Data interaction method for railway dispatching

Abstract

The invention provides a data interaction method for railway dispatching, which comprises the following steps of: extracting data characteristics from dispatching data according to the type of the dispatching data; the type of the scheduling data at least comprises one of a database, a log and an event; converting the data features by using the data feature knowledge base to obtain interaction data; the data feature knowledge base is used for storing a corresponding relationship among an original data format, a standard data format and data features of the scheduling data; according to the dynamic update routing table, determining a routing path for transmitting interaction data; the dynamic update routing table is used for storing a routing path determined according to the data characteristics and the link state. The invention further provides a data interaction device and equipment for railway dispatching and a storage medium.

Description

Technical Field

[0001] The present disclosure relates to the technical field of railway scheduling, and more particularly to a data interaction method for railway scheduling. Background Art

[0002] Traditional railway dispatching systems are centered around centralized data processing. Each dispatching subsystem (train dispatching, locomotive dispatching, and freight transport) often operates independently, with inconsistent data formats and protocols. This leads to data silos and difficulty in information collaboration. For example, data exchange between specialized systems like the Train Dispatching and Control System (TDCS) and vehicle operation safety monitoring (5T) and the Supervisory Control and Data Acquisition (SCADA) system relies on manual transmission, resulting in information delays and the risk of errors. Existing systems also have a narrow data collection scope and lack the ability to integrate heterogeneous data from multiple sources (such as sensors and monitoring), making them difficult to support real-time decision-making. Summary of the Invention

[0003] In view of the above problems, the present disclosure provides a data interaction method for railway scheduling that collects, processes and transmits multi-source heterogeneous data between multiple scheduling subsystems.

[0004] The present disclosure provides a data interaction method for railway scheduling, comprising: extracting data features from the scheduling data according to the type of the scheduling data; the type of the scheduling data includes at least one of a database, a log, and an event; converting the data features using a data feature knowledge base to obtain interactive data; the data feature knowledge base is used to store the correspondence between the original data format, the standard data format, and the data features of the scheduling data; determining a routing path for transmitting the interactive data according to a dynamically updated routing table; the dynamically updated routing table is used to store the routing path determined according to the data features and the link status.

[0005] According to an embodiment of the present disclosure, data features are extracted from the scheduling data according to the type of the scheduling data, including: in response to the scheduling data being database data, parsing the protocol header as a data feature; in response to the scheduling data being log data, parsing the protocol header or tag hierarchy as a data feature; in response to the scheduling data being event data, extracting data features from the event data using a data feature extraction model; the event data includes at least one of numerical data, video image data, and text data; the data feature extraction model is used to extract data features based on the input event data using deep learning.

[0006] According to an embodiment of the present disclosure, a data feature extraction model is used to extract data features from event data, including: in response to the event data being numerical data, a temporal convolutional network model is used to extract local features as data features; in response to the event data being video image data, a target detection model is used to extract structured event descriptions as data features; in response to the data being text data, a natural language processing model is used to generate semantic vectors as data features.

[0007] According to an embodiment of the present disclosure, a method for constructing a data feature knowledge base includes: generating a data fingerprint based on data features; storing the data fingerprint and the original data format and standard data format corresponding to the data fingerprint in the data feature knowledge base; the original data format is used for interaction within the railway scheduling subsystem; and the standard data format is used for interaction between different railway scheduling subsystems.

[0008] According to an embodiment of the present disclosure, data features are converted using a data feature knowledge base to obtain interactive data, including: in response to interactive data being transmitted to a node within a railway scheduling subsystem, converting data features into original data format to obtain interactive data; in response to interactive data being transmitted to a node of another railway scheduling subsystem, converting data features into standard data format to obtain interactive data.

[0009] According to an embodiment of the present disclosure, a method for constructing a dynamically updated routing table includes: periodically exchanging link status information through routers to construct a network topology map; the link status information includes at least one of bandwidth utilization, delay and number of hops; determining a metric feature of the scheduling data based on data characteristics; the metric feature includes at least one of size, flow and immediacy; and using a cost function to calculate the optimal routing path of the scheduling data based on the metric feature, link status information and network topology map for storage in the dynamically updated routing table.

