Compilation method of station yard graph for integrating driving prompts

Abstract

The invention discloses a compilation method of a station yard graph for integrating driving prompts, which comprises the following steps of: S1, generating a common control combination and an association mode, and forming a control use behavior model; s2, inputting the control into a graph neural network by using a behavior model to generate an intelligent layout suggestion; s3, according to the intelligent layout suggestion, performing automatic layout on the controls by adopting a force steering algorithm, and generating a preliminary station yard graph layout; s4, constructing a finite-state machine of the control based on the initial station yard graph layout, so that the control realizes dynamic behavior response; s5, forming a station yard graph with dynamic response capability based on dynamic control behaviors; s6, searching and calculating an optimal access path by using a simulated annealing tree, and performing path conflict detection and adjustment in combination with a constraint propagation algorithm; and S7, carrying out image processing and feature calibration in an augmented reality environment, and providing a visual path and a station yard view. According to the method, path optimization and station yard graph compiling are realized by utilizing a graph neural network, simulated annealing tree search and the like.

Description

Technical Field

[0001] The present invention relates to the technical field of scenario graph compilation, and particularly to a method for compiling a station yard map for integrating driving tips. Background Art

[0002] In modern rail transit dispatching and management, the compilation and maintenance of station yard maps are important components for ensuring train dispatching, driving safety, and yard management. Traditional methods of compiling yard maps usually rely on manual design and static layouts. Although this method can meet basic requirements in small-scale or fixed-mode scenarios, it exposes significant deficiencies in complex dispatching scenarios and real-time changing transportation systems. The compilation of station yard maps in the prior art often lacks intelligence, dynamic response capabilities, and user interactivity, making it difficult to meet the high requirements for real-time performance and complexity in modern rail transit.

[0003] Existing technologies for compiling station yard maps mainly rely on static graphics software and manual adjustments. Designers need to gradually complete the layout and control settings according to the actual situation of the station. This method has significant limitations. For example, when dispatching conditions or yard layouts change, re-compiling or modifying the yard map requires a large amount of manual intervention, which is time-consuming and laborious, and it is difficult to complete adaptive adjustments in a short time. In addition, static station yard maps lack the ability to adapt to real-time data and dynamic environments, resulting in problems such as lagging responses and untimely information updates when dealing with emergencies or complex dispatching tasks.

[0004] In terms of data analysis and automatic layout, although the prior art has introduced some simple algorithms to assist in layout design, such as rule-based automatic layout algorithms or some heuristic methods, these methods can usually only handle layout problems of limited scale and cannot dynamically adapt to changes in control states or complex user interaction behaviors. In addition, these algorithms lack sufficient intelligent means in layout and path planning and cannot effectively integrate historical data and user behavior patterns to provide more targeted layout suggestions or path optimization strategies. Existing layout technologies have deficiencies in complexity and flexibility and cannot achieve efficient multi-control layout and real-time optimization in large-scale scenarios.

[0005] In terms of path planning, existing technologies usually rely on basic path search algorithms such as Dijkstra's algorithm or A* algorithm. These algorithms can achieve path search and optimization in static and simple yard maps, but they show obvious limitations in dynamic environments. These traditional algorithms are difficult to provide fast and effective path optimization under real-time data synchronization and complex constraint conditions. Especially when facing frequently changing yard layouts and multi-dimensional path conflicts, it is difficult to maintain the effectiveness and accuracy of calculations. In addition, these algorithms lack flexibility and adaptability and cannot synchronize and update path planning in a multi-user operation environment, resulting in performance bottlenecks in real-time applications.

[0006] In terms of user interaction and real-time feedback, existing technologies often rely on unidirectional data streams or simple event listening mechanisms and lack efficient real-time data synchronization technologies. Data transmission between the server and the client usually faces problems of delay and inconsistency, which will affect the user's operation experience and the system's response speed during use. Although some systems may apply simple data synchronization and listening mechanisms, in the face of complex interactive operations and multi-user real-time operations, the performance and stability of the system often cannot meet the actual needs.

[0007] In terms of image processing and augmented reality integration, traditional station yard map compilation systems mainly focus on the planar display of two-dimensional graphics and lack the ability to combine with physical scenes and display in three-dimensional space. Even in existing technologies, there are some augmented reality applications, which are mostly limited to simple path overlay displays and are difficult to support complex virtual control operations and multi-view real-time adjustments. The lack of support for feature calibration and real-time device pose estimation results in insufficient display accuracy between virtual controls and physical scenes, affecting the intuitiveness and effectiveness of operations.

[0008] Therefore, how to provide a compilation method for a station yard map for integrating train operation prompts is an urgent problem to be solved by those skilled in the art. Summary of the Invention

[0009] An object of the present invention is to propose a compilation method for a station yard map for integrating train operation prompts. The present invention comprehensively applies data mining, graph neural networks, long short-term memory networks, and augmented reality technologies to achieve intelligent compilation of station yard maps and path optimization. Through the combination of an intelligent layout algorithm and simulated annealing tree search with a constraint propagation algorithm for path calculation and conflict detection, the rationality of the layout and the efficiency of path planning are effectively improved. The real-time data synchronization technology ensures fast response between the client and the server, enhancing the interactivity and stability of the system. Combining augmented reality technology, virtual controls and paths are overlaid and displayed in the physical yard, providing an intuitive and dynamic operation view to meet the requirements of modern rail transit dispatching.

