Railway passenger flow analysis method, device and equipment, storage medium and product
By determining the passenger flow distribution areas and flow paths within railway stations and combining data analysis and machine learning models, accurate capture and real-time monitoring of passenger flow status are achieved, solving the accuracy and real-time problems of passenger flow monitoring in existing technologies and improving the efficiency of passenger flow safety assessment.
Patent Information
- Application Number
- CN202510475650.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-16
- Publication Date
- 2025-09-12
AI Technical Summary
In the existing technology, the railway passenger flow analysis system has defects in cost, adaptability, maintenance and operation, and relies on manual experience, which leads to misjudgments and omissions in passenger flow monitoring, making it difficult to achieve real-time and accurate passenger flow safety assessment.
By determining the passenger distribution areas and their corresponding passenger flow paths within railway stations, real-time passenger flow data is obtained. Combined with train timetables and station layout data, convolutional neural networks, Transformer encoders, and K-nearest neighbor models are used to locate passenger distribution and track heads, calculate passenger flow indexes, and achieve accurate capture and real-time monitoring of passenger flow status.
It improves the accuracy and real-time performance of passenger flow monitoring, can dynamically assess the passenger flow safety status, and send passenger flow guidance instructions in a timely manner to ensure the safety of passengers waiting for the bus.
Smart Images
Figure CN120633962A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing technology, and in particular to a railway passenger flow analysis method, device, equipment, storage medium and product. Background Art
[0002] In recent years, the railway transportation industry has experienced rapid growth, with significant improvements in transport capacity and efficiency. Consequently, the number of passengers it carries has also continued to grow. However, with this surge in passenger volume, the issue of passenger safety within stations has gradually surfaced, becoming a critical issue that requires urgent resolution. To ensure passenger safety while waiting for trains, it is crucial to conduct real-time and accurate assessments of passenger safety within stations.
[0003] Conventional passenger flow monitoring technologies rely primarily on staff's experience to assess crowd concentration. However, during peak hours, when passenger traffic is high, this approach is prone to misjudgments and missed calls, and real-time communication between staff is difficult, potentially causing delays in passenger boarding, ticket checking, and other passenger operations. Therefore, more efficient and accurate passenger flow monitoring and safety management methods are needed. Summary of the Invention
[0004] The present invention provides a railway passenger flow analysis method, device, equipment, storage medium and product, which are used to solve the defects of the railway passenger flow analysis system in the prior art in terms of cost, adaptability, maintenance and operation, which have certain technical challenges.
[0005] The present invention provides a railway passenger flow analysis method, the method comprising: Determining passenger flow distribution areas within a railway passenger station and passenger flow paths corresponding to each passenger flow distribution area, wherein the passenger flow paths are used to transport or evacuate passengers to the passenger flow distribution areas connected to the passenger flow paths, and each passenger flow distribution area is connected to at least one passenger flow path; Acquire first passenger flow data of each passenger flow distribution area in the current time period and second passenger flow data of the passenger flow path corresponding to the passenger flow distribution area; Based on the first passenger flow data, the second passenger flow data and the basic data of the railway passenger station, the passenger flow index of each passenger flow distribution area in the current time period is determined, and the basic data includes data related to the operation and management of the railway passenger station.
[0006] According to a railway passenger flow analysis method provided by the present invention, the basic data of the railway passenger station includes train schedule data and passenger station layout data of the railway passenger station; Determining a passenger flow index for each passenger flow distribution area in a current time period based on the first passenger flow data, the second passenger flow data, and basic data of the railway passenger station includes: Determining the passenger flow weight of each passenger flow distribution area in the current time period based on the train timetable data; Determining, based on the passenger station layout data, a first area of a queuing area in the passenger flow distribution area and a second area of a functional area outside the queuing area; Based on the first passenger flow data, the second passenger flow data, the passenger flow weight, the area of the first area and the area of the second area of each passenger flow gathering area in the current time period, the passenger flow index of each passenger flow gathering area in the current time period is determined.
[0007] According to a railway passenger flow analysis method provided by the present invention, based on the train timetable data, determining the passenger flow weight of each passenger flow distribution area in the current time period, including: Based on the train timetable data, if it is determined that there is a ticket checking train in the railway passenger station during the current time period, the passenger flow weight of each passenger flow distribution area during the current time period is determined to be a first passenger flow weight; Based on the train timetable data, when it is determined that there is no ticket checking train in the railway passenger station during the current time period, the passenger flow weight of each passenger flow distribution area during the current time period is determined to be the second passenger flow flow weight; the second passenger flow flow weight is less than the first passenger flow flow weight.
