A method for urban rail transit flow prediction and evacuation based on mobile phone signaling

Abstract

This invention discloses a method for predicting and evacuating urban rail transit traffic flow based on mobile phone signaling. The method includes: obtaining the impact range and affected rail transit network area of ​​a geological disaster based on emergency warning information; real-time collection of signaling data from mobile communication networks and base station operation status data within the impact range; filtering and supplementing the signaling data based on the base station operation status data to determine an emergency available signaling dataset; constructing a dynamic grid map, mapping the signaling data from the emergency available signaling dataset to the dynamic grid, and statistically analyzing user dwell time and cross-grid movement within each grid; determining the predicted passenger flow under disaster disturbance based on the user dwell time and cross-grid movement within each grid; and generating a dynamic evacuation method for rail transit based on the predicted passenger flow and a preset real-time network vulnerability assessment value. By linking geological disaster monitoring with rail transit emergency response, emergency safety is improved.

Description

Technical Field

[0001] This invention relates to the field of geological disaster technology, and more specifically, to a method for predicting and evacuating urban rail transit traffic flow based on mobile phone signaling. Background Technology

[0002] Urban rail transit, as a high-capacity and high-efficiency mode of public transportation, plays a vital role in daily commuting and the evacuation of people in emergency situations. However, sudden geological disasters (such as earthquakes, landslides, and mudslides) are characterized by their suddenness, destructiveness, and frequent secondary disasters, posing a serious threat to the operational safety of rail transit.

[0003] Most existing methods for predicting rail transit passenger flow are based on historical, normal data, such as time series models and regression analysis models. Their core assumption is that passenger flow changes are regular and periodic. However, during geological disasters, people's travel behavior exhibits significant irrational characteristics—panic evacuation, risk-averse gatherings, and increased randomness in routes—causing historical patterns to completely fail. Traditional models cannot capture the "reverse evacuation" passenger flow characteristics triggered by disasters, leading to a sharp increase in prediction errors and making it difficult to support emergency decision-making.

[0004] Therefore, existing technologies have shortcomings and urgently need improvement. Summary of the Invention

[0005] To address at least one of the aforementioned technical problems, the present invention aims to provide a method for predicting and evacuating urban rail transit traffic flow based on mobile phone signaling, which can link geological disaster monitoring with rail transit emergency response, thereby improving emergency safety.

[0006] This invention provides a method for predicting and dispersing urban rail transit traffic flow based on mobile phone signaling, including: Based on emergency warning information caused by geological disasters, the scope of impact of geological disasters and the affected rail transit network can be obtained; Real-time collection of signaling data and base station operation status data of mobile communication networks within the affected area; Based on the base station operation status data, the signaling data is filtered and supplemented to determine the emergency available signaling dataset; Construct a dynamic grid map, map the signaling data in the emergency available signaling dataset to the dynamic grid, and count the number of users staying in each grid and the amount of movement across grids; Based on the number of users staying in each grid and the amount of movement across grids, the predicted passenger flow under disaster disturbances is determined; Based on the predicted passenger flow and the preset real-time road network vulnerability assessment value, a dynamic evacuation method for rail transit is generated. The evacuation method will be pushed to mobile phone users in the affected area via emergency broadcast and targeted signaling.

[0007] In this solution, the step of obtaining the scope of the rail transit network affected by geological disasters specifically includes: Obtain the location of the epicenter / slip surface, the radius of influence R, and the intensity distribution of the geological disaster; Obtain geographic information of rail transit lines; Spatial overlay analysis of the geographic information of rail transit lines and intensity distribution: rail stations and sections located in intensity VI and above are designated as directly affected areas; Extract historical passenger flow data for rail stations adjacent to the directly affected area and for the corresponding rail stations; Determine the correlation between the passenger flow sources of the corresponding rail stations and the directly affected areas based on historical passenger flow data of the corresponding rail stations; If the correlation between the passenger flow sources of the corresponding rail station and the directly affected area is greater than the preset correlation threshold, then the area between the corresponding rail stations in the directly affected area will be set as the indirect linkage area. The areas directly affected and indirectly affected will be merged to determine the scope of the rail transit network affected by geological disasters.

