evacuation channel distribution information and the distribution information of the activity center area according to the building distribution information; use the abnormal event type as the first label and the evacuation effect evaluation value as the second label, and construct the first crowd behavior characteristics, the second crowd behavior characteristics, the evacuation channel distribution information, the distribution information of the activity center area, the first label, and the second label into a training data.

[0036] In this embodiment, the first crowd behavior features are extracted from the first video before the abnormal event occurs, including the moving speed, moving direction, position, and aggregation degree of the crowd in a normal activity state, which reflects the behavior pattern of the crowd when it is not affected by the abnormal event. At the same time, the building distribution information is extracted, such as the layout of the building, the direction of the passage, etc.

[0037] The second crowd behavior features are extracted from the second video after the abnormal event occurs until the evacuation is completed, such as the change in the crowd's moving speed during the evacuation process, the choice of evacuation direction, whether congestion occurs, etc. These features show the crowd's behavioral response when facing abnormal events. In addition, the type of abnormal event is extracted, such as fire, earthquake, trampling, etc. The type of abnormal event is used to analyze the impact of different types of events on crowd behavior and evacuation effects. At the same time, the evacuation effect evaluation value corresponding to the monitoring video pair is obtained, which is obtained through personnel evaluation and relevant indicator calculation (such as evacuation time, number of evacuees, etc.), and is used to measure the effectiveness of this evacuation.

[0038] Based on the previously extracted building distribution information, we can further extract the evacuation channel distribution information, that is, determine the specific location, number, width, etc. of the evacuation channel, which is crucial for planning evacuation routes. At the same time, we can extract the distribution information of the activity center area, such as the location and size of the stadium's competition venue and the concert stage area at the event site. This information is conducive to better analyzing the gathering and flow of people in the event.

[0039] The above-mentioned first group behavior characteristics, second group behavior characteristics, evacuation channel distribution information, and activity center area distribution information (i.e., first group feature data) are used as the components of training data. At the same time, double labels are used, that is, the abnormal event type is used as the first label and the evacuation effect evaluation value is used as the second label. In this way, the group behavior analysis model obtained through training can learn the optimal planning method for evacuation routes for a certain type of abnormal event.

[0040] Optionally, extracting the second group feature data from the third video includes: receiving a fourth video of real-time group activities captured by a drone, extracting appearance feature information and motion feature information of each individual from the fourth video, and comprehensively evaluating a crowd diversity index based on the appearance feature information and the motion feature information; determining a shooting duration according to the crowd diversity index, controlling and receiving the third video of real-time group activities captured by the drone according to the shooting duration; and extracting the second group feature data from the third video.

[0041] In this embodiment, first, control the drone to capture a fourth video of real-time group activities, which is a sample video for preliminary analysis of the basic characteristics of the crowd (the video duration is, for example, 1 minute). Identify the appearance feature information of each individual from the fourth video, such as gender, approximate age range, body type (obese, medium, thin), clothing style, etc. These appearance features can be extracted through computer vision technologies, such as face recognition and human pose estimation algorithms. At the same time, extract the motion feature information of each individual, including moving speed, moving direction, acceleration, etc. The motion feature information reflects the dynamic behavior characteristics of the crowd.

[0042] The crowd diversity index is an index used to comprehensively measure the degree of difference in crowd characteristics in real-time group activities. Based on the above appearance feature information and motion feature information, the crowd with similar characteristics can be clustered. For example, the crowd with the same appearance features and the same motion style is classified into the same group, so as to obtain the number of crowd types in the real-time group activities, and then obtain the crowd diversity index. The crowd diversity index is, for example, an index value positively correlated with the number of crowd types, or can directly be the number of crowd types.