[0010] According to an embodiment of the present disclosure, a cost function is used to calculate the optimal routing path of scheduling data based on metric characteristics, link status information and a network topology diagram, including: calculating feature complexity based on metric characteristics; calculating node cost value for each available node using a cost function; the cost function is obtained by a weighted combination of the CPU load ratio, the ratio of network delay to delay threshold, memory occupancy and the ratio of feature complexity to maximum complexity; selecting the optimal node as the next node using the node cost value; and repeating the steps of calculating the node cost value for each available node using a cost function until the optimal routing path is determined.

[0011] A second aspect of the present disclosure provides a data interaction device for railway scheduling, which can be used to implement the above-mentioned method. The device includes: a feature extraction module, which is used to extract data features from scheduling data according to the type of scheduling data; the type of scheduling data includes at least one of a database, a log and an event; a format conversion module, which is used to convert data features using a data feature knowledge base to obtain interactive data; the data feature knowledge base is used to store the correspondence between the original data format, the standard data format and the data features of the scheduling data; a data transmission module, which is used to determine a routing path for transmitting interactive data based on a dynamically updated routing table; the dynamically updated routing table is used to store the routing path determined based on the data features and the link status.

[0012] A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the above-mentioned data interaction method for railway scheduling.

[0013] The fourth aspect of the present disclosure further provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the above-mentioned data interaction method for railway scheduling.

[0014] The data interaction method for railway dispatching provided by the present disclosure converts dispatching data in different data formats from different data sources into data features, uses a data feature knowledge base to convert the data features into integrated interactive data, and uses a dynamically updated routing table to determine the transmission routing path. By achieving standardized conversion of dispatching data and determining the optimal routing path based on the data features, it at least partially solves the technical problems of difficult integration of different data sources and transmission delays, achieving the technical effect of eliminating format and protocol differences and achieving efficient cross-system interaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 The flowchart of the data interaction method for railway scheduling according to an embodiment of the present disclosure is schematically shown;

[0016] Figure 2 Schematically illustrates a flow chart including the construction of a data feature knowledge base and a dynamically updated routing table according to an embodiment of the present disclosure;

[0017] Figure 3 A schematic diagram of a structure of a data interaction device for railway scheduling according to an embodiment of the present disclosure is shown;

[0018] Figure 4 A block diagram of an electronic device suitable for implementing a data interaction method for railway scheduling according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0019] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present disclosure. In the detailed description below, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0020] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise," "include," etc. used herein indicate the presence of the features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0021] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0022] When expressions such as "at least one of A, B, and C, etc." are used, they should generally be interpreted in accordance with the meaning commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0023] Existing railway dispatching systems largely rely on centralized cloud computing, requiring data to be transmitted to remote data centers for processing, resulting in high latency and bandwidth pressure. For example, in high-speed rail contact network defect detection scenarios, traditional methods require collected video data to be transmitted back to the cloud for analysis. However, processing speed lags behind acquisition speed, failing to meet real-time requirements. Furthermore, this centralized architecture suffers from insufficient response time for unexpected tasks (such as emergency train dispatch), potentially posing safety risks.

[0024] In response to the above problems existing in the data interaction of the integrated dispatching system, a unified data interaction method for the integrated dispatching system is constructed by using technologies such as dynamic data adaptation and dynamic routing decision-making to solve the problems of inconsistent data formats and data transmission delays. Figure 1 A flow chart of a data interaction method for railway scheduling according to an embodiment of the present disclosure is schematically shown. Figure 1As shown, an embodiment of the present disclosure provides a data interaction method for railway scheduling, including: extracting data features from scheduling data according to the type of scheduling data; the type of scheduling data includes at least one of a database, a log and an event; using a data feature knowledge base to convert data features to obtain interactive data; the data feature knowledge base is used to store the correspondence between the original data format, the standard data format and the data features of the scheduling data; according to a dynamically updated routing table, a routing path is determined for transmitting interactive data; the dynamically updated routing table is used to store the routing path determined according to the data features and the link status.

