Digital heavy haul railway artificial intelligence device, method, equipment, medium and program

Abstract

The invention relates to a digital heavy haul railway artificial intelligence device, method, equipment, medium and program, and the device comprises a data sensing module which is used for collecting a multi-source real-time operation data set of a target heavy haul railway; the external data interaction module is used for performing data format conversion on the real-time operation data set to obtain a target operation data set; the data analysis module is used for analyzing the operation state of the target operation data set to obtain the railway operation state; the railway management module is used for generating a management and control strategy of the target heavy haul railway according to the railway operation state; and the railway application module is used for intelligently scheduling the target heavy haul railway according to the management and control strategy. According to the invention, real-time monitoring of the target heavy haul railway can be realized, real-time intelligent scheduling of the target heavy haul railway is carried out, and the transportation efficiency of the target heavy haul railway is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and in particular to a digital heavy-haul railway artificial intelligence device, method, equipment, medium and program. Background Art

[0002] Traditional heavy-haul rail transport is a railway system specially designed to carry large amounts of cargo. It plays a vital role in industry and resource development. This mode of transportation usually involves long-distance, large-volume cargo transportation, such as coal, ore, steel, etc. However, due to its particularity, heavy-haul rail transport faces a series of challenges in scheduling, operation and maintenance.

[0003] However, during operation, the use of heavy-haul railways requires the processing of a large amount of data, such as train operation data, cargo information, equipment status, etc., which are crucial to ensure the safe operation of trains. However, traditional data collection and processing methods often have delays and cannot perform real-time analysis of various data during the operation of heavy-haul railways, resulting in low transportation efficiency of heavy-haul railways and the inability to monitor the operating status of heavy-haul trains in real time.

[0004] Public Content

[0005] The present invention provides a digital heavy-load railway artificial intelligence device, method, equipment, medium and program, which collect multi-source real-time operation data sets of the target heavy-load railway through a data perception module to perform real-time analysis on various data during the operation of the heavy-load railway, thereby improving the efficiency of the data analysis module in analyzing the operation status of the target heavy-load railway; and generate a control strategy through a railway management module, and the railway application module can perform real-time scheduling of the target heavy-load railway according to the control strategy, thereby improving the transportation efficiency of the target heavy-load railway.

[0006] In a first aspect, the present disclosure provides a digital heavy-load railway artificial intelligence device, comprising: a data perception module, used to collect a multi-source real-time operation data set of a target heavy-load railway; an external data interaction module, used to convert the data format of the real-time operation data set to obtain a target operation data set; a data analysis module, used to analyze the operation status of the target heavy-load railway according to the target operation data set to obtain the railway operation status; a railway management module, used to generate a control strategy for the target heavy-load railway according to the railway operation status; and a railway application module, used to perform intelligent scheduling of the target heavy-load railway according to the control strategy.

[0007] In some embodiments, when the external data interaction module performs data format conversion on the real-time operation data set to obtain the target operation data set, it is specifically used to: obtain a preset target data format; match the data conversion rules of the real-time operation data of each data source in the multi-source real-time operation data set according to the data format; extract grammatical commands from the data conversion rules to obtain rule grammatical commands of the data conversion rules; and combine the real-time operation data of each data source according to the rule grammatical commands to obtain the target data set.

[0008] In some embodiments, the data analysis module includes a data preprocessing module, a self-driven algorithm model management module and an AI algorithm module, wherein the data preprocessing module is used to perform data preprocessing on the target operation data set to obtain a standard data set; the self-driven algorithm model management module is used to manage the business algorithm model preset in the data analysis module; the AI ​​algorithm module is used to deploy an AI intelligent algorithm in the data analysis model, and perform data analysis on the standard data set through the AI ​​intelligent algorithm to obtain the railway operation status.

[0009] In some embodiments, when the data analysis module performs an operation status analysis on the target heavy-load railway according to the target operation data set to obtain the railway operation status, it is specifically used to: construct a data feature graph of the target data set, and extract the spatiotemporal characteristics of the target data set according to the data feature graph; and perform an operation status analysis on the target heavy-load railway according to the spatiotemporal characteristics to obtain the railway operation status.