[0010] A method for compiling a station yard map for integrated driving tips according to an embodiment of the present invention includes the following steps:

[0011] S1. Collect historical station yard design data and user operation records, and analyze them using an association rule mining algorithm to generate common control combinations and association patterns, forming a control usage behavior model;

[0012] S2. Input the control usage behavior model into a graph neural network for route configuration analysis, and combine it with a long short-term memory network for time series prediction of user operation behaviors to generate intelligent layout suggestions;

[0013] S3. According to the intelligent layout suggestions, use a force-directed algorithm to automatically layout the controls, and combine with an Adam optimizer to achieve a reasonable distribution of the controls in the station yard map, generating a preliminary station yard map layout;

[0014] S4. Based on the preliminary station yard map layout, construct a finite state machine for the controls, define different states and behavior conversions of the controls, and process user interaction events through an event-driven model, enabling the controls to achieve dynamic behavior responses in the station yard map layout;

[0015] S5. Based on the dynamic control behaviors, use server-client real-time data synchronization technology to achieve real-time data update between the client and the server, forming a station yard map with dynamic response capabilities;

[0016] S6. Utilize the real-time synchronized data, use simulated annealing tree search to calculate the optimal route path, and combine with a constraint propagation algorithm to detect and adjust path conflicts;

[0017] S7. Combine the station yard map with dynamic response capabilities and the optimal route path, perform image processing and feature calibration in an augmented reality environment, and achieve the superimposed display of virtual controls in the physical station yard, providing an intuitive view of the path and the station yard.

[0018] Optionally, the S2 specifically includes:

[0019] S21. Perform preliminary data preprocessing on the control usage behavior model, and normalize the model data using normalization and feature scaling techniques;

[0020] S22. Input the preprocessed control usage behavior model into a graph neural network, establish multi-dimensional feature vectors for each control in the station yard map through node embedding methods, and determine the association weights and path relationships between the controls according to the learning results of the control usage behavior model;

[0021] S23. In the graph neural network, use graph convolutional layers for information transmission and aggregation, layer by layer propagate control features and weight information, calculate and update node feature vectors through the adjacency matrix, and gradually extract the control spatial features in the station yard map;

[0022] S24. Input the control embedding result output by the graph neural network into the long short-term memory network to analyze the time series data of the control usage behavior model, extract the short-term dynamic features and long-term trend features of the control operation behavior through the long short-term memory network, and predict the user's layout adjustment preference;

[0023] S25. Combine the past control operation history and the current control usage behavior model output in the long short-term memory network, comprehensively evaluate the association pattern between controls and the user's potential layout behavior, generate a preliminary output of intelligent layout suggestions, and perform iterative adjustment to further optimize the layout suggestions;

[0024] S26. Integrate the control space features generated by the graph neural network with the layout suggestions output by the long short-term memory network to form the final intelligent layout suggestions.

[0025] Optionally, the specific steps of S3 are as follows:

[0026] S31. Receive the control feature vector and layout weight information extracted from the intelligent layout suggestions, initialize the positions, connection relationships, and physical parameters of each control node in the force-directed algorithm, and construct the basic graph structure of the control layout;

[0027] S32. Adopt an improved dynamic force adjustment mechanism. In the force-directed algorithm, adjust the attraction and repulsion parameters in real time according to the node density and layout complexity, and dynamically adapt to the distance between nodes and the neighborhood distribution state;

[0028] S33. In the iterative layout process, adopt a multi-thread parallel computing strategy, process the control nodes in parallel by partition, calculate the interaction forces and position changes between controls. Each iteration includes the adjustment of node positions and conflict detection, and gradually approaches the global optimal layout state;

[0029] S34. Introduce a hierarchical layout strategy, first adjust the positions of high-priority controls, and then adjust the low-priority controls to enhance the layering between controls and the rationality of the functional distribution of the layout;

[0030] S35. Input the layout result after iteration into an enhanced Adam optimizer. The Adam optimizer introduces a learning rate adjustment module and a gradient change tracking mechanism to achieve fine adjustment of the control node positions;

[0031] S36. Combine the adjustment results output by the Adam optimizer, perform final integration and verification on the entire layout, and form a preliminary yard plan layout.

[0032] Optionally, the specific steps of S4 are as follows:

[0033] S41. Receive the generated preliminary yard layout diagram, define the initial states and properties of the controls, including idle, occupied, and locked, and assign status identifiers and initial parameters to each control;

[0034] S42. Based on the preliminary yard layout diagram, construct a finite state machine for the controls, define the state set Q and the event set E, and set the state transition function:

[0035] δ(q,e)=q′,δ:Q×E→Q;

[0036] Among them, δ represents the state transition function, q represents the current control state, e represents the event that triggers the state change, and q' represents the target control state;

[0037] S43. Configure the event-driven model, capture user interaction events and system-triggered events through a real-time event listening mechanism, and bind them to the state transition rules of the finite state machine of the controls, so that the events trigger the state changes of the controls and ensure the real-time response of the controls during user operations;

[0038] S44. Define the dynamic state update formula of the controls, and update the state parameters by combining event triggering and time step:

[0039]

[0040] Among them, P ( t+1 ) represents the state parameter of the control at time t + 1, P ( t ) represents the state parameter of the control at time t, α represents the adjustment coefficient, w e represents the event weight, e(t) represents the event function, γ represents the stability constant, Δt represents the time step, and β represents the adjustment factor;

[0041] S45. Synchronize the control state update result to the yard layout diagram, and through data binding and real-time visualization mechanism, make the changes of the control state be immediately reflected on the graphical interface;

[0042] S46. Conduct simulation tests on the control behavior responses, verify the response speed and stability of the controls under various events and operating conditions, optimize the state transition logic of the finite state machine and the event-driven model, so that the controls can achieve dynamic behavior responses in the yard layout diagram.