[0008] In this solution, the step of filtering signaling data based on base station operation status data specifically includes: Based on the base station's operational status data, determine the base station's operational status code and average signaling delivery volume at the time point prior to triggering the emergency alert. The running status code and average signaling delivery volume at a time point after the emergency alert is triggered. ; Based on the same base station, the average signaling delivery volume Subtract average signaling delivery The average signaling delivery volume difference of the corresponding base station is obtained; If the difference in the average signaling delivery volume of the corresponding base station is less than or equal to the preset average signaling delivery volume threshold and the status code is displayed as abnormal, then the corresponding base station is determined to be abnormal. The signaling data in the corresponding grid of the base station that is determined to be abnormal will be deleted.

[0009] In this solution, the step of calculating the user dwell time within each grid cell specifically includes: The signaling data in the emergency available signaling dataset is classified according to mobile phone users and the trajectory difference is calculated to generate a sequence of virtual trajectory points at equal time intervals. Extract the distance between the virtual trajectory point of the mobile user at time node t and the grid boundary; If the distance value is greater than or equal to the preset positioning error radius, the dwell weight of the corresponding virtual trajectory point in the corresponding grid is set to 1. If the distance value is less than the preset positioning error radius, the dwell time weight of the corresponding virtual trajectory point will be distributed to multiple adjacent grids according to the distance weighting. After iterating through the distance values ​​between all virtual trajectory points of the mobile user at time node t and the grid boundary, the dwell weights of all users within the same grid are summed to obtain the user dwell value within that grid.

[0010] This plan also includes: Extract the grid cells covered by abnormal base stations and designate them as abnormal grid cells; Extracting from the abnormal grid as the center Mobile signaling users whose time points appear in adjacent or abnormal grids; If the mobile phone signaling user is If the time point also appears in an adjacent grid or other grids, the corresponding mobile signaling user will be deleted, and the remaining mobile signaling users will be set as lost users. Set the number of users who have lost contact as the number of users staying in the grid covered by the abnormal base station.

[0011] In this solution, the step of calculating the cross-grid movement specifically includes: Extract the dwell time weights of virtual trajectory points at adjacent time nodes in the same virtual trajectory point sequence; If the dwell weights of virtual trajectory points at corresponding adjacent time nodes are all greater than the preset first weight coefficient, and the virtual trajectory points at adjacent time nodes belong to different grids, then a movement is determined to have occurred, and the minimum value among the dwell weight coefficients of virtual trajectory points at corresponding adjacent time nodes is set as the movement amount for this movement. ; After traversing all virtual trajectory point sequences, extract all movement amounts from grid g to grid h and sum them up to obtain the cross-grid movement amount from grid g to grid h.

[0012] In this scheme, the step of determining the predicted passenger flow under disaster disturbance based on the user dwell time and cross-grid movement within each grid specifically includes: Extract stations from the rail transit network and extract the grid cells within the influence range of the corresponding stations; Based on the grids within the influence range of the corresponding site, extract the user dwell time, cross-grid eviction rate, and cross-grid eviction rate within the corresponding grid. Set the corresponding station as A, the grid within the influence range of the corresponding station as a, and the predicted passenger flow for the corresponding effective safe evacuation station as... Its formula is: ,in This represents the number of users staying in grid a at time point t. This represents the panic index at time t. This represents the cross-grid shift amount of grid a at time t. This represents the cross-grid movement amount of grid a at time node t. , The corresponding weighting coefficients are shown, and "*" indicates multiplication.

[0013] In this scheme, the step of generating a dynamic evacuation method for rail transit based on predicted passenger flow and preset real-time road network vulnerability assessment values ​​specifically includes: Based on the preset real-time road network vulnerability assessment value, determine the vulnerability assessment value of each station; based on the predicted passenger flow, determine the population density of the grid within the influence range of the corresponding station. If the vulnerability assessment value of a site is greater than the preset assessment threshold, the site is determined to be a high-risk site, and the grid range within the site's influence area is set as a high-risk grid range. If the population density of the grid within the influence range of the corresponding site is greater than the preset density threshold, the site is determined to be a high-density site, and the grid range within the influence range of the site is set as a high-density grid range. Based on preset evacuation rules and with minimum time as the constraint, corresponding evacuation routes are constructed according to user mobile phone signaling data. The preset evacuation rules include at least the principle that high-risk / high-density grid areas are prohibited from passage and that high-risk / high-density sites should be evacuated to low-risk / low-density sites.

