Multi-mode seamless connection transfer system of high-speed rail station

Abstract

The invention provides a multi-mode seamless connection transfer system for a high-speed rail station, and belongs to the technical field of comprehensive transportation junctions.Based on a one-to-many mode, firstly, data such as passenger flow volume and vehicle positions of all channels of the high-speed rail station are collected, and data collection and preprocessing are completed through various sensors and monitoring systems; pre-calculating passenger transport network data and training a related model; acquiring information of a starting station, a terminal station and the like of a user, planning a transfer path by using an optimized A * algorithm based on real-time passenger flow and pre-calculation data, and screening an optimal scheme by comprehensively considering station attributes and constraint conditions; then, according to a path planning result, passenger flow guiding and shunting are carried out through an intelligent mobile passenger flow partition system and a guiding subsystem, and a facility service mode is adjusted; and finally, the system can detect and update data in real time, ensures that transfer suggestions are accurate, adapts to train timetables and other factor changes, and improves the transfer efficiency and experience.

Description

Technical Field

[0001] The present invention belongs to the technical field of integrated transportation hubs. Specifically, it relates to a multi-modal seamless transfer system for high-speed railway stations. Background Art

[0002] With the rapid development of urban economy, the frequency of personnel flow and material exchange between different cities has increased significantly, bringing unprecedented pressure to the transportation system. As a large-scale integrated transportation hub, the transfer passenger flow of high-speed railway stations has increased sharply, and the inconveniences faced by passengers during the transfer process are particularly prominent.

[0003] Passengers often have difficulty obtaining real-time information required for transfer quickly and accurately, such as train schedules, transfer routes, and estimated waiting times, resulting in increased uncertainty during the transfer process. At the same time, the transfer path design within high-speed railway stations is complex, the signs are unclear or not intuitive enough, making it easy for first-time visitors to get lost, increasing unnecessary walking time and anxiety. Especially during peak hours, there are often serious congestion phenomena in transfer channels and waiting areas, further reducing the transfer experience. In the face of emergencies (such as train delays or temporary adjustments), the existing information systems and service response mechanisms are lagging, unable to provide effective guidance and support for passengers in a timely manner. In addition, the coordination of multi-modal transfers is insufficient. For passengers who need to transfer between high-speed rail and other public transportation modes, the connection between various transportation modes is not tight enough, and the transfer process is cumbersome, increasing the overall travel time. Therefore, although high-speed railway stations play an important role in promoting inter-city exchanges, the inconveniences of their internal transfer systems still bring many troubles to passengers. It is urgent to improve this situation through optimized management and technological innovation to enhance transfer efficiency and service quality. Summary of the Invention

[0004] Aiming at the problems existing in the prior art, such as relying on static information display and simple path recommendations, and being unable to effectively cope with high-density passenger flows and dynamically changing demands, the present invention proposes a multi-modal seamless transfer system for high-speed railway stations. By introducing intelligent algorithms and dynamic guidance systems, it realizes the efficient guidance and diversion of the crowd after getting off the high-speed railway, optimizes the transfer experience of passengers after getting off the high-speed railway, and improves transfer efficiency and passenger experience.

[0005] The present invention is realized through the following technical solutions:

[0006] A multi-modal seamless transfer method for high-speed railway stations: The method specifically includes the following steps:

[0007] Step 1: Collect data required for the pre-trained model;

[0008] Step 2: Train the pre-trained model according to the data in Step 1 and process the passenger transport network data;

[0009] Step 3: Obtain real-time traffic condition information;

[0010] Step 4: Combine the personalized travel needs of passengers to perform route planning;

[0011] Step 5: According to the route planning in Step 4, guide and divert passengers through the intelligent mobile crowd partition system to ensure that passengers can pass smoothly according to the optimal transfer route recommended by the system.

[0012] Further, in Step 1,

[0013] Collect historical data on vehicle and pedestrian flows and passenger flows at different transportation tool stations in each channel of the high-speed railway station through a variety of sensors, combine the static information of each station, and organize it at fixed time intervals to form structured time series data.

