Railway locomotive distribution method, device, equipment, storage medium and program product

Abstract

The invention provides a railway locomotive distribution method and device, equipment, a storage medium and a program product. Relates to the technical field of railway transportation. The method comprises the following steps: acquiring railway locomotive resource data of each target line in to-be-identified time; generating target locomotive resource features corresponding to the target lines based on the locomotive resource data; predicting the target railway locomotive resource demand state quantity corresponding to each target line according to each target railway locomotive resource feature by adopting a railway locomotive resource demand state quantity prediction model trained to be converged; calculating a railway locomotive resource utilization rate corresponding to each target line based on each target railway locomotive resource demand state quantity; determining a target resource allocation strategy corresponding to each target line according to the resource utilization rate of each locomotive; distributing the railway locomotives of each target line according to each target resource distribution strategy; the method can balance railway locomotive resource allocation and solve the problem of shortage or excess of railway locomotive resources.

Description

Technical Field

[0001] The present application relates to the technical field of railway transportation, and particularly relates to a railway locomotive allocation method, device, equipment, storage medium and program product. Background Art

[0002] Urban rail transit is an important part of public transportation in big cities. With the acceleration of the urbanization process and the continuous growth of the urban population, urban rail transit has gradually become the core of the urban transportation system due to its characteristics of fast speed, punctuality and large transportation volume. Among them, railway locomotives are an important means of transportation in urban rail transit. And the allocation and scheduling of railway locomotives are important links in railway operation, which directly affect the efficiency, safety and cost of railway locomotive transportation. Scientific allocation and scheduling of railway locomotives can ensure the reasonable use of locomotives, reduce the empty running and waiting time of locomotives, and improve the utilization efficiency of locomotives.

[0003] At present, the allocation and scheduling of railway locomotives are mainly carried out by staff according to the daily transportation needs to allocate and schedule railway locomotives to meet the daily railway transportation needs. However, with the increasing amount of railway locomotive scheduling data and the change of transportation needs, the manual allocation and scheduling method cannot face the flexible and changeable transportation needs, resulting in unbalanced allocation of railway locomotive resources, and there are problems of shortage or surplus of railway locomotive resources in some periods or regions. Summary of the Invention

[0004] The present application provides a railway locomotive allocation method, device, equipment, storage medium and program product to solve the problem of unbalanced allocation of railway locomotive resources in the prior art, resulting in shortage or surplus of railway locomotive resources in some periods or regions.

[0005] In a first aspect, the present application provides a railway locomotive allocation method, including:

[0006] Obtain the railway locomotive resource data of each target line within the time to be recognized;

[0007] Generate the target railway locomotive resource characteristics corresponding to each target line based on the railway locomotive resource data;

[0008] Adopt a railway locomotive resource demand status quantity prediction model trained to convergence and predict the target railway locomotive resource demand status quantity corresponding to each target line according to each of the target railway locomotive resource characteristics; the target railway locomotive resource demand status quantity is used to indicate whether there is a shortage of railway locomotive resources;

[0009] Calculate the railway locomotive resource utilization rate corresponding to each target line based on each of the target railway locomotive resource demand status quantities;

[0010] Determine the target resource allocation strategy corresponding to each target line according to the utilization rate of each railway locomotive resource;

[0011] Allocate railway locomotives on each target line according to each target resource allocation strategy.

[0012] In a possible implementation manner, determining the target resource allocation strategy corresponding to each target line according to the utilization rate of each railway locomotive resource includes:

[0013] Classify the utilization rate of each railway locomotive resource according to at least one preset utilization rate threshold to obtain the railway locomotive resource utilization rate level corresponding to each target line;

[0014] Determine the traffic level corresponding to the time to be recognized based on a preset traffic threshold;

[0015] Determine the target resource allocation strategy corresponding to each line according to the railway locomotive resource utilization rate level and the traffic level corresponding to the time to be recognized.

[0016] In a possible implementation manner, the railway locomotive resource utilization rate levels include: the first resource utilization rate level, the second utilization rate level, and the third utilization rate level; the traffic levels include: peak period, mid-peak period, and off-peak period; the target resource allocation strategies include: the first resource allocation strategy, the second resource allocation strategy, the third resource allocation strategy, the fourth resource allocation strategy, and the fifth resource allocation strategy;

[0017] The determining the target resource allocation strategy corresponding to each line according to the railway locomotive resource utilization rate level and the traffic level corresponding to the time to be recognized includes:

[0018] If the railway locomotive resource utilization rate level is the first resource utilization rate level and the traffic level is the peak period, then determine that the target resource allocation strategy is the first resource allocation strategy; the first resource utilization rate level is the level with the highest railway locomotive resource utilization rate; the first resource allocation strategy includes: increasing the number of railway locomotive trips, increasing the number of carriages, extending the operation time of railway locomotives, and shortening the running time interval of railway locomotives;

[0019] If the railway locomotive resource utilization rate level is the first resource utilization rate level and the traffic level is the mid-peak period or the off-peak period, then determine that the target resource allocation strategy is the second resource allocation strategy; the second resource allocation strategy includes: increasing the number of carriages and increasing the number of railway locomotive trips;

[0020] If the railway locomotive resource utilization rate level is the second resource utilization rate level and the traffic flow level is the peak period or the mid-peak period or the off-peak period, then determine that the target resource allocation strategy is the third resource allocation strategy; the second resource utilization rate level is the level where the railway locomotive resource utilization rate is lower than the first resource utilization rate level and higher than the third resource utilization rate level; the third resource allocation strategy includes: increasing the number of carriages or the number of railway locomotive trips according to the passenger flow.

[0021] If the railway locomotive resource utilization rate level is the third resource utilization rate level and the traffic flow level is the mid-peak period or the peak period; then determine that the target resource allocation strategy is the fourth resource allocation strategy; the third resource utilization rate level is the level with the lowest railway locomotive resource utilization rate; the fourth resource allocation strategy includes: reducing the number of railway locomotive trips, directly increasing the number of carriages according to the passenger flow, and transferring the redundant railway locomotives to the standby or maintenance state.

[0022] If the railway locomotive resource utilization rate level is the third resource utilization rate level and the traffic flow level is the off-peak period; then determine that the target resource allocation strategy is the fifth resource allocation strategy; the fifth resource allocation strategy includes: shortening the operation time of the railway locomotive, reducing the number of railway locomotive trips, and transferring the redundant railway locomotives to the standby or maintenance state.

[0023] In a possible implementation manner, the railway locomotive resource demand status quantity prediction model is a deep neural network model; the training steps of the railway locomotive resource demand status quantity prediction model include:

[0024] Obtain training samples; the training samples include: the target railway locomotive resource characteristics corresponding to each line and the labeled railway locomotive resource demand status quantities; the target railway locomotive resource characteristics include: train number characteristics, railway locomotive travel characteristics, railway locomotive operation efficiency characteristics, railway locomotive maintenance record characteristics, line layout characteristics, electrified section characteristics of the line, and traffic flow density characteristics of the line.

[0025] Use the training samples to train the pre-constructed neural network model until the neural network model converges, so as to obtain a railway locomotive resource demand status quantity prediction model trained to convergence.

[0026] In a possible implementation manner, the allocation of railway locomotives for each target line according to each target resource allocation strategy includes:

[0027] Obtain the current railway locomotive resource status information corresponding to each target line.

[0028] Generate an allocation plan in a preset manner according to the current railway locomotive resource status information and the target resource allocation strategies corresponding to the target lines.

[0029] In a possible implementation manner, after generating the allocation plan according to the current railway locomotive resource status information and the target resource allocation strategies corresponding to the target lines in a preset manner, it further includes:

[0030] Perform an execution risk assessment on the allocation results in the target allocation plan;

[0031] The execution risks include: railway locomotive failure risk, transportation delay risk, and line congestion risk;

[0032] The performing an execution risk assessment on the allocation results of the target allocation plan includes:

[0033] Obtain based on the railway locomotive performance evaluation index, and judge whether there is the railway locomotive failure risk according to whether the railway locomotive performance evaluation index exceeds the preset railway locomotive performance index threshold;

[0034] And, obtain the delay rate of the railway locomotive, and judge whether there is the transportation delay risk according to whether the delay rate of the railway locomotive exceeds the preset railway locomotive delay rate threshold;

[0035] And, obtain the average running speed of each railway locomotive, determine the number of railway locomotives whose average running speeds are lower than the normal passing speed thresholds corresponding to each line, and judge whether there is the line congestion risk according to whether the number of railway locomotives exceeds the preset number threshold.

[0036] In a second aspect, the present application provides a locomotive allocation device, including:

[0037] An acquisition module, configured to acquire railway locomotive resource data of each target line within a time to be identified;

[0038] A generation module, configured to generate target railway locomotive resource characteristics corresponding to each target line based on the railway locomotive resource data;

[0039] A prediction module, configured to use a railway locomotive resource demand status quantity prediction model trained to convergence and predict the target railway locomotive resource demand status quantity corresponding to each target line according to each of the target railway locomotive resource characteristics; the target railway locomotive resource demand status quantity is used to indicate whether there is a shortage of railway locomotive resources;

[0040] A calculation module, configured to calculate the railway locomotive resource utilization rate corresponding to each target line based on each of the target railway locomotive resource demand status quantities;

[0041] A determination module, configured to determine a target resource allocation strategy corresponding to each target line according to the utilization rate of each railway locomotive resource;

[0042] An allocation module, configured to allocate railway locomotives for each target line according to each target resource allocation strategy.

[0043] In a third aspect, an embodiment of the present application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0044] The memory stores computer-executable instructions;

[0045] The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of the first aspects;

[0046] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, they are used to implement the method according to the first aspect.

[0047] In a fifth aspect, the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the method according to the first aspect.

[0048] The railway locomotive allocation method, device, electronic device, storage medium, and program product provided by this application obtain the railway locomotive resource data of each target line within the time to be recognized; generate the target railway locomotive resource characteristics corresponding to each target line based on the railway locomotive resource data; use the railway locomotive resource demand status quantity prediction model trained to convergence and predict the target railway locomotive resource demand status quantity corresponding to each target line according to each target railway locomotive resource characteristic; the target railway locomotive resource demand status quantity is used to indicate whether there is a shortage of railway locomotive resources; calculate the railway locomotive resource utilization rate corresponding to each target line based on each target railway locomotive resource demand status quantity; determine the target resource allocation strategy corresponding to each target line according to each railway locomotive resource utilization rate; allocate the railway locomotives of each target line according to each target resource allocation strategy; therefore, the target railway locomotive resource characteristics corresponding to each target line obtained according to the railway locomotive resource data of each target line provide rich railway locomotive resource data for the railway locomotive resource demand status quantity prediction model, so that more accurate target railway locomotive resource demand status quantities corresponding to each target line can be obtained, and further, more accurate railway locomotive resource utilization rates corresponding to each target line can be calculated according to the target railway locomotive resource demand status quantities corresponding to each target line; thus, the usage of locomotives on each target line can be analyzed according to each railway locomotive resource utilization rate, and the target resource allocation strategy corresponding to each target line can be formulated according to the analysis results for allocating railway locomotives on each target line. Therefore, it is possible to balance railway locomotive resources and solve the problem of shortage or excess of railway locomotive resources in certain time periods or regions. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The drawings herein are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present application and used together with the specification to explain the principles of the present application.

[0050] Figure 1 It is an application scenario diagram of the railway locomotive allocation method provided by an embodiment of the present application;

[0051] Figure 2 It is a flowchart of the railway locomotive allocation method provided by an embodiment of the present application;

[0052] Figure 3 It is a flowchart block diagram of the railway locomotive allocation method provided by another embodiment of the present application;

[0053] Figure 4 It is a schematic diagram of the railway locomotive allocation device provided by an embodiment of the present application;

[0054] Figure 5 It is a schematic diagram of the structure of the electronic device provided by an embodiment of the present application.

