Method and system for predicting and evaluating two-way people flow risk in channel

Abstract

The invention discloses an in-channel bidirectional people flow risk prediction and evaluation method, and the method comprises the steps: collecting the real-time dynamic data of the bidirectional people flow in a channel, and obtaining the detection amount of the settlement of the people flow based on the real-time dynamic data, the settlement being the local congestion of the people; establishing a people flow risk prediction and evaluation model according to the detection quantity of the node; and inputting people flow data in a to-be-assessed scene into the people flow risk prediction and assessment model, assessing the detection quantity of local congestion and predicting the probability of occurrence of deadlock of bidirectional crowds. According to the method, the risk degree of the pedestrian flow can be evaluated in real time through the pedestrian flow risk prediction evaluation model, and whether the pedestrian flow will have crowd deadlock or not is judged.

Description

Technical Field

[0001] The present application relates to the technical field of crowd motion simulation and risk assessment, and in particular to a method and system for predicting and assessing the risk of bidirectional crowd flow in a channel. Background Art

[0002] Crowd motion simulation refers to simulating the movement of crowds in specific scenarios from a physical perspective. Given that there is a counterflow of crowds in channel scenarios, which may lead to public safety incidents such as stampedes, it is of great research value to conduct risk assessment of bidirectional pedestrian flows in channels through crowd motion simulation and try to find methods for risk prediction. Crowd motion is a relatively complex dynamic system, and defining detection quantities to monitor pedestrians in it is an effective way to simplify the research process. How to define appropriate detection quantities in bidirectional pedestrian flows to describe the risk level of the crowd and find detection quantities that can predict the danger that will occur to the crowd are key issues in the research.

[0003] There are many models available for crowd motion simulation, which can be roughly divided into macro models and micro models. The macro model starts from the global perspective and focuses on the overall movement of the crowd; while the micro model starts from the local perspective and focuses on the movement of individual pedestrians. As a classic micro model, the cellular automaton (CA) model uses simple rules to approximate complex models and has a fast calculation speed. By setting parameters for each pedestrian individually, more different situations can be discussed in detail.

[0004] At present, most of the detection quantities for bidirectional pedestrian flow are related to the distribution, congestion and risk level of the crowd in the scene. Their definitions are based on crowd density, speed, flow and entropy value, which can measure the movement state of pedestrians, the degree of scene congestion and the potential risk of the crowd. For example, the order parameter is used to indicate whether the lane is formed; the detection quantity congestion level is proposed based on the crowd movement velocity vector field to evaluate the potential risk level of pedestrian flow; the disorder of the horizontal pedestrian movement of the related detection quantity is defined based on particle entropy to represent the crowd distribution information.

[0005] At present, in the simulation work of using CA model to simulate the bidirectional pedestrian flow in the channel, many studies have used relevant detection quantities in the crowd to describe the movement status of pedestrians, scene congestion, crowd risk level, etc. However, these detection quantities still have some problems and room for improvement in actual use: First, their definition method is relatively complex and the conceptual understanding is not intuitive enough; second, the calculation complexity is high. In real scenes, if only the bidirectional pedestrian flow is analyzed through the crowd video captured by the camera, the calculated detection quantity results are prone to large deviations; third, there is currently no research that defines the detection quantity that can predict the danger of the crowd.

[0006] In summary, in crowd motion simulation, how to use relevant detection quantities to describe pedestrian motion status, scene congestion, and crowd risk level is a difficult problem. Therefore, in order to solve the technical problems of complex detection quantity definition, high calculation complexity, and inability to predict crowd deadlock in the existing technology, it is urgent to propose a technical method that can use crowd motion simulation field strategies to accurately predict crowd deadlock. Summary of the invention

[0007] In order to solve the problems existing in the prior art, such as the complicated calculation of crowd-related detection quantities and the inability to predict the occurrence of deadlock, a new research method is proposed to define intuitive and easy-to-calculate detection quantities from the perspective of local blockage, and explore their practicality.

