Urban rail transit passenger flow induction method and safety management system based on graph theory

Abstract

The present application relates to the field of rail transit technology, and specifically to a method for inducing passenger flow in urban rail transit and a safety management system based on graph theory. The method comprises: constructing a network topology diagram based on the spatial topological relationship within a rail transit station, and obtaining the passenger flow of each road section at different times through real-time monitoring video images of each road section within the rail transit station; calculating the traffic option value, traffic status value, traffic efficiency value, and induction weight of each road section at the current moment; obtaining the weighted network topology diagram at the current moment, combining it with a dynamic path planning algorithm to obtain the optimal induction path, and inducing passengers in the rail transit station to reasonably choose the traffic path. The present application updates the optimal induction path in real time, improves the accuracy of the induction path planning, avoids dense distribution of passengers in the station, effectively prevents and alleviates the occurrence of safety hazards, and improves the safety of passengers.

Description

Technical Field

[0001] The present application relates to the field of rail transit technology, and in particular to a graph-theory-based urban rail transit passenger flow induction method and safety management system. Background Art

[0002] As rail transit expands, large passenger flows have become the norm. These high passenger flows within rail transit stations not only cause congestion and affect passenger efficiency, but can also lead to stampedes if effective evacuation measures are not implemented, posing a significant safety hazard.

[0003] For urban rail transit such as subways and light rail, the walking guidance information currently provided to passengers in stations is mainly static guidance signs, which fail to consider the real-time dynamic impact of the periodic arrival of trains on passenger flow. This can easily lead to deviations in the judgment of passenger flow, affecting the rationality and accuracy of route planning, resulting in poor guidance effect, dense distribution of passengers in the station, and prone to safety hazards. Summary of the Invention

[0004] In order to solve the above technical problems, an urban rail transit passenger flow induction method and a safety management system based on graph theory are provided to solve the existing problems.

[0005] The solution to the technical problem of this application is to provide a graph-theory-based urban rail transit passenger flow induction method and safety management system, including the following steps:

[0006] In a first aspect, an embodiment of the present application provides a method for inducing passenger flow in urban rail transit based on graph theory, the method comprising the following steps:

[0007] Based on the spatial topological relationship within the rail transit station, a network topology map is constructed, and the passenger flow of each section at different times is obtained through real-time monitoring video images of each section within the rail transit station;

[0008] Analyze the periodic changes in passenger flow of each road section in the historical period, combine the predicted trend of passenger flow of each road section at the current moment, and calculate the available value of each road section at the current moment;

[0009] The current moment and the previous moments are recorded as a local period, and the traffic status value of each road section at the current moment is calculated based on the changing trend and discreteness of the passenger flow of each road section in the local period;

[0010] Determining a traffic efficiency value of each road section at a current moment based on the traffic optional value and the traffic status value;

[0011] Based on the distance characteristics of each road section and the traffic efficiency value, determining the induction weight of each road section at the current moment;

[0012] Based on the induction weights, a weighted network topology diagram at the current moment is obtained, and combined with a dynamic path planning algorithm, an optimal induction path is obtained to guide passengers in the rail transit station to reasonably choose a travel path.

[0013] Preferably, target detection is performed on the surveillance video image to obtain the passenger flow of each road section at different times.

[0014] Preferably, the calculation of the passable optional value of each road section at the current moment includes:

[0015] Decompose the passenger flow of each road section at all times during the historical period and calculate the periodic intensity of each road section;

[0016] Passenger flow forecasting is performed based on the changing trend of passenger flow of each road section in the historical period to determine the predicted passenger flow of each road section at the current moment;

[0017] The ratio of the periodic intensity to the predicted passenger flow is used as the traffic optional value of each road section at the current moment.

[0018] Preferably, the process of determining the predicted passenger flow is:

[0019] Based on the passenger flow of each road section at all times in the historical period, the passenger flow of each road section at multiple times after the current moment is predicted through a prediction algorithm, and the average of the predicted passenger flow of each road section at multiple times after the current moment is used as the predicted passenger flow of each road section at the current moment.

