A dispatching operation control system and method based on intelligent analysis of railway dispatching commands

Abstract

The present invention provides a dispatching operation control system and method based on intelligent analysis of railway dispatching orders. The system first performs structural analysis on railway dispatching order data of a set scale to form structured dispatching order data, and gradually trains a dispatching order information analysis model in combination with the railway dispatching order data; receives real-time railway dispatching orders and performs preliminary analysis to generate preliminary analysis data of dispatching orders; then uses the analysis model to identify and obtain the structured dispatching order data of real-time railway dispatching orders, and synthesizes the analysis results with the preliminary analysis data of dispatching orders; then the analysis result verification and upload module outputs the analysis results to the verification personnel, and transmits the real-time dispatching order analysis results to the train dispatching organization information system for calling in combination with the verification result data. The adoption of this solution can overcome the problem that the existing technology relies on manual analysis and is time-consuming, realizes efficient and intelligent analysis of dispatching order information, and provides calling support for operation organization work.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic information analysis application optimization, and in particular to a dispatching operation control system and method based on intelligent analysis of railway dispatching commands. Background Art

[0002] The dispatching order is a written order issued by the railway dispatching center to the grassroots transport stations in order to implement the operation diagram and formation plan, ensure the normal operation of the transportation order, and promptly handle emergencies in the area under its jurisdiction. It is a binding written order to deal with relevant issues in daily train operation in the field of train dispatching, and to organize and command the relevant departments, units and personnel of train operation to handle train operation under abnormal operation conditions, and to instruct the operation methods and safety precautions. It is the basis for the train dispatching departments to handle specific train operation work, and it is the necessary means of command transmission for the train dispatching organization to reliably command train operation and safe production. It is also the basis for examining the process and work quality of the train dispatching organization and command work.

[0003] Since railway dispatching orders (dispatch orders) do not have a specific text format, the issuer of the railway dispatching center uses natural language to describe the order content according to actual needs. Therefore, the train dispatching organization of the recipient needs to understand, identify and apply the dispatching order content. In the prior art, specific staff of the recipient read the received dispatching order information, understand its dispatching content, organize it into corresponding structured dispatching information content, and then manually enter it into the train dispatching organization information system one by one, so that the train operation system can perform dispatching control according to the structured dispatching information. This operation method is relatively cumbersome, time-consuming and labor-intensive, and there are situations where omissions in understanding, errors or abnormal input are likely to occur, and the reliability is insufficient.

[0004] The information disclosed in the background technology section of the present invention is only intended to deepen the understanding of the general background technology of the present invention, and should not be regarded as acknowledging or suggesting in any form that the information constitutes the prior art known to those skilled in the art. Summary of the invention

[0005] In order to solve the above problems, the present invention provides a dispatching operation control system based on intelligent analysis of railway dispatching orders. The use of this solution can overcome the problem that the existing technology relies on manual analysis and is time-consuming, realizes efficient and intelligent analysis of dispatching order information, and provides call support for operation organization work; the system first performs structural analysis on the railway dispatching order data of a set scale to form structured dispatching order data, and obtains a dispatching order information analysis model in combination with the railway dispatching order data training; uses the dispatching order receiving and initial analysis module to receive real-time railway dispatching orders and perform preliminary analysis processing to generate preliminary analysis data of dispatching orders; then uses the analysis model to identify and obtain the structured dispatching order data of the real-time railway dispatching order, and combines the analysis results with the preliminary analysis data of the dispatching order; then the analysis result verification and upload module outputs the analysis results to the verification personnel, and transmits the real-time dispatching order analysis results to the train dispatching organization information system for call in combination with the verification result data. In one embodiment, the system includes:

[0006] A parsing model progressive training module, which is configured to perform structural parsing processing and assign labels based on railway dispatching order data that meets a set scale to form structured dispatching order data, and train a large language model based on the railway dispatching order data and the structured dispatching order data as a dispatching order information parsing model;

[0007] The dispatch order receiving and initial analysis module is configured to maintain continuous communication with the railway dispatching center system, receive real-time railway dispatching orders and perform initial analysis processing to generate dispatch order initial analysis data in a unified format;

[0008] A dispatch order data parsing module, which is configured to perform parsing and identification based on the preliminary parsing data of the dispatch order of the real-time railway dispatch order using the dispatch order information parsing model, obtain structured dispatch order data of the real-time railway dispatch order, and combine it with the preliminary parsing data of the dispatch order as the real-time dispatch order parsing result;

[0009] The analysis result verification and upload module is configured to output the real-time dispatch order analysis results to the verification personnel, and to detect the verification results from the verification personnel in real time, and to transmit the real-time dispatch order analysis results to the train dispatching organization information system for call in combination with the verification result data.

[0010] Furthermore, in one embodiment, the system also includes: a data post-processing module, which is configured to identify time attribute data in the structured order data, and then determine whether the time attribute data is in a compressed form. If so, the compressed time attribute data is restored to a complete and independent form, and the structured order data is updated.

[0011] Optionally, in one embodiment, the analytical model progressive training module includes a basic labeling processing unit and a model automatic training unit;

[0012] The basic labeling processing unit is configured to receive structured dispatch order data manually identified at a set scale, wherein the structured dispatch order data is formed by corresponding staff identifying the structure type of the data content field in each railway dispatch order, and then associating and recording each structure type and its data content field and using a set identifier interval;

[0013] The model automatic training unit is configured to train the large language model based on the railway dispatching commands and corresponding structured dispatching order data after manual labeling to obtain a first intermediate parsing model.

[0014] Furthermore, in one embodiment, the analytical model progressive training module further includes a model labeling processing unit and a labeling verification unit;

[0015] The model labeling processing unit is configured to use the intermediate analytical model to identify the unlabeled railway dispatching order and obtain the corresponding structured dispatching order data as the first intermediate model analysis result;

[0016] The label verification unit outputs the intermediate model analysis result and the corresponding railway dispatching command, which are manually verified and corrected for accuracy, and receives the verification result and the corrected analysis result fed back by the manual;

[0017] When the verification result does not meet the set conditions, the corrected parsing result is used as the structured order data of the current railway dispatch order, and is combined with the previously labeled structured order data and railway dispatching orders as training samples. The model automatic training module is re-enabled to further train the current large language model to obtain a second intermediate parsing model, and the model labeling processing unit is repeatedly enabled to identify and manually verify a new batch of railway dispatching orders, and the cycle is executed until the verification result meets the set requirements or all data are labeled, and the corresponding intermediate parsing model is used as the order information parsing model.