[0025] Figure 2 The flowchart of the construction of a data feature knowledge base and a dynamically updated routing table according to an embodiment of the present disclosure is schematically shown, specifically including: S1, obtaining multi-source data; S2, extracting data features in a multi-modal manner; S3, updating the data feature knowledge base based on data features and structured data protocols; S4, obtaining the standard data structure in the data feature knowledge base based on data features, and marking and converting it; S5, obtaining the resource status of all available nodes; S6, calculating the optimal routing path based on the resource status and data features according to the feature-based dynamic decision algorithm; S7, performing data compression and encryption processing and transmitting data. Among them, data acquisition includes obtaining scheduling data through the network, interface, database, third-party service, etc.

[0026] Through the embodiments of the present disclosure, in response to the real-time collection, processing and collaborative decision-making needs of multi-source heterogeneous data in the railway dispatching system, dynamic data adaptation technology is used to realize automatic adjustment of data format and routing path, solve the problems of data silos, rigid resource allocation and lack of real-time performance in the existing technology, realize standardized interaction of multi-source heterogeneous data, and establish a dynamic routing decision-making mechanism based on data features. After the data conversion is successful, the routing path is dynamically adapted based on the data features to improve data transmission efficiency. It is suitable for comprehensive dispatching management in multiple scenarios such as high-speed railways, freight railways, and urban rail transit.

[0027] On the basis of the above embodiments, data features are extracted from the scheduling data according to the type of scheduling data, including: in response to the scheduling data being database data, parsing the protocol header as a data feature; in response to the scheduling data being log data, parsing the protocol header or tag hierarchy as a data feature; in response to the scheduling data being event data, extracting data features from the event data using a data feature extraction model; the event data includes at least one of numerical data, video image data, and text data; the data feature extraction model is used to extract data features based on the input event data using deep learning.

[0028] In this embodiment, the railway integrated dispatching system includes multiple dispatching subsystems, each of which may have a different data structure. Therefore, the railway integrated dispatching system utilizes a variety of heterogeneous data, including structured (relational databases), semi-structured (XML / JSON logs), and unstructured data (text, images, and video). Structured and semi-structured data generally have fixed protocols or formats, and protocol headers can be directly extracted as data features to generate data fingerprints. Semi-structured data can also define hierarchical relationships and data features through tags; unstructured data relies on dynamic feature extraction to generate data fingerprints. When abnormal data is identified, an abnormal data log is generated.

[0029] Through the embodiments of the present disclosure, corresponding data processing methods are proposed for scheduling data with different data structures in different scheduling subsystems. Structured data (i.e., database data) and semi-structured data (i.e., log data) are directly parsed to avoid redundant calculations; high-value features are extracted from unstructured data (i.e., event data) through deep learning models to improve feature representation capabilities.

[0030] Based on the above embodiments, a data feature extraction model is used to extract data features from event data, including: in response to the event data being numerical data, a temporal convolutional network model is used to extract local features as data features; in response to the event data being video image data, a target detection model is used to extract structured event descriptions as data features; in response to the data being text data, a natural language processing model is used to generate semantic vectors as data features.

[0031] In this embodiment, a hierarchical coding strategy is adopted to solve the data heterogeneity problem based on the characteristics of unstructured data:

[0032] (1) Numerical data: After normalization, it is input into the time series convolutional network (TCN) to extract local features from numerical time series data (such as sensor data):

[0033] ;

[0034] Among them, W conv Represents the weight matrix of the convolution kernel; Represents a sliding window of input data, containing time series data from tk to t; b is a bias term; the window size of the temporal convolutional network is adaptively adjusted according to the sampling frequency: the window size k=2f / b, f is the data frequency, and b is the reference frequency.