[0008] In a first aspect, an embodiment of the present application provides a method for predicting and assessing the risk of bidirectional human flow in a channel, the method comprising:

[0009] Congestion detection amount acquisition step: collecting real-time dynamic data of bidirectional human flow in the channel, and acquiring detection amount of knots of human flow based on the real-time dynamic data, wherein the knot is a local congestion of the crowd;

[0010] Prediction model establishment steps: Establish a risk prediction and assessment model for abortion based on the amount of knot detection;

[0011] Prediction and evaluation steps: Input the crowd flow data in the scenario to be evaluated into the crowd flow risk prediction and evaluation model, evaluate the detection amount of local congestion and predict the probability of deadlock in bidirectional crowds.

[0012] In a specific embodiment of the present invention, the above-mentioned congestion detection amount acquisition step includes:

[0013] The steps for calculating the length and width of the knot are as follows: the length of the knot is calculated by collecting the number of rows occupied by all pedestrians in the two-way flow of people in the channel; the width of the knot is calculated according to the number of columns occupied by all pedestrians collected;

[0014] The calculation steps of the intersection front width are as follows: a matrix consisting of the count values ​​of the upward and downward pedestrian flows in the channel is collected, and the total width of adjacent heterogeneous pedestrian positions in the node is calculated to obtain the intersection front width value;

[0015] The calculation steps of the squeeze energy of the knot are as follows: based on the number of pedestrians in the knot and the width of the pedestrian front, the squeeze energy of the knot is calculated;

[0016] The steps for calculating the static speed of a knot are as follows: According to the pedestrian category, the average speed of the static speeds of all pedestrians in the knot is calculated to obtain the static speed of the knot.

[0017] In a specific embodiment of the present invention, the above-mentioned congestion detection amount acquisition step includes:

[0018] The knot duration calculation steps are as follows: Calculate the number of time steps that the knot exists in the scene and obtain the knot duration;

[0019] Steps for calculating the empty cell ratio: Calculate the ratio of the number of cells not occupied by pedestrians to the total number of cells within a preset range near the intersection surface of the knot, and obtain the empty cell ratio of the knot.

[0020] In a specific embodiment of the present invention, the above-mentioned abortion risk prediction and assessment model includes:

[0021]

[0022] Among them, y i Indicates whether the i-th detection quantity is abnormal, x 1 is the width of the knot, x 2 is the length, x 3 is the width of the front, x 4 is the duration, x 5 is the extrusion energy and x 6 is the empty cell ratio, N is the scene width, t is the association parameter between the critical value of the empty cell ratio and the scene width N.

[0023] In a specific embodiment of the present invention, the above x 1 Knot width, x 2 Length, x 3 Front width, x 4 Duration, x 5 Squeeze energy and x 6 Empty cell ratio, set weight value ω respectively i , and the weight value is within the preset threshold range.

[0024] In a specific embodiment of the present invention, whether the above-mentioned two-way pedestrian flow will be deadlocked is calculated using the following formula:

[0025]

[0026] Among them, z is the determining variable for whether a deadlock will occur in the bidirectional pedestrian flow, ω i is the weight value, y i is the value of whether the i-th detection quantity is abnormal. When z is greater than or equal to 0.5, deadlock may occur; when z is less than 0.5, deadlock is unlikely to occur.

[0027] In a second aspect, an embodiment of the present application provides a system for predicting and assessing the risk of bidirectional human flow in a channel, using a method for predicting and assessing the risk of bidirectional human flow in a channel, the system comprising:

[0028] Congestion detection quantity acquisition module: used to collect real-time dynamic data of bidirectional human flow in the channel, and obtain the detection quantity of the knot of human flow based on the real-time dynamic data, where the knot is the local congestion of the crowd;

[0029] Prediction model building module: used to build a risk prediction and assessment model for abortion according to the amount of knot detection;

[0030] Prediction and evaluation module: used to input the crowd flow data in the scenario to be evaluated into the crowd flow risk prediction and evaluation model, evaluate the detection amount of local congestion and predict the probability of deadlock in bidirectional crowds.

[0031] In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes steps including the method for predicting and assessing the risk of bidirectional pedestrian flow in the channel.