[0055] Through the above-mentioned accompanying drawings, specific embodiments of the present application have been shown, and there will be a more detailed description hereinafter. These drawings and the written description are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by reference to specific embodiments. Detailed Description of the Embodiments

[0056] Here, the exemplary embodiments will be described in detail, and the examples are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0057] To clearly understand the technical solution of the present application, the solutions of the prior art will be introduced in detail first.

[0058] In the prior art, the allocation and scheduling of railway locomotives are mainly carried out by staff according to the daily transportation demand, and a detailed transportation plan is formulated according to the transportation demand; then the status of available railway locomotives is inventoried; according to the transportation plan, each available railway locomotive is allocated to a specific operation line, and the real-time status of the available railway locomotives is monitored in real time. When sudden situations such as delays and failures occur in the real-time status of the available railway locomotives, the staff adjusts the train numbers of the railway locomotives according to the specific sudden situations, so as to realize the allocation and scheduling of railway locomotives to meet the daily railway transportation demand. However, with the increasing amount of data on railway locomotive scheduling and the change of transportation demand, the method of manual allocation and scheduling cannot face the flexible and changeable transportation demand, resulting in unbalanced allocation of locomotive resources, and there are problems of shortage or surplus of locomotive resources in some periods or regions.

[0059] Therefore, when facing the existing technology, in order to balance the allocation of railway locomotive resources, the utilization rate of railway locomotive resources corresponding to each target line can be calculated first; the utilization rate of railway locomotive resources can characterize the usage of railway locomotive resources, and based on this, a target allocation strategy can be reasonably formulated according to the usage of railway locomotives corresponding to each target line; among them, the utilization rate of railway locomotive resources is easily affected by changes in locomotive resource allocation. Railway locomotive resources are easy to change according to passenger demand, locomotive performance, line conditions, etc. The demand status quantity of railway locomotive resources can accurately characterize whether the demand for railway locomotive resources is scarce. Furthermore, the utilization rate of railway locomotive resources can be calculated based on the demand status quantity of railway locomotive resources; therefore, in order to further improve the calculation accuracy of the demand status quantity of railway locomotive resources; a trained-to-converge prediction model of the demand status quantity of railway locomotive resources and target railway locomotive resource characteristics can be used to predict the demand status quantity of target railway locomotive resources corresponding to each target line. The trained-to-converge prediction model of the demand status quantity of railway locomotive resources has the characteristics of high prediction accuracy and fast prediction speed, and can deeply analyze the target railway locomotive resource characteristics containing rich locomotive resource information, so as to accurately obtain the demand status quantity of target railway locomotive resources corresponding to each target line; furthermore, a more accurate utilization rate of railway locomotive resources can also be obtained. Therefore, the target resource allocation strategy corresponding to each target line can also be reasonably determined according to the utilization rate of railway locomotive resources corresponding to each target line, so as to allocate the railway locomotive resources of each target line. Therefore, it is possible to achieve a balanced allocation of railway locomotive resources and solve the problem of shortage or surplus of railway locomotive resources in some time periods or regions.

[0060] Figure 1 FIG. is a diagram of an application scenario of the railway locomotive allocation method provided by an embodiment of the present application. In this scenario, it may include a terminal device 101, a railway locomotive allocation device 102, and a database 103; the terminal device 101 is communicatively connected to the railway locomotive allocation device 102; the railway locomotive allocation device 102 is communicatively connected to the database 103. Optionally, the railway locomotive allocation device 102 may also be integrated in the server; the railway locomotive allocation device 102 may be a server, a server cluster, or other electronic devices of the railway locomotive allocation device, and this is not limited in this embodiment.

[0061] Specifically, the user inputs the numbers of each target line and the time to be recognized into the terminal device 101, and sends the numbers of each target line and the time to be recognized to the railway locomotive allocation device 102. The railway locomotive allocation device 102 receives the numbers of each target line and the time to be recognized, and sends them to the database 103 to obtain the railway locomotive resource data of each target line within the time to be recognized, and then sends the data to the railway locomotive allocation device 102. After receiving the railway locomotive resource data of each target line within the time to be recognized, the railway locomotive allocation device 102 generates the target railway locomotive resource characteristics corresponding to each target line based on the railway locomotive resource data; then uses the railway locomotive resource demand status prediction model trained to convergence and predicts the target railway locomotive resource demand status corresponding to each target line according to the target railway locomotive resource characteristics; where the target railway locomotive resource demand status is used to indicate whether there is a shortage of railway locomotive resources; then calculates the railway locomotive resource utilization rate corresponding to each target line based on the target railway locomotive resource demand status; and determines the target resource allocation strategy corresponding to each target line according to the railway locomotive resource utilization rate; thus, it is possible to allocate the railway locomotives of each target line according to the target resource allocation strategy to balance the allocation of railway locomotive resources.

[0062] The following uses specific embodiments to elaborate in detail on the technical solution of this application and how the technical solution of this application solves the above technical problems. The following several specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0063] Figure 2 It is a flowchart of a railway locomotive allocation method provided by an embodiment of this application. As Figure 2 shown, as Figure 2 shown, the execution subject of this embodiment is a railway locomotive allocation device, and this railway locomotive allocation device can be implemented through a computer program; it can also be implemented through a medium storing relevant computer programs, such as a USB flash drive and / or an optical disc, etc., or, it can also be implemented through an entity device integrated or installed with relevant computer programs, such as a chip or a railway locomotive allocation device, etc. The railway locomotive allocation device can be a server, a server cluster, a terminal device, or other electronic devices, etc. The railway locomotive allocation method provided by this embodiment includes the following steps:

[0064] Step 201: Obtain the railway locomotive resource data of each target line within the time to be recognized.

[0065] Among them, the target line refers to the line for which railway locomotives are to be allocated. It can be lines in the same area or lines in different areas; the target lines can be selected according to requirements, and no limitation is made in this embodiment.

[0066] Among them, the time to be recognized is the time period before the time of the railway locomotive to be allocated, which can be the past week, day, hour, etc., aiming to allocate the railway locomotives for future time according to the recognized railway locomotive resource data in the past time.

[0067] Among them, the railway locomotive resource data can include: historical operation data and railway network data.

[0068] Among them, the historical operation data refers to the operation configuration parameters of the railway locomotive recorded in the past time period. It can include: the running line number, the railway locomotive number, the line station information, the departure time of the railway locomotive, the arrival time of the railway locomotive, the travel distance of the railway locomotive, the travel distance of the railway locomotive, the resource utilization rate of the railway locomotive, the average running speed of the railway locomotive, the failure rate of the railway locomotive; the maintenance date of the railway locomotive, the maintenance content and the maintenance duration of the railway locomotive, the type of the railway locomotive. The historical operation data can be recorded in the operation data storage table and stored in the database or the operation record system;

[0069] Among them, the running line number is an identifier used to distinguish and represent the line, which can be in a preset number form and is not limited in this embodiment.

[0070] Among them, the running line number is the number corresponding to the actual running line of each railway locomotive, which can be recorded after each railway locomotive actually runs.

[0071] Among them, the railway locomotive number is an identifier used to distinguish railway locomotives, which can also be in a preset number form and is not limited in this embodiment.

[0072] Among them, the line station information can refer to the information of each station where the railway locomotive stops, which can be the names of each station.

[0073] Among them, the running distance of the railway locomotive is the total length of the running line corresponding to the railway locomotive.

[0074] Among them, the travel distance of the railway locomotive refers to the actual running distance of the railway locomotive.

[0075] Among them, the average running speed of the railway locomotive refers to the number of kilometers traveled per hour on average within the running line; it can be obtained by the ratio of the total distance actually traveled by the railway locomotive within the line to the total time, and it affects the transportation time and efficiency of the railway locomotive.

[0076] Among them, the failure rate of the railway locomotive refers to the percentage of failures occurring per unit time, which can be calculated by the ratio of the number of failures of the entire railway locomotive within a certain period of time to the total working time within that period; it affects the availability and allocation plan of the locomotive.

[0077] Among them, the content of railway locomotive maintenance refers to the detailed process record of maintenance. Exemplarily, for example, which components of railway locomotives are specifically maintained, what problems are found, how to repair them, etc. It can also be other things, which are not specifically limited in this embodiment. It can be recorded by relevant personnel after maintenance and uploaded to the database or the historical operation system.

[0078] Among them, the types of railway locomotives are classified according to the different characteristics and uses of railway locomotives. They can be high-speed rail types, bullet train types, intercity types, or others, which are not limited in this embodiment.

[0079] Among them, railway network data refers to various types of data related to the railway network; it can include: line numbers, line lengths, line gradients, line curve radii, electrified section ranges and power supply system types, traffic flow and traffic density, line geographical information, railway locomotive facility information, railway locomotive technical equipment information; railway network data can be recorded in the railway network data storage table and stored in the database or the geographical information system.

[0080] Among them, the line length refers to the actual distance from the starting point to the ending point of the line, which affects the running time and dispatching range of railway locomotives. It can be obtained by measurement using the geographical information system.

[0081] Among them, the line gradient refers to the rate of change of the line in the vertical direction, usually expressed as a percentage or an angle; it can be obtained by measurement using the geographical information system; it affects the traction capacity and energy consumption of railway locomotives.

[0082] Among them, the curve radius refers to the radius of curvature of the line at the turning point, which reflects the degree of bending of the line. It can be the data recorded by actual measurement, and it affects the running speed and safety of railway locomotives.

[0083] Among them, the electrified section range refers to the line section on the railway that has been electrified or constructed. Specifically, it can be the section where traditional steam locomotives or diesel locomotives are replaced by electric locomotives, with electrical energy as the power source. It can include: the longitude and latitude of the starting point and the ending point of the electrified section and the length of the electrified section, etc., or it can be other information, which is not specifically limited in this embodiment. It affects the traction mode and power supply requirements of railway locomotives.

[0084] Among them, the power supply system type refers to the power supply method adopted by the electrified railway, which determines how electric power is transmitted to the electric locomotive. The power supply system type can be the direct power supply method, autotransformer power supply, booster transformer power supply, and direct power supply with a return line, etc. It can be directly represented by text or in the form of a category, which is not specifically limited in this embodiment.

[0085] Among them, traffic flow refers to the number of train operations recorded at different time periods and on different lines; it reflects the degree of traffic congestion.

[0086] Among them, traffic density refers to the density of railway locomotives on a line, that is, the number of railway locomotives per unit length of a line at a certain moment. It reflects the degree of congestion of the line and is an instantaneous value.

[0087] Among them, the line geographic information may include: geological structure information, such as fold belts and fault zones, which can be marked according to the grades of fold belts and fault zones. Exemplarily, strong fold belts can be marked as 1, medium fold belts as 2, weak fold belts as 3, active fault zones as 4, inactive fault zones as 5, and stable fault zones as 6. It may also include other line geographic information, which is not limited in this embodiment.

[0088] Among them, the railway locomotive facility information may include: car types, facility configurations, etc.; car types such as hard seats, soft seats, dining cars, soft sleepers, hard sleepers, etc., or other types; facility configurations may include: the materials, sizes of seats or beds, the types and performance parameters of ventilation and air-conditioning systems in the carriages, etc., and may also include other setting configurations; the railway locomotive facility information may include other facility information, which is not specifically limited in this embodiment.

[0089] Among them, the railway locomotive technical equipment information is a key component to ensure the safe and efficient operation of railway transportation. It may include: locomotive air braking systems, locomotive traction systems, locomotive signal systems. The corresponding data of the railway locomotive technical equipment information can be recorded by recording the models of locomotive air braking systems, locomotive traction systems and locomotive signal systems. The representation forms of the models can be letters, numbers, or others, which are not specifically limited in this embodiment.

[0090] Specifically, when the server receives the numbers of the target lines, the server can select the historical operation data and railway network data of the target lines during the period to be recognized according to the numbers of the target lines. It can first obtain the historical operation data of each target line during the period to be recognized from the operation data storage table in the database or the operation record system; then obtain the railway network data corresponding to each target line during the period to be recognized from the database or the geographic information system; then, it can match the running line numbers in the historical operation data of each railway locomotive with the line numbers in the railway network data, and then arrange the data with the same running line numbers in the historical operation data and the line numbers in the railway network data into one line and use it as a group of data; and it can classify each group of data according to the running line numbers, and regard the data with the same running line numbers as one category; then, it can sort the data in each category in turn according to the departure time of the railway locomotive, the type of the railway locomotive, the geographic information, and the technical equipment information of the railway locomotive, and perform data cleaning and data conversion on the sorted data; finally, it can store the data that has been arranged, classified, sorted, and subjected to data cleaning and data conversion as railway locomotive resource data in the railway locomotive dispatching sequence table. Among them, there are various data processing methods, which are not specifically limited in this embodiment.