[0010] In some embodiments, when constructing the data feature graph of the target data set, the data analysis module is specifically used to: perform data cleaning and data standardization on the target data set to obtain a standard data set; divide the data source of the standard data set to obtain one-dimensional time series data; and construct a feature matrix based on the one-dimensional time series data to obtain the data feature graph of the target data set.

[0011] In some embodiments, when the data analysis module extracts the spatiotemporal features of the target data set based on the data feature map, it is specifically used to: perform multi-layer convolution on the data feature map to obtain a spatial feature map; perform multi-layer self-attention calculation on the spatial feature map to obtain self-attention features at each level; and perform feature fusion on the self-attention features to obtain spatiotemporal features.

[0012] In a second aspect, the present disclosure provides a digital heavy-haul railway artificial intelligence method, which is applied to the digital heavy-haul railway artificial intelligence device, including: collecting a multi-source real-time operation data set of a target heavy-haul railway, converting the data format of the multi-source real-time operation data set to obtain a target data set; constructing a data feature graph of the target data set, and extracting the spatiotemporal characteristics of the target data set according to the data feature graph; analyzing the operation status of the target heavy-haul railway according to the spatiotemporal characteristics to obtain the railway operation status; and intelligently scheduling the target heavy-haul railway according to the operation status.

[0013] In a third aspect, the present disclosure provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of a digital heavy-load railway artificial intelligence method described in the above aspect.

[0014] In a fourth aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a digital heavy-load railway artificial intelligence method described in the above aspects.

[0015] In a fifth aspect, the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of a digital heavy-load railway artificial intelligence method described in the above aspects.

[0016] The present disclosure provides a digital heavy-load railway artificial intelligence device, method, equipment, medium and program. Through the data perception module, multi-source real-time operation data sets of the target heavy-load railway can be collected, and the data format of the real-time operation data sets can be converted through the external data interaction module to obtain a target operation data set with a unified format, so as to perform real-time analysis on various data in the operation process of the heavy-load railway, thereby improving the efficiency of the data analysis module in analyzing the operation status of the target heavy-load railway; through the railway management module, a control strategy is generated, and the railway application module is used to perform real-time intelligent scheduling of the target heavy-load railway, thereby improving the transportation efficiency of the target heavy-load railway. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The present disclosure will be described in more detail below based on embodiments and with reference to the accompanying drawings:

[0018] Figure 1 A functional module diagram of a digital heavy-load railway artificial intelligence device according to the first embodiment of the present disclosure is shown.

[0019] Figure 2 A schematic diagram showing a flow chart of data format conversion performed by an external data interaction module in Embodiment 1 of the present disclosure;

[0020] Figure 3A schematic diagram showing the flow of a digital heavy-haul railway artificial intelligence method according to a second embodiment of the present disclosure is shown;

[0021] Figure 4 A schematic diagram of the composition structure of an electronic device for implementing the ubiquitous computing resource allocation method according to the fourth embodiment of the present invention is shown.

[0022] In the drawings, the same reference numerals are used for the same components, and the drawings are not drawn to scale. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the technical solution of the present disclosure, and to fully understand and implement how the present disclosure applies technical means to solve technical problems and achieve the corresponding technical effects, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only embodiments of a part of the present disclosure, not all of the embodiments. The embodiments of the present disclosure and the various features in the embodiments can be combined with each other without conflict, and the technical solutions formed are all within the scope of protection of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present disclosure.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0025] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0026] Embodiment 1

[0027] Figure 1 A functional module diagram of a digital heavy-haul railway artificial intelligence device provided by an embodiment of the present disclosure, such as Figure 1As shown, a digital heavy-haul railway artificial intelligence device comprises:

[0028] The data perception module 101 is used to collect multi-source real-time operation data sets of the target heavy-load railway; the external data interaction module 102 is used to convert the data format of the real-time operation data sets to obtain the target operation data sets; the data analysis module 103 is used to analyze the operation status of the target heavy-load railway according to the target operation data sets to obtain the railway operation status; the railway management module 104 is used to generate the control strategy of the target heavy-load railway according to the railway operation status; the railway application module 105 is used to perform intelligent scheduling of the target heavy-load railway according to the control strategy.