[0043] When the number of types of people is larger, it indicates that the types of participants in this real-time group activity are more diverse. For example, there are men, women, the elderly, and children. Subsequently, when an abnormal event occurs, the number of evacuation routes to be taken will be larger. In other words, participants of the same type are more likely to choose similar evacuation routes (or escape routes). The more diverse the types of participants are, the more actual escape routes are chosen. In order to accurately analyze and obtain potential evacuation routes closer to the real situation subsequently, the present invention sets to adjust the above-mentioned shooting duration according to the magnitude of the above-mentioned crowd diversity index, that is, dynamically determine the duration of the third video to be shot. Specifically, the shooting duration is in a positive correlation with the crowd diversity index. When the third video is longer, more and richer second group characteristic data can be extracted therefrom, which is beneficial to improving the accuracy of the potential evacuation routes obtained through analysis. When the third video is shorter, the data length or data volume of the second group characteristic data extracted can be reduced, because the group characteristic data of highly similar participants (for example, almost all are teenagers) is simple and obvious, and only a third video of a short duration is sufficient to extract data that can comprehensively represent the group characteristics, thereby reducing the data processing load.

[0044] In summary, the present invention can more accurately extract second group characteristic data by first analyzing the fourth video to obtain the crowd diversity index and then determining the shooting duration to obtain the third video, improving the accuracy and effectiveness of subsequent group behavior analysis and evacuation route planning.

[0045] It should be noted that the second group characteristic data in the present invention is different from the first group characteristic data, and it only includes the first crowd behavior characteristics, evacuation passage distribution information, and distribution information of the activity center area in the first group characteristic data.

[0046] Optionally, the method further includes: grouping the potential evacuation routes to obtain a plurality of evacuation route groups, determining an execution time for each potential evacuation route in the evacuation route group; using simulation software to perform parallel simulation on each evacuation route group. During the process of simulating each evacuation route group, the potential evacuation routes are sequentially and overlapped and added according to the execution time, and the overall evacuation efficiency of each evacuation route group is evaluated; the evacuation route group with the highest overall evacuation efficiency is determined as the target evacuation route group.

[0047] In this embodiment, there are generally multiple evacuation channels (corresponding to one evacuation route) at the group activity site. The traditional concept holds that when an abnormal event occurs, opening all the evacuation channels together will achieve the highest evacuation efficiency. However, at this time, participants will spend more time choosing among multiple evacuation channels, resulting in the overall evacuation efficiency often not increasing but decreasing instead. To address this problem, the present invention also provides that multiple evacuation channels can be opened simultaneously during evacuation, but the opening time of each evacuation channel is different. For example, when an abnormal event occurs, the first evacuation route is opened first, and after a while, the second evacuation route is opened, and so on. By gradually opening the evacuation routes, it is possible to guide the participants in the group activity to evacuate and escape more efficiently.

[0048] To achieve the above technical effects, the present invention provides that each potential evacuation route is divided into several evacuation route groups, the number of evacuation routes in each evacuation route group is different, and the execution time of each evacuation route is specified. Then, the simulation software performs parallel simulations on multiple evacuation route groups. For each evacuation route group, in the aforementioned manner, after reaching the corresponding time, one potential evacuation route is superimposed and opened. Multiple simulations can be performed on each group of evacuation route groups. After the simulations are completed, all the simulation results are integrated, and the overall evacuation efficiency of each evacuation route group is evaluated. The evacuation route group with the highest overall evacuation efficiency is determined as the target evacuation route group.

[0049] Optionally, after outputting the target evacuation route to the management terminal of the real-time group activity, the method further includes: the management terminal determines the control devices and guiding devices corresponding to the target evacuation route. After an abnormal event occurs, the management terminal controls each of the control devices and the guiding devices to be opened together to perform the evacuation guidance operation.

[0050] In this embodiment, after receiving the target evacuation route (or the target evacuation route group), the management terminal will determine each control device and guiding device located on the evacuation route according to the specific distribution of the route (or all the routes in the target evacuation route group). The control device is, for example, the control system of a fire shutter door, which ensures the unobstructed evacuation passage by controlling the lifting and lowering of the shutter door; it can also be an elevator control system, which stops the elevator during evacuation to prevent people from being trapped; it can also be the control system of a ticket gate, which controls the opening of the ticket gate when an abnormal event occurs. The guiding devices include emergency indicator lights, voice broadcast systems, etc. The emergency indicator lights are usually installed on the ground or wall of the evacuation passage and will light up after an abnormal event occurs to guide people in the direction of the safety exit; the voice broadcast system can play evacuation instructions and precautions in real time, such as "Please don't panic and evacuate in an orderly manner according to the direction of the indicator lights" to help people stay calm and evacuate in an orderly manner.