[0014] In this solution, after generating the dynamic evacuation method for rail transit, the following is also included: Real-time acquisition of mobile signaling trajectories via mobile signaling data; By comparing and analyzing the mobile phone signaling trajectory with the evacuation path in the corresponding evacuation method, the individual trajectory deviation angle can be determined. Extract the trajectory deviation angles of all individuals within a preset range and calculate the average to obtain the group deviation angle; When the group deviation angle is less than the preset deviation angle threshold, if the individual trajectory deviation angle is greater than the preset deviation angle threshold and the duration is greater than the preset first time threshold, then the corresponding individual evacuation error message will be triggered. If the deviation angle of the group is greater than or equal to the preset deviation angle threshold and the duration is greater than the preset first time threshold, the current guided evacuation method is deemed to have failed and a warning message is issued; if the deviation angle of an individual trajectory is less than or equal to the preset deviation angle threshold and the duration is greater than the preset first time threshold, the corresponding evacuation trajectory real-time adjustment prompt message is triggered. Based on the warning message indicating that the current guided evacuation method has failed, the evacuation method is updated.

[0015] This plan also includes: Receive secondary disaster early warning information in real time from the geological disaster monitoring system; When a secondary disaster is detected, it is determined whether its impact range is within the current geological disaster impact range. If not, the corresponding newly added impact range is extracted. The scope of the geological disaster and the affected rail transit network will be revised based on the newly added impact area, and passenger flow forecasts and evacuation route planning will be carried out again.

[0016] One or more technical solutions proposed in this application have at least the following technical effects: 1. This invention links geological disaster monitoring with urban rail transit, upgrading the monitoring and emergency response of geological disasters and urban rail transit from manual judgment to automatic triggering, shortening the response time from minutes to seconds, and effectively realizing the allocation of emergency resources by gridding the impact range of geological disasters and urban rail transit, thereby improving safety assurance; 2. By assessing the base stations within the impact range of geological disasters, damaged base stations are identified, signaling data is then filtered, and signaling data within the range of deleted base stations is supplemented with historical signaling data, thereby improving the accuracy of signaling data; 3. By real-time monitoring of signaling data within the impact range of geological disasters and real-time comparative analysis with evacuation routes in evacuation methods, the deviation angles of individual trajectories and groups are calculated, and the deviation angles are determined. This upgrades emergency evacuation from a static plan to a dynamic adaptive system, enabling real-time response to emergencies and adjustment of evacuation routes, significantly improving evacuation efficiency. In summary, this invention constructs a complete method for predicting and evacuating urban rail transit traffic flow in geological disaster scenarios by utilizing technical features such as disaster-triggered linkage, failure base station identification, cross-grid movement prediction, multi-dimensional vulnerability assessment, and trajectory deviation angle. Attached Figure Description

[0017] Figure 1 A flowchart of an urban rail transit flow prediction and evacuation method based on mobile phone signaling according to the present invention is shown. Detailed Implementation

[0018] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0019] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0020] Figure 1 A flowchart of an urban rail transit flow prediction and evacuation method based on mobile phone signaling according to the present invention is shown.

[0021] like Figure 1 As shown, this invention discloses a method for predicting and dispersing urban rail transit traffic flow based on mobile phone signaling, comprising: S101, Based on emergency warning information caused by geological disasters, obtain the scope of impact of geological disasters and the affected rail transit network; S102, collects signaling data and base station operation status data of mobile communication network within the affected area in real time; S103, Based on the base station operation status data, filter and supplement the signaling data to determine the emergency available signaling dataset; S104, Construct a dynamic grid map, map the signaling data in the emergency available signaling dataset to the dynamic grid, and count the number of users staying in each grid and the amount of movement across grids; S105, Determine the predicted passenger flow under disaster disturbance based on the number of users staying in each grid and the amount of movement across grids; S106. Based on the predicted passenger flow and the preset real-time road network vulnerability assessment value, a dynamic evacuation method for rail transit is generated. S107, The evacuation method is pushed to mobile phone users in the affected area via emergency broadcast and directional signaling.

[0022] According to an embodiment of the present invention, the geological disaster includes earthquakes, debris flows, etc. When the emergency warning information caused by the geological disaster is triggered, the geological disaster monitoring system and the urban rail transit network work together to send directional signaling information to the population within the scope of the geological disaster. The directional signaling information is evacuation information, which includes at least evacuation routes and evacuation destinations.