[0029] Specifically, the data perception module 101 is the edge perception capability center of the digital heavy-haul railway artificial intelligence system. Sensors can be set on the equipment of the target heavy-haul railway. The edge perception capability center connects the data sensors to the Internet through the industrial Internet of Things technology, and then collects real-time operation data from multiple sources of the target heavy-haul railway to obtain a multi-source real-time operation data set, such as the railway facilities, operating environment, cargo information, train status and other key data of the target heavy-haul railway. The multi-source real-time operation data set is the basis for subsequent analysis and decision-making.

[0030] Furthermore, the data perception module 101 uses cloud native technology plus edge perception access equipment to achieve the overall construction of the IoT perception access capability of the target heavy-load railway, so as to collect multi-source real-time operation data sets of the target heavy-load railway.

[0031] In the disclosed embodiment, the external data interaction module 102 can convert the operation data from different sources in the real-time operation data set into target operation data with a consistent data format, so as to send the target operation data to the data analysis module, thereby completing the interaction between the demand data required by the data analysis module and the external collected data.

[0032] For example, the train speed, quality, energy consumption data, etc. in the real-time operation data set can be in data format; train identification, station name, maintenance record, fault report, etc. may be in text data format; time format data such as timestamp; geographic location longitude and latitude and other geographic spatial data formats as well as real-time operation data in multiple formats such as images and videos. The data format can be unified through the external data interaction module, which is conducive to the operation status analysis of the subsequent data analysis module.

[0033] In the present disclosure, Figure 2 As shown, the external data interaction module 102 includes a target data format module 211 , a data conversion rule matching module 212 , a grammar command extraction module 213 and a data combination module 214 .

[0034] Specifically, when the external data interaction module 102 performs data format conversion on the real-time operation data set to obtain the target operation data set, it is specifically used to:

[0035] The target data format module 211 is used to obtain a preset target data format;

[0036] The data conversion rule matching module 212 is used to match the data conversion rule of each data source real-time operation data in the multi-source real-time operation data set according to the data format;

[0037] The grammar command extraction module 213 is used to extract grammar commands from the data conversion rule to obtain the rule grammar commands of the data conversion rule;

[0038] The data combination module 214 is used to combine the real-time running data of each data source according to the rule grammar command to obtain a target data set.

[0039] Specifically, the target data format is the target data and China's unified data format, such as XML, JSON and other data formats. By matching the corresponding conversion rules of each data source's real-time running data according to the target data format, for example, the corresponding data conversion rules can be matched through rule matching, text language recognition or machine learning automatic identification.

[0040] Furthermore, grammar command extraction is to obtain the keywords or structures used to control the program flow in each rule grammar command. The real-time running data of the data source can be parsed through the rule grammar command to obtain the data to be converted, and the data to be converted can be formed into a target data format text according to the rule grammar command to obtain the target data set to achieve cross-data format conversion, thereby realizing the unification of the data format in the data perception module 101 and the data analysis module 103 in the digital heavy-duty railway artificial intelligence device, and effectively improving the efficiency of data interaction.

[0041] In the disclosed embodiment, the data analysis module 103 is used to analyze the operation status of the target heavy-load railway according to the target operation data set to obtain the railway operation status. Specifically, the data analysis module 103 includes a data preprocessing module, a self-driving algorithm model management module and an AI algorithm module.

[0042] The data preprocessing module is used to preprocess the target operation data set to obtain a standard data set. Specifically, the data preprocessing module is built using mature integrated data resource library technology and deployed in the data analysis module. It can realize the processing, storage, management, and application of the target operation data set, such as data cleaning, data storage into the lake, and data mart.

