Railway station passenger flow organization strategy automatic generation method, system, equipment and medium

Abstract

The present application discloses a method for automatically generating passenger flow organization strategies for railway stations, comprising: steps of generating an existing station portrait library, generating a similarity model, constructing a station knowledge graph, and automatically generating a new station passenger flow organization strategy; establishing an existing station portrait library with multiple dimensions and indicators; calculating the similarity between different products and generating a similarity model; conducting a structured analysis of the passenger flow organization strategies of existing stations, establishing a station passenger flow organization strategy knowledge base, and constructing a passenger flow organization knowledge graph based on the station passenger flow data; conducting product portraits for newly opened stations, calculating the similarity between the newly opened stations and existing stations based on the similarity model, obtaining the existing station with the highest similarity to the corresponding new station, and automatically generating a passenger flow organization strategy for the new station based on the passenger flow forecast data and the passenger flow organization knowledge graph. The present application also discloses a system for automatically generating passenger flow organization strategies for railway stations.

Description

Technical Field

[0001] The present application relates to the technical field of data processing for passenger flow organization, and in particular to a method and system for automatically generating passenger flow organization strategies for railway stations. Background Art

[0002] Currently, scientifically managing railway passenger flow is a key task for railway stations, directly impacting the passenger experience. Stations often optimize passenger flow management methods based on existing experience. However, when a new station opens, stations lack historical data to reference and passenger flow data to support them, making it difficult to formulate a sound ticketing strategy.

[0003] However, existing methods for developing passenger flow management plans for new railway stations often rely on manual coding and empirical experience, followed by continuous adjustments and optimization based on actual on-site conditions. This often results in a mismatch between passenger flow management methods and station realities during the initial opening of a new station, reducing operational efficiency across various station departments and the passenger experience. Furthermore, the successful passenger flow management experiences of many stations are unique and lack generalizability, making them inappropriate for new stations. Therefore, a hybrid model of similarity and product profiling is needed to scientifically and automatically develop passenger flow management plans for new stations.

[0004] Therefore, in order to improve the scientificity and effectiveness of passenger flow organization at new stations, it is urgent to propose an intelligent auxiliary formulation method for passenger flow organization plans when a new station is opened, that is, a new type of automatic generation method for passenger flow organization strategies for railway stations, which is used to combine passenger flow forecast data and passenger flow organization knowledge graph to automatically generate passenger flow organization plans for new stations, thereby solving the problem in the existing technology that passenger flow organization strategies cannot be accurately matched with the actual situation of the station. Summary of the Invention

[0005] An embodiment of the present application provides a novel method for automatically generating passenger flow organization strategies for railway stations, which is used to automatically generate passenger flow organization plans for new stations by combining passenger flow forecast data and a passenger flow organization knowledge graph, thereby solving the problem in the prior art that passenger flow organization strategies cannot match the actual conditions of the station.

[0006] In a first aspect, an embodiment of the present application provides a method for automatically generating a passenger flow organization strategy for a railway station, comprising:

[0007] Steps for generating an existing station portrait library: Based on the inherent attributes of existing stations, using product portrait technology, establish an existing station portrait library with multiple dimensions and indicators;

[0008] Similarity model generation step: Based on the existing station product portrait library, using a graph neural network, station indicators are integrated and dimensionally reduced to obtain station indicator vectors, and then similarities between different products are calculated to generate a similarity model;

[0009] Steps for constructing a station knowledge graph: Establish a station passenger flow organization strategy knowledge base by conducting a structured analysis of existing station passenger flow organization strategies, and then construct a passenger flow organization knowledge graph based on station passenger flow data;

[0010] Steps for automatically generating passenger flow organization strategies for new stations: create a product profile for the newly opened station, calculate the similarity between the newly opened station and the existing station based on the similarity model, obtain the existing station with the highest similarity to the corresponding new station, and automatically generate the passenger flow organization strategy for the new station by combining the passenger flow prediction data and the passenger flow organization knowledge graph.

