Intelligent railway management system based on supply chain data

Abstract

The application relates to a smart railway management system based on supply chain data. The system comprises a data acquisition module for acquiring supply chain data from multiple data sources; a data integration and processing module for converting the supply chain data into structured data after data cleaning, format conversion and missing value completion processing; a transportation optimization module for determining a train scheduling plan, a transportation path planning scheme and a transportation resource allocation scheme through a preset optimization algorithm; a prediction analysis module for predicting freight transportation demand and transportation risk events through a pre-trained machine learning model and outputting early warning information; a real-time scheduling module for updating a train operation plan, a freight loading and unloading sequence and a work personnel configuration and issuing control instructions to an external control device; and a visualization and reporting module. The system can reduce the resource consumption of railway transportation operation.

Description

Technical Field

[0001] This application relates to the field of railway management technology, and in particular to a smart railway management system, method, computer equipment, computer-readable storage medium, and computer program product based on supply chain data. Background Technology

[0002] Railway transportation is an important component of the supply chain logistics system. The effectiveness of its scheduling planning, route arrangement, and resource allocation directly affects the transmission stability of the entire logistics chain. With the diversification of data sources in the supply chain scenario, the railway transportation management process needs to integrate multiple types of data, such as cargo, trains, environment, and infrastructure, to adapt to complex transportation operation scenarios.

[0003] Traditional railway transportation management and control systems use independent functional modules to carry out train dispatching, cargo tracking, resource allocation, and data collection operations separately. Each module processes its corresponding business data independently, without incorporating supply chain-related data such as cargo origin, cargo logistics status, and real-time inventory into the railway transportation data processing system. They rely solely on single-type transportation data to formulate dispatching plans and resource allocation strategies. Some existing systems simply perform routine dispatching adjustments after conducting simple analysis of historical transportation data.

[0004] However, the aforementioned traditional railway transportation management and control methods suffer from insufficient data interoperability among various functional modules, and the inability to effectively integrate and utilize multi-source supply chain data with railway transportation data. This results in the system's inability to dynamically optimize transportation scheduling and resource allocation schemes based on real-time scenario changes, and its poor ability to predict and respond to transportation risks. Summary of the Invention

[0005] Therefore, it is necessary to provide a smart railway management system, method, computer equipment, computer-readable storage medium, and computer program product based on supply chain data that can reduce the resource consumption of railway transportation operations, addressing the aforementioned technical problems.

[0006] Firstly, this application provides a smart railway management system based on supply chain data, comprising:

[0007] The data acquisition module is used to collect supply chain data from multiple data sources, including at least one of cargo data, train status data, environmental condition data, and infrastructure data.

[0008] The data integration and processing module is used to convert the supply chain data into structured data after data cleaning, format conversion and missing value completion.

[0009] The transportation optimization module is used to determine the train scheduling plan, transportation route planning scheme, and transportation resource allocation scheme based on the structured data and through a preset optimization algorithm.

[0010] The predictive analytics module is used to predict cargo transportation demand and transportation risk events based on historical transportation data and real-time structured data using a pre-trained machine learning model, and output early warning information.

[0011] The real-time scheduling module is used to update the train operation plan, cargo loading and unloading sequence, and personnel configuration based on the train scheduling plan, the transportation route planning scheme, the transportation resource allocation scheme, the cargo transportation demand, and the transportation risk events, and to send control commands to external control equipment.

[0012] The visualization and reporting module is used to display the train scheduling plan, the transportation route planning scheme, the transportation resource allocation scheme, the cargo transportation demand, the transportation risk events, the early warning information, and the real-time transportation status of trains in the form of charts and maps.

[0013] In one embodiment, the system further includes:

[0014] The supply chain interface module is used to interact with external supply chain systems using a preset standard interface protocol.

[0015] In one embodiment, the system further includes:

[0016] The security and access control module is used to control access behavior and encrypt data during data transmission and storage.

[0017] In one embodiment, the data acquisition module includes at least one of an electronic tag reader, a positioning device, and an Internet of Things (IoT) sensor.