[0091] Among them, the sorting method according to the departure time of the railway locomotive can be sorted in the order of the departure time from early to late; it can also be sorted in other ways, which are not limited in this embodiment.

[0092] Among them, the sorting method according to the type of the railway locomotive can be sorted according to the first letter of the type of the railway locomotive. Exemplarily, the high-speed rail type is identified by "G", the intercity train type is identified by "C", and the bullet train type is identified by "D". It can be sorted in the order of "C", "D", "G", or other sorting methods, which are not specifically limited in this embodiment.

[0093] Among them, the sorting method according to the geographic information can be sorted according to the grades of the fold belt and the fault zone, which can be from small to large, from large to small, or other, which are not specifically limited in this embodiment.

[0094] Among them, the sorting method according to the technical equipment information of the railway locomotive can be to first query the locomotive air brake systems with the same model, and then sort them according to the first letter or numerical order of the model; after sorting according to the model of the locomotive air brake system, first query the camera car traction systems with the same model, and then sort them according to the first letter or numerical order of the model; after sorting according to the model order of the camera car traction system, it can continue to be sorted according to the first letter or numerical order of the model; or other sorting methods, which are not limited in this embodiment.

[0095] Step 202: Generate target railway locomotive resource characteristics corresponding to each target line based on railway locomotive resource data.

[0096] Specifically, the railway locomotive numbers, departure times, and arrival times of each railway locomotive in each target line can be sequentially extracted from the railway locomotive dispatching sequence list and the above data can be processed. The processed railway locomotive numbers, departure times, and arrival times are used as train number characteristics corresponding to each target line. Exemplarily, the train number can be encoded. For example, it can be presented in the form of one-hot encoding (abbreviation: One-Hot encoding), label encoding, etc., or in other forms, which are not specifically limited in this embodiment. The encoding process mentioned later can be the method in this embodiment, and will not be repeated in this embodiment. The departure time and arrival time of the railway locomotive can be converted into the datetime type. The datetime type is used to store the combination of date and time, and its format is 'YYYY-MM-DD HH:MM:SS'. The above time data can also be processed in other forms, which are not specifically limited in this embodiment.

[0097] Specifically, the line station information can be encoded for use as trip feature data. The travel distance of the railway locomotive is in numerical form and does not need to be further processed. Thus, the encoded line station information and the travel distance of each railway locomotive in each target line can be directly used as trip characteristics corresponding to each target line.

[0098] Specifically, the average running speed value and the railway locomotive failure rate value of each railway locomotive in each target line can be extracted from the railway locomotive dispatching sequence list and used as trip characteristics corresponding to each target line.

[0099] Specifically, the maintenance dates, maintenance contents, and maintenance durations corresponding to each railway locomotive on each target line can be extracted from the railway locomotive dispatching sequence list, and data processing can be performed on the maintenance dates, maintenance contents, and maintenance durations of each railway locomotive. The processed data can be used as maintenance record features. The data processing methods can be as follows: the maintenance dates of each railway locomotive can be converted into the datetime form; the maintenance durations of the railway locomotives can be directly extracted; the maintenance contents of the railway locomotives can be processed to remove irrelevant characters, punctuation marks, stop words, etc.; then the maintenance contents of the railway locomotives can be segmented into words or phrases. The methods for segmenting into words or phrases can be: term frequency-inverse document frequency, unsupervised keyword extraction algorithm based on graph, and other segmentation methods, or other methods, which are not specifically limited in this embodiment; after the maintenance contents of the railway locomotives are segmented, the segmented words are then converted into word vectors according to the word vector conversion method. The word vector conversion method can be a word vector model such as word vector or word embedding, or other methods, which are not specifically limited in this embodiment; there can also be other data processing methods, which are not specifically limited in this embodiment.

[0100] Specifically, the numerical values corresponding to the line lengths, the numerical values corresponding to the line gradients, and the numerical values corresponding to the curve radii corresponding to each railway locomotive on each target line can be extracted from the railway locomotive dispatching sequence list as line layout features.

[0101] Specifically, the electrified section range and power supply system type corresponding to each railway locomotive on each target line can be extracted from the railway locomotive dispatching sequence list, and then data processing is performed on the electrified section range and power supply system type. The electrified section range and power supply system type after data processing can be used as electrified section features. Exemplarily, the difference between the longitude of the starting point and the longitude of the ending point in the electrified section range can be calculated, and the difference between the longitude of the starting point and the latitude of the ending point in the electrified section range can be calculated; the length of the electrified section can be extracted, and the power supply system type can be classified and labeled. For example, it can be represented as 1, 2, 3…, and it can be labeled up to the number of types in other ways, which are not specifically limited in this embodiment. Furthermore, the length of the electrified section corresponding to each railway locomotive on each target line, the difference results of the longitude of the starting point and the longitude of the ending point in the calculated electrified section range, the difference results of the latitude of the starting point and the latitude of the ending point in the electrified section range, and the power supply system class after labeling can be used as the electrified section features of each target line. There are various data processing methods for the electrified section range and power supply system type, which are not limited in this embodiment.

[0102] Specifically, the numerical values corresponding to the traffic flow and the numerical values corresponding to the traffic density corresponding to each railway locomotive on each target line can be extracted from the railway locomotive dispatching sequence list as the traffic flow density features corresponding to each target line.

[0103] Specifically, the train number characteristics, trip characteristics, maintenance record characteristics, line layout characteristics, electrified section characteristics, line layout characteristics, and traffic flow density characteristics corresponding to the same railway locomotive number are spliced into one row or one column until all the above-mentioned characteristic data corresponding to the railway locomotives in the same target line are obtained. The above-mentioned characteristic data corresponding to all the railway locomotives in the same target line are used as the target railway locomotive resource characteristics corresponding to one line; then, the data corresponding to the target railway locomotive resource characteristics in other target lines are continuously spliced to obtain the target railway locomotive resource characteristics corresponding to each target line.

[0104] Step 203: Use the railway locomotive resource demand status prediction model trained to convergence and predict the target railway locomotive resource demand status corresponding to each target line according to the target railway locomotive resource characteristics of each target line; the target railway locomotive resource demand status is used to indicate whether there is a shortage of railway locomotive resources.

[0105] Among them, the railway locomotive resource demand status prediction model trained to convergence can be a neural network model, and other mathematical models can also be applied to calculate the target railway locomotive resource demand status, which is not specifically limited in this embodiment.

[0106] Specifically, the target railway locomotive resource characteristics corresponding to each target line obtained in step 203 can be input into the railway locomotive resource demand status prediction model trained to convergence. The railway locomotive resource demand status prediction model trained to convergence can perform feature analysis on the target railway locomotive resource characteristics of each target line, and then can predict the target railway locomotive resource demand status corresponding to each target line. Among them, the predicted target railway locomotive resource demand status can be a probability value. When the calculated target railway locomotive resource demand status is close to 0, it indicates that the demand for allocated locomotives on this line is low and no allocation is required; when the calculated target railway locomotive resource demand status is close to 1, it indicates that the demand for allocated locomotives on this line is high and locomotive allocation is required.

[0107] Optionally, the target railway locomotive resource demand status can also be calculated by the following formula, as shown in formula (1):

[0108]

[0109] Among them, R(t, l) represents the target railway locomotive resource demand status at time t and on line l; D(t, l) represents the traffic density at time t and on line l; B represents the reference value of traffic density, which is used to standardize the traffic flow density and is an empirical value; α represents the model parameter used to adjust the influence degree of traffic density on railway locomotive resource demand and is an empirical value; F i(t, l) represents the i-th railway locomotive resource data at time t and on line l; C i represents the reference value of the i-th railway locomotive resource data, which is used to standardize the railway locomotive resource data and is an empirical value; n represents the number of railway locomotive resource data; β represents the model parameter for adjusting the influence degree of the characteristic value on the railway locomotive resource demand and is an empirical value.

[0110] Among them, the railway locomotive resource data input into C i can be the line length, slope, curve radius, etc., or other data of the state quantity affecting the railway locomotive demand. It is not limited in this embodiment.

[0111] Understandably, when D(t, l) increases, it indicates that the running quantity of railway locomotives on line l rises, which means the usage frequency of railway locomotives increases, and more railway locomotives are needed to carry the transportation tasks of each line, thus causing the railway locomotive resource demand state quantity R(t, l) to rise; when F i (t, l) increases, it indicates that when the values of railway resource data such as line length, slope, and curve radius increase, higher-performance train numbers are needed to solve problems such as locomotive consumption brought by line length, slope, and curve radius to railway locomotives, thus causing the railway locomotive resource demand state quantity R(t, l) to rise; conversely, when D(t, l) and F i (t, l) decrease, the railway locomotive resource demand state quantity R(t, l) decreases.

[0112] Among them, the reference value B of traffic density, the model parameter α for adjusting the influence degree of traffic density on railway locomotive resource demand, the reference value C corresponding to each railway locomotive resource data i and the model parameter β for adjusting the influence degree of railway locomotive resource data on railway locomotive resource demand can all be obtained by relevant personnel through experiments, and the above parameters are stored in the empirical value storage table.

[0113] Specifically, the line length, slope, and curve radius corresponding to each target line can be obtained from the railway locomotive dispatching sequence table; the reference value of traffic density, the model parameter for adjusting the influence degree of traffic density on railway locomotive resource demand, the reference value corresponding to each railway locomotive resource data, and the model parameter for adjusting the influence degree of railway locomotive resource data on railway locomotive resource demand can be sequentially obtained from the empirical value storage table, and the above data are input into formula (1) to obtain the locomotive resource demand state quantity corresponding to each target line.

[0114] Step 204: Calculate the railway locomotive resource utilization rate corresponding to each target line based on each target railway locomotive resource demand state quantity.

[0115] Among them, the utilization rate of railway locomotive resources is an indicator reflecting the effective utilization of railway locomotive resources; it can be calculated by a preset mathematical method. Exemplarily, it can be a machine learning algorithm, a preset formula, etc., which are not specifically limited in this embodiment.

[0116] Specifically, the utilization rate of railway locomotive resources corresponding to each target line can be input into a preset formula to obtain the utilization rate of railway locomotive resources corresponding to each target line. Exemplarily, the utilization rate of railway locomotive resources corresponding to each target line can be calculated according to the following preset formula (2):

[0117]

[0118] Among them, U(t, l) represents the utilization rate of railway locomotive resources at time t and on line l; T busy (t, l) represents the average running time of railway locomotives at time t and on line l; T total (t, l) represents the total running time of railway locomotives at time t and on line l; B T represents the reference value of time for normalizing the running time, R(t, l) represents the demand for railway locomotive resources at time t and on line l; R max represents the maximum demand state quantity of railway locomotive resources, and ∈ represents the adjustment parameter for adjusting the influence degree of the demand for railway locomotive resources, which is an empirical value.

[0119] Among them, the reference value of time B T and the adjustment parameter ∈ for adjusting the influence degree of the demand for railway locomotive resources can be obtained by relevant personnel through experiments or data analysis, which are empirical values and stored in the empirical value storage table, or can be obtained by other means, which are not specifically limited in this embodiment.