[0014] 3. The method according to claim 2, wherein:

[0015] The pre-trained model is a correlation matrix model and a transfer passenger flow prediction model.

[0016] Further, in Step 2,

[0017] Based on the historical data of passenger flows at different transportation tool stations collected in Step 1, capture the spatio-temporal correlation characteristics of passenger flows between stations, construct a time series matrix reflecting the connection strength between stations, determine the correlation law of passenger flow between stations, and complete the training of the correlation matrix model;

[0018] Use deep learning algorithms to learn and analyze historical transfer passenger flow data, train a model that can predict the number of transfers in a future time period, and combine the influence of various factors on transfer passenger flow to complete the training of the transfer passenger flow prediction model:

[0019] Combine the characteristics of railway operations, evaluate and quantify the capacity attributes of each station, divide all stations that may be transfer points into multiple levels, assign corresponding weights to each station, calculate the transfer costs between stations, construct a passenger transport network data structure suitable for A* algorithm search, and realize the calculation of passenger transport network data.

[0020] Further, in Step 3,

[0021] Real-time monitor the changes in passenger flow in each channel of the high-speed railway station through a variety of sensors (such as cameras, infrared detectors, RFID readers, etc.), use the GPS positioning system to track the positions and operating status information of various transportation tools in real time, and transmit this real-time data to the central control system.

[0022] Further, in Step 4,

[0023] Collect the starting point, destination, planned travel date of the trip entered by the passenger, and the personal transfer preference information, and standardize this user information;

[0024] According to the A* algorithm, use the passenger's starting station as the starting point, combine the passenger transport network data and real-time traffic information, and evaluate and prioritize each possible path node according to the weights of each station, transfer costs, path distances, and real-time passenger flow factors. Prioritize exploring path branches with higher potential value to search for a preliminary set of solutions for all feasible transfer paths to the destination station;

[0025] For each initially generated transfer path, the A* algorithm combines multiple predefined constraint conditions for optimization and screening, calculates the total duration of the path, evaluates the conflict situation with other paths at transfer nodes, and counts the number of turns in the path. The transfer path finally recommended to the user is both time-saving and convenient, and avoids the collision of the passenger flow of different transfer paths.

[0026] Further, in step 5,

[0027] The intelligent mobile passenger flow partition system automatically adjusts the position of the partition device in the passage by real-time monitoring and analyzing the number of passengers arriving by different transportation modes;

[0028] The intelligent mobile passenger flow partition system includes a passenger flow arrival monitoring subsystem, a passenger flow analysis subsystem, an intelligent mobile passenger flow diversion facility control subsystem, and a passenger flow guidance subsystem.

[0029] Further, the intelligent mobile passenger flow diversion facility control subsystem determines whether to adjust the position of the partition device through the path planning in step 4 by real-time collecting and analyzing the passenger flow distribution of each passage by the passenger flow arrival monitoring subsystem and the passenger flow analysis subsystem;

[0030] When it is found that the passenger flow of a certain passage is too large or the passenger flow pressure of a certain transfer path is too small, the passenger flow guidance subsystem immediately adjusts the opening direction and number of the turnstiles according to the latest state of the partition device and the passenger flow distribution.

[0031] An electronic device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the above method are implemented.

[0032] A computer-readable storage medium is used to store computer instructions, and when the computer instructions are executed by a processor, the steps of the above method are implemented.

[0033] Advantages of the present invention

[0034] The present invention adopts the shortest path A* algorithm, that is, to find the best transfer plan between a starting point and multiple possible destinations, and screen out the most suitable options for users according to predetermined constraints (such as path duration, conflicts with other paths, number of turns, etc.).

[0035] Based on the one-to-many mode, the present invention can dynamically adjust the transfer path and guidance plan according to real-time passenger flow data and passenger needs, so as to achieve efficient crowd diversion and transfer. In addition, the passenger guidance and diversion system can monitor the passenger flow distribution of each channel in real time, and dynamically adjust the guidance strategy accordingly to ensure that passengers transfer according to the optimal path.