[0043] Optionally, the specific content of S5 includes:

[0044] S51. Receive the generated dynamic control behavior data, initialize the real-time data synchronization module between the server and the client, and establish a two-way communication channel;

[0045] S52. Define a data transmission protocol and construct a control status data packet structure D = {ID, S, T}, where ID represents the unique identifier of the control, S represents the current status information of the control, and T represents the timestamp;

[0046] S53. Configure an event listening mechanism on the server side to capture the change events of the control status in real time and trigger the data transmission function T s (d i ):

[0047]

[0048] where d i represents the control status data packet, ΔS ( t ) represents the change rate of the control status at time t, ∈ represents the smoothing term, δ represents the smoothing parameter for adjusting the state change detection, ζ represents the threshold of the state change rate, θ represents the attenuation factor for controlling the transmission delay, T 0 represents the data packet generation time, τ represents the maximum allowed delay time, and ω represents the adjustment frequency factor;

[0049] S54. The client receives and parses the status data packet D transmitted from the server, decodes and validates it through the parsing module, and the parsed control status will be applied to the layout of the station yard diagram on the client side in real time;

[0050] S55. Adopt data binding technology to synchronously update the parsed control status with the client station yard diagram, and dynamically adjust the display priority and layout hierarchy of the control during the data synchronization process;

[0051] S56. Configure a real-time monitoring and error correction mechanism in the synchronization process to monitor packet loss, delay or potential errors in data transmission. When an anomaly is detected, trigger the adaptive backtracking and retransmission mechanism, adjust the transmission strategy, and form a station yard diagram with dynamic response capabilities.

[0052] Optionally, the specific content of S6 includes:

[0053] S61. Obtain real-time synchronization data, including control status, station yard diagram layout and user interaction information, initialize the path search module, set the start node and target node of the path search, and configure the path search parameters. The path search parameters include the initial temperature, cooling rate and path evaluation criteria;

[0054] S62. Start the simulated annealing tree search algorithm, expand from the current path as the initial path, and randomly select neighboring nodes in the search tree structure to generate candidate paths; the initial path is random and is used to explore diverse solutions in the path space; for each candidate path, calculate the path weight as a measure of path quality; the path weight is comprehensively determined by the path length, the priority of path nodes, and specific constraints.

[0055] S63. After path evaluation, determine whether to accept the new path according to the acceptance probability function of the simulated annealing algorithm; the acceptance probability is controlled by the current temperature, and the higher the temperature, the greater the acceptance probability; as the iteration progresses, the temperature gradually decreases and the acceptance probability decreases, enabling the search process to gradually transition from extensive exploration to local fine search.

[0056] S64. In the path generation and path selection phases, combine the constraint propagation algorithm to detect conflicts in the path. During the detection process, scan all nodes and edges in the path to determine whether there are conflicts with fixed controls, preset path restrictions, or dynamic elements in the yard plan; if a conflict is detected, the constraint propagation algorithm identifies the neighboring area of the conflict node and marks it.

[0057] S65. After the path adjustment mechanism is started, reselect alternative nodes adjacent to the conflict node for path repair. The adjustment process continues to iterate in combination with the simulated annealing algorithm. By continuously updating and recalculating the path quality, gradually optimize the entire path to achieve a conflict-free optimal solution.

[0058] S66. After the path optimization and adjustment are completed, integrate the finally generated optimal path into the yard plan layout, update the yard plan in real time, and display the path planning result.

[0059] Optionally, the specific steps of S7 are as follows:

[0060] S71. Receive the yard plan with dynamic response capabilities and the generated optimal approach path, and load them into the augmented reality module to provide a basis for the virtual overlay display of the path and controls.

[0061] S72. Apply image processing technology to preprocess the yard plan, and use image enhancement and edge detection algorithms to optimize the image clarity.

[0062] S73. Adopt feature calibration technology to identify key positions and reference points in the physical yard, and use the scale-invariant feature transform algorithm to calibrate and match the features in the physical yard.

[0063] S74. Use the Perspective-n-Point algorithm for real-time pose estimation of the device. Combine the calibrated features of the physical yard and the parameters of the camera device to determine the real-time position and viewing angle of the device, and ensure the correct alignment of the virtual path and controls under different viewing angles.

[0064] S75. Project the optimal route path and controls into the augmented reality environment through a rendering engine to achieve the superimposed display of the virtual path and controls on the physical station yard. The rendering process includes the dynamic adjustment of path lines and the real-time response of controls.

[0065] S76. Test and verify the stability and response speed of the path and controls in the augmented reality environment, adjust the display parameters and rendering logic, and provide an intuitive path and station yard view.

[0066] The beneficial effects of the present invention are as follows:

[0067] First of all, by introducing data mining and machine learning technologies, the present invention can deeply analyze historical station yard design data and user operation records, and automatically generate a control usage behavior model and intelligent layout suggestions. This makes the compilation of the station yard map no longer rely on pure manual operations, greatly improving the design efficiency and accuracy. At the same time, the combination of graph neural network and long short-term memory network makes the configuration of controls and the prediction of user behavior more accurate, enhancing the intelligent level of the layout.

