Urban area line and subway line interconnection and intercommunication ticket dynamic threshold value clearing system and method

Abstract

The invention provides a city area line and subway line interconnection and intercommunication ticket dynamic threshold value clearing system, which comprises an input data module for creating a transmission file path class and storing feature data of each path in an object form; the judgment and optimization module is provided with a threshold range and a corresponding candidate path rule, screens candidate paths meeting conditions, and calculates the matching probability of the actual travel time and the reference time consumption of each candidate path when a plurality of candidate paths exist in a screening result; and the sorting scheme output module is used for generating and outputting a final path sorting scheme according to the judgment result. The invention also provides a city area line and subway line interconnection ticket dynamic threshold value clearing method, which comprises the following steps: creating a transmission file path class, and setting a threshold value range and a corresponding candidate path rule; and determining the actual travel path of the passenger based on the actual travel time of the passenger in combination with the threshold range and the corresponding candidate path rule, and generating and outputting a final path clearing scheme.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of rail transit fare clearing, and more particularly to a fare dynamic threshold clearing system and method for interconnection between a city line and a subway line. BACKGROUND

[0002] In the urban rail transit system, as one of the largest urban rail transit networks in the world, the fare clearing system (FCS) of Shanghai Metro is the core technical means to realize fare management, revenue distribution and operation settlement. The line network of Shanghai Metro is complex, including not only ordinary lines serving the core area of the city, but also city lines connecting the city and the suburbs. Due to the significant differences in operating mode, fare rules and passenger behavior characteristics of each line, higher technical requirements are put forward for the clearing system in terms of path recognition, cost calculation and abnormal processing capacity.

[0003] At present, with the continuous expansion of the Shanghai Metro network and the continuous growth of passenger flow, the existing clearing system is facing increasingly prominent technical challenges in the following aspects:

[0004] The interwoven operation of ordinary lines and city lines leads to increasingly diverse and complex travel paths of passengers. In the case of multiple path matching or no effective path information, the existing system lacks an efficient abnormal processing mechanism, which can easily lead to delays or errors in fare clearing results. With the continuous opening of new lines and the continuous adjustment of fare rules, the existing clearing system lacks scalability and adaptability, making it difficult to meet the needs of future development of the rail transit network.

[0005] Therefore, in view of the challenges faced by the clearing system under the interwoven operation of ordinary lines and city lines of Shanghai Metro, it is urgent to propose a more intelligent, more accurate and more adaptable technical solution to effectively solve the problems of complex path determination, abnormal situation handling and insufficient system scalability, so as to realize efficient, accurate and stable operation of the fare clearing system. SUMMARY

[0006] The present application provides a fare dynamic threshold clearing system and method for interconnection between a city line and a subway line, aiming to solve the problem of diversification and complexity of passenger travel paths caused by the interwoven operation of ordinary subway lines and city railway lines, and to improve the clearing system for no-touch transfer in the case where there are multiple travel paths between the departure and destination pairs and the travel costs differ greatly.

[0007] To achieve the above-mentioned purpose, the present application provides a fare dynamic threshold clearing system for interconnection between a city line and a subway line, comprising:

[0008] The input data module defines and stores the characteristic information of each travel route, creates a file transfer path class, and stores the characteristic data of each route as an object.

[0009] The judgment and optimization module includes:

[0010] The threshold determination engine unit is configured with a threshold range and corresponding candidate path rules. Based on the passenger's actual travel time and the threshold range, it filters candidate paths that meet the conditions. When the filtering result shows only a single candidate path, the travel path is directly determined. When the filtering result shows multiple candidate paths, the feature data of each path is sent to the probability evaluation unit to recalculate the candidate path, and the feature data of the recalculated candidate path is sent to the conflict resolution unit. When the filtering result shows no candidate path that meets the conditions, the feature data of each path is sent to the exception handling unit.

[0011] The probability evaluation unit calculates the matching probability between the actual travel time and the baseline time of each candidate path based on the normal distribution model when there are multiple candidate paths in the screening results, and recalculates the candidate paths.

[0012] The conflict resolver unit receives feature data from multiple recalculated candidate paths and selects a path based on path priority criteria using a built-in decision-making strategy.

[0013] The anomaly handling unit performs data cleaning and standardization preprocessing, identifies anomalous data, expands the threshold range and the threshold range of the corresponding candidate path in the corresponding candidate path rules, and re-determines the threshold.

[0014] The dynamic parameter tuning unit dynamically adjusts the threshold range, corresponding candidate path rules, and path priority judgment criteria based on historical operational data and real-time data analysis.