[0011] In some embodiments of the present invention, the step of generating the existing station portrait library includes:

[0012] Classification steps: Based on the station's inherent attribute indicators, multi-dimensional classification is carried out. The inherent attributes include dynamic attributes and static attributes.

[0013] Quantification step: Quantify various inherent attribute indicators.

[0014] In some embodiments of the present invention, the similarity model generation step includes:

[0015] Steps for constructing a product topology map: Based on the existing station portrait, with the existing station product in the portrait as the center and the related products of the existing station product in the portrait as adjacent nodes, the nodes are connected according to the product relationship to construct a product topology map;

[0016] Indicator alignment steps: Based on the product topology map, obtain existing station products and related product indicators, and align the product indicators;

[0017] Index refinement step: Input the existing station product index vector and the index vectors of related products after alignment into the pre-built graph neural network model to obtain refined station product indicators;

[0018] Steps for constructing station index vectors: Use the station deep autoencoder neural network to optimize and reduce the dimensionality of refined product indicators to obtain station index vectors;

[0019] The steps for calculating the similarity between products are as follows: Based on the station index vector, the similarity between the target station and other stations is calculated, and the similarity is sorted to establish a station similarity model.

[0020] In some embodiments of the present invention, the step of constructing the station knowledge graph includes:

[0021] Knowledge base construction steps: Convert the existing unstructured data of station passenger flow organization strategies into structured data, clean and classify the structured data, and form a station passenger flow organization strategy knowledge base;

[0022] Passenger flow and threshold calculation steps: obtain real-time monitoring data of passenger flow within the station and forecast data of future passenger flow within the station, analyze the triggering conditions of passenger flow organization measures in the passenger flow organization strategy knowledge base, and obtain the threshold value of triggering passenger flow within the station through simulation calculation;

[0023] Knowledge graph construction steps: Set the station passenger flow organization means, station passenger flow real-time monitoring data, and future station passenger flow forecast data as point sets, and then set the threshold corresponding to the trigger condition as an edge set. Through the edge set, connections are established between the point sets to generate a passenger flow organization knowledge graph.

[0024] In some embodiments of the present invention, the above-mentioned step of automatically generating a new station passenger flow organization strategy includes:

[0025] New station product portrait: Based on the static and dynamic attributes of the newly opened station, pre-build the portrait and establish the product portrait;

[0026] Calculate the similarity between new and existing stations: Based on the similarity model, calculate the similarity between the new station and the existing stations, sort them, and obtain the corresponding existing station with the highest similarity to the new station;

[0027] Steps for generating passenger flow organization strategies for new stations: Combine similarity calculation results and passenger flow organization strategy knowledge graph to automatically generate passenger flow organization strategies for new stations.

[0028] In some embodiments of the present invention, the indicator alignment step includes:

[0029] Let P' be the indicator dimension of existing station products and P be the indicator dimension of related products, then:

[0030]

[0031] in, is the index vector after the relevant product is aligned with the existing station product, is the original indicator vector of related products, R P is a set of P-dimensional vectors, where P is a positive integer.

[0032] In some embodiments of the present invention, the indicator refinement step includes:

[0033] The refinement of station product indicators is as follows:

[0034]

[0035] Among them, S is the refined product index, W represents the weight, b is the bias, and N is the set of the relevant product and the existing station product index vectors.

[0036] In a second aspect, an embodiment of the present application provides a system for automatically generating a passenger flow organization strategy for a railway station, which adopts the above-mentioned method for automatically generating a passenger flow organization strategy for a railway station, including:

[0037] Existing Station Portrait Library Generation Module: Based on the inherent attributes of existing stations, using product portrait technology, a portrait library of existing stations with multiple dimensions and indicators is established;

[0038] Similarity model generation module: Based on the existing station product portrait library, the graph neural network is used to integrate and reduce the station indicators. After obtaining the station indicator vector, the similarity between different products is calculated to generate a similarity model;

[0039] Station knowledge graph construction module: This module conducts a structured analysis of existing station passenger flow organization strategies, establishes a station passenger flow organization strategy knowledge base, and constructs a passenger flow organization knowledge graph based on station passenger flow data;

[0040] Automatic generation module of passenger flow organization strategy for new stations: Create product profiles for newly opened stations, calculate the similarity between newly opened stations and existing stations based on the similarity model, obtain the existing station with the highest similarity to the corresponding new station, and automatically generate passenger flow organization strategies for new stations by combining passenger flow prediction data and passenger flow organization knowledge graph.