[0036] The present invention can support seamless transfer from high-speed railway stations to various other public transportation means (such as subways, buses, intercity trains, etc.). Through the integrated information platform, passengers can obtain one-stop transfer suggestions, which greatly facilitates the needs of cross-city and even cross-country travel. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 is the flowchart of the method of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0038] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0039] A method for seamless multi-mode transfer at high-speed railway stations, the method specifically includes the following steps:

[0040] Step 1: Collect data required for the pre-training model;

[0041] Collect historical data of vehicle and pedestrian flow and passenger flow at different transportation tool stations through various sensors (such as 360° panoramic infrared cameras, infrared detectors, RFID card readers, etc.) in each channel of the high-speed railway station, and combine the static information of each station (such as station layout, channel connection conditions, etc.), and organize them at fixed time intervals to form structured time series data;

[0042] The pre-training models are the correlation matrix model and the transfer passenger flow prediction model;

[0043] The correlation matrix model captures the characteristics of passenger flow at different transportation tool stations, constructs a time series matrix reflecting the connection strength between stations; obtains how many passengers will get off and transfer in the next time period within a certain time period, and thus provides a basis for subsequent passenger flow prediction.

[0044] The transfer passenger flow prediction model uses deep learning algorithms to predict the number of transfer passengers within a certain future time period.

[0045] Step 2: Train the pre-trained model based on the data in Step 1, and process the passenger transport network data to make it more in line with the actual transfer requirements and algorithm calculation requirements, so as to quickly perform path planning and passenger flow analysis in the follow-up;

[0046] Based on the historical data of passenger flow at different transportation hubs collected in Step 1, capture the spatio-temporal correlation characteristics of passenger flow between stations, construct a time series matrix reflecting the connection strength between stations, determine the correlation law of passenger flow between stations, complete the training of the correlation matrix model, so that it can estimate the change trend of passenger flow at other relevant stations according to the current passenger flow situation at the station;

[0047] Use deep learning algorithms to learn and analyze the historical transfer passenger flow data, train a model that can predict the number of transfer passengers within a certain future time period, and complete the training of the transfer passenger flow prediction model by combining the influence of various factors (such as different time periods, dates, seasons, special events, etc.) on the transfer passenger flow;

[0048] Combined with the characteristics of railway operations, evaluate and quantify the capacity attributes of each station (such as whether there is enough waiting space, whether the transfer paths cross, etc.), divide all stations that may serve as transfer points into multiple levels, assign corresponding weights to each station, calculate the transfer costs between stations (including factors such as time cost, distance cost, transfer convenience, etc.), construct a passenger transport network data structure suitable for A* algorithm search, and realize the calculation of passenger transport network data.

[0049] Step 3: Obtain real-time traffic condition information, including real-time changes in passenger flow, accurate positions and operating conditions of transportation vehicles, etc.

[0050] Use a variety of sensors (such as cameras, infrared detectors, RFID readers, etc.) to monitor the real-time changes in passenger flow in each channel of the high-speed railway station, including information such as the degree of crowding, flow direction and speed of people, and transmit this real-time data to the central control system.

[0051] Use the GPS positioning system to track the positions and operating status information of various transportation vehicles (such as subways, buses, intercity trains, etc.) in real time, and timely grasp the dynamic distribution of traffic resources. Feed back the dynamic distribution information of these traffic resources to the central control system in a timely manner.

[0052] Step 4: Combine the personalized travel needs of passengers to perform path planning;

[0053] Collect the starting and destination stations of the trip, the planned travel date entered by the passenger, and the passenger's transfer preferences, such as whether they prefer direct routes, the limit on the number of transfers, and the preference for different transportation modes, and standardize this user information;

[0054] According to the A* algorithm, use the passenger's starting station as the starting point, combine passenger transport network data and real-time traffic information, and evaluate and prioritize each possible path node based on factors such as the weight of each station, transfer cost, path distance, and real-time passenger flow. Prioritize exploring path branches with higher potential value to search for a preliminary set of all feasible transfer path solutions to the destination station;