[0008] According to a railway passenger flow analysis method provided by the present invention, the first passenger flow data of each passenger flow distribution area in the current time period is obtained by the following method: For each of the passenger flow gathering and distribution areas in the current time period, obtaining first video data corresponding to the passenger flow gathering and distribution area in the current time period; Inputting the first video frame in the first video data into a passenger flow distribution positioning model to obtain passenger flow distribution positioning data output by the passenger flow distribution positioning model; Determine first passenger flow data of the passenger flow distribution area in the current time period based on the passenger flow distribution positioning data; The passenger flow distribution and positioning model is obtained by training the initial passenger flow distribution and positioning model using training sample data that annotates the head position data of each individual in the crowd. The initial passenger flow distribution and positioning model includes a convolutional neural network, a Transformer encoder, a Transformer decoder, and a K-nearest neighbor model.
[0009] According to a railway passenger flow analysis method provided by the present invention, the second passenger flow data of the passenger flow path corresponding to each passenger flow distribution area in the current time period is obtained by the following method: For each passenger flow path of each passenger flow gathering and distribution area in the current time period, obtaining second video data corresponding to the passenger flow path in the current time period; For each second video frame in the second video data, input the second video frame into a head detection model to obtain head feature data carrying a human body label output by the head detection model; Inputting the head feature data corresponding to each second video frame in the second video data into a head tracking model frame by frame, and obtaining a moving trajectory corresponding to each human body label output by the head tracking model; Based on the travel trajectory corresponding to each of the human body tags and the crossing detection line on the passenger flow path, the second passenger flow data of each of the passenger flow paths in the current time period is determined; the crossing detection line includes a first crossing detection line and a second crossing detection line, and the crossing direction corresponding to the first crossing detection line is opposite to the crossing direction corresponding to the second crossing detection line.
[0010] According to a railway passenger flow analysis method provided by the present invention, the method further includes: Determining the comprehensive passenger flow level of the railway passenger station in the current period based on the passenger flow index of each of the passenger flow distribution areas in the current period; When the comprehensive passenger flow level of the railway passenger station in the current time period is greater than the preset level, a passenger flow guidance instruction is sent to the railway service end to notify the railway service end to guide the passenger flow in the railway passenger station.
[0011] The present invention also provides a railway passenger flow analysis device, the device comprising: A first railway passenger flow analysis module is configured to determine passenger flow distribution areas within a railway station and passenger flow paths corresponding to each passenger flow distribution area, wherein the passenger flow paths are used to transport or evacuate passengers to the passenger flow distribution areas connected to the passenger flow paths, and each passenger flow distribution area is connected to at least one passenger flow path; The second railway passenger flow analysis module is used to obtain the first passenger flow data of each passenger flow distribution area in the current time period and the second passenger flow data of the passenger flow path corresponding to the passenger flow distribution area; The third railway passenger flow analysis module is used to determine the passenger flow index of each passenger flow distribution area in the current time period based on the first passenger flow data, the second passenger flow data and the basic data of the railway passenger station, and the basic data includes data related to the operation and management of the railway passenger station.
[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any of the above-described railway passenger flow analysis methods is implemented.
[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described railway passenger flow analysis methods.
[0014] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned railway passenger flow analysis methods.
[0015] The railway passenger flow analysis method, device, equipment, storage medium, and product provided by the present invention first define passenger distribution areas and their corresponding passenger flow paths within a railway station, providing a clear spatial framework for passenger flow management. Based on this, passenger flow data for each distribution area and its corresponding passenger flow paths during the current time period is acquired in real time, accurately capturing the passenger flow status during the current time period. Furthermore, combined with basic railway station data, a comprehensive assessment of the passenger flow index for each distribution area during the current time period is performed, effectively improving the accuracy and real-time nature of passenger flow monitoring. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0017] Figure 1 1 is a flow chart of the railway passenger flow analysis method provided by the present invention; Figure 2 This is one of the scenario diagrams of the railway passenger flow analysis method provided by the present invention; Figure 3 This is the second scenario diagram of the railway passenger flow analysis method provided by the present invention; Figure 4 This is the third scenario diagram of the railway passenger flow analysis method provided by the present invention; Figure 5 It is a structural schematic diagram of the railway passenger flow analysis device provided by the present invention; Figure 6 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION
[0018] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.