[0018] Secondly, this application also provides a smart railway management method based on supply chain data, including:

[0019] Acquire supply chain data from multiple data sources, including at least one of cargo data, train status data, environmental condition data, and infrastructure data;

[0020] The supply chain data is then cleaned, format converted, and missing value filled in before being transformed into structured data.

[0021] Based on the structured data, a train scheduling plan, a transportation route planning scheme, and a transportation resource allocation scheme are determined through a preset optimization algorithm.

[0022] Based on historical transportation data and real-time structured data, a pre-trained machine learning model is used to predict cargo transportation demand and transportation risk events, and to output early warning information.

[0023] Based on the train scheduling plan, the transportation route planning scheme, the transportation resource allocation scheme, the cargo transportation needs, and the transportation risk events, update the train operation plan, cargo loading and unloading sequence, and personnel configuration, and issue control commands to external control equipment;

[0024] The train scheduling plan, the transportation route planning scheme, the transportation resource allocation scheme, the cargo transportation demand, the transportation risk events, the early warning information, and the real-time transportation status of the trains are displayed in the form of charts and maps.

[0025] In one embodiment, the step of predicting freight transport demand and transport risk events using a pre-trained machine learning model based on historical transport data and real-time structured data includes:

[0026] The time-dependent features of historical transportation data are extracted by a pre-trained time series prediction model, and multi-dimensional feature vectors are obtained by fusing real-time structured data with a pre-trained deep learning model.

[0027] By processing the outputs of the time series prediction model and the deep learning model through a meta-learner, cargo transportation demand and transportation risk events can be obtained.

[0028] When the level of the transportation risk event reaches a preset threshold, alternative scheduling schemes and resource pre-configuration suggestions are generated.

[0029] In one embodiment, determining the train scheduling plan, transportation route planning scheme, and transportation resource allocation scheme based on the structured data using a preset optimization algorithm includes:

[0030] Based on the structured data, a genetic algorithm or linear programming algorithm is used, with real-time environmental condition data and infrastructure status data as constraints, to determine the train scheduling plan, transportation route planning scheme, and transportation resource allocation scheme.

[0031] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in any of the above claims.

[0032] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any of the preceding claims.

[0033] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in any of the above claims.

[0034] The aforementioned intelligent railway management system, methods, computer equipment, computer-readable storage media, and computer program products based on supply chain data integrate and process multi-source supply chain data through modular collaborative operations. Based on data analysis and machine learning technologies, they optimize transportation plans and intelligently predict transportation demand and risks. Based on the optimization and prediction results, they dynamically adjust transportation scheduling and achieve full-process control of transportation through a visual interface. This enables intelligent management of railway transportation, effectively improving transportation efficiency, optimizing the allocation of transportation resources, enhancing the ability to respond to transportation risks, facilitating communication between railways and other logistics links, reducing resource consumption in railway transportation operations, and improving customer service satisfaction. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 This is a schematic diagram of the structure of a smart railway management system based on supply chain data in one embodiment;

[0037] Figure 2 This is a schematic diagram of the structure of a smart railway management system based on supply chain data in another embodiment;

[0038] Figure 3 This is a flowchart illustrating a smart railway management method based on supply chain data in one embodiment;

[0039] Figure 4 This is a flowchart illustrating the steps involved in predicting cargo transportation demand and transportation risk events using a pre-trained machine learning model based on historical transportation data and real-time structured data, as shown in one embodiment.

[0040] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0041] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0042] It should be noted that the terms "comprising" and "having," and any variations thereof, as used in this application, are intended to cover non-exclusive inclusion. The term "multiple" as used in this application refers to two or more. The term "and / or" as used in this application refers to one of the solutions, or any combination of multiple solutions.

[0043] In one embodiment, such as Figure 1 As shown, a smart railway management system 00 based on supply chain data is provided, including a data acquisition module 01, a data integration and processing module 02, a transportation optimization module 03, a predictive analysis module 04, a real-time scheduling module 05, and a visualization and reporting module 06, wherein:

[0044] The data acquisition module 01 is used to collect supply chain data from multiple data sources, including at least one of cargo data, train status data, environmental condition data, and infrastructure data.

[0045] For example, the data acquisition module 01 can collect supply chain data in real time through built-in sensors, external API interfaces, and external databases.

