Rail transit hub passenger flow monitoring method and system based on bluetooth positioning

Abstract

This invention discloses a method and system for monitoring passenger flow in rail transit hubs based on Bluetooth positioning. The method includes: deploying multiple Bluetooth beacons within a predetermined area of ​​the rail transit hub and establishing a beacon location database; collecting Bluetooth signals from Bluetooth devices carried by passengers via mobile terminals and preprocessing them to generate sample data sequences; calculating the real-time location coordinates of passengers using an improved weighted centroid positioning algorithm based on the sample data sequences; constructing a passenger flow trajectory model based on the time-series data of passengers' real-time location coordinates and dividing passenger flow density hotspot areas through cluster analysis; and generating a passenger flow distribution heatmap and congestion warning information by combining historical passenger flow data with the real-time divided passenger flow density hotspot areas, and outputting a monitoring report. This invention solves the problems of real-time accurate positioning of passenger flow and rapid identification of hotspot areas in rail transit hubs through beacon deployment, Bluetooth signal preprocessing, and an improved weighted centroid positioning algorithm.

Description

Technical Field

[0001] This invention relates to the technical field of rail transit and passenger flow monitoring, and in particular to a method and system for monitoring passenger flow in rail transit hubs based on Bluetooth positioning. Background Technology

[0002] In recent years, with the acceleration of urbanization and the rapid expansion of the rail transit network in my country, the passenger flow of various large-scale rail transit hubs has shown a rapid growth trend. How to achieve accurate monitoring and effective management of passenger flow has become an important technical issue to ensure the safety of rail transit operation and improve the quality of public services.

[0003] Traditional passenger flow monitoring technologies mainly include video image recognition, infrared or laser counting, and radio frequency identification (RFID). Video image recognition uses artificial intelligence algorithms to analyze video data collected by cameras to obtain crowd flow characteristics. Infrared or laser counting relies on counting sensors at preset locations to count the number of people passing through. RFID uses electronic tags carried by passengers to achieve real-time location of individuals or groups. However, these technologies usually have limitations. For example, video monitoring is easily affected by lighting conditions, viewpoint obstruction, and changes in crowd density, making it difficult to achieve reliable monitoring in complex or high-density crowd scenarios. Infrared and laser technologies can only record the number of passengers passing through fixed detection points, making it difficult to obtain real-time location and trajectory information of passengers. RFID technology requires passengers to carry specific electronic tags, resulting in high deployment costs and implementation difficulties, and insufficient popularization, thus limiting its application scope.

[0004] Currently, with the rapid development of wireless communication technology, especially Bluetooth Low Energy technology, indoor precise positioning based on Bluetooth beacons has gradually become one of the important technical routes for passenger flow monitoring in the rail transit field. Bluetooth positioning technology uses multiple preset beacon nodes and relies on passengers' smart mobile terminal devices (such as mobile phones, wristbands, etc.) to receive the Bluetooth broadcast signals from the beacons, thereby realizing real-time monitoring and trajectory tracking of passenger locations in indoor environments. Although Bluetooth positioning technology has the advantages of high device penetration, relatively low cost, and flexible deployment, traditional Bluetooth positioning algorithms have the problem of insufficient positioning accuracy and are greatly affected by multipath effects, signal fluctuations, and environmental interference, which cannot fully meet the strict requirements of rail transit hub environments for positioning accuracy, real-time performance, and reliability.

[0005] Meanwhile, existing Bluetooth positioning methods generally lack in-depth mining and analysis of passenger flow trajectory data, making it difficult to effectively and in real time identify passenger flow gathering and congestion hotspots, and failing to provide efficient and targeted decision support for passenger flow organization and management in rail transit hubs. Summary of the Invention

[0006] The purpose of this section is to outline some aspects of the embodiments of the present invention and to briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section, as well as in the abstract and title of the present application, to avoid obscuring the purpose of this section, the abstract and title of the invention. Such simplifications or omissions shall not be used to limit the scope of the present invention.

[0007] In view of the aforementioned existing problems, the present invention is proposed.

[0008] Therefore, the technical problem solved by this invention is that existing rail transit hub passenger flow monitoring technologies suffer from insufficient positioning accuracy and difficulty in accurately identifying hotspot congestion areas in real time.

[0009] To solve the above-mentioned technical problems, the present invention provides the following technical solution: deploying multiple Bluetooth beacons within a preset area of ​​a rail transit hub and establishing a beacon location database;

[0010] The Bluetooth signals of Bluetooth devices carried by passengers are collected through mobile terminals and preprocessed to generate sample data sequences.

[0011] Based on the sample data sequence, the passenger's real-time location coordinates are calculated using an improved weighted centroid localization algorithm;

[0012] Based on the time series data of the passengers' real-time location coordinates, a passenger flow trajectory model is constructed, and passenger flow density hotspot areas are divided through cluster analysis.

[0013] By combining historical passenger flow data with real-time passenger flow density hotspots, a passenger flow distribution heat map and congestion warning information are generated, and a monitoring report is output.