[0032] In a fourth aspect, an embodiment of the present application provides a storage medium for storing a computer program for executing the method for predicting and assessing the risk of bidirectional human flow in a channel as described.

[0033] In the fifth aspect, an embodiment of the present application provides a crowd motion simulation tool, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the method for predicting and assessing the risk of bidirectional crowd flow in a channel are implemented.

[0034] Compared with the related prior art, it has the following outstanding beneficial effects:

[0035] 1. The method of the present invention proposes a method for calculating local congestion and related detection quantities in bidirectional pedestrian flow in a channel; these detection quantities are directly related to local crowd congestion and deadlock, the calculation method is simple and intuitive, and it is easy to directly measure in real scenes;

[0036] 2. Among all the detection quantities of the method of the present invention, six detection quantities have clear critical values ​​for whether deadlock occurs in different scenarios, and two of them have the probability to predict the occurrence of crowd deadlock in different scenarios.

[0037] 3. The method of the present invention establishes a risk prediction and assessment model for bidirectional pedestrian flow in a channel based on six detection quantities. In real channel scenarios, the pedestrian flow risk prediction and assessment model proposed in the present invention can be used to conduct real-time assessment of the risk level of pedestrian flow, and determine whether a crowd deadlock will occur in the pedestrian flow. Management personnel can take timely measures to control pedestrians, prevent a global deadlock in the crowd, and thereby prevent stampede accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0039] Figure 1 Schematic diagram of a method for predicting and assessing the risk of bidirectional human flow in a channel according to an embodiment of the present invention;

[0040] Figure 2 This is a thermal schematic diagram of lane status presented by pedestrian flow according to an embodiment of the present invention;

[0041] Figure 3 This is a thermal diagram of a deadlock state of pedestrian flow in an embodiment of the present invention;

[0042] Figure 4 This is an example diagram of a heat map structure according to an embodiment of the present invention;

[0043] Figure 5 This is a schematic diagram of the width of the frontal surface according to an embodiment of the present invention;

[0044] Figure 6 Schematic diagram of a system for predicting and assessing the risk of bidirectional human flow in a channel according to an embodiment of the present invention;

[0045] Figure 7 It is a schematic diagram of an electronic device shown in an embodiment of the present invention. DETAILED DESCRIPTION

[0046] It should be noted that the processor described in the present invention is the control center of the electronic device, which can be a processor or a general term for multiple processing elements. For example, it can be one or more central processing units (CPUs), or application specific integrated circuits (ASICs), or one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (FPGAs).

[0047] Optionally, the processor can perform various functions of the electronic device by running or executing a software program stored in the memory, and calling data stored in the memory.

[0048] In a specific implementation, as an embodiment, the processor may include one or more CPUs. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions). Electronic devices may include: servers, desktop computers, laptops, smart phones, tablet computers, embedded computers, etc., wherein the embedded computers include vehicles and robots, etc.

[0049] The memory is used to store the software program for executing the solution of the present invention, and the execution is controlled by the processor. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0050] It should be noted that the structure of the electronic device shown in the drawings of the present invention does not constitute a limitation thereto, and the actual knowledge structure recognition device may include more or fewer components than shown in the drawings, or a combination of certain components, or a different arrangement of components.

[0051] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0052] It should also be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0053] In the present invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0054] It should also be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0055] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0056] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0057] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0058] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0059] In order to make the above features and effects of the present invention more clearly and understandably described, embodiments are given below and described in detail with reference to the accompanying drawings. This specification discloses one or more embodiments that include the features of the present invention. The disclosed embodiments are only for illustration. The scope of protection of the present invention is not limited to the disclosed embodiments, and the present invention is defined by the attached claims.

[0060] The following is a system embodiment corresponding to the above method embodiment. This embodiment can be implemented in conjunction with the above embodiment. The relevant technical details mentioned in the above embodiment are still valid in this embodiment. In order to reduce repetition, they are not repeated here. Accordingly, the relevant technical details mentioned in this embodiment can also be applied in the above embodiment.