[0023] According to an embodiment of the present invention, the step of obtaining the scope of the rail transit network affected by the geological disaster specifically includes: Obtain the location of the epicenter / slip surface, the radius of influence R, and the intensity distribution of the geological disaster; Obtain geographic information of rail transit lines; Spatial overlay analysis of the geographic information of rail transit lines and intensity distribution: rail stations and sections located in intensity VI and above are designated as directly affected areas; Extract historical passenger flow data for rail stations adjacent to the directly affected area and for the corresponding rail stations; Determine the correlation between the passenger flow sources of the corresponding rail stations and the directly affected areas based on historical passenger flow data of the corresponding rail stations; If the correlation between the passenger flow sources of the corresponding rail station and the directly affected area is greater than the preset correlation threshold, then the area between the corresponding rail stations in the directly affected area will be set as the indirect linkage area. The areas directly affected and indirectly affected will be merged to determine the scope of the rail transit network affected by geological disasters.

[0024] It should be noted that the correlation between passenger flow sources is set as... Its formula is ,in This represents the passenger flow from the directly affected area to station i in historical passenger flow data; This represents the total passenger flow of station i in historical passenger flow data (unit: person-times / day); for example, the preset correlation threshold is 0.3; when the geological disaster is an earthquake, the direct impact zone is set according to the intensity; if the geological disaster is a landslide, the direct impact zone is constructed based on the location of the sliding surface and extending outward by a distance R.

[0025] According to an embodiment of the present invention, the step of filtering signaling data based on base station operation status data specifically includes: Based on the base station's operational status data, determine the base station's operational status code and average signaling delivery volume at the time point prior to triggering the emergency alert. The running status code and average signaling delivery volume at a time point after the emergency alert is triggered. ; Based on the same base station, the average signaling delivery volume Subtract average signaling delivery The average signaling delivery volume difference of the corresponding base station is obtained; If the difference in the average signaling delivery volume of the corresponding base station is less than or equal to the preset average signaling delivery volume threshold and the status code is displayed as abnormal, then the corresponding base station is determined to be abnormal. The signaling data in the corresponding grid of the base station that is determined to be abnormal will be deleted.

[0026] It should be noted that when there is a significant difference in the signaling data of a base station before and after a geological disaster, it indicates that the corresponding base station is damaged or communication is blocked. Therefore, the signaling data of the corresponding base station may contain errors. Thus, the corresponding signaling data is deleted to improve the accuracy of passenger flow prediction. Furthermore, the operation of the base station will not be affected when sending directional signaling to the crowd in subsequent evacuation methods.

[0027] Furthermore, after deleting the signaling data within the grid corresponding to the base station determined to be abnormal, the process also includes: taking the abnormal base station as the center of the nine-square grid and extracting the mobile signaling data of the eight surrounding base stations and the corresponding abnormal base station at time node t+0; extracting the mobile signaling data of the eight surrounding base stations at time node t+1; based on the mobile signaling data of the eight surrounding base stations and the corresponding abnormal base station at time node t+0 and the mobile signaling data of the eight surrounding base stations at time node t+1, determining the mobile users who disappeared at time node t+1, and determining whether the corresponding disappeared mobile users appeared on other base stations. If they did not appear, the corresponding disappeared mobile users were set as being within the grid covered by the abnormal base station, and the number of the corresponding disappeared mobile users was set as the user retention rate within the grid covered by the corresponding abnormal base station.

[0028] According to an embodiment of the present invention, the step of counting the number of users staying in each grid cell specifically includes: The signaling data in the emergency available signaling dataset is classified according to mobile phone users and the trajectory difference is calculated to generate a sequence of virtual trajectory points at equal time intervals. Extract the distance between the virtual trajectory point of the mobile user at time node t and the grid boundary; If the distance value is greater than or equal to the preset positioning error radius, the dwell weight of the corresponding virtual trajectory point in the corresponding grid is set to 1. If the distance value is less than the preset positioning error radius, the dwell time weight of the corresponding virtual trajectory point will be distributed to multiple adjacent grids according to the distance weighting. After iterating through the distance values ​​between all virtual trajectory points of the mobile user at time node t and the grid boundary, the dwell weights of all users within the same grid are summed to obtain the user dwell value within that grid.

[0029] It should be noted that the virtual trajectory point sequence is composed of virtual trajectory points at multiple time points, and the user dwell time is constituted by the accumulation of dwell time weights. When the distance value is less than the preset positioning error radius, the corresponding dwell time weight is assigned to the corresponding adjacent grid, thereby improving the accuracy of the dwell time and further eliminating positioning errors.