[0068] Secondly, in terms of the layout algorithm, through the combination of the force-directed algorithm and the Adam optimizer, the reasonable distribution of controls in the station yard map is achieved. Compared with traditional manual layout or simple automatic layout methods, the automatic layout of the present invention can dynamically adapt to the space requirements of different controls, optimize the layout effect, and make the visualization and function distribution of the station yard map clearer and more reasonable.

[0069] In addition, the application of the simulated annealing tree search algorithm and the constraint propagation algorithm solves the problems in path planning and conflict detection, making the path calculation more efficient and flexible, and capable of adapting to the real-time changing scheduling environment. Compared with existing path planning technologies, this method can also maintain the high efficiency and accuracy of path search under complex multi-constraint conditions, thus ensuring the practicality and reliability of the station yard map in a dynamic environment.

[0070] In terms of real-time data synchronization, the present invention realizes the rapid synchronous update of control states and path information through server-client two-way communication and event-driven mechanisms. This not only improves the response speed of the system but also ensures the interaction experience and data consistency of users in a multi-user operation environment. Users can view the changes in control states and path updates in real time on the client side, avoiding the problems of data delay and unstable synchronization in traditional systems. Finally, combined with augmented reality technology, virtual controls and paths are superimposed and displayed in the physical station yard, enabling dispatchers to intuitively view and manage train operation prompts and path planning in the actual operation environment. This intuitive augmented reality display method enhances users' understanding of the station yard map and the convenience of operation, effectively improving the efficiency and accuracy of dispatching work. Brief Description of the Drawings

[0071] The drawings are used to provide further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. In the drawings:

[0072] Figure 1 is a flowchart of a method for compiling a station yard map for integrating train operation prompts proposed by the present invention;

[0073] Figure 2 is a schematic structural diagram of simulated annealing tree search path optimization and path conflict detection adjustment for a method for compiling a station yard map for integrating train operation prompts proposed by the present invention. Detailed Description of the Embodiments

[0074] Now, the present invention will be further described in detail with reference to the drawings. These drawings are all simplified schematic diagrams, only showing the basic structure of the present invention in a schematic manner, so they only show the components related to the present invention.

[0075] Referring to Figure 1 and Figure 2 , a method for compiling a station yard map for integrating train operation prompts includes the following steps:

[0076] S1. Collect historical station yard design data and user operation records, and analyze them using an association rule mining algorithm to generate common control combinations and association patterns, forming a control usage behavior model;

[0077] S2. Input the control usage behavior model into a graph neural network for route configuration analysis, and combine it with a long short-term memory network for time series prediction of user operation behaviors to generate intelligent layout suggestions;

[0078] S3. According to the intelligent layout suggestions, use a force-directed algorithm to automatically layout the controls, and combine an Adam optimizer to achieve a reasonable distribution of the controls in the station yard map, generating a preliminary station yard map layout;

[0079] S4. Based on the preliminary station yard map layout, construct a finite state machine for the controls, define different states and behavior conversions of the controls, and process user interaction events through an event-driven model, enabling the controls to achieve dynamic behavior responses in the station yard map layout;

[0080] S5. Based on the dynamic control behaviors, use server-client real-time data synchronization technology to achieve real-time data update between the client and the server, forming a station yard map with dynamic response capabilities;

[0081] S6. Utilize real-time synchronized data, use simulated annealing tree search to calculate the optimal routing path, and combine with the constraint propagation algorithm to detect and adjust path conflicts;

[0082] S7. Combine the station yard map with dynamic response capabilities with the optimal routing path, perform image processing and feature calibration in the augmented reality environment, realize the superimposed display of virtual controls in the physical station yard, and provide an intuitive view of the path and the station yard.

[0083] In this embodiment, the specific steps of S2 include:

[0084] S21. Perform preliminary data preprocessing on the control usage behavior model, and use normalization and feature scaling techniques to standardize the model data;

[0085] S22. Input the preprocessed control usage behavior model into the graph neural network, establish multi-dimensional feature vectors of each control in the station yard map through node embedding methods, and determine the association weights and path relationships between controls according to the learning results of the control usage behavior model;

[0086] S23. In the graph neural network, use graph convolutional layers for information transmission and aggregation, layer by layer propagate control features and weight information, calculate and update node feature vectors through the adjacency matrix, and gradually extract the spatial features of controls in the station yard map;

[0087] S24. Input the control embedding results output by the graph neural network into the long short-term memory network to analyze the time series data of the control usage behavior model, extract the short-term dynamic features and long-term trend features of control operation behaviors through the long short-term memory network, and predict the user's layout adjustment preferences;

[0088] S25. Combine the past control operation history and the current output of the control usage behavior model in the long short-term memory network, comprehensively evaluate the association patterns between controls and the user's potential layout behaviors, generate a preliminary output of intelligent layout suggestions, and perform iterative adjustments to further optimize the layout suggestions;

[0089] S26. Integrate the control spatial features generated by the graph neural network with the layout suggestions output by the long short-term memory network to form the final intelligent layout suggestions.

[0090] In this embodiment, the specific steps of S3 include:

[0091] S31. Receive the control feature vectors and layout weight information extracted from the intelligent layout suggestions, initialize the positions, connection relationships, and physical parameters of each control node in the force-directed algorithm, and construct the basic graph structure of the control layout;

[0092] S32. Adopt an improved dynamic force adjustment mechanism. In the force-directed algorithm, the attraction and repulsion force parameters are adjusted in real time according to the node density and layout complexity, dynamically adapting to the distance between nodes and the state of the neighborhood distribution.

[0093] S33. During the iterative layout process, adopt a multi-threaded parallel computing strategy. Process the control nodes in parallel by partition, calculate the forces and position changes between the controls. Each iteration includes the adjustment of node positions and conflict detection, gradually approaching the global optimal layout state.