[0041] In a third aspect, an embodiment of the present application provides a computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the computer program, the method for automatically generating a passenger flow organization strategy for a railway station as described above is implemented.

[0042] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for automatically generating a passenger flow organization strategy for a railway station as described above.

[0043] Compared with the related existing technologies, it has the following outstanding beneficial effects:

[0044] 1. The method of the present invention is innovative and explainable in the process of calculating station similarity based on station product portraits. It is not only scientific but also more intelligent, convenient and fast compared to existing methods of finding connections between stations based on experience.

[0045] 2. The method of the present invention forms a knowledge graph of station passenger flow organization in terms of structuring station passenger flow organization, which can evaluate and apply passenger flow organization plans more flexibly and efficiently, thereby improving the promotion and usability of station passenger flow organization plans;

[0046] 3. The method of the present invention combines the similarity of station product portraits with the passenger flow organization knowledge graph to quickly and accurately calculate a passenger flow organization plan that is more suitable for the new station. It is more scientific and convenient than manual methods.

[0047] 4. The station similarity calculation method in this invention can be extended to other transportation fields, such as aviation and highway. When building product portraits, the station data in railways can be replaced with portrait data of aviation and highway network points, etc., and the similarity calculation requirements in other transportation fields are also applicable. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0049] Figure 1 This is a flow chart of the method for automatically generating a passenger flow organization strategy for a railway station according to the present invention;

[0050] Figure 2 Construct a flow chart for the product topology diagram of a specific embodiment of the present invention;

[0051] Figure 3 This is a flow chart of station similarity calculation in a specific embodiment of the present invention;

[0052] Figure 4 Schematic diagram of the automatic generation system of passenger flow organization strategy for railway stations according to the present invention;

[0053] Figure 5 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solutions and advantages of this application more clearly understood, the present application is described and illustrated below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely used to explain this application and are not intended to limit this application. Based on the embodiments provided in this application, all other embodiments obtained by those of ordinary skill in the art without making any creative efforts are within the scope of protection of this application.

[0055] Obviously, the drawings described below are merely examples or embodiments of the present application. Those skilled in the art can, without inventive effort, apply the present application to other similar scenarios based on these drawings. Furthermore, it is also understood that, although the effort involved in such a development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, changes in design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as an insufficiency of the content disclosed in this application.

[0056] The details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent.

[0057] References to "embodiments" in this application mean that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it refer to independent or alternative embodiments that are mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described in this application may be combined with other embodiments unless there is a conflict.

[0058] Unless otherwise defined, the technical or scientific terms used in this application should have the ordinary meaning understood by a person of ordinary skill in the technical field to which this application belongs. The words "one", "a", "the" and the like used in this application do not indicate a limit on quantity and may indicate the singular or plural. The terms "include", "comprise", "have" and any variations thereof used in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units that are inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The word "multiple" used in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific order for the objects.

[0059] This invention aims to establish a profile library for all existing stations along the railway using product profiling technology. Multi-dimensional, multi-indicator modeling is then performed within the profile library to create a comprehensive, three-dimensional product profile library. By structuring station passenger flow organization plans, a knowledge base for station passenger flow organization plans is established, and a knowledge graph is formed in conjunction with station passenger flow data. On this basis, product profiling is performed for newly opened stations, and the correlation between new and existing stations is calculated based on the similarity of the profiles. Simultaneously, passenger flow organization plans for new stations are intelligently generated by combining passenger flow forecast data with the passenger flow organization knowledge graph.