[0015] The path clearing scheme output module receives the calculation results from the judgment and optimization module, generates the final path clearing scheme, and outputs it.

[0016] In one embodiment, the characteristic information of each travel route includes route ID, route composition sequence, baseline travel time, and threshold range;

[0017] Route priority determination includes: prioritizing routes with fewer transfers, and, in the case of the same number of transfers, selecting the route whose actual travel time is closest to the route baseline time;

[0018] The probability evaluation unit selects candidate paths with high matching probabilities and assigns probability weights to the candidate paths.

[0019] A dynamic threshold clearing method for ticketing in intercity rail and metro lines, implemented by the aforementioned dynamic threshold clearing system for intercity rail and metro lines, includes:

[0020] Step S101: Define and store the feature information of each travel route, create a file transfer path class, store the feature data of each route as an object, and set the threshold range and corresponding candidate path rules;

[0021] Step S102: Combining the threshold range and the corresponding candidate path rules, determine the passenger's actual travel path based on the passenger's actual travel time. The determination rules include:

[0022] When there is a single candidate path in the determination result, the travel route is determined directly, and the process proceeds to step S105.

[0023] When there are multiple candidate paths in the judgment result, the probability evaluation unit is combined to obtain all the candidate paths that meet the conditions and their corresponding probability values, forming a candidate path set, and proceeding to step S103.

[0024] If no candidate path meets the conditions in the determination result, proceed to step S104;

[0025] Step S103: Path determination is performed based on path priority to obtain the path determination result, and then proceed to step S105.

[0026] Step S104: Expand the threshold range and the threshold range of the corresponding candidate path in the corresponding candidate path rule, and return to step S102 for re-determination;

[0027] Among them, the threshold range and the corresponding candidate path rules and path priorities are dynamically adjusted through an adaptive optimization algorithm;

[0028] Step S105: Receive the judgment results transmitted in steps S102 and S103, generate and output the final path clearing scheme.

[0029] In one embodiment, in step S102, each path is traversed by combining the threshold range and the corresponding candidate path rules. i Extract the actual travel feature values ​​of passengers, including path length L. i Travel time T i Number of transfers H i First and last station matching degree S i and time window matching degree W i The actual travel route of the passenger is determined based on the passenger's actual journey:

[0030]

[0031] Among them, T max T min These are the upper and lower limits of travel time, respectively, L max L min These are the upper and lower limits of the path length, H. max H min These are the upper and lower limits of the number of transfers, S min The minimum threshold for the matching degree between the first and last stations, W min This is the minimum threshold for time window matching.

[0032] In one embodiment, before determining the passenger's actual travel path based on the passenger's actual journey, a Gaussian membership function is used for smooth modeling, combining the threshold range and the corresponding candidate path rules. The Gaussian membership function is:

[0033]

[0034] in, For the membership degree of the actual travel time T, c i For the path baseline time, σ i For standard deviation, T i,max T i,min These are the upper and lower limits of the travel time required for path i, respectively;

[0035] When multiple paths have membership degrees, the membership degrees of each path are normalized and transformed into a path probability distribution to determine the final path selection. The path probability is calculated as follows:

[0036]

[0037] Where, p i (T) represents the selection probability of target path i, μ i (T) represents the Gaussian membership degree of the target path i, and N represents the number of all candidate paths.

[0038] In one embodiment, dynamically adjusting the threshold range and the corresponding candidate path rules and path priorities using an adaptive optimization algorithm includes:

[0039] Step S201: Collect actual route selection data of passengers, and combine the selection probabilities to form a labeled sample set, denoted as (T,p) pairs;

[0040] Step S202: Optimize the standard deviation parameter σ of the Gaussian membership function for each path using the maximum likelihood estimation method. i To ensure that the path probability distribution output by the system best matches the actual travel characteristics of passengers, the objective function is:

[0041]

[0042] Through adaptive σ i The value adjustment mechanism is designed to address the dynamic changes in passenger travel path characteristics under different route environments. The adjustment strategy is as follows:

[0043] σ′ i =σ i +k·(T i,max -T i,min )

[0044] Where, σ′ i Here, k is the updated standard deviation parameter, and k is the adaptive adjustment parameter used to dynamically adjust the standard deviation σ of the Gaussian membership function. i Alternatively, filter relevant threshold parameters through other paths;

[0045] Step S203, a two-stage stochastic programming model based on improved Benders decomposition:

[0046] The first stage involves solving the cross-line coupling constraints by addressing the main problem.