[0061] The present invention aims to propose a method for predicting and evaluating the risk of two-way pedestrian flow in a channel. When the present invention uses the CA model to simulate the movement of two-way pedestrian flow in a channel, it is found that when the crowd density in the scene is large, as the pedestrian flow moves, a local crowd jam may occur somewhere first. If the local congestion is not alleviated, and more and more pedestrians are blocked, a crowd deadlock phenomenon will occur, and the vast majority of pedestrians will be unable to move, which will lead to the occurrence of stampede accidents. Through observation and research on the formation of crowd deadlock, the present invention finds that it is possible to calculate the detection quantity related to the crowd from a different perspective from previous studies, and verify through data statistics and analysis whether the detection quantity can describe the risk level of pedestrian flow and whether it has the ability to predict the occurrence of crowd deadlock.

[0062] Since a local crowd jam can be described as two groups of pedestrians stuck somewhere in the scene, like a knot, mutually congested and unable to move, the present invention refers to the local crowd jam as a "knot". The present invention gives a mathematical definition of a knot, and calculates seven related detection quantities based on the knot, namely, the length and width of the knot, the width of the intersection surface, the duration of the knot, the extrusion energy of the knot, the proportion of empty cells, and the static speed of the knot. Afterwards, through simulation experiments, data analysis is performed on each detection quantity in the two cases of deadlock and whether the deadlock occurs, to detect whether their value range and change trend are related to the occurrence of deadlock, whether there is a corresponding critical value, and whether the occurrence of crowd deadlock can be predicted.

[0063] Embodiment 1

[0064] like Figure 1 As shown, the embodiment of the present application provides a method for predicting and assessing the risk of bidirectional human flow in a channel, the method comprising:

[0065] Congestion detection amount acquisition step 101: collecting real-time dynamic data of bidirectional human flows in the channel, and acquiring detection amounts of knots of human flows based on the real-time dynamic data, wherein a knot is a local congestion of a crowd;

[0066] In the specific embodiment of the present invention, a definition of local crowd congestion in a scene is given and is called a "knot". Figure 2-Figure 4 As shown in the figure, the following three heat maps are two-dimensional plane diagrams of crowd simulation. Each pedestrian occupies a cell, where pink cells represent upward pedestrians and blue cells represent downward pedestrians. Figure 2 and Figure 3 The two heat maps show that the pedestrian flow is in lane state and deadlock state respectively. Figure 4 If it is a heat map, it is an example of a "knot". In the simulation experiment, if two groups of pedestrians are blocked for a certain period of time, they are defined as a knot. On this basis, the present invention calculates seven detection quantities related to the knot, namely, the length and width of the knot, the width of the intersection of the knot, the duration of the knot, the extrusion energy of the knot, the proportion of empty cells and the static speed of the knot.

[0067] Prediction model establishment step 102: establishing a risk prediction and assessment model for abortion according to the amount of knot detection;

[0068] Prediction and evaluation step 103: inputting the crowd flow data in the scenario to be evaluated into the crowd flow risk prediction and evaluation model, evaluating the detection amount of local congestion and predicting the probability of deadlock of bidirectional crowds.

[0069] In a specific embodiment of the present invention, the congestion detection amount acquisition step 101 includes:

[0070] The steps for calculating the length and width of the knot are as follows: the length of the knot is calculated by collecting the number of rows occupied by all pedestrians in the two-way flow of people in the channel; the width of the knot is calculated according to the number of columns occupied by all pedestrians collected;

[0071] The length and width of a knot: The length of a knot is the number of rows occupied by all the people in the knot, and the width is the number of columns occupied by all the people. The specific calculation formula is as follows, where n is the number of people in the knot, x is i Indicates the row number where the pedestrian is located, y i Indicates the column number where the pedestrian is located.

[0072]

[0073] This measure clearly and accurately shows the size of the local congestion. It is natural to guess that larger nodes have a higher risk of crowd deadlock.