[0051] After an abnormal event is detected, the management terminal will simultaneously control each control device and guiding device to turn on. The control device quickly adjusts the evacuation environment to create favorable conditions for personnel evacuation; the guiding device guides personnel to evacuate the scene orderly along the target evacuation route through means such as lights and sounds. Through the collaborative operation of each device, the evacuation efficiency can be maximally improved, and casualties and property losses can be reduced.

[0052] As Figure 2 shown, an embodiment of the present invention also discloses an intelligent agent-based virtual crowd behavior modeling and parallel simulation system. The system includes a processing device and a storage device. The computer program code stored in the storage device is executed by the processing device to achieve: obtaining a plurality of pairs of monitoring videos of historical group activities. Each pair of monitoring videos includes a first video and a second video. The first video is the video before the occurrence of an abnormal event, and the second video is the video from the occurrence of the same abnormal event until the evacuation is completed; extracting first group feature data from each pair of monitoring videos, constructing training data according to the first group feature data, constructing a group behavior analysis model and training it using a plurality of the training data; receiving a third video of real-time group activities captured by a drone, extracting second group feature data and the type information of the group activities from the third video, and matching a plurality of abnormal events according to the type information; using the group behavior analysis model to deeply analyze the second group feature data and each abnormal event, obtaining a plurality of potential evacuation routes corresponding to each abnormal event, performing parallel simulation on each potential evacuation route using simulation software, and screening out the target evacuation route according to the simulation results; outputting the target evacuation route to the management terminal of the real-time group activities.

[0053] An embodiment of the present invention also discloses an electronic device, including: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor. The processor executes the computer program to implement the method as described in the foregoing embodiment.

[0054] An embodiment of the present invention also discloses a computer storage medium. The computer storage medium stores a computer program, and the computer program is executed by a processor to implement the method as described in the foregoing embodiment.

[0055] The computer-readable storage medium described above may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium may be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0056] An embodiment of the present invention also discloses a computer program product. The computer program product contains computer code, and when the computer code is executed by a processor of an electronic device, the method described in the foregoing embodiment is implemented.

[0057] It should be understood that various forms of the processes shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. No limitation is made herein.

[0058] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for modeling and parallel simulation of virtual crowd behavior based on intelligent agents, characterized in that: The method comprises the following steps: obtaining a plurality of surveillance video pairs of historical group activities, wherein the surveillance video pairs comprise a first video and a second video, wherein the first video is a video before an abnormal event occurs, and the second video is a video after the occurrence of the same abnormal event until the evacuation is completed; extracting first group characteristic data from each of the surveillance video pairs, constructing training data based on the first group characteristic data, constructing a group behavior analysis model, and using the plurality of the training data for training; receiving a third video of real-time group activities shot by a drone, extracting second group characteristic data and type information of group activities from the third video, and obtaining a plurality of abnormal events based on matching of the type information; using the group behavior analysis model to perform in-depth analysis on the second group characteristic data and each of the abnormal events, obtaining a plurality of potential evacuation routes corresponding to each of the abnormal events, using simulation software to perform parallel simulation on each of the potential evacuation routes, and screening a target evacuation route based on the simulation results; Outputting the target evacuation route to a management terminal of real-time group activities; The method also includes: grouping each of the potential evacuation routes to obtain a plurality of evacuation route groups, and determining an execution time for each potential evacuation route in the evacuation route group; using simulation software to perform parallel simulation on each of the evacuation route groups, and in the process of simulating each of the evacuation route groups, overlappingly adding the potential evacuation routes in sequence according to the execution time, and evaluating the overall evacuation efficiency of each of the evacuation route groups; determining the evacuation route group with the highest overall evacuation efficiency as the target evacuation route group; wherein, there are multiple evacuation channels at the group activity site, and each evacuation channel corresponds to an evacuation route.