[0019] Figure 1 FIG. 1 is a flow chart of a railway passenger flow analysis method according to an embodiment of the present invention. Figure 1 As shown, the method includes: Step 110, determine the passenger flow distribution areas within the railway passenger station and the passenger flow paths corresponding to each passenger flow distribution area, wherein the passenger flow paths are used to transport or evacuate passengers to the passenger flow distribution areas connected to the passenger flow paths, and each of the passenger flow distribution areas is connected to at least one of the passenger flow paths.
[0020] Here, passenger distribution areas are the main places where passengers gather within a railway station, such as waiting halls, platform areas, and departure halls. Passenger flow paths are the channels connecting these passenger distribution areas, such as entry and exit gates, ticket gates, and platform escalator entrances.
[0021] See also Figure 2 As shown, in this embodiment, the passenger flow distribution areas (waiting hall, platform area, exit hall) are used as analysis nodes, and the passenger flow paths (entry gate unit, exit gate unit, ticket gate unit, platform escalator entrance, etc.) are used as analysis links. Each passenger flow distribution area is connected to at least one passenger flow path, forming a passenger flow network.
[0022] Step 120: Acquire the first passenger flow data of each passenger flow gathering and distribution area in the current time period and the second passenger flow data of the passenger flow path corresponding to the passenger flow gathering and distribution area.
[0023] The first passenger flow data refers to the passenger flow data in the passenger flow distribution area, which reflects the overall state of the passenger flow in the passenger flow distribution area.
[0024] The second passenger flow data refers to the passenger flow data on the passenger flow path, which reflects the flow characteristics of the passenger flow on the passenger flow path in the passenger flow distribution area.
[0025] In this embodiment, first passenger flow data of each passenger flow distribution area and second passenger flow data of the passenger flow path corresponding to the passenger flow distribution area are collected in real time during the current period. Both the first passenger flow data and the second passenger flow data can be obtained in real time through monitoring cameras and other equipment in the station.
[0026] Step 130, based on the first passenger flow data, the second passenger flow data and the basic data of the railway passenger station, determine the passenger flow index of each passenger flow distribution area in the current time period, and the basic data includes data related to the operation and management of the railway passenger station.
[0027] Here, the basic data of railway passenger stations include data related to the operation and management of railway passenger stations, such as train timetables, station capacity, facility distribution, etc.
[0028] The passenger flow index is a comprehensive index used to reflect the passenger flow safety status of each passenger distribution area during the current time period. In this embodiment, the passenger flow index is calculated based on the first passenger flow data, the second passenger flow data, and the basic data. It takes into account the fine-grained characteristics of passenger flow (the second passenger flow data), the coarse-grained characteristics (the first passenger flow data), and external environmental factors (the basic data).
[0029] Specifically, this embodiment combines the first and second passenger flow data with basic data such as train schedules to dynamically calculate a passenger flow index for each passenger distribution area during the current time period. A higher passenger flow index indicates a worse passenger flow safety status for that area, necessitating appropriate safety management measures.
[0030] The railway passenger flow analysis method proposed in this embodiment first defines passenger distribution areas and their corresponding passenger flow paths within a railway station, providing a clear spatial framework for passenger flow management. Based on this, real-time passenger flow data for each distribution area and its corresponding passenger flow paths during the current time period is acquired, accurately capturing the passenger flow status during that time period. Furthermore, combined with basic railway station data, a comprehensive assessment of the passenger flow index for each distribution area during the current time period is performed, effectively improving the accuracy and real-time nature of passenger flow monitoring.
[0031] It should be noted that each implementation method of the present application can be freely combined, the order can be changed, or it can be executed separately, and does not need to rely on or depend on a fixed execution order.
[0032] In some embodiments, the basic data of the railway passenger station includes train schedule data and passenger station layout data of the railway passenger station; The determining, based on the first passenger flow data, the second passenger flow data and the basic data of the railway passenger station, of the passenger flow index of each passenger flow distribution area in the current time period includes: Determining the passenger flow weight of each passenger flow distribution area in the current time period based on the train timetable data; Determining, based on the passenger station layout data, a first area of a queuing area in the passenger flow distribution area and a second area of a functional area outside the queuing area; Based on the first passenger flow data, the second passenger flow data, the passenger flow weight, the area of the first area and the area of the second area of each passenger flow gathering area in the current time period, the passenger flow index of each passenger flow gathering area in the current time period is determined.