[0074] The calculation steps of the intersection front width are as follows: a matrix consisting of the count values ​​of the upward and downward pedestrian flows in the channel is collected, and the total width of adjacent heterogeneous pedestrian positions in the node is calculated to obtain the intersection front width value;

[0075] like Figure 5 As shown, the intersection width (interface_width): The intersection width is the total width of adjacent heterogeneous pedestrian positions in the knot, and the specific calculation formula is as follows. ij Indicates the state of the cell in the i-th row and j-th column in the two-dimensional plane: if it is an empty cell, it is equal to 0; if it is an up-going pedestrian, it is equal to 1; if it is a down-going pedestrian, it is equal to -1. χ(S) is an indicator function, S is a true function value of 1, otherwise it is 0.

[0076]

[0077] For example Figure 5 The intersection front width of the middle node is 6. It shows the local congestion state from the perspective of the two clusters crowding each other. The wider the intersection front width, the more likely it is that the node is more congested and more likely to cause crowd deadlock.

[0078] The calculation steps of the squeeze energy of the knot are as follows: based on the number of pedestrians in the knot and the width of the pedestrian front, the squeeze energy of the knot is calculated;

[0079] Squeezing energy of a knot (squeezing_energy): The present invention attempts to quantify the risk of a knot from the perspective of squeezing energy. Based on the number and distribution of pedestrians, the greater the squeezing energy, the more severe the local congestion, and the more likely it is to cause a crowd deadlock. The squeezing energy of a knot in the present invention is calculated from two aspects: one is the number of pedestrians in the knot, and the other is the width of the pedestrian intersection. The number of pedestrians in the knot is n, and the width of the knot intersection is interface_width. The squeezing energy of the knot can be calculated by the following formula:

[0080] squeezing_energy 1 =3,

[0081]

[0082] squeezing_energy=squeezing_energy n +6×interface_width.

[0083] The steps for calculating the static speed of a knot are as follows: According to the pedestrian category, the average speed of the static speeds of all pedestrians in the knot is calculated to obtain the static speed of the knot.

[0084] Static velocity of a knot (static_velocity): The static velocity of a knot is the average speed of all pedestrians in the knot, where the static velocity is the initial speed of the pedestrian (1.5, 1, 0.75 m / s). It has nothing to do with whether the pedestrian is currently moving, but is only determined by the pedestrian category. The specific calculation formula is as follows: There are n pedestrians in the knot, v i It represents the initial speed of the i-th pedestrian, and a value among 1.5, 1, and 0.75 is selected according to the category of the pedestrian.

[0085]

[0086] The present invention predicts and evaluates that if the knot has a higher static speed, pedestrians will move more frequently in a jammed state and have a greater chance of escaping from the congestion, thereby making it easier for the knot to be untied and local congestion to be alleviated.

[0087] The knot duration calculation steps are as follows: Calculate the number of time steps that the knot exists in the scene and obtain the knot duration;

[0088] The duration of a knot indicates the number of time steps that the knot exists in the scene. If the duration of a knot is large, it means that the local congestion persists and more and more pedestrians may be trapped in the jam.

[0089] Steps for calculating the empty cell ratio: Calculate the ratio of the number of cells not occupied by pedestrians to the total number of cells within a preset range near the intersection surface of the knot, and obtain the empty cell ratio of the knot.

[0090] Empty cell ratio (empty_proportion): The empty cell ratio indicates the ratio of cells not occupied by pedestrians to the total number of cells within a certain range near the intersection front. The present invention selects a range of 5 rows above and below the intersection front for calculation. The formula is as follows, where N represents the total number of columns of the two-dimensional grid, and unoccupied_num represents the number of empty cells in the range.

[0091]

[0092] If the proportion of empty cells in the knot is large, the blocked pedestrians will be more likely to disperse outwards as the pedestrian flow moves, making the knot easier to untie and local congestion of the crowd can be easily alleviated.

[0093] In a specific embodiment of the present invention, the above-mentioned abortion risk prediction and assessment model includes:

[0094]

[0095]

[0096] Among them, y i It indicates whether the i-th detection quantity is abnormal, x1 is the width of the knot, x2 is the length, x3 is the width of the front, x4 is the duration, x5 is the extrusion energy and x6 is the proportion of empty cells, N is the scene width, and t is the correlation parameter between the critical value of the empty cell proportion and the scene width N.