[0094] S34. Introduce a hierarchical layout strategy, first adjust the positions of high-priority controls, and then adjust the low-priority controls, enhancing the layering between controls and the rationality of the functional distribution of the layout.

[0095] S35. Input the layout result completed by iteration into an enhanced Adam optimizer. The Adam optimizer introduces a learning rate adjustment module and a gradient change tracking mechanism to achieve fine adjustment of the positions of the control nodes.

[0096] S36. Combine the adjustment results output by the Adam optimizer to perform final integration and verification on the entire layout, forming a preliminary yard plan layout.

[0097] In this embodiment, the specific content of S4 is as follows:

[0098] S41. Receive the generated preliminary yard plan layout, define the initial states and attributes of the controls, including idle, occupied, and locked, and assign a status identifier and initial parameters to each control.

[0099] S42. Based on the preliminary yard plan layout, construct a finite state machine for the controls, define the state set Q and the event set E, and set the state transition function:

[0100] δ(q,e)=q′,δ:Q×E→Q;

[0101] Among them, δ represents the state transition function, q represents the current control state, e represents the event that triggers the state change, and q' represents the target control state.

[0102] S43. Configure an event-driven model, capture user interaction events and system trigger events through a real-time event listening mechanism, and bind them to the state transition rules of the finite state machine of the controls, so that the events trigger the state changes of the controls, ensuring the real-time response of the controls during user operations.

[0103] S44. Define a dynamic state update formula for the controls, and update the state parameters by combining event triggering and time step:

[0104]

[0105] Among them, P( t + 1 ) represents the state parameter of the control at time t + 1, P ( t ) represents the state parameter of the control at time t, α represents the adjustment coefficient, w e represents the event weight, e ( t ) represents the event function, γ represents the stability constant, Δt represents the time step, β represents the adjustment factor;

[0106] S45. Synchronize the control state update result to the yard layout diagram, and through the data binding and real-time visualization mechanism, make the change of the control state be immediately reflected on the graphical interface;

[0107] S46. Conduct simulation tests on the control behavior response, verify the response speed and stability of the control under various events and operating conditions, optimize the state transition logic and event-driven model of the finite state machine, so that the control realizes dynamic behavior response in the yard layout diagram.

[0108] In this embodiment, the S5 specifically includes:

[0109] S51. Receive the generated dynamic control behavior data, initialize the real-time data synchronization module between the server and the client, and establish a two-way communication channel;

[0110] S52. Define the data transmission protocol, and construct the control state data packet structure D = { ID, S, T } , where ID represents the unique identifier of the control, S represents the current state information of the control, and T represents the time stamp;

[0111] S53. Configure an event listening mechanism on the server side to capture the change event of the control state in real time, and trigger the data transmission function T s( d i) :

[0112]

[0113] where d i represents the control state data packet, ΔS ( t ) represents the change rate of the control state at time t, ∈ represents the smoothing term, δ represents the smoothing parameter for adjusting the state change detection, ζ represents the threshold of the state change rate, θ represents the attenuation factor for controlling the transmission delay, T 0 represents the data packet generation time, τ represents the maximum allowable delay time, ω represents the adjustment frequency factor;

[0114] S54. The client receives and parses the status data packet D transmitted from the server, decodes and validates it through the parsing module, and the parsed control status will be applied to the layout of the station yard diagram of the client in real time;

[0115] S55. The data binding technology is used to synchronously update the parsed control status with the station yard diagram of the client, and the display priority and layout hierarchy of the control are dynamically adjusted during the data synchronization process;

[0116] S56. A real-time monitoring and error correction mechanism is configured in the synchronization process to monitor packet loss, delay or potential errors in data transmission. When an anomaly is detected, an adaptive backtracking and retransmission mechanism is triggered to adjust the transmission strategy, forming a station yard diagram with dynamic response capabilities.

[0117] In this embodiment, the specific steps of S6 are as follows:

[0118] S61. Obtain real-time synchronization data, including control status, station yard diagram layout and user interaction information, initialize the path search module, set the start node and target node of the path search, and configure path search parameters, where the path search parameters include initial temperature, cooling rate and path evaluation criteria;

[0119] S62. Start the simulated annealing tree search algorithm, expand from the current path as the initial path, and randomly select adjacent nodes in the search tree structure to generate candidate paths; the initial path is random and is used to explore diverse solutions in the path space; for each candidate path, calculate the path weight as a measure of path quality; the path weight is comprehensively determined by path length, the priority of path nodes and specific constraint conditions;

[0120] S63. After path evaluation, decide whether to accept the new path according to the acceptance probability function of the simulated annealing algorithm; the acceptance probability is controlled by the current temperature, and the higher the temperature, the greater the acceptance probability; as the iteration progresses, the temperature gradually decreases and the acceptance probability decreases, so that the search process gradually transitions from extensive exploration to local fine search;

[0121] S64. In the path generation and path selection stages, combine the constraint propagation algorithm to detect conflicts in the path. During the detection process, scan all nodes and edges in the path to determine whether there are conflicts with fixed controls, preset path restrictions or dynamic elements in the station yard diagram; if a conflict is detected, the constraint propagation algorithm identifies the adjacent area of the conflict node and marks it;

[0122] S65. After the path adjustment mechanism is started, reselect alternative nodes adjacent to the conflict node for path repair. The adjustment process continues to iterate in combination with the simulated annealing algorithm. By continuously updating and recalculating the path quality, gradually optimize the entire path to achieve a conflict-free optimal solution;

[0123] S66. After the path optimization and adjustment are completed, integrate the finally generated optimal path into the yard layout diagram, update the yard layout diagram in real time, and display the path planning result.