[0055] For each initially generated transfer path, the A* algorithm combines multiple predefined constraint conditions for optimization and screening, calculates the total duration of the path (including waiting time, travel time, transfer walking time, etc.), evaluates the conflict situation with other paths at transfer nodes (such as avoiding congestion caused by passengers on different lines converging simultaneously in the same narrow transfer passage), and counts the number of turns in the path (too many turns may increase the walking distance and the risk of getting lost for passengers). Finally, the transfer paths recommended to the user are both time-saving and convenient, and avoid the collision of the passenger flow of different transfer paths.

[0056] Step 5, according to the path planning in Step 4, use the intelligent mobile passenger flow partition system to guide and divert passengers to ensure that passengers can pass smoothly according to the optimal transfer path recommended by the system. At the same time, the system combines the changes in traffic conditions in real time (such as train schedule adjustments, emergencies, etc.) and automatically adjusts relevant data and guiding strategies.

[0057] The intelligent mobile passenger flow partition system automatically adjusts the position of the partition devices in the passage by real-time monitoring and analyzing the number of passengers arriving by different transportation modes, including a passenger flow arrival monitoring subsystem, a passenger flow analysis subsystem, an intelligent mobile passenger flow diversion facility control subsystem, and a passenger flow guidance subsystem.

[0058] The intelligent mobile passenger flow diversion facility control subsystem determines whether to adjust the position of the partition device based on the passenger flow distribution in each passage collected and analyzed in real time by the passenger flow arrival monitoring subsystem and the passenger flow analysis subsystem, and through the path planning in Step 4;

[0059] When it is found that the passenger flow in a certain passage is too large or the passenger flow pressure on a certain transfer path is too small, the passenger flow guidance subsystem immediately adjusts the opening direction and number of the turnstiles according to the latest state of the partition device and the passenger flow distribution.

[0060] The present invention also has a real-time monitoring and feedback mechanism, which can continuously monitor changes in the train schedule (such as train delays, increases or decreases in train numbers, adjustments to stop stations, etc.) and other factors that may affect traffic operations (such as the suspension of some traffic lines due to bad weather, temporary traffic control caused by emergencies, etc.). Once these changes are detected, the system immediately starts the data update and route re-planning procedures, synchronously updates the passenger transport network data, the transfer passenger flow prediction model, and the relevant parameters of the A* algorithm, re-plans the transfer plan, and pushes the latest guiding information and transfer suggestions to passengers.

[0061] An electronic device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the above method are implemented.

[0062] A computer-readable storage medium is used to store computer instructions, and when the computer instructions are executed by a processor, the steps of the above method are implemented.

[0063] The memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory for the method described in the present invention is intended to include, but not be limited to, these and any other suitable types of memories.

[0064] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired means such as coaxial cables, optical fibers, digital subscriber line (DSL), or wireless means such as infrared, wireless, microwave, etc. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that includes one or more integrated available media. The available medium may be a magnetic medium such as a floppy disk, hard disk, magnetic tape, an optical medium such as a high-density digital video disc (DVD), or a semiconductor medium such as a solid state disc (SSD), etc.

[0065] In the implementation process, the steps of the above method can be completed by the integrated logic circuit of the hardware in the processor or the instructions in the form of software. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by the hardware processor, or executed and completed by the combination of the hardware and software modules in the processor. The software module may be located in a mature storage medium in the art such as random access memory, flash memory, read-only memory, programmable read-only memory, or electrically erasable programmable memory, register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method. To avoid repetition, it will not be described in detail here.

[0066] It should be noted that the processor in the embodiments of the present application may be an integrated circuit chip with signal processing capabilities. In the implementation process, the steps of the above method embodiments can be completed by the integrated logic circuit in the hardware of the processor or instructions in the form of software. The above-mentioned processor may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor, or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method.