[0043] The self-driving algorithm model management module is used to manage the business algorithm model preset in the data analysis module 103. Specifically, the self-driving algorithm model management module has a visual management interface and an algorithm model repository, which can manage, modify, and issue the business algorithm model solidified in the system.

[0044] The AI ​​algorithm module is used to deploy the AI ​​intelligent algorithm in the data analysis module 103, and to analyze the standard data set through the AI ​​intelligent algorithm to obtain the railway operation status. Specifically, the AI ​​algorithm module has the functions of developing, training, and managing artificial intelligence algorithms, and can send the trained algorithms to the data perception module 101 or the railway management module 104 through the network to apply the AI ​​intelligent algorithm.

[0045] In the embodiment of the present disclosure, when the data analysis module 103 performs an operation status analysis on the target heavy-haul railway according to the target operation data set to obtain the railway operation status, it is specifically used to:

[0046] Constructing a data feature graph of the target data set, and extracting spatiotemporal features of the target data set according to the data feature graph;

[0047] The operation status of the target heavy-load railway is analyzed according to the spatiotemporal characteristics to obtain the railway operation status.

[0048] Specifically, when constructing the data feature graph of the target data set, the data analysis module 103 is specifically used to:

[0049] Performing data cleaning and data standardization on the target data set to obtain a standard data set;

[0050] Dividing the data source of the standard data set to obtain one-dimensional time series data;

[0051] A feature matrix is ​​constructed according to the one-dimensional time series data to obtain a data feature graph of the target data set.

[0052] In the disclosed embodiment, the target data set includes real-time operation data of data sources corresponding to multiple devices of each target heavy-duty railway. Therefore, the standard data set can be divided into data source data corresponding to each device, and the data source data can be sorted according to time points to obtain one-dimensional time series data. Each one-dimensional time series data is used as a row vector to construct a feature matrix to obtain a data feature graph that characterizes the distribution of the data source data.

[0053] Furthermore, when extracting the spatiotemporal features of the target data set according to the data feature graph, the data analysis module 103 is specifically used to:

[0054] Performing multi-layer convolution on the data feature map to obtain a spatial feature map;

[0055] Performing multi-layer self-attention calculation on the spatial feature map to obtain self-attention features at each level;

[0056] The self-attention features are fused to obtain spatiotemporal features.

[0057] In the disclosed embodiment, a pre-constructed two-layer convolutional layer can be used to extract the spatial features of the data feature map, and an LSTM unit can be used to extract and retain the temporal features to obtain a self-attention feature that includes temporal and spatial features. Self-attention calculations are performed separately through two independent LSTM units to obtain self-attention features of different levels. The self-attention features of different levels are feature fused to more accurately extract the temporal dependency in the spatial feature map and obtain more accurate spatiotemporal features of the target data set.

[0058] Specifically, the operation status analysis can be performed based on the AI ​​algorithm module in the data analysis module 103. For example, the AI ​​algorithm module includes multiple developed and trained operation status algorithms. The specific railway operation status is calculated by calling the operation status algorithm in the AI ​​algorithm module. For example, the status of the signal system is calculated by the signal system status algorithm, and the vehicle status is calculated by the vehicle status algorithm.

[0059] Furthermore, a large amount of target operation data can be processed through the data analysis module 103 to meet the actual needs of the target heavy-load railway. At the same time, various data during the operation of the target heavy-load railway can be analyzed in real time, and the operating status of heavy-load trains can be monitored in real time to improve the overall transportation efficiency. Traffic flow can also be predicted and trains can be intelligently dispatched to ensure that trains run at the best time and path.

[0060] The railway management module 104 is used to generate a control strategy for the target heavy-load railway based on the railway operation status calculated by the data analysis module 103. The railway management module 104 includes multiple management systems, such as a production plan management system, a production safety regulations and system management system, a driving environment risk analysis and early warning system, a driving equipment and facility safety management system, a standardized production execution management system, an emergency management system, an agency collaboration system, an agency data and material supervision management system, and a business and financial integration analysis system. The control strategy for the target heavy-load railway can be formulated through the multiple management systems in the railway application module 104.