[0124] In this embodiment, the S7 specifically includes:

[0125] S71. Receive the yard layout diagram with dynamic response ability and the generated optimal approach path, and load them into the augmented reality module to provide a basis for the virtual superposition display of the path and controls.

[0126] S72. Apply image processing technology to preprocess the yard layout diagram, and use image enhancement and edge detection algorithms to optimize the image clarity.

[0127] S73. Adopt feature calibration technology to identify the key positions and reference points in the physical yard, and use the scale-invariant feature transform algorithm to calibrate and match the features in the physical yard.

[0128] S74. Use the Perspective-n-Point algorithm for real-time pose estimation of the device. Combine the calibrated features of the physical yard and the parameters of the camera device to determine the real-time position and viewing angle of the device, and ensure the correct alignment of the virtual path and controls under different viewing angles.

[0129] S75. Project the optimal approach path and controls into the augmented reality environment through the rendering engine to achieve the superposition display of the virtual path and controls on the physical yard. The rendering process includes the dynamic adjustment of the path lines and the real-time response of the controls.

[0130] S76. Test and verify the stability and response speed of the path and controls in the augmented reality environment, adjust the display parameters and rendering logic, and provide an intuitive path and yard view.

[0131] Example 1:

[0132] To verify the feasibility of the present invention in implementation, the present invention is applied to the main railway hub of a modern city. The dispatcher is faced with the task of quickly dispatching a large number of trains during peak hours. This complex environment requires the dispatcher to be able to quickly formulate and adjust the train operation plan, and at the same time respond to emergencies and dynamic changes within an extremely short time. However, the existing methods for compiling the station yard layout diagram are difficult to achieve real-time response and adjustment to complex dispatching scenarios due to relying on manual operations and static path planning, resulting in problems such as path conflicts, resource waste, and dispatching delays during peak hours. Therefore, we apply the method for compiling the station yard layout diagram of the present invention to this embodiment to verify its effectiveness and improvement effect in practical applications.

[0133] During peak hours, the dispatcher needs to compile and update the station yard map within 5 minutes to adapt to the train arrival and departure arrangements. First, real-time yard data is accessed through the system, including the current track status, train positions, and dispatching requests. This data is used as input and imported into the system's path search module. The system generates a control usage behavior model using historical data and association rule mining algorithms to predict common control combinations and user layout preferences. Then, this control information is analyzed for route configuration through a graph neural network, combined with a long short-term memory network to predict the potential operation behaviors of the dispatcher, and intelligent layout suggestions are generated.

[0134] During the application process, the system automatically arranges the controls using the force-directed algorithm combined with the Adam optimizer to make the distribution of the controls in the station yard map reach a reasonable state and quickly complete the preliminary graphic compilation. To ensure the system's real-time response to complex path planning requests, the simulated annealing tree search algorithm is used for path optimization. The system automatically identifies path nodes and their conflicts, and selects the best path through dynamic iteration to avoid conflicts between paths. The constraint propagation algorithm is further used for path conflict detection and adjustment to ensure that the finally generated path has no conflicts.

[0135] Through this system, the dispatcher can view the generated optimal path and the dynamic response of the controls in real time, and combine augmented reality technology to overlay virtual controls onto the physical station yard, enabling the dispatcher to directly see the dynamic display of the path in the actual scenario. This method enables the dispatcher to complete the compilation and multiple adjustments of the station yard map within 5 minutes, reducing the time by 60% compared to the traditional method. The system's real-time data synchronization function ensures the consistency of dispatching information between the server and the client, thus achieving stable and accurate operations.

[0136] During one month of actual application, we selected data during the morning peak hours (7:00 - 9:00) and evening peak hours (17:00 - 19:00) every day for verification. The data shows that after implementing the method of the present invention, the time for the dispatcher to compile and adjust the station yard map during peak hours is on average reduced to 3 minutes, showing a significant improvement compared to the 8 minutes of the traditional manual compilation method. The incidence of path conflicts has decreased from the original 15% to 2%. At the same time, due to path optimization and dynamic layout, the average train dispatching delay has been reduced from 7 minutes to 3 minutes. Combining user feedback, the dispatchers unanimously stated that the system has significantly improved in terms of operation intuitiveness and response speed, and the real-time path display of augmented reality has made decision-making more efficient.

[0137] Table 1 Comparison table of the traditional invention and the present invention in terms of the time for compiling and adjusting the station yard map during peak hours

[0138]

[0139]

[0140] Table 2 Comparison Table of the Incidence of Path Conflicts between Traditional Inventions and the Present Invention

[0141]

[0142] The above Table 1 shows the comparison between the traditional method and the method of the present invention in the compilation and adjustment time of the station yard map during peak hours. The data shows that after using the method of the present invention, during the morning and evening peak hours, the average time for the dispatcher to complete the compilation of the station yard map has been significantly reduced. For example, during the morning peak (7:00 - 9:00) on November 1, 2024, the traditional method took about 8 minutes, while the method of the present invention only took 3 minutes, saving about 62.5% of the time. Similar trends have also been verified on other dates and time periods, indicating that the present invention has greatly improved the compilation efficiency when dealing with complex dispatching tasks in real time. On average, the traditional method takes about 8 minutes, while the average time taken by the method of the present invention is about 3 to 3.5 minutes, showing its significant advantage in terms of efficiency.