[0014] As a preferred embodiment of the Bluetooth positioning-based passenger flow monitoring method for rail transit hubs described in this invention, the deployment method of the Bluetooth beacon includes:

[0015] Beacons should be installed at platforms, passageways, transfer nodes, and entrances / exits, with a spacing of 5 to 10 meters between adjacent beacons and a height of 1.5 to 2.5 meters.

[0016] Each beacon is configured with a unique identifier and a transmit power adaptive module, which dynamically adjusts the signal coverage range according to environmental conditions.

[0017] The specific deployment locations of each beacon are inspected, and the effective area of ​​signal coverage is determined by testing the Bluetooth signal strength values ​​on-site. Based on the test results, the transmission power parameters are optimized again to complete the beacon deployment plan that meets the positioning requirements.

[0018] As a preferred embodiment of the Bluetooth positioning-based passenger flow monitoring method for rail transit hubs described in this invention, the establishment of a beacon location database includes:

[0019] The spatial coordinates of each Bluetooth beacon are measured and recorded, including planar coordinates and vertical height information;

[0020] Record the unique identifier, deployment location, installation area function type, and adaptive transmit power parameters for each Bluetooth beacon;

[0021] Based on the measured spatial coordinates and signal coverage area, the plan of the rail transit hub is marked, and the coordinate information of the beacons is written into the database;

[0022] The beacon information in the database is indexed and verified, and the beacon location and power parameters are checked and updated regularly according to the actual site environment.

[0023] As a preferred embodiment of the Bluetooth positioning-based passenger flow monitoring method for rail transit hubs described in this invention, the Bluetooth signal includes signal strength, beacon identifier, and timestamp, wherein:

[0024] The signal strength is a Bluetooth signal strength measurement value characterized by a received signal strength indication method;

[0025] The beacon identifier is used to uniquely identify the Bluetooth beacon that emits the Bluetooth signal;

[0026] The timestamp is used to record the specific moment when the Bluetooth signal is scanned by the mobile terminal, in order to construct the trajectory of the passenger's location changing over time;

[0027] The mobile terminal scans all visible Bluetooth beacon signals in the surrounding environment at fixed time intervals, and performs preliminary integration of the scan results, deleting duplicate beacon information;

[0028] The acquired Bluetooth signal data is then stored in chronological order.

[0029] As a preferred embodiment of the Bluetooth positioning-based passenger flow monitoring method for rail transit hubs described in this invention, the collected Bluetooth signals are preprocessed to generate a sample data sequence. The preprocessing includes signal filtering, noise suppression, and multipath effect correction, wherein:

[0030] The Kalman filter algorithm is used to smooth short-term fluctuations in Bluetooth signal strength in order to reduce signal jitter caused by transient interference.

[0031] Based on a preset threshold, Bluetooth signal strength data below the background noise level is identified as noise and discarded.

[0032] For the multipath propagation phenomenon in underground rail transit hub environments, a multipath channel model is used to correct the Bluetooth signal strength in order to reduce positioning errors;

[0033] The filtered, noise-suppressed, and corrected Bluetooth signal strength values ​​are matched one by one with the corresponding beacon identifiers and timestamps, and sorted in chronological order to form a time-series Bluetooth signal sample data sequence.

[0034] As a preferred embodiment of the Bluetooth positioning-based passenger flow monitoring method for rail transit hubs described in this invention, based on the sample data sequence, an improved weighted centroid positioning algorithm is used to calculate the real-time location coordinates of passengers, including:

[0035] Within the same time segment, select the Bluetooth signal strength values, beacon coordinates, and corresponding unique identifiers of several Bluetooth beacons from the sample data sequence;

[0036] Let d be the distance from each Bluetooth beacon to the mobile terminal. i Let the distance decay factor be denoted as α, and the weight w be defined. i With distance d i The relationship is as follows:

[0037]

[0038] Where i represents the i-th beacon, and α is a parameter set according to the environmental attenuation characteristics;

[0039] When d i When the beacon is closer, w decreases. i An increase indicates a higher contribution to the localization results;

[0040] The passenger's planar coordinates are calculated using the weighted centroid positioning formula:

[0041]

[0042] Among them, (x i ,y i Let be the planar coordinates of the i-th Bluetooth beacon in the beacon location database, and N be the number of valid Bluetooth beacons used for calculation. * ,Y * ( ) represents the passenger's two-dimensional real-time location coordinates;

[0043] For the calculated (X) * ,Y * The coordinates are assigned a timestamp to form the passenger's time-series location point, which is the passenger's real-time location coordinates.

[0044] As a preferred embodiment of the Bluetooth positioning-based passenger flow monitoring method for rail transit hubs described in this invention, a passenger flow trajectory model is constructed based on the time series data of the real-time location coordinates of the passengers, and passenger flow density hotspot areas are divided through cluster analysis, including:

[0045] The same passenger at different timestamps (X) * ,Y * The coordinates are connected in chronological order, and a smoothing algorithm is used to correct coordinates that are momentarily lost or drifted, resulting in a complete and coherent passenger flow trajectory.