[0047] The second stage optimizes path matching by addressing sub-problems.

[0048] In one embodiment, the main problem solving addresses cross-path coupling constraints, including threshold ranges and corresponding candidate path rules and path priority adjustments. The adjustment objective function is:

[0049]

[0050] The constraints are:

[0051] T m→n ≥t walk +t safe

[0052] η≥Φ(y)

[0053] Among them, C a For the clearing cost corresponding to line a, y a Let A be the path matching decision variable for route a, A be the set of routes, η be the objective value of the subproblem, and T be the path matching decision variable for route a. m→n The actual travel time t for passengers from station m to station n walk For passenger walking time, t safe For safety time redundancy;

[0054] The subproblem determines the route clearing scheme by optimizing the matching degree of each passenger's route, and its objective function is as follows:

[0055]

[0056] The constraints are:

[0057] μ p (T p )≥α

[0058] Among them, P l T represents the set of routes selected by passenger l. p c represents the actual travel time for path p. p μ is the baseline travel time corresponding to path p. p (T p ) represents the membership degree value of path p, and α is the membership degree confidence threshold.

[0059] In one embodiment, optimality cuts and feasibility cuts are performed based on the basic principles of the Benders decomposition algorithm;

[0060] When the objective value η of the current solution in the main problem exceeds the optimal solution Φ(y), an optimal cut is generated:

[0061]

[0062] Where θ is a slack variable;

[0063] When the path matching constraint is not met, generate a feasible cut:

[0064]

[0065] Among them, z p Let p be the matching decision variable for path p; P represents the set of routes selected by the current passenger l. l The number of paths matched; β is the preset threshold for path matching, representing the expected number of paths to be matched; M is a sufficiently large constant to prevent the cutting plane constraint from being too tight; δ is a binary variable indicating whether path p is forced to match.

[0066] In one embodiment, a hot-start strategy is employed to accelerate the solution of subproblems, including:

[0067] The initial solution uses the historical best solution as a warm start;

[0068] Cut plane library pre-generation: 20% of the Pareto cut plane library is pre-generated, and cut planes with common path combinations are pre-loaded into the ticketing dynamic threshold clearing system that interconnects urban lines and subway lines.

[0069] Cut plane filtering is performed every five iterations, retaining the top 10% of efficient cut planes and removing redundant cut planes.

[0070] In one embodiment, step S105 includes:

[0071] Step S1051: Clarify the passenger's selected travel route information, including route ID and route sequence;

[0072] Step S1052: Output the matching probability between the actual travel time and the baseline time of each path, and quantify the confidence of the path determination through probability evaluation;

[0073] Step S1053: List all candidate paths that meet the conditions and their corresponding probability values ​​to form a candidate path set;

[0074] Step S1054: Record in detail the processing method and final judgment result in the case of multiple matching or no candidate path;

[0075] Step S1055: Visualize the sorting output results.

[0076] The present invention has the following beneficial effects:

[0077] Accuracy: The threshold-based decision engine accurately identifies passengers' actual travel routes, and combined with the probability evaluation unit, significantly improves the accuracy and reliability of route determination. Based on route priority, routes with fewer transfers and actual travel times closest to the baseline time are prioritized, effectively reducing the route determination error rate.

[0078] Highly adaptive: The dynamic parameter tuning module combines changes in the route network with adjustments to ticketing rules to optimize the threshold range and priority of route selection in real time. By integrating real-time operational data (such as train delay information), the system dynamically adjusts the route determination logic to ensure that it can flexibly respond to changes in the operating environment and guarantee the efficient operation of the clearing system. Attached Figure Description

[0079] Figure 1 This is a schematic diagram of the structure of a dynamic threshold clearing system for interconnecting urban rail lines and subway lines according to an embodiment of the present invention;

[0080] Figure 2 This is a flowchart of a method for dynamic threshold clearing of tickets for interconnection between urban rail lines and subway lines according to an embodiment of the present invention.

[0081] Figure 3 This is a flowchart illustrating a specific implementation of a dynamic threshold clearing method for ticketing in interconnecting urban rail lines and subway lines, according to an embodiment of the present invention.