[0030] Furthermore, the step of distributing the dwell time weight of the corresponding virtual trajectory point to multiple adjacent grids according to distance weighting specifically includes: setting the grid where the virtual trajectory point falls as a1, the adjacent grids as a2, and the initial dwell time weight of the corresponding signaling data in grid a1 as... Its formula is: ,in This represents the distance value between the corresponding virtual trajectory point and the grid boundaries of a1 and a2. This represents the positioning error radius; the initial dwell time weight of the corresponding signaling data in grid a2 is set to... Its formula is If the distance from the corresponding virtual trajectory point to the grid boundaries of a1 and a2 is less than the preset positioning error radius, then the corresponding initial dwell weight is set as the dwell weight of the corresponding grid. If the distance from the corresponding virtual trajectory point to multiple grid boundaries is less than the preset positioning error radius, then the multiple initial dwell weights of grid a1 are accumulated to obtain the final initial dwell weight of grid a1. Then, the initial dwell weights of different grids are normalized to determine the corresponding virtual trajectory point. The dwell time weights of trajectory points in each grid are assigned; for example, if the initial dwell time weights of grid a1 are 0.6 and 0.8, the initial dwell time weight of adjacent grid a2 is 0.4, and the initial dwell time weight of adjacent grid a3 is 0.2, then after normalization, the dwell time weight of grid a1 is (0.6+0.8) / 2=0.7; the dwell time weight of adjacent grid a2 is 0.4 / 2=0.2; and the dwell time weight of adjacent grid a3 is 0.2 / 2=0.1.

[0031] According to an embodiment of the present invention, it further includes: Extract the grid cells covered by abnormal base stations and designate them as abnormal grid cells; Extracting from the abnormal grid as the center Mobile signaling users whose time points appear in adjacent or abnormal grids; If the mobile phone signaling user is If the time point also appears in an adjacent grid or other grids, the corresponding mobile signaling user will be deleted, and the remaining mobile signaling users will be set as lost users. Set the number of users who have lost contact as the number of users staying in the grid covered by the abnormal base station.

[0032] It should be noted that mobile phone signaling users in If the time point also appears in an adjacent grid or other grids, it indicates that the corresponding mobile signaling user is no longer within the grid covered by the abnormal base station.

[0033] According to an embodiment of the present invention, the step of calculating the cross-grid movement specifically includes: Extract the dwell time weights of virtual trajectory points at adjacent time nodes in the same virtual trajectory point sequence; If the dwell weights of virtual trajectory points at corresponding adjacent time nodes are all greater than the preset first weight coefficient, and the virtual trajectory points at adjacent time nodes belong to different grids, then a movement is determined to have occurred, and the minimum value among the dwell weight coefficients of virtual trajectory points at corresponding adjacent time nodes is set as the movement amount for this movement. ; After traversing all virtual trajectory point sequences, extract all movement amounts from grid g to grid h and sum them up to obtain the cross-grid movement amount from grid g to grid h.

[0034] It should be noted that the preset first weighting coefficient is greater than 0.5 and less than 1; the cross-grid movement amount is divided into cross-grid out-movement amount and cross-grid in-movement amount. For example, if the weight of the virtual trajectory point's dwell time in grid g at time node t+1 is greater than the preset first weighting coefficient, and the weight of the virtual trajectory point's dwell time in grid h at time node t+2 is greater than the preset first weighting coefficient, then it is determined that a movement has occurred, and it is a cross-grid out-movement amount relative to grid g, and a cross-grid in-movement amount relative to grid h.

[0035] According to an embodiment of the present invention, the step of determining the predicted passenger flow under disaster disturbance based on the user dwell time within each grid and the cross-grid movement specifically includes: Extract stations from the rail transit network and extract the grid cells within the influence range of the corresponding stations; Based on the grids within the influence range of the corresponding site, extract the user dwell time, cross-grid eviction rate, and cross-grid eviction rate within the corresponding grid. Set the corresponding station as A, the grid within the influence range of the corresponding station as a, and the predicted passenger flow for the corresponding effective safe evacuation station as... Its formula is: ,in This represents the number of users staying in grid a at time point t. This represents the panic index at time t. This represents the cross-grid shift amount of grid a at time t. This represents the cross-grid movement amount of grid a at time node t. , The corresponding weighting coefficients are shown, and "*" indicates multiplication.