[0046] In key areas such as platforms, transfer passages, or entrances and exits, clustering analysis is performed on the trajectories of all passengers. If a trajectories in a certain area show high frequency of crossing or stopping, it is marked as a candidate hotspot area.

[0047] Density clustering algorithm is used to further subdivide each candidate hotspot area, and several passenger flow density levels are divided by combining dwell time, trajectory direction and speed parameters.

[0048] Adjacent or overlapping candidate hotspot areas are merged into a larger unified area, while overly scattered candidate areas are eliminated. The spatial coordinate boundaries, time period of occurrence, and peak traffic information of each hotspot area are output.

[0049] As a preferred embodiment of the Bluetooth positioning-based passenger flow monitoring method for rail transit hubs described in this invention, the step of generating a passenger flow distribution heat map and congestion warning information by combining historical passenger flow data with real-time segmented passenger flow density hotspot areas includes:

[0050] By comparing the real-time passenger flow data of hotspot areas with historical data from the same period in the database, a comprehensive assessment of passenger flow distribution at different time periods, different transfer nodes, and different routes is conducted to obtain a baseline value of passenger flow under normal conditions.

[0051] On the plan map of the rail transit hub, each hot spot area is displayed in a hierarchical manner by means of numerical values ​​or color variations. When the passenger flow of a hot spot area exceeds the warning threshold of the historical baseline value, its display color or value will be darkened or marked with a prominent prompt.

[0052] The system determines in real time whether congestion occurs in the target area based on the set warning threshold. When the passenger flow density exceeds the warning threshold, the system automatically triggers an warning, records the time of congestion, and sends an alarm message to the management backend.

[0053] As a preferred embodiment of the Bluetooth positioning-based passenger flow monitoring system for rail transit hubs described in this invention, it includes: one or more processors;

[0054] The memory stores operable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations, including the flow of the aforementioned Bluetooth-based positioning-based passenger flow monitoring method for rail transit hubs.

[0055] As a preferred embodiment of the computer-readable medium for storing software according to the present invention, the software includes instructions executable by one or more computers, the instructions causing the one or more computers to perform operations, the operations including the process of the aforementioned Bluetooth-based positioning-based passenger flow monitoring method for rail transit hubs.

[0056] The beneficial effects of this invention are:

[0057] 1. By deploying multiple Bluetooth beacons within a pre-defined area of ​​a rail transit hub and establishing a beacon location database, the spatial coordinates, unique identifiers, and transmission power parameters of each Bluetooth beacon are clearly defined. This achieves precise wireless signal coverage of the spatial area within the rail transit hub, providing a reliable spatial reference basis for the effective acquisition and precise positioning of subsequent Bluetooth signals. It solves the problem of low accuracy caused by the lack of clear spatial coordinate references in traditional methods, and improves the accuracy of Bluetooth beacon signal coverage and positioning reference.

[0058] 2. By collecting Bluetooth signals emitted by Bluetooth devices carried by passengers through mobile terminals and preprocessing the collected signals, the authenticity, stability and reliability of the collected Bluetooth signals are ensured. This effectively eliminates signal jitter, environmental noise and multipath interference caused by the complex environment of rail transit hubs, solves the problem of abnormal signal interference caused by large passenger flow and complex signal propagation paths in rail transit hubs, and improves signal processing quality and subsequent positioning accuracy.

[0059] 3. By adjusting the distance attenuation factor and beacon weight according to the actual environment, the positioning error caused by path loss changes in the traditional positioning algorithm is effectively reduced. This solves the technical defects of the traditional Bluetooth positioning algorithm, such as insufficient positioning accuracy and inability to adjust positioning parameters in real time, and improves the robustness, stability and real-time positioning accuracy of the positioning algorithm for personnel in rail transit hubs.

[0060] 4. By using cluster analysis to segment passenger flow hotspot areas, it has achieved refined trajectory tracking and hotspot area identification of passenger flow within rail transit hubs. By mining the spatiotemporal movement characteristics of passengers, it has discovered the patterns of passenger flow gathering and dispersal in different areas, which solves the shortcomings of existing technologies that cannot efficiently, in real time, and accurately identify and judge the distribution of hotspot areas in rail transit hubs. It can identify high-density passenger flow areas in real time and promptly detect and mark abnormal passenger flow gathering situations.

[0061] 5. By effectively comparing and analyzing historical normal data with real-time dynamic data, abnormal passenger flow status can be accurately identified. This solves the problem that traditional technologies cannot intuitively, dynamically, and timely provide feedback on abnormal passenger flow and risk warnings. It provides effective auxiliary decision support for the operation and management of rail transit hubs and improves the efficiency of passenger flow organization and the level of safety assurance. Attached Figure Description

[0062] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0063] Figure 1 This is a flowchart illustrating the Bluetooth positioning-based passenger flow monitoring method for rail transit hubs as shown in this invention. Detailed Implementation

[0064] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0065] Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without inventive effort should fall within the scope of protection of this invention.