[0097] In a specific embodiment of the present invention, according to the critical values ​​of the above six detection quantities, the present invention sets a channel scene of size 50×N (10≤N≤40), that is, the scene length is 50 cells and the scene width is N. In this channel scene, a mathematical model for determining whether a deadlock occurs in a bidirectional pedestrian flow is proposed, in which only the empty cell ratio detection quantity is related to the scene width N.

[0098] In a specific embodiment of the present invention, the above x 1 Knot width, x 2 Length, x 3 Front width, x 4 Duration, x 5 Squeeze energy and x 6 Empty cell ratio, set weight value ω respectively i , and the weight value is within the preset threshold range.

[0099] Where t represents the correlation parameter between the critical value of the empty cell ratio and the scene width N, and the two are in a piecewise linear relationship, and the definition method is shown in the above formula. For the six detection quantities, the present invention sets six weights ω in its risk assessment i Since the duration of the knot and the proportion of empty cells have predictive power for deadlock, their weight values ​​are set larger. The specific values ​​are as follows:

[0100] ω 1 =ω 2 =ω 3 =ω 5 =0.1,ω 4 =ω 6 =0.3.

[0101] In a specific embodiment of the present invention, whether the above-mentioned two-way pedestrian flow will be deadlocked is calculated using the following formula:

[0102]

[0103] Among them, z is the determining variable for whether a deadlock will occur in the bidirectional pedestrian flow, ω i is the weight value, and yi is the value of whether the i-th detection quantity is abnormal. When z is greater than or equal to 0.5, deadlock may occur; when z is less than 0.5, deadlock is unlikely to occur.

[0104] For a very narrow channel scene (N<10), the critical values ​​corresponding to the six detection quantities vary greatly compared to other scenes, and more experiments are needed to perform data statistics and then define a new risk prediction and assessment model. Therefore, the present invention only provides a pedestrian flow risk prediction and assessment model in the channel scene with the above width.

[0105] In order to explore the practicality of the above seven detection quantities in pedestrian flow risk prediction and assessment, the present invention conducted ten rounds of simulation experiments, in which five channels of different widths were set up in the scene, and data statistical analysis was performed on each detection quantity under the two conditions of free movement of pedestrian flow and deadlock. The following two tables respectively give the upper or lower critical value of the value change of each detection quantity when there is no deadlock and the value range of each detection quantity when a deadlock occurs. The change in the static speed of the knot is inconsistent in all experiments, does not show regularity, and has nothing to do with the occurrence of deadlock, so Table 1 does not include this detection quantity.

[0106]

[0107] Table 1

[0108] Through data analysis, it can be found that except for the empty cell ratio, the other detection quantities have similar upper critical values ​​in different scenarios. The empty cell ratio has a lower critical value, and this critical value increases with the increase of the scene width. In addition, it is found that in the 50×5 scene, the values ​​and critical points of most detection quantities are significantly lower than those in other scenes. The reason may be that the width of the channel is too small, and once a knot is formed, it is very easy to deadlock. Therefore, the detection quantity values ​​in critical situations are small and the range of variation is also small.

[0109]

[0110] Table 2

[0111] In addition, the present invention has found two detection quantities that have the probability to predict the occurrence of deadlock: the duration of the knot and the proportion of empty cells. Their predictions of deadlock in different scenarios are summarized in Table 2. It can be seen that the prediction stability of the proportion of empty cells is slightly poor. In some cases, the occurrence of deadlock cannot be predicted, and the prediction accuracy is about 65% on average. The prediction ability of the duration of the knot is relatively strong, with an average prediction accuracy of about 90%. Because when designing the algorithm, the program can accurately locate the knots that have appeared in the scene and time them in time, and the essence of the knot is the local congestion of the crowd in the scene, so some knots with lower risk levels will be identified, that is, knots that will not eventually cause deadlock. Naturally, the knots that will eventually lead to deadlock can almost all be detected in advance. It can be considered that predicting the occurrence of deadlock from the perspective of the duration of the knot has achieved a better error than missed, so its prediction accuracy is particularly high.