[0018] In an optional embodiment, the dispatch order receiving and initial parsing module divides the entire railway dispatch order into 8 data information items for display respectively, and the 8 items are the date of order issuance, time of order issuance, dispatch order number, issuer, bureau, recipient, receiving time and order sub-items and their data contents;

[0019] The command sub-items include natural language descriptions of the contents of multiple scheduling instructions in the scheduling command.

[0020] Preferably, in one embodiment, the analysis result verification and upload module is configured as follows:

[0021] If a result that passes the representation verification is detected, the corresponding real-time dispatch order analysis result will be automatically transmitted to the train dispatching organization information system. Otherwise, the real-time dispatch order analysis result will be corrected in response to the feedback instructions from the verification personnel, or the dispatch order data analysis module and the analysis data post-processing module will be restarted to operate, and output to the verification personnel again until a result that passes the representation verification is detected.

[0022] Furthermore, in one embodiment, the parsed data post-processing module is also configured to identify the train type data in the structured dispatch order data, and then determine whether the train type data is a combined abbreviated mode. If so, further determine whether the train represented by the train type data in the combined abbreviated mode is the same train based on the train operation vehicle information database; if it is not the same train, the train type data in the combined abbreviated mode is split into fractional train forms and the structured dispatch order data is updated.

[0023] Preferably, in one embodiment, the system further comprises:

[0024] The operation table synchronization update module is configured to compare and analyze whether the basic operation timetable data contains the train operation data in the structured dispatch order data. If not, the train operation data in the structured dispatch order data is added to the basic operation timetable data.

[0025] Furthermore, in one embodiment, the system further comprises:

[0026] The correlation identification and plan generation module is configured to determine whether the current real-time railway dispatching command is correlated with the operation plan of the current station based on the structured dispatching order data. If so, a temporary plan guiding the operation of the current station train is generated by integrating the structured dispatching order data of the real-time railway dispatching command and the basic operation timetable of the current station; otherwise, no temporary plan is generated.

[0027] In an optional embodiment, the relevance identification and plan generation module is provided with a relevance identification unit, which identifies whether a certain real-time railway dispatching command data is relevant to the operation of the current station according to the following logic:

[0028] One or more associated keywords are set around the operation field of the current station as station-related words; the associated keywords include one or more valid identification fields of the current station or one or more available identification fields of adjacent stations that inevitably lead to passing through the current station;

[0029] For the train numbers in its structured dispatch data, the train numbers are retrieved one by one according to the basic operation timetable, and the stop station information of each train number is analyzed. A traversal comparison is performed to analyze whether any of the station-related words exists. If so, it is identified as being related to the operation of the current station.

[0030] Furthermore, in one embodiment, the correlation identification and plan generation module is provided with a plan generation unit, which is configured to generate a temporary plan for guiding the operation of trains at the current station according to the following logic:

[0031] Identify whether the current real-time railway dispatching order is a suspension order. If not, directly generate a temporary operation plan for the current station based on the structured dispatching order data;

[0032] If so, the suspension interval corresponding to the suspended train is further identified based on the structured dispatch order data, and the operation information of the suspended train is identified in combination with the basic operating timetable. It is analyzed whether the suspension interval described in the dispatch order contains words related to the current station to determine whether this station is in the suspension interval. If it is in the suspension interval, a temporary suspension plan for the current station is generated. If it is not in the suspension interval, the sequence position of the current station relative to the suspension interval is identified, and a temporary plan for changing the terminal or departure of the current station is generated according to the sequence position.

[0033] Based on the application aspects of the system described in any one or more of the above embodiments, the present invention also provides a dispatching operation control method based on intelligent analysis of railway dispatching commands, which is applied to the system described in any one or more of the above embodiments.

[0034] Based on other aspects of the method described in the above embodiments, the present invention further provides a storage medium storing program codes that can implement the method described in the above embodiments.

[0035] Compared with the closest prior art, the present invention also has the following beneficial effects:

[0036] The present invention provides a dispatching operation control system and method based on intelligent analysis of railway dispatching orders. The system is provided with a parsing model progressive training module, which performs structural analysis processing based on railway dispatching order data of a set scale to form structured dispatching order data, and trains a large language model as a dispatching order information analysis model based on the railway dispatching order data and the structured dispatching order data; the large language model is trained based on the structured dispatching order data of a large number of railway dispatching order samples as the dispatching order information analysis model, so as to ensure the reliability of the model function and have the ability to accurately convert the original dispatching order content into a labeled representation;

[0037] The dispatch order receiving and initial analysis module is used to receive the real-time railway dispatch order and perform preliminary analysis and processing to generate preliminary analysis data of the dispatch order; then the dispatch order information analysis model is used to analyze and identify, obtain the structured dispatch order data of the real-time railway dispatch order, and synthesize the analysis results with the preliminary analysis data of the dispatch order; then the analysis result verification and upload module outputs the analysis results to the verification personnel, and transmits the real-time dispatch order analysis results to the train dispatch organization information system for call in combination with the verification result data. It realizes efficient and intelligent analysis of dispatch order information, does not need to frequently rely on the understanding and identification of operators, and provides an efficient and reliable call basis for operation organization work. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0039] Figure 1 It is a structural schematic diagram of a dispatching operation control system based on intelligent analysis of railway dispatching commands provided by an embodiment of the present invention;

[0040] Figure 2 It is a schematic diagram of the operation logic of the right item management component of the dispatching operation control system based on the intelligent analysis of railway dispatching commands provided in an embodiment of the present invention;

[0041] Figure 3 It is a flow chart of a dispatching order data parsing module in a dispatching operation control system based on intelligent parsing of railway dispatching orders provided in an embodiment of the present invention;

[0042] Figure 4 This is an example diagram of the interface display of a component for confirming parsing results in a dispatching operation control system based on intelligent parsing of railway dispatching commands provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The following will describe the implementation methods of the present invention in detail in conjunction with the accompanying drawings and embodiments, so that the implementers of the present invention can fully understand how the present invention applies technical means to solve technical problems and achieve the implementation process of technical effects and implement the present invention specifically according to the above implementation process. It should be noted that as long as there is no conflict, the various embodiments and various features of the embodiments in the present invention can be combined with each other, and the technical solutions formed are all within the protection scope of the present invention.