[0082] Among them, 100 is the input data module; 120 is the judgment and optimization module; 121 is the threshold judgment engine unit; 122 is the probability evaluation unit; 123 is the conflict resolver unit; 124 is the exception handling unit; 125 is the dynamic parameter tuning unit; and 130 is the clearing scheme output module. Detailed Implementation

[0083] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions in the embodiments of this application will be described in more detail below with reference to the accompanying drawings. In the drawings, the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions. The described embodiments are some embodiments of this application, but not all embodiments. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0084] Figure 1 This is a schematic diagram of the structure of a dynamic threshold clearing system for ticketing that interconnects urban rail lines and subway lines according to an embodiment of the present invention, including:

[0085] Input data module 100 defines and stores the characteristic information of each travel route, creates a file transfer path class, and stores the characteristic data of each route as an object;

[0086] The judgment and optimization module 120 includes:

[0087] The threshold determination engine unit 121 is configured with a threshold range and corresponding candidate path rules. Based on the passenger's actual travel time and the threshold range, it filters candidate paths that meet the conditions. When the filtering result shows only a single candidate path, it directly determines the travel route. When the filtering result shows multiple candidate paths, it sends the feature data of each path to the probability evaluation unit 122 to recalculate the candidate path and sends the feature data of the recalculated candidate path to the conflict resolution unit 123. When the filtering result shows no candidate path that meets the conditions, it sends the feature data of each path to the exception handling unit 124.

[0088] The probability evaluation unit 122 calculates the matching probability between the actual travel time and the baseline time of each candidate path based on the normal distribution model when there are multiple candidate paths in the screening results, and recalculates the candidate paths.

[0089] The conflict resolver unit 123 receives the feature data of multiple candidate paths after recalculation and selects a path according to the path priority judgment criteria through a built-in decision strategy.

[0090] The anomaly handling unit 124 performs data cleaning and standardization preprocessing, identifies abnormal data, expands the threshold range and the threshold range of the corresponding candidate path in the corresponding candidate path rules, and re-determines the threshold.

[0091] The dynamic parameter tuning unit 125 dynamically adjusts the threshold range, corresponding candidate path rules, and path priority judgment criteria based on historical operational data and real-time data analysis.

[0092] The path clearing scheme output module 130 receives the calculation results from the judgment and optimization module 120, generates the final path clearing scheme, and outputs it.

[0093] Specifically, the threshold determination engine unit 121 is responsible for performing preliminary route screening, making interval judgments based on the passenger's actual travel time, generating a set of candidate routes that meet the conditions, and implementing the preliminary route screening logic:

[0094] actual_time∈[min_threshold,max_threshold]

[0095] Specifically, the anomaly handling unit 124 is responsible for performing data cleaning and standardization preprocessing, and identifying anomalous data (such as negative values ​​or extreme values). When there are no candidate paths that meet the conditions, the system triggers the anomaly handling process, which may include expanding the threshold range or introducing manual verification to ensure stability and robustness in abnormal situations.

[0096] The dynamic parameter adjustment unit 125 dynamically adjusts the path threshold range and path priority based on historical and real-time operational data analysis. By integrating real-time operational data, such as train delay information, it dynamically optimizes the path determination logic and parameter settings to ensure the system can quickly respond to actual operational changes. Through adaptive optimization algorithms, it continuously improves the accuracy of path sorting and the overall flexibility and adaptability of the system.

[0097] In one embodiment, the characteristic information of each travel route includes route ID, route composition sequence, baseline travel time, and threshold range;

[0098] Route priority determination includes: prioritizing routes with fewer transfers, and, in the case of the same number of transfers, selecting the route whose actual travel time is closest to the route baseline time;

[0099] The probability evaluation unit 122 selects candidate paths with high matching probabilities and assigns probability weights to the candidate paths.

[0100] Specifically, the threshold range and the corresponding candidate path rules include:

[0101] Path feature extraction: Obtain all possible paths and their corresponding feature values ​​from the path feature modeling module, including key indicators such as path length, travel time, and number of transfers.

[0102] Threshold range conditions setting: Based on ticket clearing rules and business needs, threshold range conditions are set for the characteristics of each path.

[0103] In one embodiment, the threshold range conditions for each path are as follows:

[0104] Travel time must match the passenger's actual entry and exit time window;

[0105] The route length must not exceed a reasonable range of the passenger's actual journey;

[0106] The number of transfers must not exceed the actual number of transfers a passenger may make.

[0107] Select the corresponding candidate path based on the set threshold range: compare the feature values ​​of all possible paths with the set threshold conditions one by one, and filter out the set of candidate paths that meet all threshold requirements at the same time.