[0033] Here, the train schedule data includes information such as the arrival and departure times of trains. The passenger station layout data includes the location, area, and connection relationship of each functional area in the station.
[0034] In this embodiment, based on train schedule data from railway stations, passenger flow within each time period can be predicted and analyzed. Based on the predicted flow, a passenger flow weight can be assigned to each passenger flow distribution area. In other words, based on train arrival and departure times, it is possible to predict which periods will see peak passenger flow. For example, when a train is about to arrive or has already arrived within the current time period, the passenger flow weight of the passenger flow distribution area increases.
[0035] In addition, for each passenger flow distribution area, the first area of the queuing area in the passenger flow distribution area and the second area of the functional area outside the queuing area (such as the walking area) will be determined based on the passenger station layout data.
[0036] Finally, the first passenger flow data, the second passenger flow data, the passenger flow weight, and the corresponding area of the current time period are combined through a comprehensive algorithm to combine these factors and calculate the passenger flow index of each passenger flow distribution area in the current time period.
[0037] In one example, when the passenger flow distribution area is a waiting hall area, the passenger flow path corresponding to the waiting hall area includes the station entrance and the ticket gate, and the waiting hall area is divided into a queuing area, a walking area, and a rest area; The passenger flow index of the waiting hall area is K 1 The calculation is as follows: ; in, Refers to the passenger flow weight, Refers to the second passenger flow data of the entrance. Refers to the second passenger flow data of the ticket gate, Refers to the first passenger flow data of the waiting area (here the number of people queuing in the waiting area represents the first passenger flow data of the waiting area). Refers to the area of the queue area, Refers to the area of the walking zone, Refers to the area of the rest area.
[0038] In one example, when the passenger flow distribution area is the platform area, the passenger flow path corresponding to the platform area includes the corresponding alighting gate, ticket gate and staircase entrance of each platform, and the platform area is divided into the corresponding queuing area and walking area of each platform; The passenger flow index of the platform area K 2 The calculation is as follows: ; in, Refers to the passenger flow weight, Refers to the i The second passenger flow data of the exit of each platform, Refers to the i The second passenger flow data of the ticket gate of each platform, Refers to the second passenger flow data at the stairwell of the i-th platform, Refers to the first passenger flow data of the i-th platform (here the number of people queuing in the platform represents the first passenger flow data of this platform), Refers to the area of the queue area at the i-th platform, Refers to the area of the walking zone of the i-th platform.
[0039] In one example, when the passenger flow distribution area is the exit hall area, the passenger flow path corresponding to the exit hall area includes each exit, and the exit hall area is divided into a queuing area and an exit corridor area corresponding to each exit; The passenger flow index of the exit hall area is K 3 The calculation is as follows: ; in, Refers to the passenger flow weight, Refers to the second passenger flow data of the j-th exit (here the number of ticket inspectors at this exit represents the second passenger flow data of this exit), Refers to the first passenger flow data of the j-th exit (here the number of people queuing at the exit represents the first passenger flow data of this exit), Refers to the area of the queue area at the j-th exit, Refers to the area of the exit corridor of the j-th exit.
[0040] In some embodiments, determining the passenger flow weight of each passenger flow distribution area in the current time period based on the train schedule data includes: Based on the train timetable data, if it is determined that there is a ticket checking train in the railway passenger station during the current time period, the passenger flow weight of each passenger flow distribution area during the current time period is determined to be a first passenger flow weight; Based on the train timetable data, when it is determined that there is no ticket checking train in the railway passenger station during the current time period, the passenger flow weight of each passenger flow distribution area during the current time period is determined to be the second passenger flow flow weight; the second passenger flow flow weight is less than the first passenger flow flow weight.
[0041] If there are trains with ticket inspections during the current time period, this means that a large number of passengers will need to inspect their tickets at the designated ticket gate area and then pass through the entry gate area to enter the platform area or waiting hall area. At the same time, a large number of passengers will exit the station from the departure hall area. Therefore, the passenger flow weight for each passenger flow distribution area (such as the platform area, waiting hall area, etc.) during the current time period will be set to the higher first passenger flow weight.
[0042] If there is no ticket checking train in the current time period, it means that the passenger flow may be relatively stable, with no significant concentration or dispersion trend. In this case, the passenger flow weight of each passenger flow distribution area will be set to the lower second passenger flow weight.
[0043] For example, in the calculation process of passenger flow index in the waiting hall area, platform area and other passenger flow distribution areas mentioned above, if there is a ticket checking train in the current period, then is 0.8, if there is no ticket checking train in the current period, then is 0.2.