[0143] The above Table 2 shows the comparison of the incidence of path conflicts, reflecting the superiority of the method of the present invention in path optimization and conflict detection. The data shows that the traditional method has a relatively high path conflict rate during peak hours, reaching about 15%, while the method of the present invention has significantly reduced this ratio. For example, during the morning peak on November 1, 2024, the traditional path conflict rate was 15%, while after using the method of the present invention, it was only 2%, and the incidence of conflicts decreased by about 87%. The data on other dates also show similar improvements, proving that the present invention shows better stability and reliability when dealing with complex path planning and real-time data synchronization. Through the simulated annealing tree search and constraint propagation algorithms, the present invention effectively reduces the occurrence of path conflicts, enabling the dispatcher to conduct dispatching and management more smoothly, thereby improving the overall dispatching efficiency and system security.

[0144] As described above, it is only the preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, making equivalent substitutions or changes should be covered within the protection scope of the present invention.

Claims

1. A method for compiling a station yard map with integrated driving prompts, characterized in that: The steps include: S1. Collect historical station yard design data and user operation records, and use association rule mining algorithm to analyze, generate common control combinations and association patterns, and form a control usage behavior model; S2. Input the control usage behavior model into the graph neural network for route configuration analysis, and combine it with the long short-term memory network to predict the time series of user operation behavior and generate intelligent layout suggestions; S3. Based on the intelligent layout suggestions, the force-directed algorithm is used to automatically layout the controls, and the Adam optimizer is used to achieve a reasonable distribution of controls in the station map, generating a preliminary station map layout; S4. Construct a finite state machine of the control based on the preliminary site layout, define different states and behavior transitions of the control, and process user interaction events through an event-driven model, so that the control can achieve dynamic behavior response in the site layout; S5. Based on dynamic control behavior, use server-client real-time data synchronization technology to achieve real-time data update between the client and the server, forming a station map with dynamic response capabilities; S6. Using real-time synchronization data, simulated annealing tree search is used to calculate the optimal route path, and constraint propagation algorithm is used to detect and adjust the path conflict; S7. Combine the station map with dynamic response capabilities with the optimal approach path, perform image processing and feature calibration in an augmented reality environment, realize the superimposed display of virtual controls in the physical station, and provide an intuitive path and station view.

2. A method for compiling a station yard map for integrated train driving prompts according to claim 1, characterized in that: The S2 specifically includes: S21. Perform preliminary data preprocessing on the control usage behavior model, and use normalization and feature scaling techniques to normalize the model data; S22, input the preprocessed control usage behavior model into the graph neural network, establish the multi-dimensional feature vector of each control in the station field diagram through the node embedding method, and determine the association weight and path relationship between the controls according to the learning result of the control usage behavior model; S23. In the graph neural network, the graph convolution layer is used for information transmission and aggregation, the control features and weight information are propagated layer by layer, the node feature vector is calculated and updated through the adjacency matrix, and the control space features in the station map are gradually extracted; S24, inputting the control embedding result output by the graph neural network into the long short-term memory network for analyzing the time series data of the control usage behavior model, extracting the short-term dynamic characteristics and long-term trend characteristics of the control operation behavior through the long short-term memory network, and predicting the user's layout adjustment preference; S25. Combining the past control operation history and the current control usage behavior model output in the long short-term memory network, comprehensively evaluating the association pattern between controls and the user's potential layout behavior, generating preliminary output of intelligent layout suggestions, and performing iterative adjustments to further optimize the layout suggestions; S26. The control space features generated by the graph neural network are integrated with the layout suggestions output by the long short-term memory network to form the final intelligent layout suggestions.

3. The method for compiling a station yard map for integrated driving prompts according to claim 1, characterized in that: The S3 specifically includes: S31, receiving the control feature vector and layout weight information extracted from the intelligent layout suggestion, initializing the position, connection relationship and physical parameters of each control node in the force-directed algorithm, and constructing the basic graph structure of the control layout; S32. Adopt an improved dynamic force adjustment mechanism. In the force-directed algorithm, the attraction and repulsion parameters are adjusted in real time according to the node density and layout complexity, and the distance between nodes and the neighborhood distribution state are dynamically adapted. S33. In the iterative layout process, a multi-threaded parallel computing strategy is adopted to process the control nodes in parallel by partitions, calculate the forces and position changes between the controls, and each iteration includes node position adjustment and conflict detection, gradually approaching the global optimal layout state; S34. Introduce a hierarchical layout strategy, prioritize the positions of high-priority controls, and then adjust low-priority controls, to improve the sense of hierarchy between controls and the rationality of functional distribution of the layout; S35, inputting the layout result completed by iteration into the enhanced Adam optimizer, wherein the Adam optimizer introduces a learning rate adjustment module and a gradient change tracking mechanism to achieve detailed adjustment of the control node position; S36. Combined with the adjustment results output by the Adam optimizer, the entire layout is finally integrated and verified to form a preliminary station map layout.