[0036] It should be noted that if there are multiple grids within the influence range of a site, then grid a is the sum of the corresponding multiple grids; the panic index is adjusted in real time based on the mobile signaling data within the grid. For example, if there is a significant anomaly or a sudden increase in communication in a certain mobile signaling data within grid a at time t, then the number of panicked users is incremented by one. The total number of panicked users is obtained by traversing all mobile signaling data within grid a, and then the total number of panicked users is divided by the number of users residing in grid a at time t to obtain the corresponding panic index.

[0037] According to an embodiment of the present invention, the step of generating a dynamic evacuation method for rail transit based on predicted passenger flow and a preset real-time road network vulnerability assessment value specifically includes: Based on the preset real-time road network vulnerability assessment value, determine the vulnerability assessment value of each station; based on the predicted passenger flow, determine the population density of the grid within the influence range of the corresponding station. If the vulnerability assessment value of a site is greater than the preset assessment threshold, the site is determined to be a high-risk site, and the grid range within the site's influence area is set as a high-risk grid range. If the population density of the grid within the influence range of the corresponding site is greater than the preset density threshold, the site is determined to be a high-density site, and the grid range within the influence range of the site is set as a high-density grid range. Based on preset evacuation rules and with minimum time as the constraint, corresponding evacuation routes are constructed according to user mobile phone signaling data. The preset evacuation rules include at least the principle that high-risk / high-density grid areas are prohibited from passage and that high-risk / high-density sites should be evacuated to low-risk / low-density sites.

[0038] It should be noted that the preset real-time road network vulnerability assessment value is set as V, and its formula is: ,in This represents the road network vulnerability assessment value at time node t of station A. This represents the criticality index of station A within the road network, indicating the importance of station A in the entire road network. This represents the real-time passenger flow density at station A at time point t, which can be determined based on the area covered by station A and the number of users staying within the coverage area of ​​station A. This indicates the maximum carrying capacity of station A, set according to rail transit design specifications or safe operation standards. This represents the geological hazard risk index, based on historical assessment values ​​from geological exploration data. The value ranges from 0 to 1, reflecting the inherent risk of geological hazards in the area. , and These represent the corresponding weighting coefficients.

[0039] According to an embodiment of the present invention, after generating the dynamic evacuation method for rail transit, the method further includes: Real-time acquisition of mobile signaling trajectories via mobile signaling data; By comparing and analyzing the mobile phone signaling trajectory with the evacuation path in the corresponding evacuation method, the individual trajectory deviation angle can be determined. Extract the trajectory deviation angles of all individuals within a preset range and calculate the average to obtain the group deviation angle; When the group deviation angle is less than the preset deviation angle threshold, if the individual trajectory deviation angle is greater than the preset deviation angle threshold and the duration is greater than the preset first time threshold, then the corresponding individual evacuation error message will be triggered. If the deviation angle of the group is greater than or equal to the preset deviation angle threshold and the duration is greater than the preset first time threshold, the current guided evacuation method is deemed to have failed and a warning message is issued; if the deviation angle of an individual trajectory is less than or equal to the preset deviation angle threshold and the duration is greater than the preset first time threshold, the corresponding evacuation trajectory real-time adjustment prompt message is triggered. Based on the warning message indicating that the current guided evacuation method has failed, the evacuation method is updated.

[0040] It should be noted that the deviation angle ranges from 0 to 180 degrees. When the deviation angle is zero degrees, it means that the evacuation path is followed completely. When the deviation angle is 180 degrees, it means that the movement is reversed. For example, the preset deviation angle threshold is 30 degrees and the preset first time threshold is 120 seconds.

[0041] According to an embodiment of the present invention, it further includes: Receive secondary disaster early warning information in real time from the geological disaster monitoring system; When a secondary disaster is detected, it is determined whether its impact range is within the current geological disaster impact range. If not, the corresponding newly added impact range is extracted. The scope of the geological disaster and the affected rail transit network will be revised based on the newly added impact area, and passenger flow forecasts and evacuation route planning will be carried out again.

[0042] It should be noted that, for example, a strong earthquake may be followed by multiple aftershocks, and earthquakes in mountainous areas may trigger secondary disasters such as landslides and mudslides. These secondary disasters may occur outside the original area of ​​impact, or further aggravate the risks within the original area of ​​impact. By receiving early warning information on secondary disasters in real time and updating the scope of geological disaster impact in real time, the accuracy of the prediction is ensured.