[0060] like Figure 1 As shown, a specific embodiment of the present invention provides a method for automatically generating a passenger flow organization strategy for a railway station, comprising:

[0061] Existing station portrait library generation step S10: Based on the inherent attributes of the existing stations, using product portrait technology, an existing station portrait library with multiple dimensions and indicators is established;

[0062] Similarity model generation step S20: Based on the existing station product portrait library, using a graph neural network, station indicators are integrated and dimensionally reduced to obtain station indicator vectors, and similarities between different products are calculated to generate a similarity model;

[0063] Station knowledge graph construction step S30: by conducting a structured analysis of existing station passenger flow organization strategies, a station passenger flow organization strategy knowledge base is established, and a passenger flow organization knowledge graph is constructed in combination with station passenger flow data;

[0064] Automatic generation step S40 of passenger flow organization strategy for new stations: Make a product profile for the newly opened station, calculate the similarity between the newly opened station and the existing station based on the similarity model, obtain the existing station with the highest similarity to the corresponding new station, and automatically generate the passenger flow organization strategy for the new station by combining the passenger flow prediction data and the passenger flow organization knowledge graph.

[0065] In some embodiments of the present invention, the above-mentioned step S10 of generating the existing station portrait library includes:

[0066] Classification steps: Based on the station's inherent attribute indicators, multi-dimensional classification is carried out. The inherent attributes include dynamic attributes and static attributes.

[0067] Quantification step: Quantify various inherent attribute indicators.

[0068] In some embodiments of the present invention, the similarity model generating step S20 includes:

[0069] Steps for constructing a product topology map: Based on the existing station portrait, with the existing station product in the portrait as the center and the related products of the existing station product in the portrait as adjacent nodes, the nodes are connected according to the product relationship to construct a product topology map;

[0070] Indicator alignment steps: Based on the product topology map, obtain existing station products and related product indicators, and align the product indicators;

[0071] Index refinement step: Input the existing station product index vector and the index vectors of related products after alignment into the pre-built graph neural network model to obtain refined station product indicators;

[0072] Steps for constructing station index vectors: Use the station deep autoencoder neural network to optimize and reduce the dimensionality of refined product indicators to obtain station index vectors;

[0073] The steps for calculating the similarity between products are as follows: Based on the station index vector, the similarity between the target station and other stations is calculated, and the similarity is sorted to establish a station similarity model.

[0074] In some embodiments of the present invention, the station knowledge graph construction step S30 includes:

[0075] Knowledge base construction steps: Convert the existing unstructured data of station passenger flow organization strategies into structured data, clean and classify the structured data, and form a station passenger flow organization strategy knowledge base;

[0076] Passenger flow and threshold calculation steps: obtain real-time monitoring data of passenger flow within the station and forecast data of future passenger flow within the station, analyze the triggering conditions of passenger flow organization measures in the passenger flow organization strategy knowledge base, and obtain the threshold value of triggering passenger flow within the station through simulation calculation;

[0077] Knowledge graph construction steps: Set the station passenger flow organization means, station passenger flow real-time monitoring data, and future station passenger flow forecast data as point sets, and then set the threshold corresponding to the trigger condition as an edge set. Through the edge set, connections are established between the point sets to generate a passenger flow organization knowledge graph.

[0078] In some embodiments of the present invention, the above-mentioned new station passenger flow organization strategy automatic generation step S40 includes:

[0079] New station product portrait: Based on the static and dynamic attributes of the newly opened station, pre-build the portrait and establish the product portrait;

[0080] Calculate the similarity between new and existing stations: Based on the similarity model, calculate the similarity between the new station and the existing stations, sort them, and obtain the corresponding existing station with the highest similarity to the new station;

[0081] Steps for generating passenger flow organization strategies for new stations: Combine similarity calculation results and passenger flow organization strategy knowledge graph to automatically generate passenger flow organization strategies for new stations.