[0020] Preferably, the calculation of the traffic status value of each road section at the current moment includes:

[0021] Calculate the degree of dispersion of passenger flow at all times within the local time period for each road section at the current moment;

[0022] Calculate the rate of change of passenger flow of each road section between each moment in the local time period and the previous moment; take the average of all the change rates of each road section in the local time period as the average change rate of each road section at the current moment;

[0023] The traffic state value is a normalized result of the product of the average change rate and the discrete degree.

[0024] Preferably, the traffic efficiency value is the ratio of the traffic optional value to the traffic status value.

[0025] Preferably, the determining of the induction weight of each road section at the current moment includes:

[0026] Calculate the distance length of each road section; perform negative mapping on the distance length of each road section;

[0027] By presetting the first weight and the second weight, the traffic efficiency value and the result of the negative mapping processing are weightedly summed to obtain the induced weight of each road section at the current moment, wherein the sum of the preset first weight and the preset second weight is 1, and the preset first weight is greater than the preset second weight.

[0028] Preferably, the method for obtaining the weighted network topology map at the current moment is:

[0029] Each road section corresponds to each edge in the network topology graph, and the induced weight is used as the weight of each edge in the network topology graph to obtain the weighted network topology graph at the current moment.

[0030] Preferably, obtaining the optimal induction path includes:

[0031] Obtain the passenger's starting and ending points at the current moment through the GPS positioning system;

[0032] Based on the starting point and the end point, and the weighted network topology graph, an optimal induced path is calculated by a dynamic path planning algorithm.

[0033] In a second aspect, an embodiment of the present application further provides an urban rail transit safety management system based on graph theory, the system comprising:

[0034] The road section monitoring module is used to construct a network topology map based on the spatial topology relationship within the rail transit station, and obtain the passenger flow of each road section at different times through the monitoring video images of each road section in the rail transit station in real time;

[0035] The path analysis module analyzes the periodic changes in passenger flow of each road section over a historical period, and calculates the traffic option value of each road section at the current moment in combination with the predicted trend of passenger flow of each road section at the current moment; records the current moment and multiple moments before it as a local time period, and calculates the traffic status value of each road section at the current moment based on the changing trend and discreteness of passenger flow of each road section within the local time period; determines the traffic efficiency value of each road section at the current moment based on the traffic option value and the traffic status value; determines the induction weight of each road section at the current moment based on the distance characteristics of each road section and the traffic efficiency value; obtains a weighted network topology map at the current moment based on the induction weight, and obtains the optimal induction path by combining the dynamic path planning algorithm;

[0036] The passenger flow induction module is used to issue induction information to passengers through the optimal induction path, inducing passengers in the rail transit station to reasonably choose the passage path.

[0037] This application has at least the following beneficial effects:

[0038] This application constructs a network topology diagram based on the spatial topological relationship within the station, and calculates the traffic optional value of each road section at the current moment by analyzing the periodic change pattern of passenger flow on the road section corresponding to each edge in the network topology diagram and the analysis results of the passenger flow prediction of each road section. Its beneficial effect is that it takes into account the distribution trend of passenger flow of each road section in the future period, combined with the degree of periodic change of passenger flow in the historical period, so as to more accurately reflect the accuracy of passenger flow prediction, so as to evaluate the traffic efficiency of each road section in the subsequent time period; secondly, through the fluctuation of passenger flow in the local time period at the current moment, and the rate of change of passenger flow, the traffic status value of each road section at the current moment is calculated. Its beneficial effect is that it takes into account the speed of increase or decrease of passenger flow of each road section, so as to illustrate the movement speed of passengers in the section. , and then reflect the traffic flow of the section; determine the traffic efficiency value of each section at the current moment, and obtain the induction weight of each section at the current moment. Its beneficial effect is that it takes into account the traffic efficiency of passengers on each section and the distance length of the section to evaluate the possibility of inducing passengers to choose this section for passage; construct a weighted network topology map, calculate the optimal induction path through a dynamic path planning algorithm, and release induction information to passengers to induce passengers to reasonably choose the passage path. Its beneficial effect is that it takes into account the periodic impact of the periodic entry of trains on passenger flow, and can update the optimal induction path in real time by analyzing the changes in passenger flow in real time, reduce the assessment deviation of passenger flow, improve the accuracy of induction path planning, avoid dense distribution of passengers in the station, effectively prevent and alleviate the occurrence of safety hazards, and improve passenger traffic safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The urban rail transit passenger flow induction method based on graph theory of the present application is further described in detail below with reference to the accompanying drawings.