2. The method for modeling and parallel simulation of virtual crowd behavior based on an intelligent agent according to claim 1, characterized in that: The first group characteristic data is extracted from each of the surveillance video pairs, and training data is constructed based on the first group characteristic data, including: extracting first crowd behavior characteristics and building distribution information from the first video, extracting second crowd behavior characteristics and abnormal event types from the second video, and obtaining an evacuation effect evaluation value corresponding to the surveillance video pair; extracting evacuation channel distribution information and activity center area distribution information based on the building distribution information; taking the abnormal event type as the first label and the evacuation effect evaluation value as the second label, and constructing the first crowd behavior characteristics, the second crowd behavior characteristics, the evacuation channel distribution information, the activity center area distribution information, the first label, and the second label into a piece of training data.

3. The method for virtual crowd behavior modeling and parallel simulation based on an agent according to claim 2, characterized in that: The extracting of the second group characteristic data from the third video includes: receiving a fourth video of real-time group activities shot by a drone, extracting appearance characteristic information and motion characteristic information of each human body from the fourth video, and obtaining a crowd diversity index based on a comprehensive evaluation of the appearance characteristic information and the motion characteristic information; determining a shooting duration based on the crowd diversity index, and controlling and receiving the third video of real-time group activities shot by a drone according to the shooting duration; and extracting the second group characteristic data from the third video.

4. The method for modeling and parallel simulation of virtual crowd behavior based on an agent according to claim 1, characterized in that: After the target evacuation route is output to the management terminal of real-time group activities, the method further includes: the management terminal determines the control device and the guidance device corresponding to the target evacuation route, and after an abnormal event occurs, the management terminal controls each of the control devices and the guidance devices to be turned on together to perform an evacuation guidance operation.

5. An agent-based virtual crowd behavior modeling and parallel simulation system, characterized by: The system comprises a processing device and a storage device, wherein the computer program code stored in the storage device is executed by the processing device to implement: Acquire several surveillance video pairs of historical group activities, wherein the surveillance video pairs include a first video and a second video, wherein the first video is a video before an abnormal event occurs, and the second video is a video after the same abnormal event occurs until evacuation is completed; extract first group feature data from each of the surveillance video pairs, construct training data based on the first group feature data, construct a group behavior analysis model, and use the several training data for training; receive a third video of real-time group activities shot by a drone, extract second group feature data and type information of group activities from the third video, and obtain several abnormal events based on the matching of the type information; use the group behavior analysis model to perform in-depth analysis on the second group feature data and each of the abnormal events, obtain several potential evacuation routes corresponding to each of the abnormal events, use simulation software to perform parallel simulation on each of the potential evacuation routes, and screen and obtain a target evacuation route based on the simulation results; Outputting the target evacuation route to a management terminal of real-time group activities; The method also includes: grouping each of the potential evacuation routes to obtain a plurality of evacuation route groups, and determining an execution time for each potential evacuation route in the evacuation route group; using simulation software to perform parallel simulation on each of the evacuation route groups, and in the process of simulating each of the evacuation route groups, sequentially and overlappingly adding the potential evacuation routes according to the execution time, and evaluating the overall evacuation efficiency of each of the evacuation route groups; determining the evacuation route group with the highest overall evacuation efficiency as the target evacuation route group; wherein, there are multiple evacuation channels at the group activity site, and each evacuation channel corresponds to an evacuation route.

6. The agent-based virtual crowd behavior modeling and parallel simulation system according to claim 5, characterized in that: The first group characteristic data is extracted from each of the surveillance video pairs, and training data is constructed based on the first group characteristic data, including: extracting first crowd behavior characteristics and building distribution information from the first video, extracting second crowd behavior characteristics and abnormal event types from the second video, and obtaining an evacuation effect evaluation value corresponding to the surveillance video pair; extracting evacuation channel distribution information and activity center area distribution information based on the building distribution information; taking the abnormal event type as the first label and the evacuation effect evaluation value as the second label, and constructing the first crowd behavior characteristics, the second crowd behavior characteristics, the evacuation channel distribution information, the activity center area distribution information, the first label, and the second label into a piece of training data.

7. An electronic device comprising: At least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 4.

8. A computer storage medium storing a computer program, characterized in that: The computer program is executed by a processor to implement the method according to any one of claims 1 to 4.

9. A computer program product, characterized in that: The computer program product includes computer codes, and when the computer codes are executed by a processor of an electronic device, the method according to any one of claims 1 to 4 is implemented.

Images