[0061] The railway application module 105 is used to perform intelligent scheduling of the target heavy-load railway according to the control strategy. The railway application module 105 includes a production plan management system, a production safety regulations and system management system, a driving environment risk analysis and early warning system, a driving equipment and facility safety management system, a standardized production execution management system, an emergency management system, an agency collaboration system, an agency data and material supervision management system, and a business and financial integration analysis system. The control strategy can be applied to the target heavy-load railway through the railway application module 105 to complete the intelligent scheduling of the target heavy-load railway.

[0062] Embodiment 2

[0063] Figure 3 The following is a flow chart of a digital heavy-haul railway artificial intelligence method provided by the embodiment of the present disclosure. Figure 3 As shown, a digital heavy-haul railway artificial intelligence method includes:

[0064] S1. Collect a multi-source real-time operation data set of a target heavy-haul railway, and convert the data format of the multi-source real-time operation data set to obtain a target data set.

[0065] In the disclosed embodiment, the multi-source real-time operation data set is the real-time operation data of the data sources corresponding to multiple devices of the target heavy-haul railway collected by the data perception module in the digital heavy-haul railway artificial intelligence system, wherein the real-time data of the data source collects the operation data at multiple time points, for example, the real-time operation data of the railway facilities, operating environment, cargo information, train status, etc. of the target heavy-haul railway at multiple consecutive time points, for example, the operation data of 15 time points evenly distributed within 5 seconds are collected.

[0066] In the embodiment of the present disclosure, the data format conversion of the multi-source real-time operation data set to obtain the target data set includes:

[0067] Get the preset target data format;

[0068] Matching a data conversion rule of the real-time operation data of each data source in the multi-source real-time operation data set according to the data format;

[0069] Extracting grammatical commands from the data conversion rule to obtain a rule grammatical command of the data conversion rule;

[0070] The real-time running data of each data source is combined according to the rule grammar command to obtain a target data set.

[0071] Specifically, the target data format is the target data and China's unified data format, such as XML, JSON and other data formats. By matching the corresponding conversion rules of each data source's real-time running data according to the target data format, for example, the corresponding data conversion rules can be matched through rule matching, text language recognition or machine learning automatic identification.

[0072] Furthermore, grammar command extraction is to obtain the keywords or structures used to control the program flow in each rule grammar command. The real-time running data of the data source can be parsed through the rule grammar command to obtain the data to be converted, and the data to be converted can be formed into the target data format text according to the rule grammar command to obtain the target data set to realize cross-data format conversion, thereby realizing the unification of data formats in the data perception module and the data analysis module in the digital heavy-load railway artificial intelligence system, and effectively improving the efficiency of data interaction.

[0073] S2. Construct a data feature graph of the target data set, and extract spatiotemporal features of the target data set according to the data feature graph.

[0074] In the disclosed embodiment, the data feature graph reconstructs a one-dimensional target data set into a two-dimensional feature graph structure, and then the spatial relationship between different data sources in the target data set can be captured according to the two-dimensional feature graph structure.

[0075] In the embodiment of the present disclosure, the step of constructing a data feature graph of the target data set includes:

[0076] Performing data cleaning and data standardization on the target data set to obtain a standard data set;

[0077] Dividing the data source of the standard data set to obtain one-dimensional time series data;

[0078] A feature matrix is ​​constructed according to the one-dimensional time series data to obtain a data feature graph of the target data set.

[0079] In the disclosed embodiment, the target data set includes real-time operation data of data sources corresponding to multiple devices of each target heavy-duty railway. Therefore, the standard data set can be divided into data source data corresponding to each device, and the data source data can be sorted according to time points to obtain one-dimensional time series data. Each one-dimensional time series data is used as a row vector to construct a feature matrix to obtain a data feature graph that characterizes the distribution of the data source data.

[0080] In the embodiment of the present disclosure, extracting the spatiotemporal features of the target data set according to the data feature graph includes:

[0081] Performing multi-layer convolution on the data feature map to obtain a spatial feature map;

[0082] Performing multi-layer self-attention calculation on the spatial feature map to obtain self-attention features at each level;

[0083] The self-attention features are fused to obtain spatiotemporal features.