[0043] This invention discloses a method for predicting and evacuating urban rail transit traffic flow based on mobile phone signaling, which improves emergency safety by linking geological disaster monitoring with rail transit emergency response.

[0044] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0045] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0046] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0047] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0048] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

Claims

1. A method for predicting and dispersing urban rail transit traffic flow based on mobile phone signaling, characterized in that, include: Based on emergency warning information caused by geological disasters, the scope of impact of geological disasters and the affected rail transit network can be obtained; Real-time collection of signaling data and base station operation status data of mobile communication networks within the affected area; Based on the base station operation status data, the signaling data is filtered and supplemented to determine the emergency available signaling dataset; Construct a dynamic grid map, map the signaling data in the emergency available signaling dataset to the dynamic grid, and count the number of users staying in each grid and the amount of movement across grids; Based on the number of users staying in each grid and the amount of movement across grids, the predicted passenger flow under disaster disturbances is determined; Based on the predicted passenger flow and the preset real-time road network vulnerability assessment value, a dynamic evacuation method for rail transit is generated. The evacuation method will be pushed to mobile phone users in the affected area via emergency broadcast and targeted signaling.

2. The method for predicting and dispersing urban rail transit traffic flow based on mobile phone signaling according to claim 1, characterized in that, The step of obtaining the scope of the rail transit network affected by the geological disaster specifically includes: Obtain the location of the epicenter / slip surface, the radius of influence R, and the intensity distribution of the geological disaster; Obtain geographic information of rail transit lines; Spatial overlay analysis of the geographic information of rail transit lines and intensity distribution: rail stations and sections located in intensity VI and above are designated as directly affected areas; Extract historical passenger flow data for rail stations adjacent to the directly affected area and for the corresponding rail stations; Determine the correlation between the passenger flow sources of the corresponding rail stations and the directly affected areas based on historical passenger flow data of the corresponding rail stations; If the correlation between the passenger flow sources of the corresponding rail station and the directly affected area is greater than the preset correlation threshold, then the area between the corresponding rail stations in the directly affected area will be set as the indirect linkage area. The areas directly affected and indirectly affected will be merged to determine the scope of the rail transit network affected by geological disasters.

3. The method for predicting and dispersing urban rail transit traffic flow based on mobile phone signaling according to claim 1, characterized in that, The step of filtering signaling data based on base station operation status data specifically includes: Based on the base station's operational status data, determine the base station's operational status code and average signaling delivery volume at the time point prior to triggering the emergency alert. The running status code and average signaling delivery volume at a time point after the emergency alert is triggered. ; Based on the same base station, the average signaling delivery volume Subtract average signaling delivery The average signaling delivery volume difference of the corresponding base station is obtained; If the difference in the average signaling delivery volume of the corresponding base station is less than or equal to the preset average signaling delivery volume threshold and the status code is displayed as abnormal, then the corresponding base station is determined to be abnormal. The signaling data in the corresponding grid of the base station that is determined to be abnormal will be deleted.

4. The method for predicting and dispersing urban rail transit traffic flow based on mobile phone signaling according to claim 1, characterized in that, The steps for calculating the user dwell time within each grid cell specifically include: The signaling data in the emergency available signaling dataset is classified according to mobile phone users and the trajectory difference is calculated to generate a sequence of virtual trajectory points at equal time intervals. Extract the distance between the virtual trajectory point of the mobile user at time node t and the grid boundary; If the distance value is greater than or equal to the preset positioning error radius, the dwell weight of the corresponding virtual trajectory point in the corresponding grid is set to 1. If the distance value is less than the preset positioning error radius, the dwell time weight of the corresponding virtual trajectory point will be distributed to multiple adjacent grids according to the distance weighting. After iterating through the distance values ​​between all virtual trajectory points of the mobile user at time node t and the grid boundary, the dwell weights of all users within the same grid are summed to obtain the user dwell value within that grid.

5. The method for predicting and dispersing urban rail transit traffic flow based on mobile phone signaling according to claim 4, characterized in that, Also includes: Extract the grid cells covered by abnormal base stations and designate them as abnormal grid cells; Extracting from the abnormal grid as the center Mobile signaling users whose time points appear in adjacent or abnormal grids; If the mobile phone signaling user is If the time point also appears in an adjacent grid or other grids, the corresponding mobile signaling user will be deleted, and the remaining mobile signaling users will be set as lost users. Set the number of users who have lost contact as the number of users staying in the grid covered by the abnormal base station.