[0120] Specifically, all the travel distances of railway locomotives corresponding to a target line can be obtained from the railway locomotive dispatching sequence table, and all the travel distances of railway locomotives are weighted and summed to obtain the average travel distance of railway locomotives; then the average running speed corresponding to the target line is obtained; the average travel distance of railway locomotives can be divided by the average running speed corresponding to the target line to obtain the average running time of railway locomotives on a target line; the result of the weighted sum of all the travel distances of railway locomotives can be divided by the average running speed corresponding to the target line as the total running time of railway locomotives; then the reference value of time and the reference value of time can be obtained from the empirical value storage table; the range of the maximum railway locomotive resource demand state quantity is between 0 and 1, so the maximum railway locomotive resource demand state quantity can be assigned as 1; the railway locomotive resource utilization rate corresponding to the target line calculated in step 203 can be obtained; and the above data are respectively input into formula (2), and the railway locomotive resource utilization rate corresponding to a target line can be obtained; the above methods corresponding to all target lines can be input into (2) to obtain the railway locomotive resource utilization rates corresponding to each target line.

[0121] It can be understood that the value range of U(t, l) is between 0 and 1, where 0 indicates the lowest railway locomotive resource utilization rate, indicating that there are many idle railway locomotives; 1 indicates the highest locomotive resource utilization rate, indicating that all railway locomotives are occupied; when T busy (t, l) increases, it means that the running time of the railway locomotive becomes longer, thus increasing the railway locomotive resource utilization rate U(t, l); when T total (t, l) decreases, it means that the number of railway locomotives on this line decreases, but the running time of the railway locomotive remains unchanged, indicating that there are fewer unoperated train trips on this line, thus increasing the railway locomotive resource utilization rate U(t, l); when R(t, l) increases, it means that the demand for the use of railway locomotives on this line increases, and more train trips need to be started, then the railway locomotive resource utilization rate U(t, l) increases.

[0122] Step 205: Determine the target resource allocation strategy corresponding to each target line according to each railway locomotive resource utilization rate.

[0123] Among them, the target resource allocation strategy refers to the strategy formulated for allocating railway locomotives, which can be a pre-set strategy according to requirements.

[0124] Specifically, given the resource utilization rate of each railway locomotive, the usage of railway locomotives on each target line at each time can be predicted; therefore, the target resource allocation strategy for each target line can be determined according to the resource utilization rate of each railway locomotive. Exemplarily, the resource utilization rates of each railway locomotive can be classified first, and then according to the classification, the allocation of railway locomotives on this line can be adjusted by adding carriages, increasing the number of trips, reducing the number of trips, etc. Other adjustments not specifically limited in this embodiment are also possible.

[0125] Optionally, the target resource allocation strategy for each target line with different railway locomotive resource utilization rates can also be formulated considering factors such as the peak and off-peak passenger flow periods in the current time period.

[0126] Step 206: Allocate the railway locomotives of each target line according to each target resource allocation strategy.

[0127] Specifically, after formulating the target resource allocation strategy for each target line, the real-time data of each railway locomotive, the actual transportation demand of each line, the passenger flow of the transportation corresponding to each line, and the emergency situation of the transportation on each target line can be obtained, and the above information, together with the target resource allocation strategy and the numbers of each target line, is input into the allocation plan generation model or the allocation plan generation system to generate an allocation plan. Furthermore, the result can be displayed through a data analysis tool and visualization software, and the railway locomotives of each target line are allocated according to this allocation plan. Among them, there can be various allocation methods for the allocation plan, which are not specifically limited in this embodiment. Among them, the real-time data of the railway locomotive can be any data representing the normal driving state parameters of the railway locomotive, or can also include other data, which are not limited in this embodiment. Among them, the allocation plan generation model can be a machine learning model such as a decision tree, a random forest, a neural network, etc., or a mathematical model established using linear programming, integer programming, heuristic algorithms, etc. to determine the allocation plan of the railway locomotive; the allocation plan generation system can be a generation system of artificial intelligence algorithms or a scheduling management system.

[0128] In this embodiment, railway locomotive resource data of each target line within the time to be recognized is obtained; target railway locomotive resource characteristics corresponding to each target line are generated based on the railway locomotive resource data; a railway locomotive resource demand status prediction model trained to convergence is used, and the target railway locomotive resource demand status corresponding to each target line is predicted according to the target railway locomotive resource characteristics of each target line; the target railway locomotive resource demand status is used to indicate whether there is a shortage of railway locomotive resources; the railway locomotive resource utilization rate corresponding to each target line is calculated based on the target railway locomotive resource demand status of each target line; the target resource allocation strategy corresponding to each target line is determined according to the railway locomotive resource utilization rate of each target line; the railway locomotives of each target line are allocated according to the target resource allocation strategy of each target line; therefore, the target railway locomotive resource characteristics corresponding to each target line obtained from the railway locomotive resource data of each target line provide rich railway locomotive resource data for the railway locomotive resource demand status prediction model, so as to obtain more accurate target railway locomotive resource demand status corresponding to each target line, and then the railway locomotive resource utilization rate corresponding to each target line can be calculated more accurately according to the target railway locomotive resource demand status corresponding to each target line; then, the usage of railway locomotives on each target line is analyzed according to the railway locomotive resource utilization rate of each target line, and the target resource allocation strategy corresponding to each target line is formulated according to the analysis result for allocating the railway locomotives of each target line. Therefore, it is possible to balance railway locomotive resources and solve the problem of shortage or surplus of railway locomotive resources in certain periods or regions.

[0129] As an optional implementation manner, determining the target resource allocation strategy corresponding to each target line according to the railway locomotive resource utilization rate corresponding to each target line includes:

[0130] Classify the railway locomotive resource utilization rate of each target line according to at least one preset utilization rate threshold to obtain the railway locomotive resource utilization rate level corresponding to each target line; determine the traffic level corresponding to the time to be recognized based on the preset traffic threshold; determine the target resource allocation strategy corresponding to each line according to the railway locomotive resource utilization rate level corresponding to each target line and the traffic level corresponding to the time to be recognized.

[0131] Among them, the preset utilization rate threshold is a threshold set for classifying the railway locomotive resource utilization rate, which can be set according to experience or requirements, and is not specifically limited in this embodiment.

[0132] Among them, the railway locomotive resource utilization rate level is the level marked for the railway locomotive resource utilization rate. It can be classified into the first resource utilization rate level, the second utilization rate level, and the third utilization rate level, which can be marked with 1, 2, 3, or marked as others. It is not specifically limited in this embodiment.

[0133] Among them, the first resource utilization rate level is the level with the highest utilization rate of railway locomotive resources.

[0134] Among them, the third resource utilization rate level is the level with the lowest utilization rate of railway locomotive resources.

[0135] Among them, the second resource utilization rate level is the level where the utilization rate of railway locomotive resources is lower than the first resource utilization rate level and higher than the third resource utilization rate level.

[0136] Exemplarily, the levels of the utilization rate of railway locomotive resources can be divided by dividing the utilization rate levels of railway locomotive resources. Exemplarily, the numerical values of the utilization rate of railway locomotive resources greater than or equal to 0.8 and less than or equal to 1 can be divided into the first resource utilization rate level; the numerical values of the utilization rate of railway locomotive resources greater than or equal to 0.5 and less than 0.8 can be divided into the second resource utilization rate level; the numerical values of the utilization rate of railway locomotive resources greater than or equal to 0 and less than 0.5 can be divided into the third resource utilization rate level; the levels of the utilization rate of railway locomotive resources can also be divided according to other thresholds. The above methods are only for illustrative purposes and are not specifically limited.

[0137] Among them, the preset flow threshold is the threshold used to distinguish the set flow levels. For example, it can be set according to weekdays, non-weekdays; working hours, non-working hours, etc., or it can also be set to other thresholds, which are not limited in this embodiment.

[0138] Among them, the flow level refers to different levels divided according to the amount of transport flow during the operation of railway locomotives. The flow levels can be divided into: low peak period, medium peak period and high peak period. Among them, the low peak period represents the period with the least passenger flow; the high peak period represents the period with the most passenger flow; the medium peak period represents the period with a higher passenger flow than the low peak period and a lower passenger flow than the high peak period.

[0139] Specifically, the flow levels can be divided according to time periods. If it belongs to the morning and evening peak periods on weekdays or holiday marks, it is the peak period; the morning and afternoon on weekdays except for the morning and evening peak periods are marked as the medium peak period; other times are marked as the low peak period.

[0140] Optionally, the flow levels can also be determined according to the statistical passenger flow, customer consumption frequency, and geographical location, which are not specifically limited in this embodiment.

[0141] Among them, in order to facilitate the use of the low peak period, medium peak period and high peak period, the low peak period can be marked as 1, the medium peak period can be marked as 2, and the high peak period can be marked as 3, or it can also be marked as other, which are not specifically limited in this embodiment.

[0142] Specifically, it is possible to sequentially determine the preset utilization rate threshold intervals to which the railway locomotive resource utilization rates corresponding to each target line belong, and determine the railway locomotive resource utilization rate levels corresponding to each target line; and then further determine the traffic levels corresponding to each target line within the time to be recognized. If the time to be recognized is one day, it is possible to first determine whether the time to be recognized belongs to a holiday. If it belongs to a holiday, it is directly determined as the peak period; if the time to be recognized does not belong to a holiday, it is possible to further determine whether each hour of that day belongs to the morning peak or the evening peak to mark the traffic level, so as to obtain the traffic level for one day; if the time to be recognized is one week or the like, the traffic levels corresponding to each day can be determined in sequence according to the above method, and the traffic levels of each time period of each day can be marked as the traffic level corresponding to one week; if the time to be recognized is one hour, it is directly determined whether the hour belongs to the morning peak period or the evening peak period to mark the traffic level, so as to obtain the traffic level corresponding to the hour. After determining the railway locomotive resource utilization rate levels and the traffic levels corresponding to the time to be recognized, different target resource allocation strategies can be marked for each target line according to different railway locomotive resource utilization rate levels and the traffic corresponding to the time to be recognized.

[0143] Among them, the numbers of each target line and the corresponding railway locomotive resource utilization rate levels can be stored in the resource utilization rate level storage table.

[0144] Among them, the traffic levels corresponding to each day and the traffic levels corresponding to each time period can be numbered; and the numbers corresponding to each target line, each target line corresponding to each day, 24 hours of each day, and the corresponding traffic level numbers can be stored in the traffic level storage table.

[0145] In this embodiment, determining the target resource allocation strategy corresponding to each target line according to the railway locomotive resource utilization rate corresponding to each target line includes: classifying the railway locomotive resource utilization rates according to at least one preset utilization rate threshold to obtain the railway locomotive resource utilization rate levels corresponding to each target line; determining the traffic level corresponding to the time to be recognized based on the preset traffic threshold; determining the target resource allocation strategy corresponding to each line according to the railway locomotive resource utilization rate levels and the traffic level corresponding to the time to be recognized, and determining the target resource allocation strategy from two levels of the railway locomotive resource utilization rate and the traffic level, making the target resource allocation strategy more reasonable and more in line with the actual allocation requirements.

[0146] As an optional implementation, the railway locomotive resource utilization rate levels include: the first resource utilization rate level, the second utilization rate level, and the third utilization rate level; the traffic levels include: peak period, mid-peak period, and off-peak period; the target resource allocation strategies include: the first resource allocation strategy, the second resource allocation strategy, the third resource allocation strategy, the fourth resource allocation strategy, and the fifth resource allocation strategy; determining the target resource allocation strategy corresponding to each line according to each railway locomotive resource utilization rate level and the traffic level corresponding to the time to be identified, including:

[0147] If the railway locomotive resource utilization rate level is the first resource utilization rate level and the traffic level is the peak period, then determine that the target resource allocation strategy is the first resource allocation strategy; the first resource utilization rate level is the level with the highest railway locomotive resource utilization rate; the first resource allocation strategy includes: increasing the number of railway locomotive trips, increasing the number of carriages, extending the operation time of railway locomotives, and shortening the operation time interval of railway locomotives; if the railway locomotive resource utilization rate level is the first resource utilization rate level and the traffic level is the mid-peak period or the off-peak period, then determine that the target resource allocation strategy is the second resource allocation strategy; the second resource allocation strategy includes: increasing the number of carriages and increasing the number of railway locomotive trips; if the railway locomotive resource utilization rate level is the second resource utilization rate level and the traffic level is the peak period or the mid-peak period or the off-peak period, then determine that the target resource allocation strategy is the third resource allocation strategy; the second resource utilization rate level is the level where the railway locomotive resource utilization rate is lower than the first resource utilization rate level and higher than the third resource utilization rate level; the third resource allocation strategy includes: increasing the number of carriages or increasing the number of railway locomotive trips according to the passenger flow; if the railway locomotive resource utilization rate level is the third resource utilization rate level and the traffic level is the mid-peak period or the peak period; then determine that the target resource allocation strategy is the fourth resource allocation strategy; the third resource utilization rate level is the level with the lowest railway locomotive resource utilization rate; the fourth resource allocation strategy includes: reducing the number of railway locomotive trips, directly increasing the number of carriages according to the passenger flow, and transferring the redundant railway locomotives to standby or maintenance status; if the railway locomotive resource utilization rate level is the third resource utilization rate level and the traffic level is the off-peak period; then determine that the target resource allocation strategy is the fifth resource allocation strategy; the fifth resource allocation strategy includes: shortening the operation time of railway locomotives, reducing the number of railway locomotive trips, and transferring the redundant railway locomotives to standby or maintenance status.