[0084] In the disclosed embodiment, a pre-constructed two-layer convolutional layer can be used to extract the spatial features of the data feature map, and an LSTM unit can be used to extract and retain the temporal features to obtain a self-attention feature that includes temporal and spatial features. Self-attention calculations are performed separately through two independent LSTM units to obtain self-attention features of different levels. The self-attention features of different levels are feature fused to more accurately extract the temporal dependency in the spatial feature map and obtain more accurate spatiotemporal features of the target data set.

[0085] In the disclosed embodiment, by extracting the spatiotemporal features of the target data set, the spatial and temporal feature relationships between the target data sets can be learned, the data features of the target data sets can be mined at a deeper level, and the accuracy of subsequent operation status analysis can be improved.

[0086] S3. Analyze the operating status of the target heavy-load railway according to the spatiotemporal characteristics to obtain the railway operating status.

[0087] In the disclosed embodiments, the railway operating status refers to the real-time status of a heavy-load train during transportation, reflecting the operating conditions of the train and the various conditions it may face, such as the vehicle status, the running gear status of the train running gear, the status of the signal system, the status of the surrounding environment, the speed status, the fault monitoring status, and other real-time operating status.

[0088] Specifically, the operation status analysis can be performed based on the AI ​​algorithm module included in the data analysis module in the digital heavy-load railway artificial intelligence system. For example, the AI ​​algorithm module includes multiple developed and trained operation status algorithms. The specific railway operation status is calculated by calling the operation status algorithm in the AI ​​algorithm module. For example, the status of the signal system is calculated by the signal system status algorithm, and the vehicle status is calculated by the vehicle status algorithm.

[0089] S4. Intelligently dispatching the target heavy-load railway according to the operating status.

[0090] In the disclosed embodiment, intelligent scheduling is a specific scheduling method for a target heavy-haul railway, and the target heavy-haul railway is controlled through intelligent scheduling.

[0091] In the embodiment of the present disclosure, the intelligent scheduling of the target heavy-haul railway according to the operating status includes:

[0092] Determining a control strategy for the target heavy-haul railway according to the operating status;

[0093] Calculating the similarity between the control strategy and the pre-built scheduling state set;

[0094] A matching scheduling state is determined according to the similarity, and the target heavy-haul railway is scheduled according to the matching scheduling state.

[0095] In the disclosed embodiments, the control strategy is a strategy for central control of the target heavy-load railway, for example, the control strategy for driving environment safety, the control strategy for construction operations, the control strategy for emergency response, the control strategy for enterprise collaboration, the control strategy for enterprise operations, and the control strategy for party building, etc. Through the control strategy, macro-control can be carried out on the driving environment safety, construction operations, emergency response, enterprise collaboration, enterprise operations, and party building of the target heavy-load railway.

[0096] Furthermore, the control strategy of the target heavy-load railway can be determined based on the railway management module in the digital heavy-load railway artificial intelligence device, wherein the railway management module includes AI business algorithms corresponding to the driving environment safety control module, the construction operation control module, the emergency disposal control module, the enterprise collaboration control module, the enterprise operation control module and the party building work control module, which can respectively perform driving environment safety control analysis, construction operation control analysis, emergency disposal control analysis, enterprise collaboration control analysis, enterprise operation control analysis and party building work control analysis according to the operating status to obtain the overall control strategy of the target heavy-load railway.

[0097] Furthermore, the dispatching state set is the control state corresponding to the target heavy-load railway under different control strategies, such as the running time, running path, maintenance status, agency coordination status, etc. of the heavy-load train. More detailed dispatching command is carried out through the control strategy, and then the target heavy-load railway is dispatched. Among them, the similarity between the control strategy and the pre-constructed dispatching state set can be calculated by calculating the feature similarity.