[0082] In some embodiments of the present invention, the indicator alignment step includes:

[0083] Let P' be the indicator dimension of existing station products and P be the indicator dimension of related products, then:

[0084]

[0085] in, is the index vector after the relevant product is aligned with the existing station product, is the original indicator vector of related products, R P is a set of P-dimensional vectors, where P is a positive integer.

[0086] In some embodiments of the present invention, the indicator refinement step includes:

[0087] The refinement of station product indicators is as follows:

[0088]

[0089] Among them, S is the refined product index, W represents the weight, b is the bias, and N is the set of the relevant product and the existing station product index vectors.

[0090] The following describes in detail the specific embodiments of the present invention with reference to the accompanying drawings:

[0091] 1. Establishment of station product portrait

[0092] 1) If Figure 2 As shown in the figure, the inherent attributes of stations can be classified from different perspectives, including dynamic attributes and static attributes. Static attributes refer to long-term stable and basically unchanged attribute information, while dynamic attributes refer to attribute information that will undergo significant changes over time and is not fixed.

[0093] Static attributes include: basic characteristics (station size, building area, station level, geographical location, etc.), city level, convenience of surrounding facilities, competitive traffic conditions, city attributes (whether it is a tourist city, whether it is a provincial capital, city GDP, permanent population, urban population distribution, etc.), whether it is a transfer station, the number of schools in the area, the quality of hospitals in the area, etc.

[0094] Dynamic attributes include: operational indicators (number of trains running, number of people getting on at stations, number of people getting off at stations, number of people transferring at stations, etc.), number of floating population in the city, large-scale events (conferences, concerts, competitions, etc.), weather, etc.

[0095] 2) Quantify various indicators.

[0096] 2. Station similarity calculation

[0097] like Figure 3 As shown in the figure, based on the station product portrait library, the graph neural network is used to integrate station product indicators from multiple angles to obtain refined station product indicators. At the same time, considering the relationship between computational complexity and accuracy, the refined indicators are reduced in dimension to obtain station indicator vectors, and the similarity between different products is calculated based on them. The specific steps are as follows:

[0098] 1) Product topology map construction: Based on the station product portrait, with the station product as the center and related products as adjacent nodes, the nodes are connected according to the product relationship to build a topology map.

[0099] 2) Indicator alignment: Based on the topological map, obtain the station product indicators and related product indicators. Since the indicator dimensions of different products are not necessarily the same, in order to perform indicator refinement operations, it is necessary to align the product indicators first. Let P' be the station product indicator dimension and P be the related product indicator dimension, then:

[0100]

[0101] in, is the index vector after the relevant product is aligned with the existing station product, is the original indicator vector of related products, R P is a set of P-dimensional vectors, where P is a positive integer.

[0102] 3) Indicator refinement: Build a graph neural network model, take the station product indicator vector and the subsequent indicator vector of related products as input items, input them into the graph neural network model, and output the refined station product indicator that integrates the related product indicators.

[0103] Refinement of station product indicators:

[0104]

[0105] Among them, S is the refined product index, W represents the weight, b is the bias, and N is the set of the relevant product and the existing station product index vectors.

[0106] 4) Construction of station indicator vector: Based on the refined product indicators, the station deep autoencoder neural network is used to optimize and reduce the indicators. The refined product indicator S is used as the input item and input into the intermediate layer neural network with n dimensions. S' is used as the output item of the neural network for training. When S is infinitely close to S', the training stops. At this time, an intermediate layer with n dimensions can be obtained. The intermediate layer result is output to obtain the station indicator vector.

[0107] 5) Calculation of product similarity: Calculate the similarity between stations based on the station indicator vectors. Let the indicator vector of target station A be a, and the set of indicator vectors for other stations be T. Calculate the similarity between a and any indicator vector in set T. In the similarity calculation, the Pearson correlation coefficient method is used to obtain the similarity between each station, sort them, and establish a station similarity model. The station similarity calculation process is as follows:

[0108] 3. Construction of knowledge graph for station passenger flow organization

[0109] The unstructured passenger flow organization plan is structured and analyzed to form a passenger flow organization knowledge base. Based on the passenger flow situation of each station at different times, the relationship between passenger flow organization methods and passenger flow is found to establish a passenger flow organization knowledge map. The specific steps are as follows:

[0110] 1) Knowledge Base Construction: By combining machine learning and human experience, unstructured data such as station passenger flow organization plans is converted into structured data that can be directly read by computers. The data is cleaned and classified to form a station passenger flow organization knowledge base.