[0066] 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 those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0067] According to an embodiment of the present invention, in combination Figure 1 The flowchart shown illustrates a method for monitoring passenger flow in rail transit hubs based on Bluetooth positioning, which specifically includes the following steps:

[0068] S1. Deploy multiple Bluetooth beacons within a predetermined area of ​​the rail transit hub and establish a beacon location database. Note the following in this step:

[0069] In key areas such as platforms, passageways, transfer nodes, and entrances / exits of rail transit hubs, several installation locations will be selected as Bluetooth beacon deployment points based on the actual environment and coverage requirements.

[0070] The spacing between adjacent Bluetooth beacons is 5 to 10 meters, and the installation height of each Bluetooth beacon is 1.5 to 2.5 meters to achieve continuous and effective Bluetooth signal coverage in the target area;

[0071] Each Bluetooth beacon is configured with a unique identifier (ID) and a transmit power adaptive module. The transmit power adaptive module is used to dynamically adjust the Bluetooth signal coverage range according to environmental conditions.

[0072] The deployment locations were inspected and tested, and the on-site signal strength of the Bluetooth beacon was measured under the current transmit power setting.

[0073] Based on the measured Bluetooth signal strength values, determine the effective coverage area boundary and compare it with the expected coverage area;

[0074] If the beacon signal cannot meet the pre-set coverage requirements, the transmission power parameters will be optimized a second time, and the testing and optimization will be repeated until the positioning requirements of the rail transit hub are met, thus completing the final beacon deployment plan.

[0075] Furthermore, under a defined coordinate reference system (e.g., using the overall station plan as a two-dimensional reference coordinate system, with an additional vertical height reference), spatial coordinate measurements are performed on each Bluetooth beacon, where:

[0076] Spatial coordinates include planar coordinates and vertical height;

[0077] Record the unique identifier ID for each beacon, a description of its installation location (functional type of the area), and the adaptive transmit power parameter P determined after testing and optimization. i Where i is the beacon number;

[0078] The obtained beacon space coordinates and their unique identifier ID i The functional type of the deployment area (such as platform, entrance / exit, transfer passage) and the final adaptive transmission power parameter P i To establish a connection;

[0079] The coordinates and signal coverage of each beacon are marked on the plan of the rail transit hub, and the marked information is written into the database.

[0080] All beacon information (including coordinate information and power parameters) in the database is indexed and verified. By comparing field test records and historical setting information, it is ensured that the actual beacon location matches the data stored in the database.

[0081] Establish a regular inspection and update mechanism, including periodically retesting the physical location and transmission power parameters of each beacon; if the location of a Bluetooth beacon is found to have moved, the environment has changed, or the signal attenuation level has deviated significantly from the set value, the corresponding record in the beacon location database should be corrected in a timely manner.

[0082] For example, the database uses a structured format for storage, including but not limited to the data fields shown in the table below:

[0083] Table 1. Database Structure Table

[0084]

[0085] Furthermore, the coordinates of each beacon are graphically marked on the electronic plan of the rail transit hub, and the coordinates are matched with those on the electronic map in the database entries, enabling quick retrieval for subsequent positioning and data analysis.

[0086] Preferably, by establishing a data index (such as an index based on BeaconID), the real-time configuration information and coordinates of any beacon can be quickly queried, and historical records of its location updates and transmit power parameter adjustments can be traced.

[0087] S2. Collect Bluetooth signals from Bluetooth devices carried by passengers via mobile terminals, and preprocess them to generate sample data sequences. Note the following in this step:

[0088] The mobile terminal continuously scans for Bluetooth signals emitted by all visible Bluetooth beacons in the surrounding environment within a fixed time interval Δt.

[0089] The scanned Bluetooth signals are initially recorded, and each recorded Bluetooth signal information includes at least:

[0090] Signal Strength RSSI i , is the Bluetooth signal strength measurement value characterized by the received signal strength indication method;

[0091] Beacon Identifier ID i This is used to uniquely identify the Bluetooth beacon that emitted the Bluetooth signal;

[0092] timestamp t i This is used to record the exact moment when the Bluetooth signal was scanned by the mobile terminal;

[0093] After obtaining the initial scan results, redundant information generated by repeated identification within the same scan cycle is deleted, and only the unique and valid beacon identifier and corresponding signal strength value are retained.