[0040] Figure 1 A flowchart of the steps of the urban rail transit passenger flow induction method based on graph theory provided in an embodiment of the present application;

[0041] Figure 2 A flowchart of the steps of the method for obtaining the passable optional value of each road section at the current moment provided in an embodiment of the present application;

[0042] Figure 3 A flowchart of the steps of the method for obtaining the traffic status value of each road section at the current moment provided in an embodiment of the present application;

[0043] Figure 4 A block diagram of the urban rail transit safety management system based on graph theory provided in an embodiment of the present application. DETAILED DESCRIPTION

[0044] To make the objectives, technical solutions, and advantages of this application more clearly understood, the graph-theory-based urban rail transit passenger flow induction method and safety management system proposed in this application are further described in detail below with reference to the accompanying drawings and implementation examples. It should be understood that the specific embodiments described herein are merely intended to explain this application and are not intended to limit this application.

[0045] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0046] See also Figure 1 , which shows a flowchart of the steps of a method for inducing passenger flow in urban rail transit based on graph theory provided by an embodiment of the present application, the method comprising the following steps:

[0047] Step 1: Based on the spatial topological relationship within the rail transit station, a network topology map is constructed, and the passenger flow of each section at different times is obtained through real-time monitoring video images of each section within the rail transit station.

[0048] Graph theory is a branch of mathematics dedicated to the study of graphs. It provides a language for describing networks and a platform for research. By studying graphs, we can derive specific topological properties of real-world networks. Therefore, we use graph theory to represent the network topology within subway stations in urban rail transit.

[0049] Therefore, through the spatial topological relationship within the subway station, each entrance and exit, security gate, staircase or elevator, and waiting area in the subway station are abstracted as nodes, and the sections of road that can be passed between different nodes are abstracted as edges, thus forming a network topology graph.

[0050] Secondly, each section of the route is monitored in real time through surveillance cameras in subway stations. Target detection algorithms are used to detect passengers in the surveillance videos of each section of the route, and the passenger flow of each section is obtained in real time.

[0051] In this embodiment, the Faster R-CNN algorithm is used for target detection. The Faster R-CNN algorithm is a well-known technology and will not be described in detail here. As other implementation methods, the implementer may adopt other methods of the existing technology, such as the YOLOV5 algorithm, etc. This embodiment does not impose any special restrictions on this. Secondly, in this embodiment, the passenger flow is counted for each road section every 1 minute.

[0052] It should be noted that each road segment corresponds to each edge in the network topology graph.

[0053] At this point, the passenger flow of each road section and the network topology map are obtained in real time.

[0054] Step 2: Analyze the periodic changes in passenger flow of each road section during the historical period, and calculate the available value of each road section at the current moment based on the predicted trend of passenger flow of each road section at the current moment.