[0044] Although the flowcharts describe the operations as sequential processes, many of the operations may be performed in parallel, concurrently, or simultaneously. The order of the operations may be rearranged. A process may be terminated when its operations are completed, but may also have additional steps not included in the accompanying drawings. A process may correspond to a method, function, procedure, subroutine, subprogram, etc.

[0045] Computer devices include user devices and network devices. Among them, user devices or clients include but are not limited to computers, smart phones, PDAs (Personal Digital Assistants), etc.; network devices include but are not limited to a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of computers or network servers. Computer devices can be run alone to implement the present invention, or they can be connected to the network and implement the present invention through interactive operations with other computer devices in the network. The network where the computer device is located includes but is not limited to the Internet, wide area network, metropolitan area network, local area network, VPN network, etc.

[0046] The terms "first", "second", etc. may be used herein to describe various units, but these units should not be limited by these terms, and these terms are used only to distinguish one unit from another unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items. When a unit is referred to as being "connected" or "coupled" to another unit, it can be directly connected or coupled to the other unit, or there can be intermediate units.

[0047] The terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments. Unless the context clearly indicates otherwise, the singular forms "one", "one" and "item" used herein are also intended to include plural numbers. It should also be understood that the terms "include" and / or "comprise" used herein specify the existence of stated features, integers, steps, operations, units and / or components, without excluding the existence or addition of one or more other features, integers, steps, operations, units, components and / or combinations thereof.

[0048] The dispatching order is a written order issued by the railway dispatching center to the grassroots transport stations in order to implement the operation diagram and formation plan, ensure the normal operation of the transportation order, and promptly handle emergencies in the area under its jurisdiction. The dispatching order refers to the binding written instructions issued in the field of train dispatching to deal with relevant issues in daily train operation, as well as to organize and command the relevant departments, units and personnel of train operation to handle train operation under abnormal operation conditions, and to instruct the operation methods and safety precautions. It is the basis for the specific handling of train operation by the train dispatching departments, and is the necessary means of command transmission for the train dispatching organization to reliably command train operation and safe production. It is also one of the bases for examining the process and work quality of the train dispatching organization and command work.

[0049] Usually, the issuance of a railway dispatching order (transfer order) marks the issuance of a dispatching order, and the issuance process of this dispatching order is regarded as a successful transfer at the legal level.

[0050] Since the dispatch order has no specific text format, the sender of the railway dispatching center uses natural language to describe the command content according to actual needs. Therefore, the receiving party's train dispatching organization needs to understand, identify and apply the dispatch order content. In the prior art, a specific receiving party's staff reads the received dispatch order information, understands its dispatch content, organizes it into corresponding structured dispatch information content, and then manually enters it into the train dispatching organization information system one by one, so that the train operation system can perform dispatching control according to the structured dispatch information. This operation method is relatively cumbersome, time-consuming and labor-intensive, and there are situations where omissions in understanding, errors or abnormal input occur, and the reliability is insufficient.

[0051] To solve the above problems, the present invention provides a dispatching operation control system and method based on intelligent analysis of railway dispatching orders. The system automatically performs intelligent analysis and understanding of the dispatching order information content based on a large language model, and autonomously generates effective structured representation dispatching information commonly used in train operation organization systems. In the entire process, only the final order-receiving staff needs to confirm before the information can be automatically entered into the train dispatching organization information system. The system is easy to operate, has a high execution rate, and has high analysis reliability.

[0052] Next, the structural components, connection modes and functional principles of the system of the embodiment of the present invention are described in detail based on the drawings. Although the logical order of each operation is shown in the process of describing the operating principle of the system structure, in some cases, the operations shown or described can be performed in a different order than here.

[0053] Embodiment 1:

[0054] Figure 1 FIG. 1 shows a schematic diagram of a dispatching operation control system based on intelligent analysis of railway dispatching commands provided in Embodiment 1 of the present invention, with reference to FIG. Figure 1It can be seen that the system includes:

[0055] A parsing model progressive training module, which is configured to perform structural parsing processing and assign labels based on the railway dispatching order data that meets the set scale conditions to form structured dispatching order data, and train a large language model based on the railway dispatching order data and the structured dispatching order data as a dispatching order information parsing model;

[0056] The dispatch order receiving and initial analysis module is configured to maintain continuous communication with the railway dispatching center system, receive real-time railway dispatching orders and perform initial analysis processing to generate dispatch order initial analysis data in a unified format;

[0057] A dispatch order data parsing module, which is configured to perform parsing and identification based on the preliminary parsing data of the dispatch order of the real-time railway dispatch order using the dispatch order information parsing model, obtain structured dispatch order data of the real-time railway dispatch order, and combine it with the preliminary parsing data of the dispatch order as the real-time dispatch order parsing result;

[0058] The analysis result verification and upload module is configured to output the real-time dispatch order analysis results to the verification personnel, and to detect the verification results from the verification personnel in real time, and to transmit the real-time dispatch order analysis results to the train dispatching organization information system for call in combination with the verification result data.

[0059] If a result that passes the representation verification is detected, the corresponding real-time dispatch order analysis result will be automatically transmitted to the train dispatching organization information system. Otherwise, the real-time dispatch order analysis result will be corrected in response to the feedback instructions from the verification personnel, or the dispatch order data analysis module and the analysis data post-processing module will be restarted to operate, and output to the verification personnel again until a result that passes the representation verification is detected.

[0060] Taking into account the nature and processing efficiency of labeling processing, the present invention arranges the labeling processing unit to adopt a method combining manual and analytical models to realize progressive structural analysis and model training of massive railway dispatching commands; in an optional embodiment, the analytical model progressive training module includes a basic labeling processing unit, a model automatic training unit, a model labeling processing unit and a labeling verification unit.

[0061] Firstly, based on the railway dispatching order data that meets the set scale conditions, a set proportion of railway dispatching order objects are randomly selected, and their structure types are manually identified and labeled to form structured dispatching order data;

[0062] The basic labeling processing unit is configured to receive structured dispatch order data manually identified at a set scale, wherein the structured dispatch order data is formed by corresponding staff identifying the structure type of the data content field in each railway dispatch order, and then associating and recording each structure type and its data content field and using a set identifier interval;

[0063] The dispatch order structure type database is a data content field object of all possible structure types formed based on comprehensive historical railway dispatch order record statistics, and a single structure type corresponds to one or more data content fields.