[0108] A dynamic threshold clearing method for ticketing in intercity rail and metro lines, implemented by the aforementioned dynamic threshold clearing system for intercity rail and metro lines, includes:

[0109] Step S101: Define and store the feature information of each travel route, create a file transfer path class, store the feature data of each route as an object, and set the threshold range and corresponding candidate path rules;

[0110] Step S102: Combining the threshold range and the corresponding candidate path rules, determine the passenger's actual travel path based on the passenger's actual travel time. The determination rules include:

[0111] When there is a single candidate path in the determination result, the travel route is determined directly, and the process proceeds to step S105.

[0112] When there are multiple candidate paths in the judgment result, the probability evaluation unit 122 is combined to obtain all the candidate paths that meet the conditions and their corresponding probability values, forming a candidate path set, and proceeding to step S103.

[0113] If no candidate path meets the conditions in the determination result, proceed to step S104;

[0114] Step S103: Path determination is performed based on path priority to obtain the path determination result, and then proceed to step S105.

[0115] Step S104: Expand the threshold range and the threshold range of the corresponding candidate path in the corresponding candidate path rule, and return to step S102 for re-determination;

[0116] Among them, the threshold range and the corresponding candidate path rules and path priorities are dynamically adjusted through an adaptive optimization algorithm;

[0117] Step S105: Receive the judgment results transmitted in steps S102 and S103, generate and output the final path clearing scheme.

[0118] In one embodiment, in step S102, each path is traversed by combining the threshold range and the corresponding candidate path rules. i Extract the actual travel feature values ​​of passengers, including path length L. i Travel time T i Number of transfers H i First and last station matching degree S i and time window matching degree W i The actual travel route of the passenger is determined based on the passenger's actual journey:

[0119]

[0120] Among them, T max T min These are the upper and lower limits of travel time, respectively, L max L min These are the upper and lower limits of the path length, H. max H min These are the upper and lower limits of the number of transfers, S min The minimum threshold for the matching degree between the first and last stations, W min This is the minimum threshold for time window matching.

[0121] In one embodiment, before determining the passenger's actual travel path based on the passenger's actual journey, a Gaussian membership function is used for smooth modeling, combining the threshold range and the corresponding candidate path rules. The Gaussian membership function is:

[0122]

[0123] in, For the membership degree of the actual travel time T, c i For the path baseline time, σ i For standard deviation, T i,max T i,min These are the upper and lower limits of the travel time required for path i, respectively;

[0124] When multiple paths have membership degrees, the membership degrees of each path are normalized and transformed into a path probability distribution to determine the final path selection. The path probability is calculated as follows:

[0125]

[0126] Where, p i (T) represents the selection probability of target path i, μ i(T) represents the Gaussian membership degree of the target path i, and N represents the number of all candidate paths.

[0127] In one embodiment, such as Figure 3 As shown, the adaptive optimization algorithm dynamically adjusts the threshold range and the corresponding candidate path rules and path priorities, including:

[0128] Step S201: Collect actual route selection data of passengers, and combine the selection probabilities to form a labeled sample set, denoted as (T,p) pairs;

[0129] Step S202: Optimize the standard deviation parameter σ of the Gaussian membership function for each path using the maximum likelihood estimation method. i To ensure that the output path probability distribution best matches the actual travel characteristics of passengers, this step quantifies the "closest to the passenger's true choice probability distribution" as a "maximization of the objective function" problem. The corresponding optimization objective function is:

[0130]

[0131] The σ corresponding to the path selection probability distribution with the highest consistency. i ;

[0132] Through adaptive σ i The value adjustment mechanism is designed to address the dynamic changes in passenger travel path characteristics under different route environments. The adjustment strategy is as follows:

[0133] σ′ i =σ i +k·(T i,max -T i,min )

[0134] Where, σ′ i Here, k is the updated standard deviation parameter, and k is the adaptive adjustment parameter used to dynamically adjust the standard deviation σ of the Gaussian membership function. i Alternatively, filter relevant threshold parameters through other paths;

[0135] Step S203, a two-stage stochastic programming model based on improved Benders decomposition:

[0136] The first stage involves solving the cross-line coupling constraints by addressing the main problem.

[0137] The second stage optimizes path matching by addressing sub-problems.