[0094] Further, store the processed Bluetooth signal data in chronological order, mark each scan serial number, and form the initial raw data set {ID i , RSSI i , t i}, providing data input for subsequent preprocessing and positioning algorithms;

[0095] When the same beacon is detected multiple times in adjacent scan intervals Δt, record it as multiple valid observations in chronological order for subsequent time series analysis and signal smoothing;

[0096] In an optional implementation, the Kalman filter algorithm is used to smooth the short-term fluctuations of RSSI i to reduce the signal jitter caused by instantaneous interference;

[0097] In an optional implementation, according to a preset noise threshold Thres, Bluetooth signal strength values below the background noise level are excluded. If RSSI i < Thres, it is considered noise data and not included in subsequent positioning calculations;

[0098] In an optional implementation, for the common multipath propagation phenomenon in underground rail transit hubs, a multipath channel correction model is used to correct RSSI i to obtain the corrected signal strength RSSI′ i , reducing the positioning deviation caused by signal diffraction and reflection;

[0099] Match the Bluetooth signal strength RSSI′ i , the corresponding beacon identifier ID i and the timestamp t i one by one, and form a time-ordered Bluetooth signal data sequence from all valid records, expressed as:

[0100]

[0101] where D j represents the j-th valid Bluetooth signal record, and J is the total number of records currently collected and retained;

[0102] By indexing Ω chronologically, it is used to construct the trajectory basic data of passengers changing over time, providing input for the positioning algorithm in step S3.

[0103] It should be noted that the final Ω is stored in a database or cache module and retrieved in conjunction with the Bluetooth beacon location database. In order to meet the requirements of positioning accuracy and real-time performance, an upper limit is set for the effective time window of the observation data in Ω (such as retaining the data of the most recent month) based on the actual passenger flow and equipment performance, and expired records are cleaned up regularly.

[0104] S3. Based on the sample data sequence, an improved weighted centroid localization algorithm is used to calculate the passenger's real-time location coordinates. Note that the following points should be noted in this step:

[0105] Within the same time segment, extract several data points that conform to the target timestamp t from the sample data sequence Ω generated in step S2. n Observational data;

[0106] Bluetooth beacon identifier ID included in each observation data. i Corrected signal strength RSSI′ i and timestamp t i Perform reading;

[0107] By querying the beacon location database, the planar coordinates (x, y) of the corresponding beacon can be obtained. i ,y i ) and environmental attenuation reference parameters used for distance calculation (e.g., transmit power, path loss coefficient);

[0108] Let d be the distance from each Bluetooth beacon to the mobile terminal. i Then, the Bluetooth signal strength RSSI′ i Convert to corresponding distance d i Let the distance decay factor be denoted as α, and the weight w be defined. i With distance d i The relationship is as follows:

[0109]

[0110] Where i represents the i-th beacon, and α is a parameter set according to the environmental attenuation characteristics;

[0111] When d i When the beacon is closer, w decreases. i An increase in the value indicates that the beacon contributes more to the positioning results;

[0112] Count the total number N of available beacons within the current time segment, exclude observations identified as noise or distance anomalies, and retain only valid d. i Used for weighted centroid calculation;

[0113] For the selected N beacon coordinates (x) i ,y i Multiply by its weight wi The weighted sum in the planar coordinate system is obtained as follows: and

[0114] The passenger's planar coordinates (X) are calculated using the weighted centroid positioning formula. * ,Y * ):

[0115]

[0116] Among them, (x i ,y i Let be the planar coordinates of the i-th Bluetooth beacon in the beacon location database, and N be the number of valid Bluetooth beacons used for calculation. * ,Y * (X) represents the passenger's two-dimensional real-time location coordinates. * ,Y * ,t n ) contains the target timestamp t n Passenger time sequence location points;

[0117] When N < 3, the positioning results for that time slice are discarded according to the configuration strategy to improve positioning stability.

[0118] The calculated (X) * ,Y * ) and the corresponding target timestamp t n Association, denoted as (X * ,Y * ,t n );

[0119] The time sequence location points are incorporated into the passenger's real-time trajectory sequence for use in the subsequent step S4 for passenger flow trajectory model construction and hotspot area division.

[0120] The latest calculated (X) * ,Y * ) Stored in real time in a location database or cache;

[0121] When the next time segment arrives, the above calculation process is repeated to form a continuous time sequence of location points, thereby realizing the dynamic tracking and updating of passenger locations;

[0122] The sample data sequence generated in step S2 is kept synchronized, expired beacon observation data is periodically removed, and the updated positioning results are used in steps S4 and S5.

[0123] S4. Based on the time-series data of passengers' real-time location coordinates, construct a passenger flow trajectory model and use cluster analysis to delineate passenger flow density hotspot areas. Note that the following points should be noted in this step:

[0124] Collect the real-time location coordinates and timestamps of passengers from step S3;

[0125] Coordinates of the same passenger at different timestamps Connect them in chronological order to form a discretized position sequence, where m represents the sampling number;

[0126] The Kalman filter algorithm is used to correct for momentary loss of lock or position drift, obtaining a continuous and coherent passenger flow trajectory. The trajectory of each passenger is recorded as follows:

[0127] T k ={P k (τ)|P k (τ)=(x k (τ),y k (τ)),τ∈[t min ,t max ]}

[0128] Where k is the passenger identifier, x k (τ),y k (τ) represents the passenger's planar coordinates at time τ, [t min ,t max This refers to the time range during which the passenger is active within the rail transit hub.