[0044] The railway passenger flow analysis method proposed in this embodiment accurately evaluates the passenger flow index of each passenger flow distribution area in the current time period through the above method, effectively improving the accuracy and real-time performance of passenger flow monitoring.
[0045] In some embodiments, the first passenger flow data of each passenger flow distribution area in the current time period is obtained by: For each of the passenger flow gathering and distribution areas in the current time period, obtaining first video data corresponding to the passenger flow gathering and distribution area in the current time period; Inputting the first video frame in the first video data into a passenger flow distribution positioning model to obtain passenger flow distribution positioning data output by the passenger flow distribution positioning model; Determine first passenger flow data of the passenger flow distribution area in the current time period based on the passenger flow distribution positioning data; The passenger flow distribution and positioning model is obtained by training the initial passenger flow distribution and positioning model using training sample data that annotates the head position data of each individual in the crowd. The initial passenger flow distribution and positioning model includes a convolutional neural network, a Transformer encoder, a Transformer decoder, and a K-nearest neighbor model.
[0046] In this embodiment, the passenger flow distribution and positioning model is constructed by a trained convolutional neural network, a Transformer encoder, a Transformer decoder, and a K-nearest neighbor model.
[0047] In this embodiment, a camera installed in the passenger flow distribution area can capture and store video data of the passenger flow distribution area during the current time period, namely, the first video data. A video frame is then extracted from the first video data (e.g., the first video frame, the last video frame, or an intermediate video frame in the first video data), namely, the first video frame. The first video frame is then input into a passenger flow distribution positioning model, which determines passenger flow distribution positioning data for the passenger flow distribution area, namely, the head position data of each individual in the first video frame.
[0048] Specifically, see Figure 3 As shown, when the first video frame Input into the convolutional neural network to obtain features , the feature F is transformed into a 1-dimensional sequence and embedded in the position code to obtain the feature , the Transformer encoder transforms the feature F p The self-attention mechanism SA is used as input to generate the encoded feature Fe. The Transformer decoder uses cross-self-attention between the instance Qh and the feature Fe to generate the feature Fd. Finally, the feature Fd is decomposed by the post-processing module into the initial head position prediction data for each individual in the first video frame. After obtaining the initial head position prediction data for each individual in the first video frame, these initial head position prediction data are further fine-tuned in conjunction with the K-nearest neighbor model to more accurately reflect the head position data of each individual in the first video frame.
[0049] Finally, by analyzing the passenger flow distribution and positioning data, that is, counting and position analysis of the head position data of each individual in the first video frame, combined with the statistical area requirements of the first passenger flow data (such as the first passenger flow data is the passenger flow data in the queuing area in the passenger flow distribution area), the first passenger flow data of the passenger flow distribution area is determined.
[0050] The railway passenger flow analysis method proposed in this embodiment realizes real-time monitoring and analysis of the first passenger flow data of the passenger flow distribution area by combining the first video data corresponding to the passenger flow distribution area and the passenger flow distribution positioning model.
[0051] In some embodiments, the second passenger flow data of the passenger flow path corresponding to each of the passenger flow distribution areas in the current time period is obtained by: For each passenger flow path of each passenger flow gathering and distribution area in the current time period, obtaining second video data corresponding to the passenger flow path in the current time period; For each second video frame in the second video data, input the second video frame into a head detection model to obtain head feature data carrying a human body label output by the head detection model; Inputting the head feature data corresponding to each second video frame in the second video data into a head tracking model frame by frame, and obtaining a moving trajectory corresponding to each human body label output by the head tracking model; Based on the travel trajectory corresponding to each of the human body tags and the crossing detection line on the passenger flow path, the second passenger flow data of each of the passenger flow paths in the current time period is determined; the crossing detection line includes a first crossing detection line and a second crossing detection line, and the crossing direction corresponding to the first crossing detection line is opposite to the crossing direction corresponding to the second crossing detection line.
[0052] For each passenger flow path corresponding to each passenger distribution area during the current time period, the system first obtains video data corresponding to the flow path, namely the second video data. Each second video frame in the second video data is then input into the head detection model. The head detection model assigns a unique label (human body label) to each head detected in the second video frame. Specifically, the head detection model outputs head feature data carrying the human body label, which is used for subsequent tracking and analysis.