[0064] For example, in an optional embodiment, for a railway dispatching order, the original dispatching order content is as follows.

[0065] "On February 13, 17, 21, 25 and 29, 2024, additional trains Z308 / 9 will be added between Qiqihar and Shenzhen East.

[0066] An additional Z310 / 07 train will be added between Shenzhen East and Qiqihar on February 15, 19, 23, 27 and March 2, 2024.

[0067] Marshalling: Z308 / 9 train departing from Qiqihar, with YZ1 (118), YZ1 (106), YZ1 (Ban 106), CA1, RW1 (36), YW1 (Guang 57), YW3 (57), YW6 (66), YW1 (Su), a total of 16 cars, serial numbers 1-16.

[0068] The labeling processing unit identifies the structural type of each part of the data content field, associates and records each structural type and its data content field, and uses a set identifier interval to obtain the structured command data after labeling processing as follows.

[0069] "Structure type data content field

[0070] Dispatch type: Additional trips

[0071] Date: 2024-02-13,17,21,25,29

[0072] Train No.: Z308 / 9 Qiqihar-Shenzhen East

[0073] Date: 2024-02-15,19,23,27,03-02

[0074] Train No.: Z310 / 07 Shenzhen East - Qiqihar

[0075] Train formation: YZ1 (118), YZ1 (106), YZ1 (Office 106), CA1, RW1 (36), YW1 (Guang 57), YW3 (57), YW6 (66), YW1 (Suzhou)

[0076] Number of carriages: 16

[0077] Carriage order: 1-16”.

[0078] Based on this, the labeled railway dispatching orders and the corresponding structured dispatching order data are used as training samples to train the established large language model and obtain the intermediate parsing model.

[0079] Therefore, in one embodiment, the model automatic training unit is configured to train a large language model based on the railway dispatching commands and corresponding structured dispatching order data after manual labeling to obtain a first intermediate parsing model.

[0080] The intermediate analytical model obtained at this time has certain analytical capabilities, but there is room for improvement in reliability.

[0081] Furthermore, the model labeling processing unit is configured to use the intermediate parsing model to identify the unlabeled railway dispatching commands and obtain corresponding structured dispatching order data as the first intermediate model parsing result.

[0082] Based on this, the labeling verification unit outputs the intermediate model parsing result and the corresponding railway dispatching command, which are manually verified and corrected for accuracy, and the manually fed back verification result and the corrected parsing result are received; when the verification result does not meet the set conditions, the corrected parsing result is used as the structured dispatching order data of the current railway dispatching order, and is combined with the previously labeled structured dispatching order data and railway dispatching command as a training sample, and the model automatic training module is re-enabled to further train the current large language model to obtain a second intermediate parsing model, and the model labeling processing unit is repeatedly enabled to identify and manually verify a new batch of railway dispatching commands, and the cycle is executed until the verification result meets the set requirements or all data are labeled, and the corresponding intermediate parsing model is used as the dispatching order information parsing model.

[0083] In actual application, for example, firstly, a part of the collected massive transfer order data, such as 10% of the transfer order data, is randomly selected for manual analysis and annotation; the large language model is trained with these annotated data to obtain an intermediate analysis model A, so that it has a certain analysis ability; further, the intermediate analysis model A is used to automatically parse a part of the remaining unlabeled data in the transfer order data, such as 10% of the transfer order data, and the analysis data is manually checked, the error rate is counted, and the erroneous analysis results are modified to the expected correct results; based on this, the above-mentioned annotated data are merged and the model is trained to obtain the intermediate model B, so that its analysis ability is enhanced; the above-mentioned operations are repeated until the error rate is lower than the set condition or all the data are labeled, for example, the error rate of the output result is lower than 0.01%, then the training can be stopped to obtain the final model.

[0084] The above method can significantly reduce the workload of manual labeling, while ensuring that the recognition accuracy of the dispatch order information parsing model is improved layer by layer.

[0085] After labeling a large number of railway dispatch orders, the large language model is fine-tuned and optimized with the data content of the original dispatch order as input and the structured data content of the labeled representation as output, so that it has the ability to convert the original dispatch order content into labeled representation. After the optimization training is completed, for the new railway dispatch order received, the preliminary parsed command items are input into the fine-tuned and optimized large language model, which can reliably parse and obtain the labeled data content representation corresponding to the command item.

[0086] Among them, the large language model described in the embodiments of the present invention is essentially a text-to-text transformer, that is, its input and output are both in text format, and different types of data are read and recognized as text formats. Therefore, the model itself has the ability to be compatible with various data formats; for example, in the data annotation process, there is a rule in the output format of each field, such as the "capacity" field, whose annotations are all numbers. In the process of training a large amount of data, the model will master this rule, and when outputting the "capacity" field, it is more inclined to output digital content.

[0087] Railway dispatching instructions often need to record multiple functional attribute data, such as the time of issuance and the issuer. The preliminary parsing data of the dispatching order is mainly divided and processed according to the number of types of functional attributes contained in the railway dispatching instructions, and decomposed into different functional attributes and data contents for separate presentation.

[0088] Therefore, in actual application, the real-time railway dispatching command is received and initially parsed through the dispatching order receiving and initial parsing module to generate dispatching order initial parsing data in a unified format.

[0089] Specifically, in one embodiment, for a railway dispatching instruction containing multiple functional attribute data such as the date of issuance, the time of issuance, the transfer order number, the issuer, the bureau, the recipient, the receiving time and the sub-items of the order, the entire railway dispatching instruction is divided into multiple data information and displayed separately through preliminary parsing processing, for example, divided into 8 data information, namely the date of issuance, the time of issuance, the transfer order number, the issuer, the bureau, the recipient, the receiving time and the sub-items of the order and their data contents;

[0090] Among them, command sub-items refer to multiple scheduling instruction contents in a scheduling command, which is a natural language description of the original text of the scheduling command.