[0111] 2) Passenger flow and threshold calculation: Utilize the real-time station entry and ticket inspection information to monitor the passenger flow within the station in real time, predict the future passenger flow based on the ticket sales information, analyze the triggering conditions of the passenger flow organization means in the passenger flow organization knowledge base, and perform data simulation calculations on various triggering conditions to obtain the corresponding passenger flow within the station when the triggering conditions occur, and set it as the threshold.

[0112] 3) Knowledge graph construction: The means of organizing passenger flow at stations, real-time monitoring data of passenger flow at stations, and future passenger flow forecast data at stations are set as point sets, and the thresholds corresponding to the trigger conditions are set as edge sets. The point sets are connected through the edge sets to form a passenger flow organization knowledge graph.

[0113] 4. Intelligent generation of passenger flow organization plans for new stations

[0114] When a new station is opened, the similarity between the new station and the existing stations is calculated based on the product profile information of the new station. The passenger flow organization knowledge map is read based on the similarity, and the passenger flow is predicted based on the opening of the new station to intelligently generate a passenger flow organization plan for the new station. The specific steps are as follows:

[0115] 1) Product portrait of a new station: Before a new station opens, the static attributes of the station are relatively fixed, so a portrait can be pre-built in advance. Dynamic attributes fluctuate greatly, so they need to be predicted based on the station situation and continuously optimized over time to establish a product portrait.

[0116] 2) Calculation of similarity between new and existing stations: Based on the similarity model generated in Section 2, the similarity between the new and existing stations is calculated, and the stations with the highest similarity to the new station are sorted to obtain the corresponding station.

[0117] 3) Form a passenger flow organization plan for the new station: Combine the similarity calculation results and the passenger flow organization plan knowledge graph to form a passenger flow organization plan for the new station.

[0118] Second, as Figure 4 As shown, the embodiment of the present application provides a railway station passenger flow organization strategy automatic generation system, which adopts the railway station passenger flow organization strategy automatic generation method as described above, including:

[0119] Existing station portrait library generation module 10: Based on the inherent attributes of existing stations, using product portrait technology, an existing station portrait library with multiple dimensions and indicators is established;

[0120] Similarity model generation module 20: Based on the existing station product portrait library, the graph neural network is used to fuse and reduce the station indicators. After obtaining the station indicator vector, the similarity between different products is calculated to generate a similarity model;

[0121] Station knowledge graph construction module 30: By conducting a structured analysis of existing station passenger flow organization strategies, a station passenger flow organization strategy knowledge base is established, and a passenger flow organization knowledge graph is constructed in combination with station passenger flow data;

[0122] Automatic generation module 40 of passenger flow organization strategy for new stations: Produce product profiling for newly opened stations, calculate the similarity between the newly opened stations and existing stations based on the similarity model, obtain the existing stations with the highest similarity to the corresponding new stations, and automatically generate passenger flow organization strategies for new stations by combining passenger flow prediction data and passenger flow organization knowledge graph.

[0123] In a third aspect, an embodiment of the present application provides a computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the computer program, the method for automatically generating a passenger flow organization strategy for a railway station as described above is implemented.

[0124] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for automatically generating a passenger flow organization strategy for a railway station as described above.

[0125] In addition, combined Figure 1 The method for automatically generating a passenger flow organization strategy for a railway station described in the embodiment of the present application can be implemented by a computer device. Figure 5 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present application.

[0126] The computer device may include a processor 81 and a memory 82 storing computer program instructions.