[0053] In one example, a head detection model can be trained using the Yolov5 model. Specifically, a dataset containing a large number of head images and their labels (i.e., head positions) is collected and fed into the Yolov5 model. Using optimization methods such as backpropagation and gradient descent, the model parameters are continuously adjusted to accurately identify heads in images, resulting in a trained head detection model.
[0054] Next, the head feature data corresponding to each second video frame is fed into the head tracking model frame by frame. Based on the head feature data between the previous and next frames, the head tracking model tracks the motion trajectory of each head (i.e., each tag). Based on the head tracking model, the trajectory corresponding to each head tag can be obtained.
[0055] In one example, a head tracking model can be trained using a Discriminative Correlation Filter (DCF) model. Specifically, a dataset containing head tracking sequences is collected. These datasets typically consist of a series of video frames, each annotated with the head position. The dataset is then fed into the DCF model, and optimization methods such as minimizing the least squares loss function are used to continuously adjust the model parameters to ensure accurate trajectory tracking, ultimately resulting in a trained head tracking model.
[0056] Finally, in order to quantify the second passenger flow data on the passenger flow path, a first crossing detection line and a second crossing detection line are set in this embodiment. The first crossing detection line and the second crossing detection line have opposite crossing directions and are used to record the flow of passenger flow in different directions.
[0057] See also Figure 4 As shown, based on the travel trajectory corresponding to each head tag and the crossing direction of the crossing detection line, the number of heads (i.e., the number of people) crossing the first crossing detection line and the second crossing detection line is counted. Based on the statistical results of the first crossing detection line and the second crossing detection line, the second passenger flow data for each passenger flow path in the current time period is obtained.
[0058] The railway passenger flow analysis method proposed in this embodiment realizes real-time monitoring and analysis of the second passenger flow data of the passenger flow path through the above method.
[0059] In some embodiments, the method further comprises: Determining the comprehensive passenger flow level of the railway passenger station in the current period based on the passenger flow index of each of the passenger flow distribution areas in the current period; When the comprehensive passenger flow level of the railway passenger station in the current time period is greater than the preset level, a passenger flow guidance instruction is sent to the railway service end to notify the railway service end to guide the passenger flow in the railway passenger station.
[0060] Based on the calculated passenger flow index of each passenger flow distribution area, the overall passenger flow level of the railway passenger station in the current period can be comprehensively evaluated and determined. For example, the overall passenger flow level of the railway passenger station in the current period can be obtained by taking a weighted average calculation of the passenger flow index of all passenger flow distribution areas.
[0061] In this embodiment, the passenger flow at a railway station is divided into different levels based on the comprehensive passenger flow index. The criteria for dividing the passenger flow levels at a railway station can be formulated based on the actual operating conditions and passenger flow management requirements of the railway station. For example, the passenger flow levels at a railway station can be divided into four levels: low, medium, high, and very high, each corresponding to a different comprehensive passenger flow index.
[0062] After determining the comprehensive passenger flow level of a railway station during the current period, it is necessary to compare it with a preset level. The preset level is set based on the railway station's operational capacity and passenger flow management needs, and is used to determine whether passenger flow guidance measures are necessary.
[0063] If the passenger flow level of the railway passenger station in the current period is greater than the preset passenger flow level, it means that the passenger flow situation has exceeded the normal operating capacity of the railway passenger station. At this time, a passenger flow guidance instruction can be sent to the railway service end to notify it to take corresponding passenger flow guidance measures.
[0064] The railway passenger flow analysis method proposed in this embodiment effectively manages the passenger flow status of railway stations by determining the passenger flow level based on the passenger flow index and sending passenger flow guidance instructions when necessary.
[0065] Based on any of the above embodiments, the present invention further provides a railway passenger flow analysis device, Figure 5 Schematic diagram of the structure of the railway passenger flow analysis device provided by the present invention. Figure 5 As shown, the device includes: A first railway passenger flow analysis module 510 is configured to determine passenger flow distribution areas within a railway station and passenger flow paths corresponding to each passenger flow distribution area, wherein the passenger flow paths are used to transport or evacuate passengers to the passenger flow distribution areas connected thereto, and each passenger flow distribution area is connected to at least one passenger flow path; The second railway passenger flow analysis module 520 is used to obtain the first passenger flow data of each passenger flow distribution area in the current time period and the second passenger flow data of the passenger flow path corresponding to the passenger flow distribution area; The third railway passenger flow analysis module 530 is used to determine the passenger flow index of each passenger flow distribution area in the current time period based on the first passenger flow data, the second passenger flow data and the basic data of the railway passenger station, and the basic data includes data related to the operation and management of the railway passenger station.