[0055] Normally, when inducing passenger flow, it is generally necessary to consider the passenger flow and distance of each road section, and try to let passengers pass through the road section with less passenger flow, less travel time and the shortest distance. However, the passenger flow in the subway station changes very quickly, especially when the train enters the station, a large number of passengers will enter the train, and a large number of passengers will leave the station. Since the arrival time of each train is fixed, the passenger flow in the subway station will change periodically. The passenger flow of each road section is predicted based on the passenger flow changes in the historical period, and then the pass option value of each road section is calculated. The step flow chart of the method for obtaining the pass option value of each road section at the current moment provided in the embodiment of the present application is as follows: Figure 2 As shown, specifically including:

[0056] Through the surveillance video images of several days in history, the passenger flow of each road section at each time in the historical period is obtained;

[0057] In this embodiment, assuming that the operating hours of the subway station are from 6:00 to 23:00, the passenger flow of each road section at each time between 6:00 and 23:00 is obtained; therefore, surveillance videos of 7 days a week are selected, and the passenger flow of each road section at each time during the historical period is obtained through the target detection algorithm. As other implementation methods, the implementer can set them according to the actual situation.

[0058] Decompose the passenger flow of each road section at all times during the historical period and calculate the periodic intensity of each road section;

[0059] In this embodiment, the STL (Seasonal and Trend decomposition using Loess) algorithm is used for trend decomposition. The STL algorithm is a well-known technique and will not be described in detail here. Secondly, the STL algorithm is used to decompose the passenger flow of each road segment at all times during the historical period into a seasonal series and a residual series. The seasonal series generally reflects the cyclical changes in passenger flow. Therefore, the calculation of the cyclical strength is consistent with the calculation of the seasonal strength. The calculation formula for the cyclical strength is: ,in, is the periodic intensity, is the variance of the residual sequence, is the variance of the seasonal series and the residual series, To find the maximum value; the calculation formula of seasonal intensity is a well-known technology and will not be described here.

[0060] It should be noted that, the greater the periodic intensity, the stronger the regularity of the passenger flow change on the section within the subway station.

[0061] Based on the passenger flow of each road section at all times in the historical period, the passenger flow of each road section at multiple times after the current moment is predicted through a prediction algorithm. The average of the passenger flow predicted for each road section at multiple times after the current moment is used as the predicted passenger flow of each road section at the current moment.

[0062] In this embodiment, a long short-term memory (LSTM) network model is used for prediction. The LSTM network model is a well-known technology and will not be described in detail here. As other implementation methods, the implementer may adopt other methods of the existing technology, such as the BP neural network model, the ARIMA model, etc. This embodiment does not impose any special restrictions on this. Secondly, the predicted passenger flow of each road section at all times within 7 minutes after the current time is obtained. As other implementation methods, the implementer may set it according to the actual situation.

[0063] The ratio of the periodic intensity to the predicted passenger flow is used as the traffic optional value of each road section at the current moment;

[0064] It should be noted that the smaller the predicted passenger flow, the smaller the passenger flow of the section at subsequent times, and the larger the obtained traffic option value, reflecting that the traffic on the section is smoother at this time, and the more passengers should be induced to choose this section for passage.

[0065] At this point, the available values ​​for each road section at the current moment are obtained.

[0066] Step 3: record the current moment and the previous moments as a local period, and calculate the traffic status value of each road section at the current moment by the changing trend and discreteness of the passenger flow of each road section in the local period.

[0067] Furthermore, if there are continuous passengers entering the subway station but the train is still a long time away from arriving, the passenger flow inside the station will only increase and not decrease for a period of time. Then the passenger flow in different areas of the station will be in a large state. After passenger flow induction, there will be a larger passenger flow in some local areas, which will increase the probability of safety hazards.

[0068] Secondly, among the passengers entering the subway station, one type of passengers is there to travel by train. This type of passengers moves relatively slowly when faced with a large passenger flow. Another type of passengers commutes between the two entrances and exits of the station to reach the other side of the road. This type of passengers can enter the station and quickly exit from the other exit, so the passenger movement speed is relatively fast. By analyzing the changing speed of passenger flow on different road sections and calculating the traffic status value, the step flow chart of the method for obtaining the traffic status value of each road section at the current moment provided by the embodiment of the present application is as follows: Figure 3 As shown, specifically including:

[0069] The current moment and the previous moments are recorded as local time periods;

[0070] In this embodiment, the current moment and the seven moments before it are recorded as a local time period, wherein the value 7 is selected based on the departure time interval of trains in urban rail transit. As other implementation methods, the implementer can set it according to actual conditions.