6. The method for predicting and dispersing urban rail transit traffic flow based on mobile phone signaling according to claim 1, characterized in that, The step of calculating the cross-grid movement specifically includes: Extract the dwell time weights of virtual trajectory points at adjacent time nodes in the same virtual trajectory point sequence; If the dwell weights of virtual trajectory points at corresponding adjacent time nodes are all greater than the preset first weight coefficient, and the virtual trajectory points at adjacent time nodes belong to different grids, then a movement is determined to have occurred, and the minimum value among the dwell weight coefficients of virtual trajectory points at corresponding adjacent time nodes is set as the movement amount for this movement. ; After traversing all virtual trajectory point sequences, extract all movement amounts from grid g to grid h and sum them up to obtain the cross-grid movement amount from grid g to grid h.

7. The method for predicting and dispersing urban rail transit traffic flow based on mobile phone signaling according to claim 1, characterized in that, The step of determining the predicted passenger flow under disaster disturbance based on the user dwell time within each grid and the movement across grids specifically includes: Extract stations from the rail transit network and extract the grid cells within the influence range of the corresponding stations; Based on the grids within the influence range of the corresponding site, extract the user dwell time, cross-grid eviction rate, and cross-grid eviction rate within the corresponding grid. Set the corresponding station as A, the grid within the influence range of the corresponding station as a, and the predicted passenger flow for the corresponding effective safe evacuation station as... Its formula is: ,in This represents the number of users staying in grid a at time point t. This represents the panic index at time t. This represents the cross-grid shift amount of grid a at time t. This represents the cross-grid movement amount of grid a at time node t. , For the corresponding weighting coefficients, "*" indicates multiplication.

8. The method for predicting and dispersing urban rail transit traffic flow based on mobile phone signaling according to claim 1, characterized in that, The step of generating a dynamic evacuation method for rail transit based on predicted passenger flow and preset real-time road network vulnerability assessment values ​​specifically includes: Based on the preset real-time road network vulnerability assessment value, determine the vulnerability assessment value of each station; based on the predicted passenger flow, determine the population density of the grid within the influence range of the corresponding station. If the vulnerability assessment value of a site is greater than the preset assessment threshold, the site is determined to be a high-risk site, and the grid range within the site's influence area is set as a high-risk grid range. If the population density of the grid within the influence range of the corresponding site is greater than the preset density threshold, the site is determined to be a high-density site, and the grid range within the influence range of the site is set as a high-density grid range. Based on preset evacuation rules and with minimum time as the constraint, corresponding evacuation routes are constructed according to user mobile phone signaling data. The preset evacuation rules include at least the principle that high-risk / high-density grid areas are prohibited from passage and that high-risk / high-density sites should be evacuated to low-risk / low-density sites.

9. A method for predicting and dispersing urban rail transit traffic flow based on mobile phone signaling according to claim 1, characterized in that, Following the generation of the dynamic evacuation method for rail transit, the method further includes: Real-time acquisition of mobile signaling trajectories via mobile signaling data; By comparing and analyzing the mobile phone signaling trajectory with the evacuation path in the corresponding evacuation method, the individual trajectory deviation angle can be determined. Extract the trajectory deviation angles of all individuals within a preset range and calculate the average to obtain the group deviation angle; When the group deviation angle is less than the preset deviation angle threshold, if the individual trajectory deviation angle is greater than the preset deviation angle threshold and the duration is greater than the preset first time threshold, then the corresponding individual evacuation error message will be triggered. If the deviation angle of the group is greater than or equal to the preset deviation angle threshold and the duration is greater than the preset first time threshold, the current guided evacuation method is deemed to have failed and a warning message is issued; if the deviation angle of an individual trajectory is less than or equal to the preset deviation angle threshold and the duration is greater than the preset first time threshold, the corresponding evacuation trajectory real-time adjustment prompt message is triggered. Based on the warning message indicating that the current guided evacuation method has failed, the evacuation method is updated.

10. A method for predicting and dispersing urban rail transit traffic flow based on mobile phone signaling according to claim 1, characterized in that, Also includes: Receive secondary disaster early warning information in real time from the geological disaster monitoring system; When a secondary disaster is detected, it is determined whether its impact range is within the current geological disaster impact range. If not, the corresponding newly added impact range is extracted. The scope of the geological disaster and the affected rail transit network will be revised based on the newly added impact area, and passenger flow forecasts and evacuation route planning will be carried out again.

Images