[0129] For all constructed passenger trajectories T k Clustering analysis was conducted on key areas such as platforms, transfer passages, and entrances / exits.

[0130] If a high-frequency trajectory is observed to cross or stay for a long time in a certain spatial area (e.g., by counting the number of times trajectory points appear in the same area or the total stay time), then the area is marked as a candidate hotspot area.

[0131] Using a grid-based partitioning method, the cumulative passenger trajectory density of each grid within a unit of time is calculated, and a threshold β is set to determine whether a candidate hotspot unit has been reached.

[0132] When the passenger flow density of a grid satisfies textDensity>β, the grid is identified as a candidate hotspot cell.

[0133] Furthermore, for the labeled candidate hotspot units, a density clustering algorithm is used for secondary subdivision, merging hotspot units with adjacent or similar trajectory distributions into more representative hotspot regions;

[0134] Based on multiple parameters including passenger dwell time (e.g., exceeding a threshold within the same area), trajectory direction (averaged via vector direction), and transit speed (calculated by the gradient of position over time), hotspot areas are classified into passenger flow density levels, which are denoted as:

[0135] H1,H2,…,H L

[0136] Among them, H i This indicates different levels of hotspot areas (e.g., normal, crowded, extremely crowded), where L is the total number of levels.

[0137] It should be noted that when multiple adjacent or overlapping hotspot regions generated after clustering are merged, if the distance between the boundaries of two regions is less than a set threshold δ, they are considered to be the same hotspot region.

[0138] Candidate areas that are too scattered or have insufficient foot traffic will be eliminated to avoid misjudging hotspot information;

[0139] The final output includes the spatial coordinate boundaries of each hotspot region (e.g., described using a polygon coordinate set or center point + radius), and the main time period in which it occurs ([t...). start ,t end ]) and peak passenger flow MaxFlow;

[0140] For example, the result is expressed as:

[0141]

[0142] Among them, Γ j This represents the spatial boundary description of the j-th hotspot region. MaxFlow identifies the main periods of occurrence in this area during the monitoring period. j M represents the peak passenger flow, and M represents the number of hotspot areas ultimately identified.

[0143] Preferably, the constructed passenger flow trajectory model and hotspot area information R are uniformly stored in a database for use in subsequent step S5 to generate passenger flow distribution heat maps and congestion warnings.

[0144] S5. Combining historical passenger flow data with real-time identified passenger flow density hotspot areas, generate a passenger flow distribution heat map and congestion warning information, and output a monitoring report. Note that the following points should be noted in this step:

[0145] Read passenger flow information corresponding to the current monitoring period from the historical database, including historical passenger flow data under the same time period, the same transfer node, and similar route operating conditions;

[0146] Statistical analysis of historical passenger flow data is conducted to determine the normal distribution and average level of passenger flow in different time periods and key areas;

[0147] For example, the formula for calculating the benchmark value is:

[0148] Baseline(l,t) = μl,t +γ·σ l,t

[0149] Where l represents a line, transfer node, or specific functional area, t represents a specific time period, and μ l,t σ represents the historical average passenger flow. l,t The historical standard deviation is given, and γ is the adjustment parameter.

[0150] From the passenger flow density hotspot area results output in step S4, obtain the current real-time passenger flow flow for each hotspot area. r ;

[0151] Based on the spatial location of the hotspot areas (platform, transfer passage, entrance / exit), compare them with the historical baseline data for the same period;

[0152] If Flow r >Bseline is considered to be a sign of congestion;

[0153] This comprehensive assessment process is automatically repeated at fixed time intervals (e.g., 15 minutes) to obtain dynamic changes in passenger flow over different time periods.

[0154] Furthermore, in the plan view of the rail transit hub, the previously obtained hotspot areas Γ j and its corresponding real-time passenger flow. r Visualization;

[0155] The display is tiered based on the volume of customers, using numerical values ​​or color gradients. The tiers are set according to specific needs (e.g., 5 or 10 color segments).

[0156] When a certain hotspot area Γ j When the passenger flow exceeds the warning threshold defined by its historical baseline, it will be highlighted by darkening the color.

[0157] It should be noted that congestion is determined in real time based on a set threshold η;

[0158] When the passenger flow density in the hotspot area Flow r When the congestion threshold is exceeded, the system automatically triggers a congestion warning.

[0159] Record the timestamp t of the congestion occurrence alarm and region identifier Γ j And send alarm information (such as pop-up notifications, SMS or email) through the management backend to prompt the operation and dispatch personnel to take corresponding diversion or organization measures;

[0160] If congestion persists, the system will automatically upgrade the warning level (e.g., from level 2 to level 3);

[0161] If the congestion dissipates, record the specific time when the warning is lifted and update the passenger flow status.