[0148] Specifically, in the resource utilization rate level storage table, first match the resource utilization rate level corresponding to the first target line number; then match the traffic flow level corresponding to the first target line number at the time to be recognized from the traffic flow level query table. If the time to be recognized is 1 day, first query the traffic flow level corresponding to that day from the traffic flow level query table. If the time to be recognized corresponding to the first target line is the peak period, then there is no need to continue querying the traffic flow levels corresponding to each time period, and the peak period is determined as the traffic flow level corresponding to the time to be recognized. And if the railway locomotive resource utilization rate level corresponding to the first target line number is the first utilization rate level, it indicates that during the current time period when the passenger flow of the target line is large, many passengers choose to travel on this target line, and the first resource allocation strategy can be implemented for this target line. The first resource allocation strategy includes: increasing the number of railway locomotive trips, increasing the number of carriages, extending the operation time of railway locomotives, and shortening the running time interval of railway locomotives. If the time to be recognized corresponding to the first target line is the peak period and the railway locomotive utilization rate level corresponding to the first target line is the second utilization rate level, it means that although the current time belongs to the period with a large passenger flow, the number of trips of railway locomotives used on this target line is not high, indicating that the number of passengers choosing this line is small; then the third resource allocation strategy can be implemented for this target line; the number of carriages of the railway locomotives running on this target line can be appropriately increased and the number of trips can be appropriately increased according to the passenger flow for this target line. If the time to be recognized corresponding to the first target line is the peak period and the railway locomotive utilization rate level corresponding to the first target line is the third utilization rate level, it means that although the current time belongs to the period with a large passenger flow, few passengers choose to travel on this target line, then the fourth resource allocation strategy can be implemented for this target line during the time to be recognized; the number of railway locomotive trips can be reduced, the number of carriages can be directly increased according to the passenger flow, and the redundant railway locomotives can be transferred to standby or maintenance status. If the time to be recognized corresponding to the first target line is the mid-peak period, then further judge the traffic flow levels corresponding to each hour of the day, and for each traffic flow level to which each hour belongs, further target resource allocation strategies are carried out.

[0149] Specifically, if it is determined that the traffic level corresponding to each hour is the mid-peak period, and the railway locomotive resource utilization rate level corresponding to the first target line is the first utilization rate level, it indicates that the current time period belongs to the level with moderate passenger flow, but many passengers choose to travel on this target line. Then, the second resource allocation strategy can be executed, and the number of carriages can be increased and the number of railway locomotive trips can be appropriately increased. If it is determined that the traffic level corresponding to each hour is the mid-peak period, and the railway locomotive resource utilization rate level corresponding to the first target line is the second utilization rate level, it indicates that the current time period belongs to the level with moderate passenger flow, but not many passengers choose to travel on this target line. Then, the third resource allocation strategy can be executed, and the number of carriages can be increased or, if necessary, the number of railway locomotive trips can be appropriately increased. If it is determined that the traffic level corresponding to each hour is the mid-peak period, and the railway locomotive resource utilization rate level corresponding to the first target line is the third utilization rate level, it indicates that the current time period belongs to the level with moderate passenger flow, but very few passengers choose to travel on this target line. Then, the fourth resource allocation strategy can be executed, and the number of railway locomotive trips can be reduced, and the number of carriages can be increased directly according to the passenger flow, and the redundant railway locomotives can be transferred to standby or maintenance status.

[0150] Specifically, if it is determined that the traffic level corresponding to each hour is the off-peak period, and the railway locomotive resource utilization rate level corresponding to the first target line is the first utilization rate level, it indicates that the passenger flow in the current time period is small, but many passengers choose to travel on this target line. Then, the second resource allocation strategy can be executed, and the number of carriages can be increased and the number of railway locomotive trips can be appropriately increased. If it is determined that the traffic level corresponding to each hour is the off-peak period, and the railway locomotive resource utilization rate level corresponding to the target line is the second utilization rate level, it indicates that the current time period belongs to the period with small passenger flow, and some passengers choose to travel on this target line. Then, the third resource allocation strategy can be executed, and the number of carriages can be increased or, if necessary, the number of railway locomotive trips can be increased. If it is determined that the traffic level corresponding to each hour is the off-peak period, and the railway locomotive resource utilization rate level corresponding to the target line is the third utilization rate level, it indicates that the current time period belongs to the level with small passenger flow, and very few passengers choose to travel on this target line. Then, the fifth resource allocation strategy can be executed, and the operation time of the railway locomotive can be shortened, the number of railway locomotive trips can be reduced, and the redundant railway locomotives can be transferred to standby or maintenance status.

[0151] Among them, the target resource allocation strategies of other target lines within the time to be identified can be continuously determined in the above manner, so that the target resource allocation strategies corresponding to each target line can be determined. If the time to be identified is one week or one hour, etc., the target resource allocation strategies corresponding to one week or one hour, etc. can be determined in the above manner. The target resource allocation strategies of each target line within the time to be identified and the numbers of each target line can be stored in the target resource allocation strategy storage table.

[0152] In this embodiment, the railway locomotive resource utilization rate levels include: the first utilization rate level, the second utilization rate level, and the third utilization rate level; the traffic levels include: peak period, mid-peak period, and off-peak period; the target resource allocation strategies include: the first resource allocation strategy, the second resource allocation strategy, the third resource allocation strategy, the fourth resource allocation strategy, and the fifth resource allocation strategy; determining the target resource allocation strategy corresponding to each line according to each railway locomotive resource utilization rate level and the traffic level corresponding to the time to be identified, including: if the railway locomotive resource utilization rate level is the first resource utilization rate level and the traffic level is the peak period, then determine the target resource allocation strategy as the first resource allocation strategy; the first resource utilization rate level is the level with the highest railway locomotive resource utilization rate; the first resource allocation strategy includes: increasing the number of railway locomotive trips, increasing the number of carriages, extending the operation time of railway locomotives, and shortening the running time interval of railway locomotives; if the railway locomotive resource utilization rate level is the first resource utilization rate level and the traffic level is the mid-peak period or the off-peak period, then determine the target resource allocation strategy as the second resource allocation strategy; the second resource allocation strategy includes: increasing the number of carriages and increasing the number of railway locomotive trips; if the railway locomotive resource utilization rate level is the second resource utilization rate level and the traffic level is the peak period or the mid-peak period or the off-peak period, then determine the target resource allocation strategy as the third resource allocation strategy; the second resource utilization rate level is the level where the railway locomotive resource utilization rate is lower than the first resource utilization rate level and higher than the third resource utilization rate level; the third resource allocation strategy includes: increasing the number of carriages or increasing the number of railway locomotive trips according to the passenger flow; if the railway locomotive resource utilization rate level is the third resource utilization rate level and the traffic level is the mid-peak period or the peak period; then determine the target resource allocation strategy as the fourth resource allocation strategy; the third resource utilization rate level is the level with the lowest railway locomotive resource utilization rate; the fourth resource allocation strategy includes: reducing the number of railway locomotive trips, directly increasing the number of carriages according to the passenger flow, and transferring the redundant railway locomotives to standby or maintenance status; if the railway locomotive resource utilization rate level is the third resource utilization rate level and the traffic level is the off-peak period; then determine the target resource allocation strategy as the fifth resource allocation strategy; the fifth resource allocation strategy includes: shortening the operation time of railway locomotives, reducing the number of railway locomotive trips, and transferring the redundant railway locomotives to standby or maintenance status; determining different target resource allocation strategies for different traffic levels in combination with different locomotive resource utilization rate levels, making the target resource allocation strategy more matching with the actual usage requirements, and enabling the reasonable allocation of railway locomotives.

[0153] As an optional implementation manner, the railway locomotive resource demand status quantity prediction model is a deep neural network model; the training steps of the railway locomotive resource demand status quantity prediction model include:

[0154] Obtain training samples; the training samples include: the target railway locomotive resource characteristics corresponding to each line and their labeled railway locomotive resource demand status quantities; the target railway locomotive resource characteristics include: train number characteristics, railway locomotive travel characteristics, railway locomotive operation efficiency characteristics, railway locomotive maintenance record characteristics, line layout characteristics, electrified section characteristics of the line, and traffic flow density characteristics of the line; use the training samples to train the pre-constructed neural network model until the neural network model converges, so as to obtain a railway locomotive resource demand status quantity prediction model trained to convergence.

[0155] Among them, the deep neural network model can be: recurrent neural network model, convolutional neural network model, sequence-to-sequence model, graph neural network, etc. These deep neural network models have powerful learning and feature extraction capabilities, and can learn higher-dimensional features of the training samples to generate a railway locomotive resource demand status quantity prediction model with high prediction accuracy.

[0156] Among them, the labeled railway locomotive resource demand status quantity refers to the label marked for the railway locomotive resource demand status corresponding to each line; the railway locomotive resource demand status quantity of the line that needs to allocate locomotives from other regions and has no idle railway locomotives can be marked as 1, indicating that the line has a high demand for railway locomotive resources; for each line that does not need to allocate locomotives from other regions and has 40% or more idle railway locomotives in the data of this line, it indicates that the demand for railway locomotive resources is low, then it is marked as 0; for each line that does not need to allocate locomotives from other regions and has less than 40% of the number of idle railway locomotives, it indicates that the demand for locomotive resources is moderate, then it is marked as 0.5; it can also be marked with other symbols, which are not specifically limited in this embodiment. The labeled railway locomotive resource demand status quantity can be recorded by the staff according to the daily operation of railway locomotives on each line, and the record result and its corresponding line number are recorded in the resource demand status quantity storage table. Among them, 40% is only for illustrative purposes, and it can also be other thresholds, which can be adjusted according to needs and are not specifically limited in this embodiment.

[0157] Specifically, the historical operation data before the time to be identified can be obtained from a database or an operation record system; the railway network data before the time to be identified can be obtained from a database or a geographic information system; then the historical operation data and railway network data before the time to be identified are used to generate the target railway locomotive resource characteristics corresponding to each line according to the data processing method of step 201 and the method of step 202, and the railway locomotive resource demand state quantity corresponding to each line is matched in the resource demand state quantity storage table according to the number of each line; thereby generating training samples, and the training samples can be divided into a training set and a test set according to a ratio of 3:7, the training set is used for training the deep neural network model, and the prediction set is used to verify the accuracy and robustness of the deep neural network algorithm model. Then, the training set can be input into the pre-constructed deep neural network model and iterative training is performed. During each iterative training, the verification set will be synchronously input into the trained model, thereby generating the verification accuracy, which is compared with the accuracy of the previous verification each time. When the verification accuracy no longer increases or is greater than or equal to the set accuracy threshold, it is considered that the model has converged, and the deep learning model trained to convergence can be used as a railway locomotive resource demand state quantity prediction model trained to convergence. The accuracy threshold may be set to 95%, 97%, etc., or other values, which are not limited in this embodiment.