[0091] Furthermore, the preliminary parsing data of the dispatch order based on the real-time railway dispatching order is parsed and identified using the dispatch order information parsing model to obtain structured dispatch order data of the real-time railway dispatching order, which is combined with the preliminary parsing data of the dispatch order as the real-time dispatch order parsing result.

[0092] For each command item obtained after the preliminary parsing process, the item data is input into the dispatch order information parsing model, and the command item is classified using the "command classification function control" Prompt to parse out the structure type described by the item, such as "additional train runs", "suspended train runs", etc., and the parsed structure type and the corresponding command data content field are output; wherein the structure type has been collected in advance as an order structure type database, covering the information structure types of all common railway dispatching commands; when the structure type is known, which data content field information should be extracted for the structure type is determined accordingly; therefore, the structured information representation corresponding to the real-time railway dispatch order can be output through the dispatch order information parsing model processing.

[0093] When the content of a certain command item does not contain a known scheduling command structure type, the scheduling command parsing module will output a prompt message of "cannot be classified".

[0094] In actual application, the order data analysis module can be configured as a software program function module. In an optional embodiment, the order data analysis module is provided with a variety of targeted functional components, including at least: import order / import telegram component, order sub-item analysis component, confirm analysis result component (modify analysis result, add analysis result), submit analysis result component, delete analysis result component, keyword / related word configuration component.

[0095] Furthermore, in order to facilitate the staff to optimize and adjust the parsing result content according to the needs, the dispatch order data parsing module is also configured with an editing parsing result component; wherein the staff is a user who meets the set operation authority. In an optional embodiment, the user management and right management functions are configured as a configuration management component of the system.

[0096] When the user starts the management and control system of the embodiment of the present invention, the user enters the login page. In an optional embodiment, it can be set that after the correct user name and password are entered, the user successfully logs in and enters the operation diagram (basic diagram) management page, such as Figure 2 As shown, it is convenient for users to intuitively understand the latest train operation information.

[0097] The logic for making a claim authentication decision is as follows:

[0098] 1. The user clicks the "Login" button to verify the username and password. If both are correct, the login is considered successful;

[0099] 2. If the user name is incorrect, the system prompts "Account does not exist"; if the password is incorrect, the system prompts "Wrong password, please re-enter", and stays on the current page; if the login is successful, enter the basic map management page; the operation process of the command data analysis module is as follows Figure 3 shown.

[0100] Confirm the parsing result component page display effect example as follows Figure 4 shown.

[0101] The operation logic of the component to confirm the parsing result is as follows:

[0102] 1. On the page for confirming the analysis results, basic information is displayed at the top: transfer order date, number, and analysis completion time.

[0103] 2. Display the dispatch order data related to the station and the dispatch order data not related to the station respectively. The basis for judging whether it is related is: if there is a related train number in the basic map, or if the dispatch order mentions and matches the preset keywords, it is considered related. The system automatically switches the dispatch order items between the "related" and "irrelevant" lists according to the train number information and station information adjusted by the user when modifying the parsing results.

[0104] 3. In the parsed content, the first column displays the item number, the second column displays the original text of the order, the third column displays the parsed operation type, the fourth column displays the parsed result, the fifth column displays the expected accuracy, and the results of different accuracy are marked with corresponding icons. The sixth column displays the checkbox, and the corresponding contents in the second and fourth columns are marked with the same color. Optionally, hovering the mouse over the text will highlight and enlarge it, and it will return to its original size after the mouse is moved away, for easy comparison.

[0105] 4. Users can add, modify, and delete analysis results.

[0106] In addition, considering that the parsing result of the dispatch order information after real-time railway dispatch order parsing and identification may be significantly different from the original dispatch order content, and when multiple real-time railway dispatching commands are involved in the system at the same time, the operator has the need to compare and review the parsing result with the original dispatch order content synchronously. Therefore, in a preferred embodiment, the dispatch order data parsing module is also provided with a parsing result comparison and viewing component, a simulation action result component and a view all action result component.

[0107] In order to improve the output speed of the large language model, when labeling large-scale historical railway dispatch order data, some data is usually compressed without affecting the information representation. For example, the date part is compressed as follows:

[0108] "2024-02-15, 19, 23, 27, 03-02".

[0109] The system also includes a data parsing post-processing module, which is configured to identify time attribute data in the structured order data, and then determine whether the time attribute data is in compressed form. If so, the compressed time attribute data is restored to a complete and independent form, and the structured order data is updated. Otherwise, the content of the structured order data is not interfered with.

[0110] Correspondingly, the analysis result verification and upload module outputs the real-time dispatch order analysis results updated by the analysis data post-processing module to the verification personnel, and detects the verification results from the verification personnel in real time, and transmits the real-time dispatch order analysis results combined with the verification result data to the train dispatching organization information system for call.

[0111] The data post-processing module can identify the compressed date information in the above text and restore it to a complete independent date representation, as shown in the following example:

[0112] "2024-02-15, 2024-02-19, 2024-02-23, 2024-02-27, 2024-03-02".

[0113] The parsed data post-processing module is also configured to identify the train type data in the structured dispatch order data, and then determine whether the train type data is a combined abbreviated mode. If so, further determine whether the train represented by the train type data in the combined abbreviated mode is the same train based on the train operation vehicle information database; otherwise, no further processing is performed; if it is not the same train, the train type data in the combined abbreviated mode is split into fractional train forms and the structured dispatch order data is updated. If it is the same train, the original form is maintained; for example: Z308 / 9.

[0114] The train number it actually represents is Z308 / Z309. It is necessary to check in the basic operation timetable whether Z308 and Z309 are the same train number. If they are not the same train number, they need to be split into two train numbers for processing.

[0115] Each time the operation diagram is adjusted, the operation dispatching organization system will generate official basic operation timetable data based on the data of each operation diagram adjustment to provide support for the execution of train dispatching.

[0116] Preferably, in one embodiment, the system also includes an operation table synchronization update module, which is configured to compare and analyze whether the basic operation timetable data contains the train operation data in the structured dispatch order data. If not, the train operation data in the structured dispatch order data is added to the basic operation timetable data.

[0117] In a preferred embodiment, the added train number data is split into fractional train number data.