[0162] For example, heat maps and real-time monitoring information during the early warning process (such as peak passenger flow, congestion periods, and duration) are summarized to form periodic (e.g., daily) passenger flow monitoring reports. These reports include, but are not limited to:

[0163] Hotspot Area List: Lists the main hotspot areas, average visitor flow, peak visitor flow, and time periods during this period;

[0164] Congestion records include the timestamp of congestion occurrence, duration, congested area range, and cause analysis (such as special events, sudden malfunctions, and holiday peaks).

[0165] Comparative analysis: Compare the current period's passenger flow status with historical data from the same period or other reference scenarios to determine the trend of passenger flow changes;

[0166] Management Recommendations: Based on congestion conditions and passenger flow trends, suggestions for improvement are made regarding personnel scheduling, line diversion, and optimization of signage at rail transit hubs.

[0167] The monitoring report is stored in the management database so that the operations management department or senior decision-makers can conduct subsequent queries, statistics, and decision analysis.

[0168] The aforementioned preprocessing methods for the collected data can be carried out using existing technologies and methods, and will not be elaborated further in this example.

[0169] In addition to the above embodiments, other aspects of the present invention also propose a rail transit hub passenger flow monitoring system based on Bluetooth positioning, including: one or more processors and a memory.

[0170] The memory is used to store operable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations, including the flow of the Bluetooth positioning-based passenger flow monitoring method for rail transit hubs described in the foregoing embodiments, particularly... Figure 1 The flowchart of the method is shown.

[0171] Other aspects disclosed in the embodiments of the present invention also propose a computer-readable medium for storing software including instructions executable by one or more computers, which, upon execution, cause the one or more computers to perform operations including the flow of the Bluetooth positioning-based passenger flow monitoring method for rail transit hubs described in the foregoing embodiments, particularly... Figure 1 The flowchart of the method is shown.

[0172] It should be recognized that embodiments of the present invention may be implemented or carried out by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable storage medium.

[0173] The method can be implemented using standard programming techniques, including a non-transitory computer-readable storage medium configured with a computer program in the computer program, wherein the storage medium is configured such that the computer operates in a specific and predefined manner.

[0174] Each program can be implemented in a high-level procedural or object-oriented programming language to communicate with the computer system; however, if required, the program can be implemented in assembly or machine language.

[0175] In any case, the language can be either compiled or interpreted.

[0176] Furthermore, for this purpose, the program can run on programmed application-specific integrated circuits.

[0177] The processes described herein (or variations and / or combinations thereof) can be executed under the control of one or more computer systems configured with executable instructions, and can be implemented by hardware or a combination thereof as code (e.g., executable instructions, one or more computer programs, or one or more applications) that commonly executes on one or more processors. The computer program includes a plurality of instructions executable by one or more processors.

[0178] Furthermore, the method can be implemented in any suitable computing platform, including but not limited to personal computers, minicomputers, mainframes, workstations, networked or distributed computing environments, standalone or integrated computer platforms, or in communication with charged particle tools or other imaging devices.

[0179] Various aspects of the present invention can be implemented in machine-readable code stored on a non-transitory storage medium or device, whether portable or integrated into a computing platform, such as a hard disk, optical read and / or write storage medium, RAM, ROM, etc., such that it can be read by a programmable computer, and when the storage medium or device is read by the computer, it can be used to configure and operate the computer to perform the processes described herein.

[0180] Furthermore, machine-readable code, or parts thereof, can be transmitted via wired or wireless networks.

[0181] When such media includes instructions or programs that combine with a microprocessor or other data processor to implement the steps described above, the invention described herein includes these and other different types of non-transitory computer-readable storage media.