[0098] Furthermore, the control strategies include comprehensive control strategies such as driving environment safety control strategies, construction work control strategies, emergency response control strategies, enterprise collaboration control strategies, enterprise operation control strategies, and party building work control strategies. Among them, each control strategy has a corresponding dispatching status set to carry out comprehensive intelligent dispatching and improve the accuracy of intelligent dispatching of target heavy-load railways.

[0099] Embodiment 3

[0100] On the basis of the above embodiments, in order to more clearly understand the present disclosure, the following further explains the method of the first embodiment of the present disclosure through a third embodiment, where the operation status of the target heavy-load railway needs to be analyzed more quickly according to the spatiotemporal characteristics to obtain the railway operation status, including:

[0101] Performing feature encoding on the spatiotemporal features to obtain encoded features;

[0102] The coding features are fully connected to obtain the railway operation status of the target heavy-haul railway.

[0103] Specifically, the spatiotemporal features can be encoded again through an independent pre-built LSTM (Long Short-Term Memory) network, which can alleviate the forgetting phenomenon and extract important temporal features to obtain more accurate encoding features.

[0104] Furthermore, the coded features are fully connected through the fully connected layer constructed by two convolutional modules, and the coded features are mapped to the feature space corresponding to each operating state to obtain the corresponding railway operating state, wherein the railway operating state may include the railway operating state corresponding to driving environment safety, construction operation control, emergency disposal control analysis, enterprise collaborative control analysis, enterprise operation control analysis and party building work control analysis.

[0105] In the disclosed embodiment, the railway operation status of the target heavy-load railway can be directly calculated through the fully connected layer, thereby improving the efficiency of railway operation status calculation.

[0106] Embodiment 4

[0107] like Figure 4 As shown, this embodiment also provides a computer electronic device, which may include a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a ubiquitous computing resource allocation program.

[0108] Among them, the processor 10 can be composed of an integrated circuit in some embodiments, for example, it can be composed of a single packaged integrated circuit, or it can be composed of multiple integrated circuits packaged with the same function or different functions, including one or more central processing units (CPU), microprocessors, digital processing chips, graphics processors and a combination of various control chips.

[0109] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc.

[0110] The communication bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0111] The communication interface 13 is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices.

[0112] In some implementations of this embodiment, a computer-readable storage medium is provided, on which a computer program is stored, characterized in that when the computer program is executed by a processor, the steps of the method described in the above embodiment are implemented.

[0113] In some implementations of this embodiment, a computer program product is provided, including a computer program / instructions, characterized in that when the computer program is executed by a processor, the steps of the method described in the above embodiment are implemented.

[0114] The processor may include, but is not limited to, one or more processors or microprocessors. Each processor may be an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components to execute the method in the above embodiments.

[0115] The computer-readable storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, and the computer-readable storage medium may include but is not limited to, for example, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, computer storage media (e.g., hard disk, floppy disk, solid-state drive, removable disk, CD-ROM, DVD-ROM, Blu-ray disc, etc.).

[0116] The computer-readable storage medium may also store at least one computer executable program / instruction, which may be, for example, a computer-readable instruction. The computer-readable storage medium includes, but is not limited to, for example, a volatile memory and / or a non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The computer-readable storage medium may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. For example, a non-transitory computer-readable storage medium may be connected to a computing device such as a computer, and then, when the computing device runs the computer-readable instructions stored on the computer-readable storage medium, the various methods described above may be performed.

[0117] In addition, the computer device may also include (but not limited to) a data bus, an input / output (I / O) bus, a display, and input / output devices (eg, keyboard, mouse, speaker, etc.), etc.

[0118] The processor may communicate with external devices via an I / O bus via a wired or wireless network.

[0119] In one embodiment, the at least one computer executable instruction may also be compiled into or constitute a software product / computer program product, wherein one or more computer executable instructions are executed by a processor to perform the various functions and / or method steps in the embodiments described in the present technology.