[0118] Furthermore, considering that when the train involved in the dispatch order is related to the train operation of the current station, for example, passing through the current station (including only passing through the line section of the current station and stopping at the station to pick up passengers), the operation dispatch organization needs to make adaptive adjustments to the work arrangement, and the general dispatch order will not mention all the stations of the train. In order to better reduce the analysis work of subsequent operators, in a preferred embodiment, the system also includes:

[0119] The correlation identification and plan generation module is configured to determine whether the current real-time railway dispatching command is correlated with the operation plan of the current station based on the structured dispatching order data. If so, a temporary plan guiding the operation of the current station train is generated by integrating the structured dispatching order data of the real-time railway dispatching command and the basic operation timetable of the current station; otherwise, no temporary plan is generated.

[0120] The correlation identification and plan generation module is provided with a correlation identification unit, which identifies whether a certain real-time railway dispatching command data is correlated with the operation of the current station according to the following logic.

[0121] One or more associated keywords are set around the operation field of the current station as station-related words; the associated keywords include one or more available identification fields of the current station or one or more available identification fields of neighboring stations that inevitably lead to passing through the current station.

[0122] For the train numbers in its structured dispatch data, the train numbers are retrieved one by one according to the basic operation timetable, and the stop station information of each train number is analyzed. A traversal comparison is performed to analyze whether any of the station-related words exists. If so, it is identified as being related to the operation of the current station.

[0123] In actual application, if it is a suspension order, different temporary plans may need to be set according to the suspension interval; therefore, further, the correlation identification and plan generation module is provided with a plan generation unit, which is configured to generate a temporary plan guiding the operation of the current station train according to the following logic:

[0124] Identify whether the current real-time railway dispatching order is a suspension order. If not, directly generate a temporary operation plan for the current station based on the structured dispatching order data;

[0125] If so, the suspension interval corresponding to the suspended train is further identified based on the structured dispatch order data, and the operation information of the suspended train is identified in combination with the basic operating timetable. It is analyzed whether the suspension interval described in the dispatch order contains words related to the current station to determine whether this station is in the suspension interval. If it is in the suspension interval, a temporary suspension plan for the current station is generated. If it is not in the suspension interval, the sequence position of the current station relative to the suspension interval is identified, and a temporary plan for changing the terminal or departure of the current station is generated according to the sequence position.

[0126] Specifically, for the suspension order and the train numbers in its structured order data, the train numbers are retrieved one by one according to the basic operation timetable, and based on the suspension interval described in the order, it is determined whether the station is within the suspension interval. If it is within the suspension interval, it is treated as suspended. If not, it is treated as changed to the final destination or changed to the starting point based on whether the station is before or after the suspension interval.

[0127] In actual application, the processing logic of the above embodiment can be applied to any other station with operation scheduling requirements.

[0128] In an optional embodiment, a temporary plan for station dispatching operation is generated according to the set information distribution format according to the demand, for example, the information distribution format of the temporary plan is set to include at least the following plan information items:

[0129] Train number, station number, up and down line, grade, starting station, final station, arrival time, departure time, track, running relationship, vehicle type, car bottom, positive and negative marshaling, number of marshalings, marshaling details, passing through, water supply, sewage suction, luggage, high-speed rail express, total capacity, business seat, special seat, first class seat, second class seat, soft sleeper, hard sleeper, first class soft seat, second class soft seat, hard seat, prohibited from sale, other (remarks), start date, end date, operation pattern, operation cycle, route number, waiting room, ticket gate.

[0130] In a preferred embodiment, the structured parsing results, updated basic operation schedule and formatted temporary schedule files generated by the system of this aspect support operator viewing, multi-table data synchronous comparison viewing and format-preserving export. Therefore, the system is provided with corresponding viewing components, multi-file synchronous scrolling comparison viewing components and export components.

[0131] Based on the above embodiment, corresponding temporary plan information can be generated in advance for a real-time railway dispatching command and related stations, and uploaded to the information system of the train operation dispatching organization together with the analysis results of the railway dispatching instructions, which is convenient for staff to call. On the basis of ensuring the reliability of dispatching command data processing, the business that requires manual analysis and post-processing is greatly reduced, which can provide strong support for the optimization of railway operation dispatching.

[0132] In the dispatching operation control system based on intelligent analysis of railway dispatching commands provided by the embodiment of the present invention, each module or unit structure can operate independently or in combination according to actual model training requirements and information recognition requirements to achieve corresponding technical effects.

[0133] Embodiment 2:

[0134] The system is described in detail in the embodiments disclosed in the above invention. Based on other aspects of the system described in any one or more embodiments, the present invention also provides a dispatching operation control method based on intelligent parsing of railway dispatching commands, which is applied to the dispatching operation control system based on intelligent parsing of railway dispatching commands described in any one or more embodiments. Specific embodiments are given below for detailed description.

[0135] Specifically, the dispatching operation control method based on intelligent analysis of railway dispatching commands provided in the embodiment of the present invention includes:

[0136] The analytical model progressive training step: based on the analytical model progressive training module, the railway dispatching order data that meets the set scale is subjected to structural analysis and labeling to form structured dispatching order data, and a large language model is trained according to the railway dispatching order data and the structured dispatching order data as the dispatching order information analysis model;

[0137] Order receiving and initial analysis step: through the order receiving and initial analysis module, the real-time railway dispatching order is received and initially analyzed and processed to generate the initial analysis data of the order in a unified format;

[0138] The dispatch order data parsing step: using the dispatch order data parsing module to perform parsing and identification based on the dispatch order preliminary parsing data of the real-time railway dispatch order using the dispatch order information parsing model, to obtain the structured dispatch order data of the real-time railway dispatch order, and to combine it with the dispatch order preliminary parsing data as the real-time dispatch order parsing result;

[0139] Verification and upload steps: The analysis result verification and upload module outputs the real-time dispatch order analysis results to the verification personnel, and detects the verification results from the verification personnel in real time. Combined with the verification result data, the real-time dispatch order analysis results are transmitted to the train dispatching organization information system for call.

[0140] Furthermore, in one embodiment, the method further comprises:

[0141] Parsed data post-processing step: The parsed data post-processing module identifies the time attribute data in the structured call order data, and then determines whether the time attribute data is in a compressed form. If so, the compressed time attribute data is restored to a complete and independent form, and the structured call order data is updated.