[0071] Calculate the degree of dispersion of passenger flow at all times within the local time period for each road section at the current moment;

[0072] In this embodiment, the degree of dispersion is measured by calculating the standard deviation of the passenger flow of each road section at the current moment at all moments in the local time period. As other implementation methods, the implementer can adopt other methods of the existing technology, such as variance, mean absolute deviation, etc., and this embodiment does not impose any special restrictions on this.

[0073] Calculate the change rate of passenger flow of each road section at the current moment between two adjacent moments in the local time period; take the average of all the change rates of each road section at the current moment in the local time period as the average change rate of each road section at the current moment;

[0074] It should be noted that the calculation of the change rate is a well-known technology and will not be described in detail here.

[0075] Normalizing the product of the average rate of change and the degree of dispersion as the traffic state value of each road section at the current moment;

[0076] In this embodiment, the sigmoid function is used for normalization processing, wherein the sigmoid function is a well-known technology and will not be described in detail here. As other implementation methods, the implementer can adopt other methods of the existing technology, such as the tanh function, etc. This embodiment does not impose any special restrictions on this.

[0077] It should be noted that, if the average rate of change is a positive number and its absolute value is larger, the faster the passenger flow on the section is growing, which reflects that the passenger flow has increased significantly, the passenger flow on the section is dense, and the traffic is relatively congested; if the average rate of change is a negative number and its absolute value is larger, the faster the passenger flow on the section is decreasing, which reflects that passengers can pass quickly on the section; the greater the degree of dispersion, the greater the fluctuation of passenger flow in the local time period. Therefore, after normalization processing, the smaller the traffic status value obtained, the faster the passenger flow on the section is decreasing, which reflects that the traffic on the section is smoother, and the more passengers should be guided to the section with smoother traffic to facilitate their quick travel to the waiting area.

[0078] At this point, the traffic status value of each road section at the current moment is obtained.

[0079] Step 4: Based on the traffic optional value and the traffic status value, determine the traffic efficiency value of each road section at the current moment; based on the distance characteristics of each road section and combined with the traffic efficiency value, determine the induction weight of each road section at the current moment; based on the induction weight, obtain the weighted network topology map at the current moment, combine with the dynamic path planning algorithm, obtain the optimal induction path, and induce passengers in the rail transit station to reasonably choose the traffic path.

[0080] Furthermore, based on the traffic optional value and the traffic state value, a traffic efficiency value is determined, specifically:

[0081] The ratio of the traffic optional value to the traffic status value is used as the traffic efficiency value of each road section at the current moment;

[0082] It should be noted that the larger the traffic efficiency value is, the higher the traffic efficiency of the road section is, and the more passengers should be induced to choose this road section for passage.

[0083] Secondly, in order to allow passengers to travel on sections with less passenger volume and shorter travel time, the induction weight of each section is calculated based on the traffic efficiency value and the distance of each section, specifically:

[0084] Calculate the distance length of each road segment;

[0085] Perform negative mapping on the distance lengths of all road segments;

[0086] In this embodiment, the negative mapping process is: calculating the cumulative sum of the maximum and minimum distance lengths of all road sections; and subtracting the difference between the cumulative sum and the distance of each road section.

[0087] By performing a weighted summation on the traffic efficiency value and the result of the negative mapping process using a preset first weight and a preset second weight, an induced weight of each road section at the current moment is obtained, wherein the sum of the preset first weight and the preset second weight is 1, and the preset first weight is greater than the preset second weight;

[0088] In this embodiment, the preset first weight value is 0.7, and the preset second weight value is 0.3. As other implementation methods, the implementer can set them according to actual conditions.

[0089] It should be noted that the greater the induction weight, the more passengers should be induced to choose this road section for passage.