[0035] (2) Video image data: Deploy a lightweight version of the YOLOv5s model on edge nodes, retaining only the backbone network for object detection and outputting structured event descriptions, which can be used for railway track anomaly detection (such as pedestrian intrusion and obstacle recognition):

[0036] ;

[0037] Among them, E v Represents a set of detected events; obj i is the object category (pedestrian, obstacle, etc.); loc i is the relative orbital coordinate; t i Indicates the timestamp when the event occurs; N indicates the total number of objects detected.

[0038] (3) Text data (dispatching instructions): The BERT-Tiny model is used to extract semantic vectors and map them to a unified feature space.

[0039] Through the embodiments of this disclosure, dedicated feature extraction models are designed for numerical, video, and text event data: TCN captures local dependencies in time series data (such as high-frequency sensor sampling), YOLOv5s enables real-time object detection in track videos, and BERT-Tiny extracts scheduling instruction semantics and adapts to data characteristics. Furthermore, the use of lightweight models allows for deployment at edge nodes, reducing transmission pressure in the cloud.

[0040] Based on the above embodiments, a method for constructing a data feature knowledge base includes: generating a data fingerprint based on data features; storing the data fingerprint and the original data format and standard data format corresponding to the data fingerprint in the data feature knowledge base; the original data format is used for interaction within the railway dispatching subsystem; and the standard data format is used for interaction between different railway dispatching subsystems.

[0041] In this embodiment, data features are extracted, a data fingerprint is generated, and dynamically stored in a data feature knowledge base. The data feature knowledge base stores the correspondence between data features, original data formats, and standardized data formats, thereby enabling conversion between original data formats and standardized data formats. The data feature knowledge base supports manual correction and maintenance.

[0042] The disclosed embodiments address the significant differences in data formats across different data sources, which can make data integration difficult and impact data processing efficiency and accuracy. Intelligent algorithms (such as rule engines and machine learning models) automatically identify heterogeneous data from multiple sources (such as sensors, weather, and passenger information), extract data features, generate data feature fingerprints, and store them in a data feature knowledge base, achieving standardized storage and conversion of heterogeneous data from multiple sources. Multimodal data from rail sensors, onboard equipment, and ticketing systems is integrated and converted into a unified format (such as JSON), eliminating format and protocol differences between subsystems and enabling efficient cross-system interaction.

[0043] Based on the above embodiment, the data feature knowledge base is used to convert the data features to obtain the interactive data, including: in response to the interactive data being transmitted to the node within the railway dispatching subsystem, the data features are converted into the original data format to obtain the interactive data; in response to the interactive data being transmitted to the node of another railway dispatching subsystem, the data features are converted into the standard data format to obtain the interactive data.

[0044] Through the embodiments of the present disclosure, the original data format can be used for interaction within the subsystem, but the integrated scheduling system contains multiple scheduling subsystems, and the data types and standards between the subsystems are different. To achieve data sharing and business collaboration, it is necessary to build a standardized data format. According to the data characteristics, the standard data structure in the data feature knowledge base is obtained, and marked and converted. The standard protocol is used for interaction between the systems within the integrated scheduling system. Therefore, it is necessary to build a data feature knowledge base to store the correspondence between the original data characteristics, the original data format and the standard data format, so as to achieve mutual conversion between the original data format and the standardized data format.

[0045] Based on the above embodiment, a method for constructing a dynamically updated routing table includes: periodically exchanging link state information through routers to construct a network topology map; the link state information includes at least one of bandwidth utilization, delay and hop count; determining a metric feature of the scheduling data based on data characteristics; the metric feature includes at least one of size, flow and immediacy; based on the metric feature, the link state information and the network topology map, using a cost function to calculate the optimal routing path of the scheduling data for storage in the dynamically updated routing table.

[0046] In this embodiment, the core principle of dynamically adjusting routing based on data characteristics is to dynamically optimize data transmission paths by monitoring network status in real time (such as traffic load, link latency, topology changes, etc.) in combination with a predefined algorithm. The principles of dynamic routing decision-making based on data characteristics are as follows:

[0047] (1) State perception and information exchange: Routers periodically exchange link state information (LSAs) through protocols such as OSPF to build a global network topology view. Data features such as bandwidth utilization, latency, and hop count are collected as metrics for routing calculations.