[0142] Optionally, in one embodiment, the analytical model progressive training step includes:

[0143] Basic labeling processing steps: receiving structured dispatch order data manually identified at a set scale, wherein the structured dispatch order data is formed by corresponding staff identifying the structure type of the data content field in each railway dispatch order, and then associating and recording each structure type and its data content field and using a set identifier interval;

[0144] Automatic model training steps: Based on the manually labeled railway dispatching commands and the corresponding structured dispatching command data, the large language model is trained to obtain the first intermediate parsing model.

[0145] Furthermore, in one embodiment, the analytical model progressive training step further includes:

[0146] Model labeling processing step: using the intermediate analytical model to identify the unlabeled railway dispatching order, and obtaining the corresponding structured dispatching order data as the first intermediate model analysis result;

[0147] Label verification step: outputting the intermediate model analysis results and the corresponding railway dispatching commands, manually verifying and correcting the accuracy, and receiving the verification results and corrected analysis results fed back by the manual staff;

[0148] When the verification result does not meet the set conditions, the corrected parsing result is used as the structured order data of the current railway dispatch order, and is combined with the previously labeled structured order data and railway dispatching orders as training samples. The model automatic training step is re-executed to further train the current large language model to obtain a second intermediate parsing model, and the model labeling step is repeated to identify and manually verify a new batch of railway dispatching orders, and the cycle is executed until the verification result meets the set requirements or all data are labeled, and the corresponding intermediate parsing model is used as the order information parsing model.

[0149] In an optional embodiment, in the order receiving and initial parsing step, the entire railway dispatching order is divided into 8 data information items for display respectively, and the 8 items are order date, order time, order number, issuer, bureau, recipient, receiving time and order sub-items and their data contents;

[0150] The command sub-items include natural language descriptions of the contents of multiple scheduling instructions in the scheduling command.

[0151] Preferably, in one embodiment, the verification and uploading steps include:

[0152] If a result that passes the representation verification is detected, the corresponding real-time dispatch order analysis result will be automatically transmitted to the train dispatching organization information system. Otherwise, the real-time dispatch order analysis result will be corrected in response to the feedback instructions from the verification personnel, or the dispatch order data analysis step and the analysis data post-processing step will be re-executed and output to the verification personnel again until a result that passes the representation verification is detected.

[0153] Furthermore, in one embodiment, the parsed data post-processing step further includes:

[0154] Identify the train type data in the structured dispatch order data, and then determine whether the train type data is a combined abbreviated mode. If so, further determine whether the train represented by the train type data in the combined abbreviated mode is the same train based on the train operation vehicle information database; if it is not the same train, split the train type data in the combined abbreviated mode into fractional train forms and update the structured dispatch order data.

[0155] Preferably, in one embodiment, the method further comprises:

[0156] Operation table synchronization update steps: compare and analyze whether the basic operation timetable data contains the train operation data in the structured dispatch order data. If not, add the train operation data in the structured dispatch order data to the basic operation timetable data.

[0157] Furthermore, in one embodiment, the method further comprises:

[0158] Correlation identification and plan generation steps: Determine whether the current real-time railway dispatching command is correlated with the operation plan of the current station based on the structured dispatching order data. If so, generate a temporary plan to guide the train operation of the current station by integrating the structured dispatching order data of the real-time railway dispatching command and the basic operation timetable of the current station; otherwise, do not generate a temporary plan.

[0159] In an optional embodiment, the correlation identification and plan generation steps include:

[0160] Relevance identification step: Identify whether a certain real-time railway dispatching command data is relevant to the operation of the current station according to the following logic:

[0161] One or more associated keywords are set around the operation field of the current station as station-related words; the associated keywords include one or more valid identification fields of the current station or one or more available identification fields of adjacent stations that inevitably lead to passing through the current station;

[0162] For the train numbers in its structured dispatch data, the train numbers are retrieved one by one according to the basic operation timetable, and the stop station information of each train number is analyzed. A traversal comparison is performed to analyze whether any of the station-related words exists. If so, it is identified as being related to the operation of the current station.

[0163] Furthermore, in one embodiment, the relevance identification and plan generation step further includes a plan generation step:

[0164] Identify whether the current real-time railway dispatching order is a suspension order. If not, directly generate a temporary operation plan for the current station based on the structured dispatching order data;

[0165] If so, the suspension interval corresponding to the suspended train is further identified based on the structured dispatch order data, and the operation information of the suspended train is identified in combination with the basic operating timetable. It is analyzed whether the suspension interval described in the dispatch order contains words related to the current station to determine whether this station is in the suspension interval. If it is in the suspension interval, a temporary suspension plan for the current station is generated. If it is not in the suspension interval, the sequence position of the current station relative to the suspension interval is identified, and a temporary plan for changing the terminal or departure of the current station is generated according to the sequence position.

[0166] For the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the order of the actions described, because according to the present invention, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0167] It should be pointed out that in other embodiments of the present invention, the method can also obtain a new dispatching operation control method based on intelligent analysis of railway dispatching commands by combining one or several of the above-mentioned embodiments, so as to realize intelligent analysis and application optimization of railway dispatching commands.

[0168] Embodiment three:

[0169] It should be noted that, based on the method in any one or more of the above-mentioned embodiments of the present invention, the present invention also provides a storage medium, on which is stored a program code that can implement the method as described in any one or more of the above-mentioned embodiments, and when the code is executed by the operating system, it can implement the above-mentioned dispatching operation control method based on intelligent analysis of railway dispatching commands.

[0170] It should be understood that the embodiments disclosed in the present invention are not limited to the specific structures, processing steps or materials disclosed herein, but should be extended to equivalent substitutions of these features understood by ordinary technicians in the relevant field. It should also be understood that the terms used herein are only used for the purpose of describing specific embodiments and are not meant to be limiting.

[0171] The "one embodiment" mentioned in the specification means that a particular feature, structure or characteristic described in conjunction with the embodiment is included in at least one embodiment of the present invention. Therefore, the phrase "one embodiment" appearing in various places throughout the specification does not necessarily refer to the same embodiment.

[0172] Although the embodiments disclosed in the present invention are as above, the above contents are only embodiments adopted for facilitating the understanding of the present invention and are not intended to limit the present invention. Any technician in the technical field to which the present invention 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 invention, but the patent protection scope of the present invention shall still be subject to the scope defined in the attached claims.