[0046] The data integration and processing module 02 is used to clean, convert, and fill in missing values ​​in the supply chain data, and then convert it into structured data.

[0047] For example, the data integration and processing module 02 may include a data cleaning submodule and a distributed storage submodule. The data cleaning submodule can remove duplicate and erroneous data from the supply chain data, perform format unification conversion and fill in missing values, and then store the processed data in a distributed storage submodule using a cloud storage or edge computing architecture, outputting standardized structured data to subsequent functional modules. Using distributed storage can achieve high availability for the big data processing system.

[0048] The transportation optimization module 03 is used to determine train scheduling plans, transportation route planning schemes, and transportation resource allocation schemes based on structured data and through preset optimization algorithms.

[0049] For example, the transportation optimization module 03 can call a preset genetic algorithm or linear programming algorithm to calculate and generate a train scheduling plan, an optimal transportation route planning scheme, and a human and equipment transportation resource allocation scheme based on the transportation constraints in the structured data, with the goal of minimizing transportation time and cost.

[0050] The predictive analysis module 04 is used to predict cargo transportation demand and transportation risk events based on historical transportation data and real-time structured data through a pre-trained machine learning model, and output early warning information.

[0051] For example, the predictive analysis module 04 can push cargo transportation demand, transportation risk events and corresponding confidence intervals to the real-time scheduling module.

[0052] Optionally, the predictive analysis module 04 may include an adaptive update submodule, used to dynamically adjust the model parameters and / or fusion weights of the machine learning model based on the deviation between the prediction results and the actual running data, so as to achieve continuous online learning of the model. The predictive analysis module 04 and the real-time scheduling module 05 can be linked through a bidirectional feedback loop.

[0053] The real-time dispatch module 05 is used to update the train operation plan, cargo loading and unloading sequence, and personnel configuration based on the train dispatch plan, transportation route planning scheme, transportation resource allocation scheme, cargo transportation demand, and transportation risk events, and to send control commands to external control equipment.

[0054] For example, the predictive analysis module 04 can push cargo transportation demand, transportation risk events, and corresponding confidence intervals to the real-time scheduling module; after the real-time scheduling module 05 executes the scheduling decision, it can feed back the scheduling execution results and status change data to the predictive analysis module 04 to correct the subsequent prediction results of the predictive analysis module 04. The real-time scheduling module 05 may include a communication interface submodule, through which it interacts with the train control system and storage equipment.

[0055] The Visualization and Reporting Module 06 is used to display train scheduling plans, transportation route planning schemes, transportation resource allocation schemes, freight transportation demand, transportation risk events, early warning information, and real-time train transportation status in the form of charts and maps.

[0056] For example, the visualization and reporting module 06 can display the above data information in the form of line charts, bar charts and electronic maps through the web-based dashboard visualization interface, supporting interactive viewing and access via mobile devices.

[0057] Specifically, the data acquisition module 01, data integration and processing module 02, transportation optimization module 03, predictive analysis module 04, real-time scheduling module 05, and visualization and reporting module 06 can communicate with each other via a central bus or an application programming interface (API).

[0058] The aforementioned intelligent railway management system based on supply chain data integrates and processes multi-source supply chain data through modular collaborative operations. It optimizes transportation plans and intelligently predicts transportation demand and risks based on data analysis and machine learning technologies. It dynamically adjusts transportation scheduling based on optimization and prediction results, and achieves full-process control of transportation through a visual interface. This enables intelligent management of railway transportation, effectively improving transportation efficiency, optimizing the allocation of transportation resources, enhancing the ability to respond to transportation risks, facilitating communication between railways and other logistics links, reducing resource consumption in railway transportation operations, and improving customer service satisfaction.

[0059] Optionally, such as Figure 2 As shown, the aforementioned intelligent railway management system 00 based on supply chain data may further include:

[0060] Supply chain interface module 07 is used to interact with external supply chain systems using a preset standard interface protocol.

[0061] Specifically, the supply chain interface module 07 can use RESTful API and EDI standard interface protocols to establish data connections with external ERP systems and WMS systems, enabling bidirectional exchange and collaborative operation of supply chain data.