[0158] In this embodiment, the railway locomotive resource demand state quantity prediction model is a deep neural network model; the training steps of the railway locomotive resource demand state quantity prediction model include: obtaining training samples; the training samples include: target railway locomotive resource characteristics corresponding to each line and the railway locomotive resource demand state quantity marked thereon; the target railway locomotive resource characteristics include: train characteristics, railway locomotive travel characteristics, railway locomotive operating efficiency characteristics, railway locomotive maintenance record characteristics, line layout characteristics, line electrification section characteristics and line traffic flow density characteristics; the training samples are used to train the pre-constructed neural network model until the neural network model is trained to converge, so as to obtain the railway locomotive resource demand state quantity prediction model trained to convergence. The sample data composed of the target railway locomotive resource characteristics provides rich railway locomotive resource data for the training of the deep learning model; by training the deep learning model to obtain the railway locomotive resource demand state quantity prediction model trained to convergence, the deep learning model can deeply explore the characteristics of the training samples, and thus through its feature extraction ability, it can learn higher-dimensional railway resource data characteristics, thereby generating a railway locomotive resource demand state quantity prediction model trained to convergence with high prediction accuracy and strong robustness, thereby realizing accurate prediction of the railway locomotive resource demand state quantity.

[0159] As an optional implementation method, allocating railway locomotives to each target line according to each target resource allocation strategy includes:

[0160] Obtain the current railway locomotive resource status information corresponding to each target line; generate an allocation plan in a preset manner according to each current railway locomotive resource status information and the target resource allocation strategy corresponding to each target line.

[0161] Among them, the current railway locomotive resource status information is the real-time status information of each railway locomotive; it may include: the performance level of the railway locomotive, the numbers of the railway locomotives available for each target line, and the maintenance plans of each railway locomotive.

[0162] Among them, the numbers of the railway locomotives available for each target line refer to the numbers corresponding to the railway locomotives that can operate normally.

[0163] Specifically, the numbers of the railway locomotives with the locomotive transportation status being the normal transportation status can be obtained in real time from the monitoring system and stored in the railway locomotive resource status information storage table.

[0164] Among them, the performance level of the railway locomotive can be a level determined according to the engine state performance index, the braking system performance index, and the electrical system state index. It may include: the first performance level, the second performance level, and the third performance level.

[0165] Among them, the first performance level refers to the level where the engine state performance index, the braking system performance index, and the electrical system state index are all qualified.

[0166] Among them, the second performance level refers to the level where only some of the engine state performance index, the braking system performance index, and the electrical system state index are qualified.

[0167] Among them, the third performance level refers to the situation where all of the engine state performance index, the braking system performance index, and the electrical system state index are unqualified.

[0168] Specifically, the engine status index, braking system performance index, and electrical system status index of each available railway locomotive can be obtained in real time from the monitoring system. Then, it is determined whether the engine status index meets the preset qualified threshold for the engine status, whether the braking system performance index meets the preset qualified threshold for the braking system performance, and whether the electrical system status index meets the preset qualified threshold for the electrical system status. If all of the above three indexes meet their corresponding thresholds, it can be indicated that the engine status, braking system performance, and electrical system status are all qualified and do not require repair, and the railway locomotive performance level corresponding to the railway locomotive can be determined to be the first performance level. If only one of the above three indexes meets its corresponding threshold, it indicates that there are abnormal indexes for the railway locomotive and repairs are required to ensure that the vehicle can drive normally in the future. If all of the above three indexes do not meet their corresponding thresholds, it indicates that there are serious abnormal indexes for the railway locomotive and in-depth repairs are required to ensure that the vehicle can drive normally in the future. Finally, the locomotive performance level corresponding to each available railway locomotive is matched to its corresponding number in the railway locomotive resource status information storage table and stored at the associated position corresponding to the number. Among them, the preset qualified threshold for the engine status is the threshold for judging whether the engine status is qualified; the preset qualified threshold for the braking system performance is the threshold for judging whether the braking system performance is qualified; the preset qualified threshold for the electrical system status is the threshold for judging whether the electrical system status is qualified; the preset qualified threshold for the engine status, the preset qualified threshold for the braking system performance, and the preset qualified threshold for the electrical system status can all be set according to experience and are not limited in this embodiment.

[0169] Among them, the maintenance plans for each railway locomotive can include: the first maintenance plan, the second maintenance plan, and the third maintenance plan.

[0170] Among them, the first maintenance plan refers to the maintenance plan formulated for trains without fault abnormalities. Exemplarily, the first maintenance plan can be to perform targeted repairs on the railway locomotive, mainly to inspect and repair the braking system, some auxiliary units, high-voltage and low-voltage electrical appliances, protection devices, and mechanical components, etc.

[0171] Among them, the second maintenance plan refers to the maintenance plan formulated for trains with partial abnormalities. Exemplarily, the second maintenance plan can be to conduct a comprehensive inspection of the railway locomotive and overhaul the abnormal components or systems to improve the locomotive performance.

[0172] Among them, the third maintenance plan refers to the maintenance plan formulated for trains with serious abnormalities. Exemplarily, the third maintenance plan can be to conduct a comprehensive inspection and repair of the railway locomotive to restore the basic performance of the locomotive, which belongs to a restorative comprehensive repair.

[0173] Specifically, it is possible to determine the train numbers corresponding to the first performance level of the railway locomotive, and implement the first maintenance plan; it is possible to determine the train numbers corresponding to the second performance level of the railway locomotive, and implement the second maintenance plan; it is possible to determine the train numbers corresponding to the third performance level of the railway locomotive, and implement the third maintenance plan; and the maintenance method corresponding to each available locomotive is matched to its corresponding number in the railway locomotive resource status information storage table and stored at the associated position corresponding to the corresponding line number.

[0174] Among them, the allocation plan refers to the plan for allocating railway locomotives.

[0175] Among them, the preset method can be automatically generated in the generation system based on artificial intelligence algorithms, can be automatically generated through the integrated scheduling management system, or can be other methods, which are not specifically limited in this embodiment.

[0176] Optionally, it is also possible to determine whether there are stations with high-priority allocation train numbers or key transportation stations among the stations included in each target line. If so, the name of the high-priority allocation station or the key transportation station corresponding to the target line can be recorded in the key station storage table. The high-priority allocation station or the key transportation station can be set by relevant personnel according to needs or can be set by other methods, which are not specifically limited in this embodiment.

[0177] Specifically, it is possible to obtain the railway locomotive performance level, the numbers of the railway locomotives available for each target line, and the maintenance plans of each railway locomotive from the railway locomotive resource status information storage table; and obtain the target resource allocation strategies corresponding to each target line at the time to be recognized from the target resource allocation strategy storage table; obtain the names of high-priority allocation stations and key transportation stations from the key station storage table; and input the list of route staff, each railway locomotive, the number of staff arranged at each station, the list of maintenance staff, the railway locomotive performance level, the numbers of the railway locomotives available for each target line, the maintenance plans of each railway locomotive, the target resource allocation strategies corresponding to each target line at the time to be recognized, the names of high-priority allocation stations and key transportation stations into the generation system of artificial intelligence algorithms or the scheduling management system. The generation system of artificial intelligence algorithms or the scheduling management system can, through analyzing the above information, reasonably allocate the numbers of the railway locomotives running on each target line, the departure time, the stations passed by the line, the arrival time at each station, the maintenance time of each railway locomotive, the numbers of the railway locomotives maintained by the maintenance staff corresponding to each train number, the staff corresponding to each railway locomotive, the staff corresponding to each station, etc., so as to generate an allocation plan.

[0178] In this embodiment, the allocation of railway locomotives for each target line according to each target resource allocation strategy includes: obtaining the current railway locomotive resource status information corresponding to each target line; generating an allocation plan according to each current railway locomotive resource status information and the target resource allocation strategy corresponding to each target line in a preset manner. It is possible to formulate a reasonable and effective allocation plan by analyzing the current railway locomotive resource status information and the target resource allocation strategy corresponding to each target line, so as to achieve the allocation of railway locomotives and to balance the railway locomotive resources corresponding to each target line.

[0179] As an optional implementation manner, after generating an allocation plan according to each current railway locomotive resource status information and the target resource allocation strategy corresponding to each target line in a preset manner, it further includes: performing an execution risk assessment on the allocation result of the target allocation plan;

[0180] Correspondingly, the execution risks include: railway locomotive failure risk, transportation delay risk, and line congestion risk; performing an execution risk assessment on the allocation result in the target allocation plan includes: obtaining based on the railway locomotive performance evaluation index, and judging whether there is a railway locomotive failure risk according to whether the railway locomotive performance evaluation index exceeds the preset railway locomotive performance index threshold; and, obtaining the delay rate of the railway locomotive, and judging whether there is a transportation delay risk according to whether the delay rate of the railway locomotive exceeds the preset railway locomotive delay rate threshold; and, obtaining the average running speed of each railway locomotive, determining the number of railway locomotives whose average running speed is lower than the normal passing speed threshold corresponding to each line, and judging whether there is a line congestion risk according to whether the number of railway locomotives exceeds the preset number threshold.

[0181] Among them, the railway locomotive failure risk refers to the risk that each running railway locomotive has a railway locomotive failure.

[0182] Among them, the transportation delay risk refers to the risk that each running railway locomotive has a risk of arriving at the station late.

[0183] Among them, the line congestion risk refers to the risk that there is railway locomotive congestion in each line.

[0184] Among them, the delay rate of the railway locomotive is the ratio of the number of trains of the railway locomotive that do not arrive at the end point on time to the total number of all running railway locomotives on this line; specifically, the number of railway locomotives that do not arrive at the end point on time for each target line can be counted; then the number of all running railway locomotives on each target line can be counted; calculating the ratio of the number of railway locomotives that do not arrive at the end point on time for each target line to the number of all running railway locomotives on each target line can obtain the delay rate corresponding to each target line. In the above manner, the delay rates corresponding to each target line can be obtained, and the numbers of each target line and their corresponding delay rates are stored in the delay rate storage table.

[0185] Among them, the preset threshold of the performance index of the railway locomotive is the data preset to determine whether the performance index of the railway locomotive is qualified, which can be set according to requirements or experience and is not limited in this embodiment.

[0186] Among them, the preset delay rate threshold of the railway locomotive is the threshold preset for judging whether there is a risk of railway locomotive delay, which can be set according to requirements or experience and is not limited in this embodiment.

[0187] Among them, the normal passing speed threshold is the threshold preset for judging whether the normal passing speed is exceeded in each line, which can be set according to requirements or experience and is not limited in this embodiment.

[0188] Among them, the railway locomotive performance evaluation index is an index used to evaluate the operation performance of the railway locomotive, and its calculation method is as shown in formula (3):

[0189]

[0190] Among them, P(t, l) represents the railway locomotive performance evaluation index at time t and on line l; U(t, l) represents the railway locomotive resource utilization rate at time t and on line l; B U represents the reference value of the railway locomotive resource utilization rate, which is used to standardize the railway locomotive resource utilization rate; A U represents the model parameter used to adjust the influence degree of the railway locomotive resource utilization rate; F(t, l) represents the railway locomotive failure rate at time t and on line l; B F represents the reference value of the railway locomotive failure rate, which is used to standardize the failure rate; A F represents the model parameter used to adjust the influence degree of the railway locomotive failure rate; V(t, l) represents the average running speed of the railway locomotive at time t and on line l; V max represents the maximum running speed of the railway locomotive, which is used to standardize the average running speed, and A V represents the model parameter used to adjust the influence degree of the railway locomotive running speed.

[0191] Among them, the model parameter A U used to adjust the influence degree of the railway locomotive resource utilization rate, F the model parameter A V used to adjust the influence degree of the railway locomotive failure rate, and U the model parameter A U used to adjust the influence degree of the railway locomotive running speed are empirical values, which can be experimentally measured by relevant personnel and stored in the empirical value storage table. The reference value B of the railway locomotive resource utilization rate can be calculated by taking the average value of the railway locomotive resource utilization rates of each line.; Similarly, the average value of the failure rates of each railway locomotive can also be calculated as the reference value B of the railway locomotive failure rate F .