[0066] The device provided by the embodiments of the present invention first defines the passenger distribution areas and their corresponding passenger flow paths within a railway station, providing a clear spatial framework for passenger flow management. Based on this, it acquires real-time passenger flow data for each distribution area and its corresponding passenger flow path during the current time period, accurately capturing the passenger flow status during that time period. Furthermore, combined with basic railway station data, it comprehensively evaluates the passenger flow index for each distribution area during the current time period, effectively improving the accuracy and real-time nature of passenger flow monitoring.
[0067] The railway passenger flow analysis device described in this embodiment and the railway passenger flow analysis method provided by the present invention described above can be referred to each other, and will not be described in detail here.
[0068] Figure 6 An example of a physical structure diagram of an electronic device is shown below. Figure 6 As shown, the electronic device may include: a processor 610, a communications interface 620, a memory 630, and a communication bus 640, wherein the processor 610, the communications interface 620, and the memory 630 communicate with each other via the communication bus 640. The processor 610 may call the logic instructions in the memory 630 to execute the railway passenger flow analysis method, which includes: Determining passenger flow distribution areas within a railway passenger station and passenger flow paths corresponding to each passenger flow distribution area, wherein the passenger flow paths are used to transport or evacuate passengers to the passenger flow distribution areas connected to the passenger flow paths, and each passenger flow distribution area is connected to at least one passenger flow path; Acquire first passenger flow data of each passenger flow distribution area in the current time period and second passenger flow data of the passenger flow path corresponding to the passenger flow distribution area; Based on the first passenger flow data, the second passenger flow data and the basic data of the railway passenger station, the passenger flow index of each passenger flow distribution area in the current time period is determined, and the basic data includes data related to the operation and management of the railway passenger station.
[0069] Furthermore, the logic instructions in the aforementioned memory 630 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.
[0070] On the other hand, the present invention further provides a computer program product, comprising a computer program, which may be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can perform the railway passenger flow analysis method provided by the above methods, which includes: Determining passenger flow distribution areas within a railway passenger station and passenger flow paths corresponding to each passenger flow distribution area, wherein the passenger flow paths are used to transport or evacuate passengers to the passenger flow distribution areas connected to the passenger flow paths, and each passenger flow distribution area is connected to at least one passenger flow path; Acquire first passenger flow data of each passenger flow distribution area in the current time period and second passenger flow data of the passenger flow path corresponding to the passenger flow distribution area; Based on the first passenger flow data, the second passenger flow data and the basic data of the railway passenger station, the passenger flow index of each passenger flow distribution area in the current time period is determined, and the basic data includes data related to the operation and management of the railway passenger station.
[0071] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the railway passenger flow analysis method provided by the above methods, the method comprising: Determining passenger flow distribution areas within a railway passenger station and passenger flow paths corresponding to each passenger flow distribution area, wherein the passenger flow paths are used to transport or evacuate passengers to the passenger flow distribution areas connected to the passenger flow paths, and each passenger flow distribution area is connected to at least one passenger flow path; Acquire first passenger flow data of each passenger flow distribution area in the current time period and second passenger flow data of the passenger flow path corresponding to the passenger flow distribution area; Based on the first passenger flow data, the second passenger flow data and the basic data of the railway passenger station, the passenger flow index of each passenger flow distribution area in the current time period is determined, and the basic data includes data related to the operation and management of the railway passenger station.
[0072] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.
[0073] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.
[0074] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical coding feature diagrams therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.
Claims
1. A railway passenger flow analysis method, characterized in that: include: Determining passenger flow distribution areas within a railway passenger station and passenger flow paths corresponding to each passenger flow distribution area, wherein the passenger flow paths are used to transport or evacuate passengers to the passenger flow distribution areas connected to the passenger flow paths, and each passenger flow distribution area is connected to at least one passenger flow path; Acquire first passenger flow data of each passenger flow distribution area in the current time period and second passenger flow data of the passenger flow path corresponding to the passenger flow distribution area; Based on the first passenger flow data, the second passenger flow data and the basic data of the railway passenger station, the passenger flow index of each passenger flow distribution area in the current time period is determined, and the basic data includes data related to the operation and management of the railway passenger station.