[0067] The above has introduced in detail a multi-mode seamless transfer system for high-speed railway stations proposed by the present invention, and elaborated on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A multi-mode seamless transfer method at a high-speed railway station, characterized in that: The method specifically comprises the following steps: Step 1: Collect the data required for the pre-training model; Step 2: Train the pre-trained model based on the data in step 1 and process the passenger transport network data; Step 3: Get real-time traffic information; Step 4: Plan the route based on the passengers’ personalized travel needs; Step 5: According to the path planning in step 4, passengers are guided and diverted through the intelligent mobile crowd partition system to ensure that passengers can pass smoothly along the optimal transfer path recommended by the system.

2. The method according to claim 1, characterized in that: In step 1, Through various sensors in various channels of the high-speed railway station, historical data on vehicle and pedestrian flows, and passenger flows at different transportation stations are collected. Combined with the static information of each station, the data is sorted at fixed time intervals to form structured time series data.

3. The method according to claim 2, characterized in that: The pre-trained models are a correlation matrix model and a transfer passenger flow prediction model.

4. The method according to claim 3, characterized in that: In step 2, Based on the historical data of passenger flow at different transportation stations collected in step 1, the temporal and spatial correlation characteristics of passenger flow between stations are captured, a time series matrix reflecting the connection strength between stations is constructed, the correlation law of passenger flow between stations is determined, and the training of the correlation matrix model is completed; Using deep learning algorithms, we study and analyze historical transfer passenger flow data, train a model that can predict the number of transfer passengers in a certain period of time in the future, and complete the training of the transfer passenger flow prediction model by combining the impact of multiple factors on the transfer passenger flow: In combination with the characteristics of railway business, the capacity attributes of each station are evaluated and quantified, all stations that may serve as transfer points are divided into multiple levels, and a corresponding weight is assigned to each station. The transfer cost between stations is calculated, and a passenger transport network data structure suitable for A* algorithm search is constructed to realize the calculation of passenger transport network data.

5. The method according to claim 4, characterized in that: In step 3, Through a variety of sensors (such as cameras, infrared detectors, RFID readers, etc.), the passenger flow changes in each channel of the high-speed railway station are monitored in real time. The GPS positioning system is used to track the location and operating status information of various types of transportation in real time, and these real-time data are transmitted to the central control system.

6. The method according to claim 5, characterized in that: In step 4, Collect the starting and destination stations, planned travel dates and personal transfer preference information entered by passengers, and standardize this user information; According to the A* algorithm, the user's departure station is taken as the starting point, and the passenger transportation network data and real-time traffic information are combined. According to the weight of each station, transfer cost, path distance and real-time passenger flow factors, each possible path node is evaluated and prioritized, and the path branches with higher potential value are explored first, and a preliminary set of all feasible transfer paths to the target station is searched out; For each initially generated transfer path, the A* algorithm combines multiple predetermined constraints for optimization and screening, calculates the total duration of the path, evaluates conflicts with other paths at transfer nodes, counts the number of turns in the path, and ultimately recommends a transfer path to the user that is both time-saving and convenient, and avoids collisions between people on different transfer paths.

7. The method according to claim 6, characterized in that: In step 5, The intelligent mobile crowd partition system automatically adjusts the position of the partition device in the channel by real-time monitoring and analyzing the number of passengers arriving by different modes of transportation; The intelligent mobile passenger flow separation system includes a passenger flow arrival monitoring subsystem, a passenger flow analysis subsystem, an intelligent mobile passenger flow diversion facility control subsystem and a passenger flow guiding subsystem.

8. The method according to claim 7, characterized in that: The intelligent mobile passenger flow diversion facility control subsystem collects and analyzes the passenger flow distribution of each channel in real time according to the passenger flow arrival monitoring subsystem and the passenger flow analysis subsystem, and determines whether the position of the partition device needs to be adjusted through the path planning of step 4; When it is found that the passenger flow of a certain channel is too large or the passenger flow pressure of a certain transfer path is too small, the passenger flow guidance subsystem will instantly adjust the opening direction and number of gates according to the latest state of the partition device and passenger flow distribution.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium for storing computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the method described in any one of claims 1 to 8 are implemented.

Images