Claims

1. A dispatching operation control system based on intelligent analysis of railway dispatching commands, characterized in that: The system comprises: A parsing model progressive training module, which is configured to perform structural parsing processing and assign labels based on railway dispatching order data that meets a set scale to form structured dispatching order data, and train a large language model based on the railway dispatching order data and the structured dispatching order data as a dispatching order information parsing model; The dispatch order receiving and initial analysis module is configured to maintain continuous communication with the railway dispatching center system, receive real-time railway dispatching orders and perform initial analysis processing to generate dispatch order initial analysis data in a unified format; A dispatch order data parsing module, which is configured to perform parsing and identification based on the preliminary parsing data of the dispatch order of the real-time railway dispatch order using the dispatch order information parsing model, obtain structured dispatch order data of the real-time railway dispatch order, and combine it with the preliminary parsing data of the dispatch order as the real-time dispatch order parsing result; The analysis result verification and upload module is configured to output the real-time dispatch order analysis result to the verification personnel, detect the verification result from the verification personnel in real time, and transmit the real-time dispatch order analysis result to the train dispatch organization information system for calling in combination with the verification result data; The system further comprises: a data analysis post-processing module configured to identify time attribute data in the structured dispatch order data, and then determine whether the time attribute data is in a compressed form, and if so, restore the compressed time attribute data to a complete independent form, and update the structured dispatch order data; The correlation identification and plan generation module is configured to determine whether the current real-time railway dispatching command is correlated with the operation plan of the current station based on the structured dispatching order data. If so, a temporary plan guiding the operation of the current station train is generated by integrating the structured dispatching order data of the real-time railway dispatching command and the basic operation timetable of the current station; otherwise, no temporary plan is generated.

2. The system according to claim 1, characterized in that The analytical model progressive training module includes a basic labeling processing unit and a model automatic training unit; The basic labeling processing unit is configured to receive structured dispatch order data manually identified at a set scale, wherein the structured dispatch order data is formed by corresponding staff identifying the structure type of the data content field in each railway dispatch order, and then associating and recording each structure type and its data content field and using a set identifier interval; The model automatic training unit is configured to train the large language model based on the railway dispatching commands and corresponding structured dispatching order data after manual labeling to obtain a first intermediate parsing model.

3. The system according to claim 1, characterized in that The analytical model progressive training module also includes a model labeling processing unit and a labeling verification unit; The model labeling processing unit is configured to use the intermediate analytical model to identify the unlabeled railway dispatching order and obtain the corresponding structured dispatching order data as the first intermediate model analysis result; The label verification unit outputs the intermediate model analysis result and the corresponding railway dispatching command, which are manually verified and corrected for accuracy, and receives the verification result and the corrected analysis result fed back by the manual; When the verification result does not meet the set conditions, the corrected parsing result is used as the structured order data of the current railway dispatch order, and is combined with the previously labeled structured order data and railway dispatching orders as training samples. The model automatic training module is re-enabled to further train the current large language model to obtain a second intermediate parsing model, and the model labeling processing unit is repeatedly enabled to identify and manually verify a new batch of railway dispatching orders, and the cycle is executed until the verification result meets the set requirements or all data are labeled, and the corresponding intermediate parsing model is used as the order information parsing model.

4. The system according to claim 1, characterized in that The dispatch order receiving and initial parsing module divides the entire railway dispatch order into multiple data information and displays them separately, including the date of issuance, time of issuance, dispatch order number, issuer, bureau, recipient, receiving time and order sub-items and their data contents; Among them, the command sub-items include natural language descriptions of the contents of multiple scheduling instructions in the scheduling command.

5. The system according to claim 1, characterized in that The analysis result verification and upload module is configured as follows: If a result that passes the representation verification is detected, the corresponding real-time dispatch order analysis result will be automatically transmitted to the train dispatching organization information system. Otherwise, the real-time dispatch order analysis result will be corrected in response to the feedback instructions from the verification personnel, or the dispatch order data analysis module and the analysis data post-processing module will be restarted to operate, and output to the verification personnel again until a result that passes the representation verification is detected.

6. The system according to claim 1, characterized in that The parsed data post-processing module is also configured to identify the train type data in the structured dispatch order data, and then determine whether the train type data is a combined abbreviated mode. If so, further determine whether the train number represented by the train type data in the combined abbreviated mode is the same train based on the train operation vehicle information database; if it is not the same train, the train type data in the combined abbreviated mode is split into fractional train types and the structured dispatch order data is updated.

7. The system according to claim 1, characterized in that The system further comprises: The operation table synchronization update module is configured to compare and analyze whether the basic operation timetable data contains the train operation data in the structured dispatch order data. If not, the train operation data in the structured dispatch order data is added to the basic operation timetable data.

8. The system according to claim 1, characterized in that The relevance identification and plan generation module is provided with a relevance identification unit, which identifies whether a certain real-time railway dispatching command data is relevant to the operation of the current station according to the following logic: One or more associated keywords are set around the operation field of the current station as station-related words; the associated keywords include one or more valid identification fields of the current station or one or more available identification fields of adjacent stations that inevitably pass through the current station; For the train numbers in its structured dispatch data, the train numbers are retrieved one by one according to the basic operation timetable, and the stop station information of each train number is analyzed. A traversal comparison is performed to analyze whether any of the station-related words exists. If so, it is identified as being related to the operation of the current station.

9. The system according to claim 8, characterized in that The correlation identification and plan generation module is provided with a plan generation unit, which is configured to generate a temporary plan for guiding the operation of trains at the current station according to the following logic: Identify whether the current real-time railway dispatching order is a suspension order. If not, directly generate a temporary operation plan for the current station based on the structured dispatching order data; If so, the suspension interval corresponding to the suspended train is further identified based on the structured dispatch order data, and the operation information of the suspended train is identified in combination with the basic operating timetable. It is analyzed whether the suspension interval described in the dispatch order contains words related to the current station to determine whether this station is in the suspension interval. If it is in the suspension interval, a temporary suspension plan for the current station is generated. If it is not in the suspension interval, the sequence position of the current station relative to the suspension interval is identified, and a temporary plan for changing the terminal or departure of the current station is generated according to the sequence position.

10. A dispatching operation control method based on intelligent analysis of railway dispatching commands, characterized in that: The method is applied to the system described in any one of claims 1 to 9.

11. A storage medium, characterized in that: The storage medium stores program codes for implementing the method as claimed in claim 10.

Images