[0062] In this way, by adding a supply chain interface module and using standard interface protocols to interact with external supply chain systems, data exchange and business collaboration between the railway transportation system and the upstream and downstream of the external supply chain can be achieved.

[0063] Alternatively, please continue to refer to Figure 2 The aforementioned intelligent railway management system 00 based on supply chain data may also include:

[0064] The Security and Access Management Module 08 is used to control access behavior and encrypt data during data transmission and storage.

[0065] Specifically, the security and access control module 08 can adopt role-based access control policies to perform user authentication and access control for system access behavior; it can also use blockchain technology to encrypt data during transmission and storage to ensure that the data is tamper-proof.

[0066] In this way, by adding a security and access control module to manage access permissions and encrypt data, the security of system access and the confidentiality and integrity of supply chain data transmission and storage can be guaranteed.

[0067] Optionally, the data acquisition module 01 mentioned above includes at least one of an electronic tag reading device, a positioning device, and an Internet of Things (IoT) sensing device.

[0068] Specifically, the data acquisition module 01 may include a cargo RFID tag reader, a GPS positioning device, and an IoT sensor; the RFID tag reader reads cargo identification information, the GPS positioning device obtains cargo and train location data, and the IoT sensor collects cargo temperature and humidity environmental data.

[0069] In this way, by configuring electronic tag reading devices, positioning devices, and IoT sensing devices, it is possible to achieve multi-dimensional, high-precision real-time collection of supply chain data, thereby improving the accuracy and comprehensiveness of basic data.

[0070] Optionally, the aforementioned intelligent railway management system 00 based on supply chain data may further include:

[0071] The system configuration module is used to set system operating parameters, business rules, and early warning thresholds to customize and adjust the system's operating behavior.

[0072] The report generation module is used to automatically generate transportation performance reports and compliance documents based on system operation data. It supports custom report formats and automatically distributes reports via email or messaging services.

[0073] The system configuration module and the report generation module can work together to support user-defined report formats and scheduling rules.

[0074] In one embodiment, such as Figure 3 As shown, a smart railway management method based on supply chain data is provided. This embodiment illustrates the method applied to a terminal. It is understood that this method can also be applied to a server, or to a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0075] S110, acquire supply chain data from multiple data sources, including at least one of cargo data, train status data, environmental condition data, and infrastructure data.

[0076] Supply chain data can be heterogeneous data generated by various nodes in the railway system's transportation supply chain. In one possible implementation, supply chain data may also include cargo location data, cargo temperature and humidity data, train positioning data, etc.

[0077] For example, data interfaces can be opened to connect to railway operation databases, meteorological public service platforms, and infrastructure monitoring platforms to simultaneously collect cargo data such as delivery and receipt addresses and categories, train status data such as train speed, load, and formation, environmental condition data such as temperature and precipitation information along the railway system, and / or infrastructure data such as track and signal light maintenance status.

[0078] S120 converts supply chain data into structured data after data cleaning, format conversion, and missing value completion.

[0079] For example, the collected raw supply chain data can be cleaned by removing duplicate data and correcting erroneous data, unifying the data format and filling in missing data items, and storing the processed data in a distributed storage unit using cloud storage or edge computing architecture to output standardized structured data.

[0080] S130 determines the train scheduling plan, transportation route planning scheme, and transportation resource allocation scheme based on structured data and through a preset optimization algorithm.

[0081] For example, based on structured data, genetic algorithms or linear programming algorithms can be used to generate train scheduling plans, transportation route planning schemes, and transportation manpower and equipment resource allocation schemes by using real-time environmental condition data and infrastructure status data as constraints and minimizing transportation time and costs.

[0082] S140 predicts freight transport demand and transport risk events using a pre-trained machine learning model based on historical transport data and real-time structured data, and outputs early warning information.

[0083] For example, historical transportation data and real-time structured data can be input into a pre-trained machine learning model to output freight transportation demand prediction results, transportation risk event prediction results and corresponding confidence intervals. Early warning information can be generated based on the prediction results. The parameters and fusion weights of the machine learning model can be dynamically adjusted according to the deviation between the prediction results and the actual operating data to achieve continuous online learning of the model.