[0192] It can be understood that the value range of P(t, l) is between 0 and 1. 0 indicates the worst performance of the railway locomotive, and 1 indicates the best performance of the railway locomotive. The closer the value is to 1, the better the performance of the railway locomotive, and the closer it is to 0, the worse the performance of the railway locomotive. It can be seen from formula (3) that when U(t, l) increases, it means that the number of available railway locomotives increases, indicating that the performance state of the railway locomotive is normal, thus increasing the railway locomotive performance evaluation index P(t, l); when F(t, l) decreases, it means that the failure rate of the railway locomotive decreases, indicating that the number of non-faulty railway locomotives increases and the performance state of the railway locomotive is normal, thus increasing the railway locomotive performance evaluation index P(t, l); when V(t, l) increases, it means that the average running speed of the railway locomotive increases, indicating that the state of the railway locomotive is normal and can provide a strong traction force for the railway locomotive, thus increasing the railway locomotive performance evaluation index P(t, l).

[0193] Specifically, the average running speed V(t, l) of the railway locomotive and the failure rate F(t, l) of the railway locomotive generated after the implementation of the allocation plan can be obtained from the database or the operation record system; then, the average value of the failure rates of all locomotives on this line can be taken as the reference value B of the railway locomotive failure rate F ; The railway locomotive resource utilization rate U(t, l) of this line after the implementation of the allocation plan can be calculated according to the scheme for calculating the railway locomotive resource utilization rate in this application, and the railway locomotive resource utilization rates of other lines can be calculated synchronously, and the average value of the locomotive resource utilization rates corresponding to all lines can be taken as the reference value B of the railway locomotive resource utilization rate U ; The average running speed of each railway locomotive after the implementation of the allocation plan can be obtained from the database or the operation record system, and the maximum value of the average running speed can be taken as the maximum running speed V of the railway locomotive max ; The model parameter A for adjusting the influence degree of the railway locomotive resource utilization rate can be obtained from the empirical value storage table U , the model parameter A for adjusting the influence degree of the railway locomotive failure rate F and the model parameter A for adjusting the influence degree of the railway locomotive running speed V are empirical values; and all the above-obtained parameters are input into formula (3), so as to obtain the railway locomotive performance evaluation index of the line after the implementation of the allocation plan; repeating the above process, the railway locomotive performance evaluation indexes corresponding to each target line can be obtained. The numbers of each target line and their corresponding railway locomotive performance evaluation indexes can be stored in the evaluation index storage table

[0194] Understandably, after the railway locomotives are allocated according to the target allocation plan, it is also possible to conduct an execution risk assessment on the execution result of the allocation plan. Specifically, the railway locomotive performance evaluation indexes corresponding to each target line can be obtained from the evaluation index storage table, and each railway locomotive performance evaluation index can be compared with the preset railway locomotive performance index threshold, and it is judged in turn whether each railway locomotive performance evaluation index exceeds the preset railway locomotive performance index threshold. If there is a line where the railway locomotive performance evaluation index exceeds the preset railway locomotive performance index threshold, it is judged that there is a risk of railway locomotive failure. The delay rate corresponding to each target line can be obtained from the delay rate storage table and compared with the preset delay rate threshold of the railway locomotive respectively. If there is a target line that exceeds the preset delay rate threshold of the railway locomotive, it indicates that there is a risk of transportation delay; the average running speed of each railway locomotive generated after the execution of the allocation plan can be obtained from the database or the operation record system; first, it is judged whether the average running speed of all railway locomotives on the same target line exceeds the normal passing speed threshold. If it exceeds, the number of locomotives whose average running speed exceeds the normal passing speed threshold is further counted. If the number of locomotives whose average running speed exceeds the normal passing speed threshold exceeds the preset number threshold, it indicates that there is a risk of line congestion on this line. Among them, the preset number threshold can be set according to requirements and is not limited in the embodiment.

[0195] Specifically, if there is any one of the risks of railway locomotive failure risk, transportation delay risk and line congestion risk, it indicates that the execution of the target allocation plan is risky, and it is necessary to allocate the whole locomotive, optimize the operation line and adjust the schedule to realize the adjustment of the target allocation plan. Exemplarily, if there is a risk of railway locomotive failure, it means that the railway locomotive with the risk of railway locomotive failure runs frequently or the maintenance plan is arranged unreasonably, and this railway locomotive is prone to failure. The maintenance times of each locomotive and the maintenance time arrangement of each railway locomotive can be adjusted according to the current railway locomotive resource status information of the railway locomotive during the non-peak period of each day to reduce the failure rate of the railway locomotive; if there is a risk of transportation delay, it may be due to insufficient staff allocation resulting in the risk of transportation delay, and the dispatching staff can be reasonably allocated; it may also be due to abnormal weather resulting in the risk of transportation delay, and additional standby train trips can be added to the route with the risk of transportation delay; if there is a risk of line congestion, it may be because too many railway locomotives are allocated on this line. On the basis of meeting the transportation passenger flow, the number of railway locomotive trips on this line can be reduced, or the departure time of each railway locomotive can be adjusted. There may be various reasons for the risks of railway locomotive failure risk, transportation delay risk and line congestion risk. The above is only an exemplary description and is not limited in this embodiment. When aiming at the reasons for different risks of railway locomotive failure risk, transportation delay risk and line congestion risk, the allocation plan can be flexibly adjusted.

[0196] In this embodiment, after generating an allocation plan according to the current railway locomotive resource status information and the target resource allocation strategies corresponding to each target line in a preset manner, the following steps are further included: performing an execution risk assessment on the allocation results in the target allocation plan; the execution risks include: railway locomotive failure risk, transportation delay risk, and line congestion risk; performing an execution risk assessment on the allocation results of the target allocation plan includes: obtaining a railway locomotive performance evaluation index, and judging whether there is a railway locomotive failure risk according to whether the railway locomotive performance evaluation index exceeds a preset railway locomotive performance index threshold; and obtaining the delay rate of the railway locomotive, and judging whether there is a transportation delay risk according to whether the delay rate of the railway locomotive exceeds a preset railway locomotive delay rate threshold; and obtaining the average running speed of each railway locomotive, determining the number of railway locomotives whose average running speed is lower than the normal passing speed threshold corresponding to each line, and judging whether there is a line congestion risk according to whether the number of railway locomotives exceeds a preset number threshold. By performing an execution risk assessment on the allocation results of the target allocation plan, the problems existing in the execution of the target allocation plan can be discovered in time, and then the target allocation plan can be adjusted in a timely and effective manner to meet the usage requirements of each target line for railway locomotive allocation.

[0197] Figure 3 The flowchart of the railway locomotive allocation method provided by another embodiment of the present application is as Figure 3 shown. Then, the railway locomotive allocation method provided by this embodiment includes the following steps:

[0198] Step 301, obtaining training samples, including: the target railway locomotive resource characteristics corresponding to each line and the marked railway locomotive resource demand status quantities.

[0199] Step 302, iteratively training a deep learning model with the training samples to generate a railway locomotive resource demand status quantity prediction model trained to convergence.

[0200] Step 303, obtaining the railway locomotive resource data of each target line during the time to be recognized.

[0201] Step 304, generating the target railway locomotive resource characteristics corresponding to each target line based on the railway locomotive resource data.

[0202] Step 305, using the railway locomotive resource demand status quantity prediction model trained to convergence and according to the target railway locomotive resource characteristics of each target line, predicting the target railway locomotive resource demand status quantity corresponding to each target line.

[0203] Step 306, calculating the railway locomotive resource utilization rate corresponding to each target line based on the target railway locomotive resource demand status quantities.

[0204] Step 307: Obtain the current railway locomotive resource status information corresponding to each target line; generate an allocation plan in a preset manner according to each current railway locomotive resource status information and the target resource allocation strategy corresponding to each target line, and allocate railway locomotives to each target line according to the allocation plan.

[0205] Step 308: Perform an execution risk assessment on the allocation results in the target allocation plan, and dynamically adjust the allocation plan according to the assessment results.

[0206] In this embodiment, the implementation manners and technical effects of steps 301 - 308 are similar to those of the corresponding solutions in the above embodiment, and will not be elaborated here.

[0207] Figure 4 FIG. is a schematic structural diagram of a railway locomotive allocation device provided in an embodiment of the present application. The railway locomotive allocation device provided in this embodiment is located in a railway locomotive allocation device. Then, the railway locomotive allocation device 40 provided in this embodiment includes: an acquisition module 401, a generation module 402, a prediction module 403, a calculation module 404, a determination module 405, and an allocation module 406.

[0208] The acquisition module 401 is configured to acquire railway locomotive resource data of each target line within the time to be recognized.

[0209] The generation module 402 is configured to generate target railway locomotive resource characteristics corresponding to each target line based on the railway locomotive resource data.

[0210] The prediction module 403 is configured to use a railway locomotive resource demand status quantity prediction model trained to convergence and predict the target railway locomotive resource demand status quantity corresponding to each target line according to each target railway locomotive resource characteristic; the target railway locomotive resource demand status quantity is used to indicate whether there is a shortage of railway locomotive resources.

[0211] The calculation module 404 is configured to calculate the railway locomotive resource utilization rate corresponding to each target line based on each target railway locomotive resource demand status quantity.

[0212] The determination module 405 is configured to determine the target resource allocation strategy corresponding to each target line according to each railway locomotive resource utilization rate.

[0213] The allocation module 406 is configured to allocate railway locomotives of each target line according to each target resource allocation strategy.

[0214] Optionally, when determining the target resource allocation strategy corresponding to each target line according to each railway locomotive resource utilization rate, the determination module 405 is specifically configured to:

[0215] Classify the utilization rate of each railway locomotive resource according to at least one preset utilization rate threshold to obtain the utilization rate level of the railway locomotive resources corresponding to each target line; determine the traffic level corresponding to the time to be identified based on the preset traffic threshold; determine the target resource allocation strategy corresponding to each line according to the utilization rate level of each railway locomotive resource and the traffic level corresponding to the time to be identified.

[0216] Optionally, the utilization rate levels of railway locomotive resources include: the first utilization rate level, the second utilization rate level, and the third utilization rate level; the traffic levels include: peak period, mid-peak period, and off-peak period; the target resource allocation strategies include: the first resource allocation strategy, the second resource allocation strategy, the third resource allocation strategy, the fourth resource allocation strategy, and the fifth resource allocation strategy.

[0217] Correspondingly, the determining module 405, when determining the target resource allocation strategy corresponding to each line according to the utilization rate level of each railway locomotive resource and the traffic level corresponding to the time to be identified, is specifically configured to:

[0218] If the utilization rate level of the railway locomotive resource is the first utilization rate level and the traffic level is the peak period, determine that the target resource allocation strategy is the first resource allocation strategy; the first utilization rate level is the level with the highest utilization rate of railway locomotive resources; the first resource allocation strategy includes: increasing the number of railway locomotive trips, increasing the number of carriages, extending the operation time of railway locomotives, and shortening the running time interval of railway locomotives; if the utilization rate level of the railway locomotive resource is the first utilization rate level and the traffic level is the mid-peak period or the off-peak period, determine that the target resource allocation strategy is the second resource allocation strategy; the second resource allocation strategy includes: increasing the number of carriages and increasing the number of railway locomotive trips; if the utilization rate level of the railway locomotive resource is the second utilization rate level and the traffic level is the peak period or the mid-peak period or the off-peak period, determine that the target resource allocation strategy is the third resource allocation strategy; the second utilization rate level is the level where the utilization rate of railway locomotive resources is lower than the first utilization rate level and higher than the third utilization rate level; the third resource allocation strategy includes: increasing the number of carriages or the number of railway locomotive trips according to the passenger flow; if the utilization rate level of the railway locomotive resource is the third utilization rate level and the traffic level is the mid-peak period or the peak period; determine that the target resource allocation strategy is the fourth resource allocation strategy; the third utilization rate level is the level with the lowest utilization rate of railway locomotive resources; the fourth resource allocation strategy includes: reducing the number of railway locomotive trips, directly increasing the number of carriages according to the passenger flow, and transferring the redundant railway locomotives to standby or maintenance status; if the utilization rate level of the railway locomotive resource is the third utilization rate level and the traffic level is the off-peak period; determine that the target resource allocation strategy is the fifth resource allocation strategy; the fifth resource allocation strategy includes: shortening the operation time of railway locomotives, reducing the number of railway locomotive trips, and transferring the redundant railway locomotives to standby or maintenance status.