[0138] In one embodiment, the main problem solving addresses cross-path coupling constraints, including threshold ranges and corresponding candidate path rules and path priority adjustments. The adjustment objective function is:

[0139]

[0140] The constraints are:

[0141] T m→n ≥t walk +t safe

[0142] η≥Φy)

[0143] Among them, C a For the clearing cost corresponding to line a, y a Let A be the path matching decision variable for route a, A be the set of routes, η be the objective value of the subproblem, and T be the path matching decision variable for route a. m→n The actual travel time t for passengers from station m to station n walk For passenger walking time, t safe For safety time redundancy;

[0144] The subproblem determines the route clearing scheme by optimizing the matching degree of each passenger's route, and its objective function is as follows:

[0145]

[0146] The constraints are:

[0147] μ p (T p )≥α

[0148] Among them, P l T represents the set of routes selected by passenger l. p c represents the actual travel time for path p. p μ is the baseline travel time corresponding to path p. p (T p ) represents the membership degree value of path p, and α is the membership degree confidence threshold.

[0149] In one embodiment, optimality cuts and feasibility cuts are performed based on the basic principles of the Benders decomposition algorithm;

[0150] When the objective value η of the current solution in the main problem exceeds the optimal solution Φ(y), an optimal cut is generated:

[0151]

[0152] Here, θ is a slack variable used to control the flexibility of the cutting plane. θ = ε·Φ(y), where ε is a small non-negative constant (e.g., 0.1 to 0.5), indicating that the target value is allowed to float upwards by 1% to 5% to relax the optimal cutting constraint;

[0153] When the path matching constraint is not met, generate a feasible cut:

[0154]

[0155] Among them, z p Let p be the matching decision variable for path p; P represents the set of routes selected by the current passenger l. l The number of paths matched; β is the preset threshold for path matching, representing the expected number of paths to be matched; M is a sufficiently large constant to prevent the cutting plane constraint from being too tight; δ is a binary variable indicating whether path p is forced to match.

[0156] In one embodiment, a hot-start strategy is employed to accelerate the solution of subproblems, including:

[0157] The initial solution uses the historical best solution as a warm start;

[0158] Cut plane library pre-generation: 20% of the Pareto cut plane library is pre-generated, and cut planes with common path combinations are pre-loaded into the ticketing dynamic threshold clearing system that interconnects urban lines and subway lines.

[0159] Cut plane filtering is performed every five iterations, retaining the top 10% of efficient cut planes and removing redundant cut planes.

[0160] In one embodiment, step S105 includes:

[0161] Step S1051: Clarify the passenger's selected travel route information, including route ID and route sequence;

[0162] Step S1052: Output the matching probability between the actual travel time and the baseline time of each path, and quantify the confidence of the path determination through probability evaluation;

[0163] Step S1053: List all candidate paths that meet the conditions and their corresponding probability values ​​to form a candidate path set;

[0164] Step S1054: Record in detail the processing method and final judgment result in the case of multiple matching or no candidate path;

[0165] Step S1055: Visualize the sorting output results.

[0166] Specifically, the path clearing scheme output module 130 is used to receive the calculation results from the judgment and optimization module 120, generate the final path clearing scheme, and output it. Specifically, it includes the following functions:

[0167] First, clarify the route information selected by passengers, including route identifiers and route sequence, to ensure the accuracy and traceability of route determination;

[0168] Secondly, the matching probability between the actual travel time and the baseline time of each path is output, and the confidence of the path determination is quantified by probability assessment.

[0169] Then, all candidate paths that meet the criteria and their corresponding probability values ​​are listed to form a candidate path set for further analysis and decision-making.

[0170] In addition, detailed records are kept of the processing methods and final judgment results in the case of multiple matching or no candidate path, to ensure the stability and interpretability of the system under abnormal conditions;

[0171] Finally, the clearing results are visualized to facilitate users' intuitive viewing, analysis, and support for subsequent operational decisions.

[0172] The present invention has the following beneficial effects:

[0173] Accuracy: The threshold-based decision engine accurately identifies passengers' actual travel routes, and combined with the probability evaluation unit, significantly improves the accuracy and reliability of route determination. Based on route priority, routes with fewer transfers and actual travel times closest to the baseline time are prioritized, effectively reducing the route determination error rate.

[0174] Highly adaptive: The dynamic parameter tuning module combines changes in the route network with adjustments to ticketing rules to optimize the threshold range and priority of route selection in real time. By integrating real-time operational data (such as train delay information), the system dynamically adjusts the route determination logic to ensure that it can flexibly respond to changes in the operating environment and guarantee the efficient operation of the clearing system.

[0175] In the description of this application, it should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments according to this application. For ease of description, the dimensions of the various parts shown in the drawings are not drawn to actual scale. Techniques, methods, and devices known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and devices should be considered part of the specification. In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values. It should be noted that similar reference numerals and letters in the following drawings denote similar items; therefore, once an item is defined in one drawing, it need not be further discussed in subsequent drawings.