[0084] S150 updates the train operation plan, cargo loading and unloading sequence, and personnel configuration based on the train dispatching plan, transportation route planning scheme, transportation resource allocation scheme, cargo transportation needs, and transportation risk events, and issues control commands to external control equipment.

[0085] For example, train operation plans, cargo loading and unloading sequences, and personnel configurations can be dynamically updated based on train scheduling plans, transportation route planning schemes, transportation resource allocation schemes, cargo transportation demands, and transportation risk events. Scheduling control commands can be sent to external control equipment such as train control systems and warehousing equipment through communication interfaces. The scheduling execution results and status change data can be fed back to the prediction stage to correct subsequent prediction results.

[0086] S160 displays train scheduling plans, transportation route planning schemes, transportation resource allocation schemes, freight transportation demand, transportation risk events, early warning information, and real-time train transportation status in the form of charts and maps.

[0087] For example, the above data and status information can be displayed in the form of line charts, bar charts, and electronic maps through a web-based visual dashboard, supporting access and interactive viewing on mobile devices.

[0088] The aforementioned intelligent railway management method based on supply chain data integrates and processes multi-source supply chain data, optimizes transportation plans and intelligently predicts transportation demand and risks based on data analysis and machine learning technologies, dynamically adjusts transportation scheduling based on optimization and prediction results, and achieves full-process control of transportation through a visual interface. This enables intelligent management of railway transportation, effectively improves transportation efficiency, optimizes the allocation of transportation resources, enhances the ability to respond to transportation risks, facilitates communication between railways and other logistics links, reduces resource consumption in railway transportation operations, and improves customer service satisfaction.

[0089] Optionally, such as Figure 4 As shown, the steps described above for predicting freight transport demand and transport risk events using a pre-trained machine learning model based on historical transport data and real-time structured data may include:

[0090] S210 extracts the time-dependent features of historical transportation data through a pre-trained time series prediction model, and obtains a multi-dimensional feature vector by fusing real-time structured data through a pre-trained deep learning model.

[0091] For example, a pre-trained time series prediction model can be used to extract time-dependent features based on historical cargo throughput, train punctuality rate, and historical delay data; a deep learning model based on attention mechanism recurrent neural network or graph neural network can be used to generate multi-dimensional feature vectors based on cargo category, loading and unloading node operation efficiency, real-time weather radar map, health index of infrastructure along the line, and external social event information.

[0092] S220 processes the outputs of the time series prediction model and the deep learning model through a meta-learner to obtain cargo transportation demand and transportation risk events.

[0093] For example, a meta-learner can be used to receive the output results of the time series prediction model and the deep learning model, and perform weighted fusion or stacked generalization processing to obtain the cargo transportation demand, cargo throughput probability distribution, multi-level transportation risk level and potential congestion point location within a future preset time window.

[0094] S230 generates alternative scheduling schemes and resource pre-configuration suggestions when the level of a transportation risk event reaches a preset threshold.

[0095] For example, the delay risk level of a transportation risk event can be determined. When the delay risk level exceeds a preset threshold, an alternative scheduling plan including adjusting train running times and changing transportation routes, as well as resource pre-configuration suggestions for manpower and equipment allocation, can be automatically generated. The warning instructions and alternative scheduling plans will be prioritized for scheduling execution and visualization.

[0096] In this embodiment, by employing multi-model fusion and meta-learner collaboration for transportation forecasting, and automatically generating alternative scheduling and resource pre-configuration schemes when the risk level meets the standard, the accuracy and reliability of transportation forecasting can be improved, and the ability to proactively handle transportation risks and reserve scheduling plans can be strengthened.

[0097] Optionally, the above S120 may include: determining the train scheduling plan, transportation route planning scheme, and transportation resource allocation scheme by using a genetic algorithm or linear programming algorithm based on structured data and taking real-time environmental condition data and infrastructure status data as constraints.

[0098] For example, based on standardized structured data, genetic algorithms or linear programming algorithms can be called to perform calculations, using real-time collected environmental condition data such as temperature, precipitation, and wind force, as well as infrastructure status data such as track health status, station equipment operation and maintenance status, and line capacity as constraints, with the goal of minimizing transportation time and cost, to calculate and generate train scheduling plans, transportation route planning schemes, and transportation resource allocation schemes.