[0048] (2) Deep perception of data features: Extract data features (statistics, time series, semantics, immediacy, data volume, etc.) from raw data to quantify the complexity and resource requirements of data processing.

[0049] (3) Dynamic path calculation: Update the network topology based on real-time data features, combine feature information with real-time resource status, construct a dynamic cost function, and recalculate the optimal path. Paths are selected based on preset strategies (such as load balancing and minimum latency) to avoid congestion or single points of failure. This includes: obtaining a list of available nodes; calculating feature complexity; calculating the cost of each node; and selecting the most optimized node.

[0050] Among them, the dynamic cost function is as follows:

[0051]

[0052] in, Indicates the current CPU usage of node i; represents the maximum CPU capacity of node i; Indicates the current memory usage of node i; represents the maximum memory capacity of node i; represents the network delay of node i; Indicates the network delay threshold; Indicates the complexity of data features; Represents the preset maximum feature complexity; α, β, γ, and δ represent the weights of each item respectively.

[0053] The initial values ​​of the weights are as follows: α = 0.3, β = 0.3, γ = 0.2, δ = 0.2. The weight parameters are dynamically adjusted using the Q-Learning method.

[0054] It should be noted that for some data features, the routing node chooses to adopt feature-sensitive routing rules, including: in response to the data feature pattern being high-frequency time series data, a routing strategy of routing to the nearest edge GPU node is adopted; in response to the data feature pattern being high-dimensional text features, a routing strategy of allocating large memory nodes and enabling memory cache is adopted; in response to the data feature pattern being sparse graph data, a routing strategy of using dedicated nodes for graph computing is adopted. Among them, high-frequency time series data, high-dimensional text features, and sparse graph data are all determined by comparing with preset thresholds. Optionally, the sampling rate of high-frequency time series data is greater than 1kHz; the dimension of high-dimensional text features is greater than 500; and the edge density of sparse graph data is less than 0.1.

[0055] (4) Routing table update and convergence: Update the local routing table based on the calculation results and synchronize with other routers through the protocol to ensure consistent routing information across the entire network. Converge quickly when the network topology changes, reducing packet loss and transmission interruptions.

[0056] Through the embodiments of this disclosure, traditional data transmission methods are prone to transmission delays when faced with massive amounts of data, making them unable to meet the real-time scheduling requirements of railways. Routing paths are dynamically adjusted based on real-time network load and the real-time status of network nodes. This disclosure proposes a dynamic routing decision method based on data characteristics. This method determines the network transmission conditions required for data based on data characteristics, dynamically adjusts routing, and improves transmission efficiency.

[0057] On the basis of the above embodiment, the optimal routing path of the scheduling data is calculated using a cost function according to the metric characteristics, link status information and network topology diagram, including: calculating the feature complexity according to the metric characteristics; calculating the node cost value for each available node using the cost function; the cost function is obtained by a weighted combination of the CPU load ratio, the ratio of the network delay to the delay threshold, the memory occupancy rate and the ratio of the feature complexity to the maximum complexity; using the node cost value, the optimal node is selected as the next node; and the step of calculating the node cost value for each available node using the cost function is repeated until the optimal routing path is determined.

[0058] According to the embodiments of the present disclosure, a cost function is used to balance resource utilization and real-time requirements, and a routing path is dynamically selected.

[0059] Based on the above data interaction method for railway scheduling, the present disclosure also provides a data interaction device for railway scheduling. Figure 3 The device is described in detail.

[0060] like Figure 3 As shown, the data interaction device for railway scheduling of this embodiment can be used to implement the above method, and the device includes: a feature extraction module, which is used to extract data features from scheduling data according to the type of scheduling data; the type of scheduling data includes at least one of database, log and event; a format conversion module, which is used to convert data features using a data feature knowledge base to obtain interactive data; the data feature knowledge base is used to store the correspondence between the original data format, standard data format and data features of the scheduling data; a data transmission module, which is used to determine a routing path for transmitting interactive data based on a dynamically updated routing table; the dynamically updated routing table is used to store a routing path determined based on data features and link status.