[0182] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A passenger flow monitoring method for rail transit hub based on Bluetooth positioning, characterized in that, include: Multiple Bluetooth beacons are deployed within a pre-defined area of ​​the rail transit hub, and a beacon location database is established; Beacons should be installed at platforms, passageways, transfer nodes, and entrances / exits, with a spacing of 5 to 10 meters between adjacent beacons and a height of 1.5 to 2.5 meters. The Bluetooth signals of Bluetooth devices carried by passengers are collected through mobile terminals and preprocessed to generate sample data sequences. The preprocessing includes signal filtering, noise suppression, and multipath effect correction. Specifically: a Kalman filter algorithm is used to smooth short-term fluctuations in Bluetooth signal strength to reduce signal jitter caused by transient interference; Bluetooth signal strength data below the background noise level is identified as noise and removed based on a preset threshold; for multipath propagation phenomena in underground rail transit hub environments, a multipath channel model is used to correct the Bluetooth signal strength to reduce positioning errors; the filtered, noise-suppressed, and corrected Bluetooth signal strength values ​​are matched one-to-one with the corresponding beacon identifiers and timestamps, and sorted according to chronological order to finally form a time-series Bluetooth signal sample data sequence. Based on the sample data sequence, an improved weighted centroid localization algorithm is used to calculate the passenger's real-time location coordinates; including: Within the same time segment, select the Bluetooth signal strength values, beacon coordinates, and corresponding unique identifiers of several Bluetooth beacons from the sample data sequence; The distance from each Bluetooth beacon to the mobile terminal is denoted as... The distance attenuation factor is denoted as Define weights With distance The relationship is as follows: wherein, represents a first beacon, is a parameter set according to the environmental attenuation characteristics; When decreases, i.e. the beacon is closer, increases, indicating a higher contribution to the positioning result; The passenger's planar coordinates are calculated using the weighted centroid positioning formula: in, For the first The planar coordinates of each Bluetooth beacon in the beacon location database, where N is the number of valid Bluetooth beacons used for calculation. The two-dimensional real-time location coordinates of the passenger; For the calculated The coordinates are assigned a timestamp to form the passenger's temporal location point, which is the passenger's real-time location coordinates; Based on the time-series data of the passengers' real-time location coordinates, a passenger flow trajectory model is constructed, and cluster analysis is used to delineate passenger flow density hotspot areas; including: The same passenger at different timestamps The coordinates are connected in chronological order, and a smoothing algorithm is used to correct coordinates that are momentarily lost or drifting, resulting in a complete and coherent passenger flow trajectory. In key areas such as platforms, transfer passages, or entrances and exits, the trajectories of all passengers are analyzed for clustering. If a trajectory in a certain area shows high frequency of crossing or stopping, it is marked as a candidate hotspot area. A density clustering algorithm is used to further subdivide each candidate hotspot area, and several passenger flow density levels are divided by combining the dwell time, trajectory direction, and passing speed parameters. Adjacent or overlapping candidate hotspot areas are merged into a larger unified area, while overly scattered candidate areas are eliminated. The spatial coordinate boundaries, time period of occurrence, and peak passenger flow information of each hotspot area are output. By combining historical passenger flow data with real-time identified passenger flow density hotspots, a passenger flow distribution heat map and congestion warning information are generated, and a monitoring report is output, including: The system compares real-time passenger flow data of hotspot areas with historical data from the same period in the database to comprehensively evaluate passenger flow distribution at different times, transfer nodes, and lines, obtaining a baseline value for passenger flow under normal conditions. On the rail transit hub's plan map, each hotspot area is displayed in a hierarchical manner using numerical values ​​or varying color shades. When the passenger flow of a hotspot area exceeds the warning threshold of the historical baseline value, its displayed color or value will be darkened or marked more prominently. Based on the set warning threshold, the system judges in real time whether congestion occurs in the target area. When the passenger flow density exceeds the warning threshold, the system automatically triggers an alarm, records the time of congestion, and sends an alarm message to the management backend. 2.The passenger flow monitoring method for rail transit hub based on Bluetooth positioning according to claim 1, characterized in that, The deployment methods of the Bluetooth beacon include: Each beacon is configured with a unique identifier and a transmit power adaptive module, which dynamically adjusts the signal coverage range according to environmental conditions. The specific deployment locations of each beacon are inspected, and the effective area of ​​signal coverage is determined by testing the Bluetooth signal strength values ​​on-site. Based on the test results, the transmission power parameters are optimized again to complete the beacon deployment plan that meets the positioning requirements. 3.The passenger flow monitoring method for rail transit hub based on Bluetooth positioning according to claim 2, characterized in that, The establishment of the beacon location database includes: The spatial coordinates of each Bluetooth beacon are measured and recorded, including planar coordinates and vertical height information; Record the unique identifier, deployment location, installation area function type, and adaptive transmit power parameters for each Bluetooth beacon; Based on the measured spatial coordinates and signal coverage area, the plan of the rail transit hub is marked, and the coordinate information of the beacons is written into the database; The beacon information in the database is indexed and verified, and the beacon location and power parameters are checked and updated regularly according to the actual site environment. 4.The passenger flow monitoring method for rail transit hub based on Bluetooth positioning according to claim 1, wherein, The Bluetooth signal includes signal strength, beacon identifier, and timestamp, wherein: The signal strength is a Bluetooth signal strength measurement value characterized by a received signal strength indication method; The beacon identifier is used to uniquely identify the Bluetooth beacon that emits the Bluetooth signal; The timestamp is used to record the specific moment when the Bluetooth signal is scanned by the mobile terminal, in order to construct the trajectory of the passenger's location changing over time; The mobile terminal scans all visible Bluetooth beacon signals in the surrounding environment at fixed time intervals, and performs preliminary integration of the scan results, deleting duplicate beacon information; The acquired Bluetooth signal data is then stored in chronological order.

5. A rail transit hub passenger flow monitoring system based on Bluetooth positioning, characterized in that, include: One or more processors; The memory stores operable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations, including the flow of the Bluetooth-based positioning-based passenger flow monitoring method for rail transit hubs as described in any one of claims 1 to 4.

6. A computer readable medium storing software, characterized in that: The software includes instructions executable by one or more computers, which cause the one or more computers to perform operations, including the flow of the Bluetooth-based positioning-based passenger flow monitoring method for rail transit hubs as described in any one of claims 1 to 4.

Images