[0127] Specifically, the processor 81 may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0128] Among them, the memory 82 may include a large-capacity memory for data or instructions. By way of example and not limitation, the memory 82 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 82 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 82 may be inside or outside the data processing device. In a specific embodiment, the memory 82 is a non-volatile memory. In a specific embodiment, the memory 82 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM) or a flash memory (FLASH), or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), where the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0129] The memory 82 may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 81 .

[0130] The processor 81 reads and executes computer program instructions stored in the memory 82 to implement any one of the methods for automatically generating a railway station passenger flow organization strategy in the above embodiments.

[0131] In some embodiments, the computer device may further include a communication interface 83 and a bus 80. Figure 5 As shown, the processor 81, the memory 82, and the communication interface 83 are connected via a bus 80 and communicate with each other.

[0132] The communication interface 83 is used to enable communication between the various modules, devices, units, and / or devices in the embodiments of the present application. The communication port 83 can also enable data communication with other components such as external devices, image / data acquisition devices, databases, external storage, and image / data processing workstations.

[0133] The bus 80 includes hardware, software, or both, and couples components of the computer device to each other. The bus 80 includes, but is not limited to, at least one of the following: a data bus, an address bus, a control bus, an expansion bus, and a local bus. By way of example and not limitation, bus 80 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Bus 80 may include one or more buses, where appropriate. Although embodiments herein describe and illustrate a particular bus, this application contemplates any suitable bus or interconnect.

[0134] Compared with the existing technology, the method of the present invention is innovative and explainable in that the process of calculating the similarity of stations based on station product portraits is scientific and more intelligent, convenient and fast than the existing method of finding connections between stations based on experience. In terms of the structuring of station passenger flow organization, a station passenger flow organization knowledge graph is formed, which can evaluate and apply passenger flow organization plans more flexibly and efficiently, thereby improving the promotion and usability of station passenger flow organization plans. Combining the similarity of station product portraits with the passenger flow organization knowledge graph, a passenger flow organization plan that is more suitable for a new station can be calculated quickly and accurately, which is more scientific and convenient than manual methods. At the same time, the station similarity calculation in this method can be extended to other transportation fields, such as aviation, highways, etc. When constructing product portraits, the station data in the railway can be replaced with portrait data of aviation, highway network points, etc., which is also applicable to the similarity calculation needs in other transportation fields.

[0135] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0136] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A method for automatically generating a passenger flow organization strategy for a railway station, characterized in that: include: Steps for generating an existing station portrait library: Based on the inherent attributes of existing stations, using product portrait technology, establish an existing station portrait library with multiple dimensions and indicators; Similarity model generation step: Based on the existing station product portrait library, using a graph neural network, station indicators are integrated and dimensionally reduced to obtain station indicator vectors, and then similarities between different products are calculated to generate a similarity model; Steps for constructing a station knowledge graph: Establish a station passenger flow organization strategy knowledge base by conducting a structured analysis of existing station passenger flow organization strategies, and then construct a passenger flow organization knowledge graph based on station passenger flow data; Steps for automatically generating passenger flow organization strategies for new stations: create a product profile for the newly opened station, calculate the similarity between the newly opened station and the existing station based on the similarity model, obtain the existing station with the highest similarity to the corresponding new station, and automatically generate the passenger flow organization strategy for the new station by combining the passenger flow prediction data and the passenger flow organization knowledge graph.

2. The method for automatically generating a passenger flow organization strategy for a railway station according to claim 1, characterized in that: The steps of generating the existing station portrait library include: Classification step: Perform multi-dimensional classification based on the station's inherent attribute indicators, where the inherent attributes include two categories: dynamic attributes and static attributes; Quantification step: quantify each type of inherent attribute index.