[0120] In the embodiments provided in the present disclosure, it should be understood that the disclosed systems and methods can also be implemented in other ways. The system embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to the multiple embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the above-mentioned module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes 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 and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0121] It should be noted that in the present disclosure, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element limited by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0122] Although the embodiments disclosed in the present disclosure are as above, the above contents are only embodiments adopted for facilitating the understanding of the present disclosure and are not intended to limit the present disclosure. Any technician in the technical field to which the present disclosure belongs can make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in the present disclosure, but the scope of patent protection of the present disclosure shall still be subject to the scope defined in the attached claims.

Claims

1. A digital heavy-haul railway artificial intelligence device, characterized in that: include: Data perception module, used to collect multi-source real-time operation data sets of target heavy-haul railways; An external data interaction module is used to convert the data format of the real-time operation data set to obtain a target operation data set; A data analysis module, used for analyzing the operation status of the target heavy-haul railway according to the target operation data set to obtain the railway operation status; A railway management module, used for generating a control strategy for the target heavy-load railway according to the railway operation status; The railway application module is used to intelligently dispatch the target heavy-load railway according to the management and control strategy.

2. The digital heavy-haul railway artificial intelligence device according to claim 1 is characterized in that: When the external data interaction module performs data format conversion on the real-time operation data set to obtain the target operation data set, it is specifically used to: Get the preset target data format; Matching a data conversion rule of the real-time operation data of each data source in the multi-source real-time operation data set according to the data format; Extracting grammatical commands from the data conversion rule to obtain a rule grammatical command of the data conversion rule; The real-time running data of each data source is combined according to the rule grammar command to obtain a target data set.

3. The digital heavy-haul railway artificial intelligence device according to claim 1 is characterized in that: The data analysis module includes a data preprocessing module, a self-driving algorithm model management module and an AI algorithm module, wherein: The data preprocessing module is used to perform data preprocessing on the target operation data set to obtain a standard data set; The self-driving algorithm model management module is used to manage the business algorithm model preset in the data analysis module; The AI ​​algorithm module is used to deploy the AI ​​intelligent algorithm in the data analysis model, and to perform data analysis on the standard data set through the AI ​​intelligent algorithm to obtain the railway operation status.

4. The digital heavy-haul railway artificial intelligence device according to claim 1 is characterized in that: When the data analysis module performs an operation status analysis on the target heavy-haul railway according to the target operation data set to obtain the railway operation status, it is specifically used to: Constructing a data feature graph of the target data set, and extracting spatiotemporal features of the target data set according to the data feature graph; The operation status of the target heavy-load railway is analyzed according to the spatiotemporal characteristics to obtain the railway operation status.

5. The digital heavy-haul railway artificial intelligence device according to claim 4 is characterized in that: When constructing the data feature graph of the target data set, the data analysis module is specifically used to: Performing data cleaning and data standardization on the target data set to obtain a standard data set; Dividing the data source of the standard data set to obtain one-dimensional time series data; A feature matrix is ​​constructed according to the one-dimensional time series data to obtain a data feature graph of the target data set.

6. The digital heavy-haul railway artificial intelligence device according to claim 4 is characterized in that: When the data analysis module extracts the spatiotemporal features of the target data set according to the data feature graph, it is specifically used to: Performing multi-layer convolution on the data feature map to obtain a spatial feature map; Performing multi-layer self-attention calculation on the spatial feature map to obtain self-attention features at each level; The self-attention features are fused to obtain spatiotemporal features.

7. A digital heavy-haul railway artificial intelligence method, applied to the digital heavy-haul railway artificial intelligence device, comprising: Collecting a multi-source real-time operation data set of a target heavy-haul railway, and performing data format conversion on the multi-source real-time operation data set to obtain a target data set; Constructing a data feature graph of the target data set, and extracting spatiotemporal features of the target data set according to the data feature graph; Analyzing the operation status of the target heavy-haul railway according to the spatiotemporal characteristics to obtain the railway operation status; The target heavy-load railway is intelligently dispatched according to the operating status.

8. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the digital heavy-haul railway artificial intelligence method described in claim 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, the steps of the digital heavy-haul railway artificial intelligence method described in claim 7 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the digital heavy-haul railway artificial intelligence method described in claim 7 are implemented.

Images