[0061] Figure 4 A block diagram of an electronic device suitable for implementing a data interaction method for railway scheduling according to an embodiment of the present disclosure is schematically shown.

[0062] like Figure 4As shown, the electronic device 400 according to an embodiment of the present disclosure includes a processor 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage portion 408 into a random access memory (RAM) 403. The processor 401 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 401 may also include onboard memory for caching purposes. The processor 401 may include a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiment of the present disclosure.

[0063] Various programs and data required for the operation of the electronic device 400 are stored in RAM 403. The processor 401, ROM 402, and RAM 403 are connected to each other via a bus 404. The processor 401 performs various operations of the method flow according to the embodiment of the present disclosure by executing the programs in ROM 402 and / or RAM 403. It should be noted that the programs may also be stored in one or more memories other than ROM 402 and RAM 403. The processor 401 may also perform various operations of the method flow according to the embodiment of the present disclosure by executing the programs stored in the one or more memories.

[0064] According to an embodiment of the present disclosure, electronic device 400 may further include an input / output (I / O) interface 405, which is also connected to bus 404. Electronic device 400 may also include one or more of the following components connected to I / O interface 405: an input section 406 including a keyboard, mouse, etc.; an output section 407 including devices such as a cathode ray tube (CRT), liquid crystal display (LCD), and speakers; a storage section 408 including a hard disk; and a communication section 409 including a network interface card such as a LAN card or modem. Communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to I / O interface 405 as needed. Removable media 411, such as a magnetic disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed in drive 410 as needed, so that computer programs read from the removable media can be installed into storage section 408 as needed.

[0065] In this embodiment, the hardware deployment solution can be optionally as follows: edge computing node configuration: Huawei Atlas 500 intelligent station; central server cluster: 3 Kunpeng 920 processor nodes; network equipment: H3C S6850 series switch networking; system parameter configuration: data fragment size: 256KB±10% dynamic adjustment; heartbeat detection interval: 500ms; maximum retransmission number: 3 times (exponential backoff strategy). The data transmission example is as follows: Scenario: integrating CTC scheduling commands (XML), trackside sensors (CSV), and monitoring data; implementation steps: (1) Router obtains data stream (2) Feature extraction generates standardized format data (3) Dynamic routing decision (4) Output standardized data stream message queue

[0066] Through the embodiments of the present disclosure, different types of data features are identified, converted into standardized data formats, and standardized data streams are output.

[0067] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments, or may exist independently and not be incorporated into the device / apparatus / system. The computer-readable storage medium carries one or more programs, and when executed, implements the method according to the embodiments of the present disclosure.

[0068] According to an embodiment of the present disclosure, a computer-readable storage medium may be a non-volatile computer-readable storage medium, and may include, for example, but not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 402 and / or RAM 403 described above, and / or one or more memories other than ROM 402 and RAM 403.

[0069] The embodiments of the present disclosure also include a computer program product, which includes a computer program containing program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the method provided by the embodiments of the present disclosure.

[0070] The computer program executes the above functions defined in the system / device of the embodiment of the present disclosure when the processor 401 executes the computer program. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0071] In one embodiment, the computer program may be stored on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may be transmitted and distributed in the form of a signal on a network medium, downloaded and installed via the communication portion 409, and / or installed from a removable medium 411. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0072] In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 409, and / or installed from the removable medium 411. When the computer program is executed by the processor 401, the above-mentioned functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the systems, devices, means, modules, units, etc. described above can be implemented by computer program modules.

[0073] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computer programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C" or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect via the Internet).

[0074] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the above-mentioned module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0075] Those skilled in the art will appreciate that the features described in the various embodiments and / or claims of this disclosure may be combined and / or coupled in various ways, even if such combinations and / or couplings are not explicitly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this disclosure may be combined and / or coupled in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or couplings are intended to fall within the scope of this disclosure.