[0090] Each road section corresponds to each edge in the network topology graph, and the induced weight is used as the weight of each edge in the network topology graph to obtain a weighted network topology graph at the current moment;

[0091] Through the GPS positioning system, the starting and ending points of the passengers at the current moment are obtained, and the optimal guidance path is calculated through the dynamic path planning algorithm. Guidance information is issued to passengers, or the recommended path is displayed through the electronic display screen in the station to guide passengers to reasonably choose the passage path, thereby avoiding the dense distribution of passengers in the station, effectively preventing and alleviating the occurrence of safety hazards, and improving the travel safety of passengers.

[0092] In this embodiment, the dynamic path planning algorithm adopts the D*Lite algorithm, wherein the D*Lite algorithm is a well-known technology and will not be described in detail here. As other implementation methods, the implementer can adopt other methods of the existing technology, such as the Dijkstra algorithm, etc. This embodiment does not impose any special restrictions on this.

[0093] Based on the same inventive concept as the above method, an embodiment of the present application further provides a graph-theory-based urban rail transit safety management system, the system comprising:

[0094] The road section monitoring module is used to construct a network topology map based on the spatial topology relationship within the rail transit station, and obtain the passenger flow of each road section at different times through the monitoring video images of each road section in the rail transit station in real time;

[0095] The path analysis module analyzes the periodic changes in passenger flow of each road section over a historical period, and calculates the traffic option value of each road section at the current moment in combination with the predicted trend of passenger flow of each road section at the current moment; records the current moment and multiple moments before it as a local time period, and calculates the traffic status value of each road section at the current moment based on the changing trend and discreteness of passenger flow of each road section within the local time period; determines the traffic efficiency value of each road section at the current moment based on the traffic option value and the traffic status value; determines the induction weight of each road section at the current moment based on the distance characteristics of each road section and the traffic efficiency value; obtains a weighted network topology map at the current moment based on the induction weight, and obtains the optimal induction path by combining the dynamic path planning algorithm;

[0096] The passenger flow induction module is used to issue induction information to passengers through the optimal induction path, inducing passengers in the rail transit station to reasonably choose the passage path.

[0097] Among them, the block diagram of the urban rail transit safety management system based on graph theory provided by the embodiment of the present application is as follows Figure 4 shown.

[0098] It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0099] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above 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.

[0100] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the present application. It should be noted that a person skilled in the art can make various modifications and improvements without departing from the spirit of the present application. Therefore, any simple modifications, equivalent variations, and modifications to the above embodiments made in accordance with the technical essence of the present application without departing from the content of the present application's technical solution fall within the scope of protection of the present application's technical solution.

Claims

1. A graph-theory-based urban rail transit passenger flow induction method, characterized in that: The method comprises the following steps: Based on the spatial topological relationship within the rail transit station, a network topology map is constructed, and the passenger flow of each section at different times is obtained through real-time monitoring video images of each section within the rail transit station; Analyze the periodic changes in passenger flow of each road section in the historical period. Combined with the predicted trend of passenger flow of each road section at the current moment, calculate the pass option value of each road section at the current moment. The pass option value is the ratio of periodic intensity to predicted passenger flow. Periodic intensity is obtained by trend decomposing the passenger flow of each road section at all times in the historical period. The predicted passenger flow is obtained by predicting the passenger flow of each road section based on the changing trend of passenger flow in the historical period. Periodic intensity is used to characterize the regularity of passenger flow changes on the road section. The current moment and the previous moments are recorded as a local period, and the traffic status value of each road section at the current moment is calculated based on the changing trend and discreteness of the passenger flow of each road section in the local period; Determining a traffic efficiency value of each road section at a current moment based on the traffic optional value and the traffic status value; Based on the distance characteristics of each road section and in combination with the traffic efficiency value, an induction weight for each road section at the current moment is determined. The induction weight is obtained by weighted summing the results of negative mapping the traffic efficiency value and the distance length of each road section using a preset first weight and a preset second weight, where the sum of the preset first weight and the preset second weight is 1, and the preset first weight is greater than the preset second weight. The induction weight is used to represent the probability of inducing passenger flow to select a road section for passage; Based on the induction weights, a weighted network topology diagram at the current moment is obtained, and combined with a dynamic path planning algorithm, an optimal induction path is obtained to guide passengers in the rail transit station to reasonably choose a travel path.