[0219] Optionally, the prediction model for the resource demand status of railway locomotives is a deep neural network model.

[0220] Optionally, the railway locomotive allocation device further includes: a training module.

[0221] Correspondingly, the training module is used to: obtain training samples; the training samples include: the target railway locomotive resource characteristics corresponding to each line and the labeled resource demand status of railway locomotives; the target railway locomotive resource characteristics include: train number characteristics, railway locomotive travel characteristics, railway locomotive operation efficiency characteristics, railway locomotive maintenance record characteristics, line layout characteristics, electrified section characteristics of the line, and traffic flow density characteristics of the line; use the training samples to train the pre-constructed neural network model until the neural network model converges, so as to obtain a prediction model for the resource demand status of railway locomotives that has converged.

[0222] When allocating railway locomotives for each target line according to each target resource allocation strategy, the allocation module 406 is used for:

[0223] Obtain the current railway locomotive resource status information corresponding to each target line; generate an allocation plan according to each current railway locomotive resource status information and the target resource allocation strategy corresponding to each target line in a preset manner.

[0224] Optionally, the railway locomotive allocation device further includes: an evaluation module.

[0225] Correspondingly, after generating an allocation plan according to each current railway locomotive resource status information and the target resource allocation strategy corresponding to each target line in a preset manner, the evaluation module is used for:

[0226] Perform an execution risk assessment on the allocation result of the target allocation plan.

[0227] Optionally, the execution risks include: railway locomotive failure risk, transportation delay risk, and line congestion risk.

[0228] When performing an execution risk assessment on the allocation result in the target allocation plan, the evaluation module is specifically used for:

[0229] Obtain the railway locomotive performance evaluation index, and determine whether there is a railway locomotive failure risk according to whether the railway locomotive performance evaluation index exceeds the preset railway locomotive performance index threshold; and, obtain the delay rate of the railway locomotive, and determine whether there is a transportation delay risk according to whether the delay rate of the railway locomotive exceeds the preset railway locomotive delay rate threshold; and, obtain the average running speed of each railway locomotive, determine the number of railway locomotives whose average running speed is lower than the normal passing speed threshold corresponding to each line, and judge whether there is a line congestion risk according to whether the number of railway locomotives exceeds the preset number threshold.

[0230] Figure 5 This is a schematic structural diagram of the electronic device provided in the embodiment of the present application. As Figure 5 shown, the electronic device 50 provided in this embodiment includes: a processor 501 and a memory 502 communicatively connected to the processor 501.

[0231] The memory 502 stores computer-executable instructions; the processor 501 executes the computer-executable instructions stored in the memory to implement the railway locomotive allocation method provided in any one of the above embodiments. For specific details, reference can be made to the relevant descriptions in the above method embodiments, and no further elaboration will be provided here.

[0232] Among them, the program may include program code, and the program code includes computer-executable instructions. The memory 502 may include high-speed RAM memory and may also include non-volatile memory, such as at least one disk memory.

[0233] Among them, in this embodiment, the memory 502 is connected to the processor 501 through a bus. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity of representation, Figure 5 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0234] The embodiment of the present application also provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, they are used to implement the railway locomotive allocation method provided in any one of the above embodiments. For example, the computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0235] The embodiment of the present application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the railway locomotive allocation method in any one of the above embodiments.

[0236] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should be aware that this application is not limited by the described action sequence, because according to this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0237] It is further noted that although the steps in the flowchart are shown sequentially in the direction of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0238] It should be understood that the above device embodiments are illustrative only, and the devices of this application can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.

[0239] In addition, without special instructions, in each embodiment of this application, the functional units / modules can be integrated in one unit / module, or each unit / module can exist physically alone, or two or more units / modules can be integrated together. The above integrated unit / module can be implemented in the form of hardware or in the form of a software program module.

[0240] When the integrated unit / module is implemented in the form of hardware, the hardware can be a digital circuit, an analog circuit, etc. The physical implementation of the hardware structure includes but is not limited to transistors, memristors, etc. Unless otherwise specified, the processor can be any suitable hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC, etc. Unless otherwise specified, the storage unit can be any suitable magnetic storage medium or magneto-optical storage medium, such as resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), hybrid memory cube (HMC), etc.

[0241] When the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of various embodiments of this application. And the aforementioned memory includes: various media that can store program codes, such as USB flash drives, read-only memory (ROM), random access memory (RAM), mobile hard disks, magnetic disks, or optical discs.

[0242] In the above embodiments, the descriptions of the various embodiments each have their own emphasis. For parts not described in detail in a certain embodiment, reference may be made to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification. Those skilled in the art will readily conceive of other implementation manners of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any variations, uses, or adaptations of the present application, which follow the general principles of the present application and include well-known knowledge or conventional technical means in the technical field not disclosed in the present application. The specification and the embodiments are only regarded as exemplary, and the true scope and spirit of the present application are pointed out by the following claims. It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present application is only limited by the appended claims.

Claims

1. A method for allocating railway locomotives, characterized in that, Including: Obtain the railway locomotive resource data of each target line within the time to be recognized; Generate the target railway locomotive resource characteristics corresponding to each target line based on the railway locomotive resource data; Adopt a railway locomotive resource demand status quantity prediction model trained to convergence and predict the target railway locomotive resource demand status quantity corresponding to each target line according to each of the target railway locomotive resource characteristics; the target railway locomotive resource demand status quantity is used to indicate whether there is a shortage of railway locomotive resources; Calculate the railway locomotive resource utilization rate corresponding to each target line based on each of the target railway locomotive resource demand status quantities; Determine the target resource allocation strategy corresponding to each target line according to each of the railway locomotive resource utilization rates; Allocate the railway locomotives of each target line according to each target resource allocation strategy.

2. The method according to claim 1, wherein Determine the target resource allocation strategy corresponding to each target line according to each of the railway locomotive resource utilization rates, including: Classify each of the railway locomotive resource utilization rates according to at least one preset utilization rate threshold to obtain the railway locomotive resource utilization rate level corresponding to each target line; Determine the traffic level corresponding to the time to be recognized based on a preset traffic threshold; Determine the target resource allocation strategy corresponding to each line according to each railway locomotive resource utilization rate level and the traffic level corresponding to the time to be recognized.

3. The method according to claim 2, wherein The railway locomotive resource utilization rate levels include: the first resource utilization rate level, the second utilization rate level, and the third utilization rate level; the traffic levels include: peak period, mid-peak period, and off-peak period; the target resource allocation strategies include: the first resource allocation strategy, the second resource allocation strategy, the third resource allocation strategy, the fourth resource allocation strategy, and the fifth resource allocation strategy; Determine the target resource allocation strategy corresponding to each line according to each railway locomotive resource utilization rate level and the traffic level corresponding to the time to be recognized, including: If the railway locomotive resource utilization rate level is the first resource utilization rate level and the traffic level is the peak period, determine that the target resource allocation strategy is the first resource allocation strategy; the first resource utilization rate level is the level with the highest railway locomotive resource utilization rate; the first resource allocation strategy includes: increasing the number of railway locomotive trips, increasing the number of carriages, extending the operation time of railway locomotives, and shortening the running time interval of railway locomotives; If the railway locomotive resource utilization rate level is the first resource utilization rate level and the traffic level is the mid-peak period or the off-peak period, determine that the target resource allocation strategy is the second resource allocation strategy; the second resource allocation strategy includes: increasing the number of carriages and increasing the number of railway locomotive trips; If the railway locomotive resource utilization rate level is the second resource utilization rate level and the traffic level is the peak period or the mid-peak period or the off-peak period, determine that the target resource allocation strategy is the third resource allocation strategy; the second resource utilization rate level is the level where the railway locomotive resource utilization rate is lower than the first resource utilization rate level and higher than the third resource utilization rate level; the third resource allocation strategy includes: increasing the number of carriages or increasing the number of railway locomotive trips according to the passenger flow; If the railway locomotive resource utilization rate level is the third resource utilization rate level and the traffic flow level is the medium peak period or the peak period; then determine that the target resource allocation strategy is the fourth resource allocation strategy; the third resource utilization rate level is the level with the lowest railway locomotive resource utilization rate; the fourth resource allocation strategy includes: reducing the number of railway locomotive trips, directly increasing the number of carriages according to the passenger flow, and transferring the redundant railway locomotives to the standby or maintenance state; If the railway locomotive resource utilization rate level is the third resource utilization rate level and the traffic flow level is the low valley period; then determine that the target resource allocation strategy is the fifth resource allocation strategy; the fifth resource allocation strategy includes: shortening the operation time of railway locomotives, reducing the number of railway locomotive trips, and transferring the redundant railway locomotives to the standby or maintenance state.

4. The method according to any one of claims 1 to 3, characterized in that, The railway locomotive resource demand status prediction model is a deep neural network model; The training steps of the railway locomotive resource demand status prediction model include: Obtain training samples; the training samples include: the target railway locomotive resource characteristics corresponding to each line and the labeled railway locomotive resource demand status; the target railway locomotive resource characteristics include: train number characteristics, railway locomotive travel characteristics, railway locomotive operation efficiency characteristics, railway locomotive maintenance record characteristics, line layout characteristics, electrified section characteristics of the line, and traffic flow density characteristics of the line; Use the training samples to train the pre-constructed neural network model until the neural network model converges, so as to obtain a railway locomotive resource demand status prediction model trained to convergence.

5. The method according to claim 1, wherein The allocation of railway locomotives for each target line according to each target resource allocation strategy includes: Obtain the current railway locomotive resource status information corresponding to each target line; Generate an allocation plan according to the current railway locomotive resource status information and the target resource allocation strategy corresponding to each target line in a preset manner.

6. The method according to claim 5, wherein After generating the allocation plan according to the current railway locomotive resource status information and the target resource allocation strategy corresponding to each target line in a preset manner, it further includes: Conduct an execution risk assessment on the allocation result in the target allocation plan; The execution risks include: railway locomotive failure risk, transportation delay risk, and line congestion risk; The execution risk assessment of the allocation result of the target allocation plan includes: Obtain the railway locomotive performance evaluation index, and judge whether there is the railway locomotive failure risk according to whether the railway locomotive performance evaluation index exceeds the preset railway locomotive performance index threshold; And obtain the delay rate of the railway locomotive, and judge whether there is the transportation delay risk according to whether the delay rate of the railway locomotive exceeds the preset railway locomotive delay rate threshold; And obtain the average running speed of each railway locomotive, determine the number of railway locomotives whose average running speed is lower than the normal passing speed threshold corresponding to each line, and judge whether there is the line congestion risk according to whether the number of railway locomotives exceeds the preset number threshold.

7. A railway locomotive allocation device, comprising: An acquisition module, configured to acquire the railway locomotive resource data of each target line within the time to be recognized; A generation module, configured to generate the target railway locomotive resource features corresponding to each target line based on the railway locomotive resource data; A prediction module, configured to use the railway locomotive resource demand status quantity prediction model trained to convergence and predict the target railway locomotive resource demand status quantity corresponding to each target line according to each of the target railway locomotive resource features; the target railway locomotive resource demand status quantity is used to indicate whether there is a shortage of railway locomotive resource demand; A calculation module, configured to calculate the railway locomotive resource utilization rate corresponding to each target line based on each of the target railway locomotive resource demand status quantities; A determination module, configured to determine the target resource allocation strategy corresponding to each target line according to each of the railway locomotive resource utilization rates; An allocation module, configured to allocate the railway locomotives of each target line according to each of the target resource allocation strategies.

8. An electronic device, comprising: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, Computer-executable instructions are stored in the computer-readable storage medium, and when the computer-executable instructions are executed by a processor, they are used to implement the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that, It includes a computer program, and when the computer program is executed by a processor, it implements the method according to any one of claims 1-6.

Images