4. The method for compiling a station yard map for integrated train driving prompts according to claim 1, characterized in that: The S4 specifically includes: S41, receiving the generated preliminary station layout, defining the initial state and properties of the controls, including idle, occupied and locked, and assigning a state identifier and initial parameters to each control; S42. Based on the preliminary site layout, construct the finite state machine of the control, define the state set Q and event set E, and set the state transition function: δ(q,e)=q',δ:Q×E→Q; Among them, δ represents the state transition function, q represents the current control state, e represents the event that triggers the state change, and q' represents the target control state; S43, configuring an event-driven model, capturing user interaction events and system triggering events through a real-time event monitoring mechanism, and binding them with the state transition rules of the finite state machine of the control, so that the event triggers the state change of the control, ensuring the real-time response of the control in the user operation; S44. Define the dynamic state update formula of the control, and update the state parameters in combination with event triggering and time step: Among them, P(t+1) represents the state parameter of the control at time t+1, P(t) represents the state parameter of the control at time t, α represents the adjustment coefficient, and w e represents the event weight, e(t) represents the event function, γ represents the stability constant, Δt represents the time step, and β represents the adjustment factor; S45, synchronizing the control state update result to the station layout, and making the control state change instantly reflected on the graphical interface through data binding and real-time visualization mechanism; S46. Conduct simulation tests on the control behavior response to verify the response speed and stability of the control under various events and operating conditions, optimize the state transition logic and event-driven model of the finite state machine, and enable the control to achieve dynamic behavior response in the station layout.

5. The method for compiling a station yard map for integrated train driving prompts according to claim 1, characterized in that: The S5 specifically includes: S51, receiving the generated dynamic control behavior data, initializing the real-time data synchronization module between the server and the client, and establishing a two-way communication channel; S52, define a data transmission protocol, and construct a control state data packet structure D = {ID, S, T}, where ID represents a unique identifier of the control, S represents current state information of the control, and T represents a timestamp; S53, configure the event monitoring mechanism on the server side, capture the change event of the control state in real time, and trigger the data transmission function T s (d i ): Among them, d i represents the control state data packet, ΔS(t) represents the rate of change of the control state at time t, ∈ represents the smoothing term, δ represents the smoothing parameter for adjusting the state change detection, ζ represents the threshold of the state change rate, θ represents the attenuation factor of the control transmission delay, T0 represents the data packet generation time, τ represents the maximum allowed delay time, and ω represents the adjustment frequency factor; S54, the client receives and parses the status data packet D transmitted from the server, decodes and verifies it through the parsing module, and the parsed control status will be applied to the station layout of the client in real time; S55. Use data binding technology to synchronize the parsed control state with the client site map, and dynamically adjust the display priority and layout hierarchy of the control during the data synchronization process; S56. Configure real-time monitoring and error correction mechanisms in the synchronization process to monitor packet loss, delay or potential errors in data transmission. When an abnormality is detected, trigger the adaptive backtracking and retransmission mechanism, adjust the transmission strategy, and form a site map with dynamic response capabilities.

6. A method for compiling a station yard map for integrated train driving prompts according to claim 1, characterized in that: The S6 specifically includes: S61, acquiring real-time synchronization data, including control status, station layout and user interaction information, initializing the path search module, setting the starting node and target node of the path search, and configuring the path search parameters, wherein the path search parameters include initial temperature, cooling rate and path evaluation criteria; S62, start the simulated annealing tree search algorithm, expand from the current path as the initial path, randomly select adjacent nodes in the search tree structure to generate candidate paths; the initial path is random and is used to explore diverse solutions in the path space; for each candidate path, calculate the path weight as a measure of path quality; the path weight is comprehensively determined by the path length, the priority of the path node and specific restrictions; S63, after the path evaluation, decide whether to accept the new path according to the acceptance probability function of the simulated annealing algorithm; the acceptance probability is controlled by the current temperature, the higher the temperature, the greater the acceptance probability; as the iteration proceeds, the temperature gradually decreases, the acceptance probability decreases, and the search process gradually transitions from extensive exploration to local fine search; S64. In the path generation and path selection phase, the constraint propagation algorithm is combined to perform conflict detection on the path. During the detection process, all nodes and edges in the path are scanned to determine whether there is a conflict with fixed controls, preset path restrictions or dynamic elements in the station field diagram; if a conflict is detected, the constraint propagation algorithm identifies the neighboring area of ​​the conflicting node and marks it; S65, after the path adjustment mechanism is started, the candidate node adjacent to the conflicting node is reselected to repair the path. The adjustment process is combined with the simulated annealing algorithm to continue to iterate, and the entire path is gradually optimized to achieve a conflict-free optimal solution by continuously updating and recalculating the path quality; S66. After the path optimization and adjustment are completed, the optimal path finally generated is integrated into the station map layout, the station map is updated in real time and the path planning results are displayed.

7. The method for compiling a station yard map for integrated train driving prompts according to claim 1, characterized in that: The S7 specifically includes: S71, receiving a station map with dynamic response capability and a generated optimal approach path, and loading them into an augmented reality module to provide a basis for virtual overlay display of paths and controls; S72. Apply image processing technology to pre-process the station map and use image enhancement and edge detection algorithms to optimize image clarity; S73, using feature calibration technology to identify key locations and reference points in the physical station field, and using a scale-invariant feature transformation algorithm to calibrate and match features in the physical station field; S74. Use the Perspective-n-Point algorithm to perform real-time posture estimation of the device, combine the calibration features of the physical station and the parameters of the camera device, determine the real-time position and viewing angle of the device, and ensure the correct alignment of the virtual path and controls at different viewing angles; S75, projecting the optimal route path and controls into the augmented reality environment through a rendering engine, realizing superimposed display of the virtual path and controls on the physical station field, wherein the rendering process includes dynamic adjustment of the path lines and real-time response of the controls; S76. Test and verify the stability and responsiveness of paths and controls in the augmented reality environment, adjust display parameters and rendering logic, and provide intuitive path and site views.

Images