[0112] In general, the above six detection quantities have clear critical values ​​related to crowd deadlock in different width scenarios, showing good regularity in simulation experiments, and two of them have the probability of predicting the occurrence of deadlock in different scenarios. In real scenes, these detection quantities are detected in real time as the pedestrian flow moves. If the values ​​of several detection quantities exceed the critical values ​​and reach abnormal values ​​within a period of time, it indicates that the pedestrian flow may be deadlocked. Therefore, the critical values ​​of the above detection quantities can be tried as a measure of the risk level of pedestrian flow, and used to evaluate the risk level of the crowd in real scenes in real time.

[0113] Embodiment 2

[0114] like Figure 6 As shown, the embodiment of the present application provides a system for predicting and assessing the risk of bidirectional human flow in a channel, using a method for predicting and assessing the risk of bidirectional human flow in a channel, and the system includes:

[0115] The congestion detection amount acquisition module 201 is used to collect real-time dynamic data of bidirectional human flow in the channel, and acquire the detection amount of the knot of human flow based on the real-time dynamic data, wherein the knot is a local congestion of the crowd;

[0116] Prediction model building module 202: used to build a risk prediction and assessment model for abortion according to the amount of knot detection;

[0117] Prediction and evaluation module 203: used to input the crowd flow data in the scene to be evaluated into the crowd flow risk prediction and evaluation model, evaluate the detection amount of local congestion and predict the probability of deadlock of bidirectional crowds.

[0118] Embodiment 3

[0119] An embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes steps of the method for predicting and assessing the risk of bidirectional human flow in a channel.

[0120] Embodiment 4

[0121] An embodiment of the present application provides a storage medium for storing a computer program for executing the method for predicting and assessing the risk of bidirectional human flow in a channel.

[0122] Embodiment 5

[0123] An embodiment of the present application provides a crowd motion simulation tool, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the method for predicting and assessing the risk of bidirectional crowd flow in a channel are implemented.

[0124] In addition, combined Figure 1 The method for predicting and assessing the risk of bidirectional human flow in a channel described in the embodiment of the present application can be implemented by an electronic device, such as a computer device. Figure 7 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present application.

[0125] In some of these embodiments, the computer device may further include a communication interface 83 and a bus 80. Figure 7 As shown, the processor 81, the memory 82, and the communication interface 83 are connected via a bus 80 and communicate with each other.

[0126] Specifically, the processor 81 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0127] The memory 82 may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 81 .

[0128] The processor 81 reads and executes the computer program instructions stored in the memory 82 to implement any one of the methods for predicting and assessing the risk of bidirectional human flow in a channel in the above embodiments.

[0129] In summary, compared with the prior art, the method of the present invention has the following beneficial effects:

[0130] The present invention observes the formation process of the deadlock of two-way pedestrian flow in the channel from a more intuitive and concise perspective, bringing a different idea to the calculation of the detection quantity related to the crowd. Compared with the existing detection quantity, the detection quantity in the present invention is simpler and faster in calculation, and it is easy to obtain more accurate results in real scenes.

[0131] In terms of practicality, the present invention calculates six detection quantities with clear upper or lower bounds for the occurrence of deadlock, and two of the detection quantities have the probability of predicting the occurrence of deadlock. Based on the above detection quantities, the risk prediction and assessment model of bidirectional pedestrian flow in channels of different widths is evaluated to determine whether the pedestrian flow will be deadlocked. It can evaluate the risk level of pedestrian flow in real time, which helps managers to implement control of pedestrians in the channel, prevent crowd congestion and deadlock, and thus avoid stampede accidents.

[0132] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0133] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for predicting and assessing the risk of bidirectional human flow in a channel, characterized in that: The method comprises: Congestion detection amount acquisition step: collecting real-time dynamic data of bidirectional human flow in the channel, and acquiring detection amount of knots of human flow based on the real-time dynamic data, wherein the knot is a local congestion of the crowd; Prediction model establishment step: establishing an abortion risk prediction and assessment model according to the detection amount of the knot; Prediction and evaluation step: inputting the crowd flow data in the scenario to be evaluated into the crowd flow risk prediction and evaluation model, evaluating the detection amount of the local congestion and predicting the probability of deadlock of bidirectional crowds.