3. The method for automatically generating a passenger flow organization strategy for a railway station according to claim 1, characterized in that: The similarity model generation step includes: Product topology map construction step: Based on the existing station portrait, with the existing station product in the portrait as the center, and the related products of the existing station product in the portrait as adjacent nodes, the nodes are connected according to the product relationship to construct a product topology map; Indicator alignment step: based on the product topology map, obtaining the existing station products and related product indicators, and aligning the product indicators; Index refinement step: inputting the existing station product index vector and the aligned index vectors of related products into a pre-built graph neural network model to obtain refined station product indicators; Steps for constructing a station index vector: using a station deep autoencoder neural network to optimize and reduce the dimensionality of the refined product index to obtain a station index vector; The similarity calculation step between products is as follows: based on the station index vector, the similarity between the target station and other stations is calculated, and the similarity is sorted to establish a station similarity model.

4. The method for automatically generating a passenger flow organization strategy for a railway station according to claim 1, characterized in that: The steps of constructing the station knowledge graph include: Knowledge base construction step: converting the existing station passenger flow organization strategy unstructured data into structured data, and cleaning and classifying the structured data to form a station passenger flow organization strategy knowledge base; Passenger flow and threshold calculation step: obtaining real-time monitoring data of passenger flow in the station and forecast data of future passenger flow in the station, analyzing the triggering conditions of passenger flow organization means in the passenger flow organization strategy knowledge base, and obtaining the threshold value of the number of passenger flow triggering in the station through simulation calculation; Knowledge graph construction steps: set the station passenger flow organization means, station passenger flow real-time monitoring data, and future station passenger flow forecast data as point sets respectively, and then set the threshold corresponding to the trigger condition as an edge set, establish connections between the point sets through the edge set, and generate a passenger flow organization knowledge graph.

5. The method for automatically generating a passenger flow organization strategy for a railway station according to claim 4, characterized in that: The step of automatically generating the new station passenger flow organization strategy includes: New station product portrait: Based on the static and dynamic attributes of the newly opened station, a portrait is pre-built to establish a product portrait; Calculating the similarity between the new station and the existing stations: Calculating the similarity between the new station and the existing stations based on the similarity model, sorting them, and obtaining the existing station with the highest similarity to the new station; The step of generating the passenger flow organization strategy for the new station: combining the similarity calculation results and the passenger flow organization strategy knowledge graph to automatically generate the passenger flow organization strategy for the new station.

6. The method for automatically generating a passenger flow organization strategy for a railway station according to claim 3, characterized in that: The indicator alignment step includes: obtaining station product indicators and related product indicators based on the product topology map, and calculating and obtaining indicator vectors after the related products are aligned with the existing station products.

7. The method for automatically generating a passenger flow organization strategy for a railway station according to claim 3, characterized in that: The indicator refinement step includes: constructing a graph neural network model, taking the station product indicator vector and the indicator vector after alignment of related products as input items, inputting them into the graph neural network model, and outputting the refined station product indicator that integrates the related product indicators.

8. A railway station passenger flow organization strategy automatic generation system, using the railway station passenger flow organization strategy automatic generation method according to any one of claims 1 to 7, characterized in that: include: Existing Station Portrait Library Generation Module: Based on the inherent attributes of existing stations, using product portrait technology, a portrait library of existing stations with multiple dimensions and indicators is established; Similarity model generation module: Based on the existing station product portrait library, the graph neural network is used to fuse and reduce the station indicators. After obtaining the station indicator vector, the similarity between different products is calculated to generate a similarity model; Station knowledge graph construction module: This module conducts a structured analysis of existing station passenger flow organization strategies, establishes a station passenger flow organization strategy knowledge base, and constructs a passenger flow organization knowledge graph based on station passenger flow data; Automatic generation module of passenger flow organization strategy for new stations: Make product profiling for the newly opened stations, calculate the similarity between the newly opened stations and the existing stations based on the similarity model, obtain the existing stations with the highest similarity to the corresponding new stations, and automatically generate passenger flow organization strategies for the new stations by combining passenger flow prediction data and the passenger flow organization knowledge graph.

9. A computer 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 computer program, the method for automatically generating a railway station passenger flow organization strategy according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for automatically generating a passenger flow organization strategy for a railway station as described in any one of claims 1 to 7 is implemented.

Images