[0176] It should be noted that, in this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. It should also be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Furthermore, features described with reference to certain examples may be combined in other examples.

[0177] Furthermore, it should be noted that, unless otherwise explicitly specified and limited, the terms "connection" and "driving" used in the description of this application should be interpreted broadly. They can refer to direct connections, connections through an intermediate medium, or relationships within two elements. Those skilled in the art can understand their specific meaning in this application based on the specific circumstances.

[0178] The above embodiments are provided for those skilled in the art to implement or use this application. Those skilled in the art can make various modifications or changes to the above embodiments without departing from the spirit of this application. Therefore, the scope of protection of this application is not limited to the above embodiments, but should be the maximum scope that conforms to the innovative features mentioned in the claims.

Claims

1. A ticket dynamic threshold clearing system for interconnection and intercommunication of urban lines and subway lines, characterized in that, Comprise: An input data module that defines and stores the characteristic information of each ride path, creates a transmission file path class, and stores the characteristic data of each path as an object form; A judgment and optimization module that comprises: A threshold judgment engine unit provided with a threshold range and corresponding candidate path rules, which filters the candidate paths that meet the conditions based on the actual travel time of the passengers and the threshold range, and when the screening result has only a single candidate path, directly judges the ride path, when the screening result has multiple candidate paths, sends the characteristic data of each path to the probability evaluation unit to recalculate the candidate paths, and sends the characteristic data of the recalculated candidate paths to the conflict resolver unit, and when the screening result has no candidate path that meets the conditions, sends the characteristic data of each path to the abnormality processing unit; A probability evaluation unit that, when there are multiple candidate paths in the screening result, calculates the matching probability of the actual travel time and the reference time consumption of each candidate path based on a normal distribution model, and recalculates the candidate paths; A conflict resolver unit that receives the characteristic data of the recalculated multiple candidate paths, and selects the path according to the path priority judgment standard through the built-in decision strategy; An abnormality processing unit that performs data cleaning and standardization preprocessing, identifies abnormal data, expands the threshold range and the threshold range of the corresponding candidate paths in the corresponding candidate path rules, and re-performs threshold judgment; A dynamic parameter adjustment unit that dynamically adjusts the threshold range and the corresponding candidate path rules and the path priority judgment standard based on historical operation data and real-time data analysis; A clearing scheme output module that receives the calculation results of the judgment and optimization module, generates the final path clearing scheme and outputs it.

2. The ticket dynamic threshold clearing system for interconnection and intercommunication of city regional line and subway line according to claim 1, characterized in that, The characteristic information of each ride path includes path ID, line composition sequence, reference time consumption, and threshold range; The path priority judgment includes: preferentially selecting the path with fewer transfers, and in the case of the same number of transfers, selecting the ride path with the actual travel time closest to the path reference time consumption; The probability evaluation unit selects the candidate path with high matching probability and judges the probability weight for the candidate path.

3. A ticket dynamic threshold clearing method for interconnection and interworking between a city line and a subway line, realized by the ticket dynamic threshold clearing system for interconnection and interworking between a city line and a subway line according to any one of claims 1 to 2, comprising: Step S101, defining and storing the characteristic information of each ride path, creating a transmission file path class, storing the characteristic data of each path as an object form, and setting a threshold range and corresponding candidate path rules; Step S102, based on the actual travel time of the passengers, judging the actual travel path of the passengers in combination with the threshold range and the corresponding candidate path rules, and the judgment rules include: When there is a single candidate path in the judgment result, directly judge the ride path and enter step S105; When there are multiple candidate paths in the judgment result, combine the probability evaluation unit to obtain all candidate paths that meet the conditions and their corresponding probability values to form a candidate path set, and enter step S103; When there is no candidate path that meets the conditions in the judgment result, enter step S104; Step S103, path determination based on path priority, path determination result is obtained, and step S105 is entered; Step S104, expand the threshold range and the threshold range of the corresponding candidate path in the corresponding candidate path rule, return to step S102 for re-determination; Wherein, the threshold range and the corresponding candidate path rule and the path priority are dynamically adjusted by the adaptive optimization algorithm; Step S105, receiving the determination results transmitted by steps S102 and S103, generating and outputting the final path clearing scheme.