2. The method for predicting and assessing the risk of bidirectional human flow in a channel according to claim 1, characterized in that: The congestion detection amount acquisition step comprises: The knot length and width calculation steps are as follows: the length of the knot is calculated according to the number of rows occupied by all pedestrians in the bidirectional pedestrian flow in the channel; the width of the knot is calculated according to the number of columns occupied by all pedestrians collected; The intersection front width calculation step: collecting a matrix consisting of count values ​​of the upward and downward pedestrian flows in the channel, calculating the total width of adjacent heterogeneous pedestrian positions in the node, and obtaining the intersection front width value; The step of calculating the extrusion energy of the knot: calculating the extrusion energy of the knot based on the number of pedestrians in the knot and the width of the intersection front of the pedestrians; The static speed calculation step of the knot is as follows: according to the pedestrian category, the average speed of the static speeds of all pedestrians in the knot is calculated to obtain the static speed of the knot.

3. The method for predicting and assessing the risk of bidirectional human flow in a channel according to claim 1, characterized in that: The congestion detection amount acquisition step comprises: The step of calculating the duration of the knot: calculating the number of time steps that the knot exists in the scene, and obtaining the duration of the knot; Empty cell ratio calculation step: Calculate the ratio of the number of cells not occupied by pedestrians to the total number of cells within a preset range near the intersection surface of the knot, and obtain the empty cell ratio of the knot.

4. The method for predicting and assessing the risk of bidirectional human flow in a channel according to claim 1, characterized in that: The abortion risk prediction and assessment model includes: Among them, y i It indicates whether the i-th detection quantity is abnormal, x1 is the width of the knot, x2 is the length, x3 is the width of the front, x4 is the duration, x5 is the extrusion energy and x6 is the proportion of empty cells, N is the scene width, and t is the correlation parameter between the critical value of the empty cell proportion and the scene width N.

5. The method for predicting and assessing the risk of bidirectional human flow in a channel according to claim 1, characterized in that: The weight values ​​ω are set for the width of the x1 junction, the length of x2, the width of the front, the duration of x4, the extrusion energy of x5 and the empty cell ratio of x6. i , and the weight value is within a preset threshold range.

6. The method for predicting and assessing the risk of bidirectional human flow in a channel according to claim 1, characterized in that: Whether a deadlock will occur in the bidirectional pedestrian flow is calculated using the following formula: Among them, z is the determining variable for whether a deadlock will occur in the bidirectional pedestrian flow, ω i is the weight value, y i is the value of whether the i-th detection quantity is abnormal. When z is greater than or equal to 0.5, deadlock may occur; when z is less than 0.5, deadlock is unlikely to occur.

7. A system for predicting and assessing the risk of bidirectional human flow in a channel, using the method for predicting and assessing the risk of bidirectional human flow in a channel as claimed in any one of claims 1 to 6, characterized in that: The system comprises: Congestion detection quantity acquisition module: used to collect real-time dynamic data of bidirectional human flow in the channel, and acquire detection quantity of knots of human flow based on the real-time dynamic data, wherein the knots are local congestion of the crowd; Prediction model building module: used to build a risk prediction and evaluation model for abortion according to the detection amount of the knot; Prediction and evaluation module: used to input the crowd flow data in the scenario to be evaluated into the crowd flow risk prediction and evaluation model, evaluate the detection amount of the local congestion and predict the probability of deadlock in bidirectional crowds.

8. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the steps of the method for predicting and assessing the risk of bidirectional human flow in a channel as described in any one of claims 1 to 6.

9. A storage medium, characterized in that: Used to store a computer program for executing the method for predicting and evaluating the risk of bidirectional human flow in a channel as described in any one of claims 1-6.

10. A crowd motion simulation tool, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the method for predicting and assessing the risk of bidirectional crowd flow in a channel as described in any one of claims 1 to 6 are implemented.

Images