2. The urban rail transit passenger flow induction method based on graph theory according to claim 1, characterized in that: Target detection is performed on the surveillance video image to obtain the passenger flow of each road section at different times.

3. The urban rail transit passenger flow induction method based on graph theory according to claim 1, characterized in that: The process of determining the predicted passenger flow is as follows: Based on the passenger flow of each road section at all times in the historical period, the passenger flow of each road section at multiple times after the current moment is predicted through a prediction algorithm, and the average of the predicted passenger flow of each road section at multiple times after the current moment is used as the predicted passenger flow of each road section at the current moment.

4. The urban rail transit passenger flow induction method based on graph theory according to claim 1, characterized in that: The calculation of the traffic status value of each road section at the current moment includes: Calculate the degree of dispersion of passenger flow at all times within the local time period for each road section at the current moment; Calculate the rate of change of passenger flow of each road section between each moment in the local time period and the previous moment; take the average of all the change rates of each road section in the local time period as the average change rate of each road section at the current moment; The traffic state value is a normalized result of the product of the average change rate and the discrete degree.

5. The urban rail transit passenger flow induction method based on graph theory according to claim 1, characterized in that: The traffic efficiency value is the ratio of the traffic optional value to the traffic status value.

6. The urban rail transit passenger flow induction method based on graph theory according to claim 1, characterized in that: The method for obtaining the weighted network topology map at the current moment is: Each road section corresponds to each edge in the network topology graph, and the induced weight is used as the weight of each edge in the network topology graph to obtain the weighted network topology graph at the current moment.

7. The urban rail transit passenger flow induction method based on graph theory according to claim 1, characterized in that: Obtaining the optimal induction path includes: Obtain the passenger's starting and ending points at the current moment through the GPS positioning system; Based on the starting point and the end point, and the weighted network topology graph, an optimal induced path is calculated by a dynamic path planning algorithm.

8. An urban rail transit safety management system based on graph theory, applying the urban rail transit passenger flow induction method based on graph theory in claim 1, characterized in that: The system comprises: The road section monitoring module is used to construct a network topology map based on the spatial topology relationship within the rail transit station, and obtain the passenger flow of each road section at different times through the monitoring video images of each road section in the rail transit station in real time; The path analysis module analyzes the periodic changes in passenger flow of each road section in the historical period, and calculates the traffic option value of each road section at the current moment in combination with the predicted trend of passenger flow of each road section at the current moment. The traffic option value is the ratio of periodic intensity to predicted passenger flow. Periodic intensity is obtained by trend decomposing the passenger flow of each road section at all times in the historical period. The predicted passenger flow is obtained by predicting the passenger flow based on the changing trend of passenger flow of each road section in the historical period. Periodic intensity is used to characterize the regularity of passenger flow changes on the road section. The current moment and multiple moments before it are recorded as local time periods. The traffic option value of each road section at the current moment is calculated by the changing trend and discreteness of the passenger flow of each road section in the local time period. The traffic state value; based on the traffic optional value and the traffic state value, determining the traffic efficiency value of each road section at the current moment; based on the distance characteristics of each road section, combined with the traffic efficiency value, determining the induction weight of each road section at the current moment, the induction weight is obtained by weighted summing the results of negative mapping processing of the traffic efficiency value and the distance length of each road section by a preset first weight and a preset second weight, the sum of the preset first weight and the preset second weight is 1, and the preset first weight is greater than the preset second weight, and the induction weight is used to characterize the probability of inducing passenger flow to select a road section for passage; based on the induction weight, obtaining a weighted network topology map at the current moment, and combining it with a dynamic path planning algorithm to obtain the optimal induction path; The passenger flow induction module is used to issue induction information to passengers through the optimal induction path, inducing passengers in the rail transit station to reasonably choose the passage path.

Images