2. The railway passenger flow analysis method according to claim 1, characterized in that: The basic data of the railway passenger station includes the train schedule data and passenger station layout data of the railway passenger station; Determining a passenger flow index for each passenger flow distribution area in a current time period based on the first passenger flow data, the second passenger flow data, and basic data of the railway passenger station includes: Determining the passenger flow weight of each passenger flow distribution area in the current time period based on the train timetable data; Determining, based on the passenger station layout data, a first area of a queuing area in the passenger flow distribution area and a second area of a functional area outside the queuing area; Based on the first passenger flow data, the second passenger flow data, the passenger flow weight, the area of the first area and the area of the second area of each passenger flow gathering area in the current time period, the passenger flow index of each passenger flow gathering area in the current time period is determined.
3. The railway passenger flow analysis method according to claim 2, characterized in that: Determining the passenger flow weight of each passenger flow distribution area in the current time period based on the train timetable data includes: Based on the train timetable data, if it is determined that there is a ticket checking train in the railway passenger station during the current time period, the passenger flow weight of each passenger flow distribution area during the current time period is determined to be a first passenger flow weight; Based on the train timetable data, when it is determined that there is no ticket checking train in the railway passenger station during the current time period, the passenger flow weight of each passenger flow distribution area during the current time period is determined to be the second passenger flow flow weight; the second passenger flow flow weight is less than the first passenger flow flow weight.
4. The railway passenger flow analysis method according to claim 1, characterized in that: The first passenger flow data of each passenger flow distribution area in the current time period is obtained by: For each of the passenger flow gathering and distribution areas in the current time period, obtaining first video data corresponding to the passenger flow gathering and distribution area in the current time period; Inputting the first video frame in the first video data into a passenger flow distribution positioning model to obtain passenger flow distribution positioning data output by the passenger flow distribution positioning model; Determine first passenger flow data of the passenger flow distribution area in the current time period based on the passenger flow distribution positioning data; The passenger flow distribution and positioning model is obtained by training the initial passenger flow distribution and positioning model using training sample data that annotates the head position data of each individual in the crowd. The initial passenger flow distribution and positioning model includes a convolutional neural network, a Transformer encoder, a Transformer decoder, and a K-nearest neighbor model.
5. The railway passenger flow analysis method according to claim 1, characterized in that: The second passenger flow data of the passenger flow path corresponding to each of the passenger flow distribution areas in the current time period is obtained in the following manner: For each passenger flow path of each passenger flow gathering and distribution area in the current time period, obtaining second video data corresponding to the passenger flow path in the current time period; For each second video frame in the second video data, input the second video frame into a head detection model to obtain head feature data carrying a human body label output by the head detection model; Inputting the head feature data corresponding to each second video frame in the second video data into a head tracking model frame by frame, and obtaining a moving trajectory corresponding to each human body label output by the head tracking model; Based on the travel trajectory corresponding to each of the human body tags and the crossing detection line on the passenger flow path, the second passenger flow data of each of the passenger flow paths in the current time period is determined; the crossing detection line includes a first crossing detection line and a second crossing detection line, and the crossing direction corresponding to the first crossing detection line is opposite to the crossing direction corresponding to the second crossing detection line.
6. The railway passenger flow analysis method according to claim 1, characterized in that: The method further comprises: Determining the comprehensive passenger flow level of the railway passenger station in the current period based on the passenger flow index of each of the passenger flow distribution areas in the current period; When the comprehensive passenger flow level of the railway passenger station in the current time period is greater than the preset level, a passenger flow guidance instruction is sent to the railway service end to notify the railway service end to guide the passenger flow in the railway passenger station.
7. A railway passenger flow analysis device, characterized in that: include: A first railway passenger flow analysis module is configured to determine passenger flow distribution areas within a railway station and passenger flow paths corresponding to each passenger flow distribution area, wherein the passenger flow paths are used to transport or evacuate passengers to the passenger flow distribution areas connected to the passenger flow paths, and each passenger flow distribution area is connected to at least one passenger flow path; The second railway passenger flow analysis module is used to obtain the first passenger flow data of each passenger flow distribution area in the current time period and the second passenger flow data of the passenger flow path corresponding to the passenger flow distribution area; The third railway passenger flow analysis module is used to determine the passenger flow index of each passenger flow distribution area in the current time period based on the first passenger flow data, the second passenger flow data and the basic data of the railway passenger station, and the basic data includes data related to the operation and management of the railway passenger station.
8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the railway passenger flow analysis method according to any one of claims 1 to 6 is implemented.
9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the railway passenger flow analysis method according to any one of claims 1 to 6 is implemented.
10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the railway passenger flow analysis method according to any one of claims 1 to 6 is implemented.