[0099] In this embodiment, by employing a specific optimization algorithm and combining real-time environment and infrastructure status as constraints to formulate a transportation planning scheme, the fit and feasibility of transportation scheduling and route planning can be improved, making resource allocation more suitable for actual on-site operating conditions.

[0100] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0101] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a smart railway management method based on supply chain data. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0102] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0103] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0104] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0105] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0106] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0107] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above 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 application.

[0108] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A smart railway management system based on supply chain data, characterized in that, The system includes: The data acquisition module is used to collect supply chain data from multiple data sources, including at least one of cargo data, train status data, environmental condition data, and infrastructure data. The data integration and processing module is used to convert the supply chain data into structured data after data cleaning, format conversion and missing value completion. The transportation optimization module is used to determine the train scheduling plan, transportation route planning scheme, and transportation resource allocation scheme based on the structured data and through a preset optimization algorithm. The predictive analytics module is used to predict cargo transportation demand and transportation risk events based on historical transportation data and real-time structured data using a pre-trained machine learning model, and output early warning information. The real-time scheduling module is used to update the train operation plan, cargo loading and unloading sequence, and personnel configuration based on the train scheduling plan, the transportation route planning scheme, the transportation resource allocation scheme, the cargo transportation demand, and the transportation risk events, and to send control commands to external control equipment. The visualization and reporting module is used to display the train scheduling plan, the transportation route planning scheme, the transportation resource allocation scheme, the cargo transportation demand, the transportation risk events, the early warning information, and the real-time transportation status of trains in the form of charts and maps.

2. The system according to claim 1, characterized in that, The system also includes: The supply chain interface module is used to interact with external supply chain systems using a preset standard interface protocol.

3. The system according to claim 1, characterized in that, The system also includes: The security and access control module is used to control access behavior and encrypt data during data transmission and storage.

4. The system according to claim 1, characterized in that, The data acquisition module includes at least one of an electronic tag reading device, a positioning device, and an Internet of Things (IoT) sensing device.

5. A smart railway management method based on supply chain data, characterized in that, The method includes: Acquire supply chain data from multiple data sources, including at least one of cargo data, train status data, environmental condition data, and infrastructure data; The supply chain data is then cleaned, format converted, and missing value filled in before being transformed into structured data. Based on the structured data, a train scheduling plan, a transportation route planning scheme, and a transportation resource allocation scheme are determined through a preset optimization algorithm. Based on historical transportation data and real-time structured data, a pre-trained machine learning model is used to predict cargo transportation demand and transportation risk events, and to output early warning information. Based on the train scheduling plan, the transportation route planning scheme, the transportation resource allocation scheme, the cargo transportation needs, and the transportation risk events, update the train operation plan, cargo loading and unloading sequence, and personnel configuration, and issue control commands to external control equipment; The train scheduling plan, the transportation route planning scheme, the transportation resource allocation scheme, the cargo transportation demand, the transportation risk events, the early warning information, and the real-time transportation status of the trains are displayed in the form of charts and maps.

6. The method according to claim 5, characterized in that, The method of predicting freight transport demand and transport risk events using a pre-trained machine learning model based on historical transport data and real-time structured data includes: The time-dependent features of historical transportation data are extracted by a pre-trained time series prediction model, and multi-dimensional feature vectors are obtained by fusing real-time structured data with a pre-trained deep learning model. By processing the outputs of the time series prediction model and the deep learning model through a meta-learner, cargo transportation demand and transportation risk events can be obtained. When the level of the transportation risk event reaches a preset threshold, alternative scheduling schemes and resource pre-configuration suggestions are generated.

7. The method according to claim 5, characterized in that, The step of determining the train scheduling plan, transportation route planning scheme, and transportation resource allocation scheme based on the structured data and using a preset optimization algorithm includes: Based on the structured data, a genetic algorithm or linear programming algorithm is used, with real-time environmental condition data and infrastructure status data as constraints, to determine the train scheduling plan, transportation route planning scheme, and transportation resource allocation scheme.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 5 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 5 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 5 to 7.

Images