[0076] The embodiments of the present disclosure are described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although each embodiment has been described separately above, this does not mean that the measures in each embodiment cannot be used in combination to advantage. The scope of the present disclosure is defined by the appended claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A data interaction method for railway scheduling, characterized in that: include: Extracting data features from the scheduling data according to the type of the scheduling data; The type of the scheduling data includes at least one of a database, a log, and an event; The data features are converted using a data feature knowledge base to obtain interactive data; the data feature knowledge base is used to store the correspondence between the original data format of the scheduling data, the standard data format and the data features; According to the dynamically updated routing table, a routing path is determined for transmitting the interactive data; the dynamically updated routing table is used to store the routing path determined according to the data characteristics and the link status.

2. The method according to claim 1, wherein The extracting data features from the scheduling data according to the type of the scheduling data includes: In response to the scheduling data being database data, parsing a protocol header as a data feature; In response to the dispatch data being log data, parsing a protocol header or a tag layer as a data feature; In response to the scheduling data being event data, a data feature extraction model is used to extract data features from the event data; the event data includes at least one of numerical data, video image data, and text data; the data feature extraction model is used to extract data features based on the input event data using deep learning.

3. The method according to claim 2, wherein: The method of extracting data features from event data using a data feature extraction model includes: In response to the fact that the event data is numerical data, a temporal convolutional network model is used to extract local features as data features; In response to the event data being video image data, a target detection model is used to extract structured event descriptions as data features; In response to the data being text data, a natural language processing model is used to generate a semantic vector as a data feature.

4. The method according to claim 1, wherein The method for constructing the data feature knowledge base includes: Generate data fingerprint based on data characteristics; The data fingerprint and the original data format and standard data format corresponding to the data fingerprint are stored in the data feature knowledge base; the original data format is used for interaction within the railway scheduling subsystem; the standard data format is used for interaction between different railway scheduling subsystems.

5. The method according to claim 1, wherein The step of converting the data features using a data feature knowledge base to obtain interaction data includes: In response to the interactive data being transmitted to a node within the railway dispatching subsystem, converting the data features into an original data format to obtain interactive data; In response to the interactive data being transmitted to another node of the railway dispatching subsystem, the data features are converted into a standard data format to obtain interactive data.

6. The method according to claim 1, wherein The method for constructing the dynamic update routing table includes: Periodically exchanging link state information through routers to construct a network topology; the link state information includes at least one of bandwidth utilization, delay, and hop count; Determining a metric characteristic of the scheduling data based on the data characteristics; the metric characteristic includes at least one of size, flow, and immediacy; According to the metric characteristics, link state information and network topology, the cost function is used to calculate the optimal routing path of the scheduling data for storage in the dynamically updated routing table.

7. The method according to claim 6, wherein: The method of calculating the optimal routing path for the scheduling data using a cost function based on the metric characteristics, link state information, and network topology diagram includes: Calculate feature complexity based on metric features; For each available node, a cost function is used to calculate the node cost; the cost function is obtained by a weighted combination of CPU load ratio, the ratio of network delay to delay threshold, memory usage, and the ratio of feature complexity to maximum complexity; Using the node cost value, select the optimal node as the next node; The step of calculating the node cost value using the cost function for each available node is repeated until the optimal routing path is determined.

8. A data interaction device for railway dispatching, characterized in that: The device can be used to implement the method according to any one of claims 1 to 7, and the device includes: A feature extraction module, configured to extract data features from the scheduling data according to the type of the scheduling data; the type of the scheduling data includes at least one of a database, a log, and an event; a format conversion module, configured to convert the data features using a data feature knowledge base to obtain interactive data; the data feature knowledge base is configured to store the correspondence between the original data format of the scheduling data, the standard data format, and the data features; The data transmission module is used to determine a routing path for transmitting the interactive data according to a dynamically updated routing table; the dynamically updated routing table is used to store the routing path determined according to data characteristics and link status.

9. An electronic device comprising: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors are enabled to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to perform the method according to any one of claims 1 to 7.

Images