4. The method of claim 3, wherein the dynamic threshold clearing method for ticketing interconnection between a suburban line and a subway line is characterized by, In step S102, the threshold range and the corresponding candidate path rule are combined, and each path Path i is traversed to extract the actual travel feature value of the passenger, including path length L i , travel time T i , number of transfers H i , first and last station matching degree S i and time window matching degree W i , and the actual travel path of the passenger is determined based on the actual travel of the passenger between the passengers. wherein, T max , T min are the upper and lower limits of travel time, respectively, L max , L min are the upper and lower limits of path length, respectively, H max , H min are the upper and lower limits of transfer times, respectively, S min is the minimum threshold of the first and last station matching degree, and W min is the minimum threshold of the time window matching degree.

5. The method of claim 3, wherein the dynamic threshold clearing method for ticketing interconnection between a suburban line and a subway line is characterized by, In combination with the threshold range and the corresponding candidate path rule, before determining the actual travel path of the passenger based on the actual travel of the passenger, a Gaussian membership function is used for smoothing modeling, and the Gaussian membership function is: wherein, is the membership of the actual travel time T, c i is the path reference time consumption, σ i is the standard deviation, T i,max , T i,min are the upper and lower limits of the travel time required for path i, respectively; When multiple paths have membership degrees, the membership degrees of each path are normalized and converted into path probability distribution to determine the final path selection, and the path probability calculation is: where p i (T) is the selection probability of target path i, μ i (T) is the Gaussian membership of target path i, and N is the number of all candidate paths.

6. The method of claim 5, wherein the dynamic threshold clearing method for ticketing interconnection between a metro line and a subway line is characterized by, The adaptive optimization algorithm dynamically adjusts the threshold range and the corresponding candidate path rule and the path priority, including: Step S201, collecting passenger actual path selection data, combining selection probability to form a labeled sample set, denoted as (T, p) pair; Step S202, the Gaussian membership function standard deviation parameter σ corresponding to each path is optimized by a maximum likelihood estimation method i The path probability distribution output by the system is made to conform to the actual travel characteristics of passengers to the greatest extent, and the optimization objective function is: By adaptive σ i adjustment mechanism to cope with the dynamic changes of passenger travel path characteristics under different line environments, the adjustment strategy is: σ' i = σ i + k · (T i,max - T i,min ) wherein σ′ i is the updated standard deviation parameter, k is an adaptive adjustment parameter for dynamically adjusting the standard deviation σ i of the Gaussian membership function, or other path screening related threshold parameter; Step S203, based on the two-stage stochastic programming model of improved Benders decomposition: The first stage solves the cross-line coupling constraint through the main problem; The second stage optimizes the path matching degree through the sub-problem.

7. The method of claim 6, wherein the dynamic threshold clearing method for ticketing interconnection between a metro line and a subway line is characterized by, The main problem solves the cross-line coupling constraint, including the adjustment of the threshold range and the corresponding candidate path rule and the path priority, and the adjustment target function is: The constraint condition is: T m→n ≥t walk +t safe η≥Φ(y) where C a is the clearing cost for line a, y a is the path matching decision variable for line a, A is the set of lines, η is the objective value of the subproblem, T m→n is the actual travel time of a passenger from stop m to stop n, t walk is the passenger walking time, t safe is the safety time redundancy; The sub-problem determines the path clearing scheme by optimizing the matching degree of each path of the passenger, and the target function is as follows: The constraint condition is: μ p (T p )≥α where P l is the set of paths selected by passenger l, T p is the actual travel time of path p, c p is the reference travel time corresponding to path p, μ p (T p ) is the membership value of path p, and a is the membership confidence threshold.

8. The method of claim 7, wherein the dynamic threshold clearing method for ticketing interconnection between a metro line and a subway line is characterized by, According to the basic principle of Benders decomposition algorithm, the optimality cut and the feasibility cut are performed; When the target value η of the current solution in the main problem exceeds the optimal solution Φ(y), the optimality cut is generated: Wherein, θ is the relaxation variable; When the path matching degree constraint is not satisfied, the feasibility cut is generated: where z p is the matching decision variable for path p; represents the number of paths in the set of paths P l selected by the current passenger l that are matched; β is the preset threshold for path matching, representing the expected number of matched paths; M is a large enough constant to prevent the cut plane constraint from being too tight; and δ is a binary variable indicating whether path p is forced to be matched.

9. The method of claim 8, wherein the dynamic threshold clearing method for ticketing interconnection between a metro line and a subway line is characterized by, The hot start strategy is used to accelerate the solution of the sub-problem, including: Initial solution, the historical optimal solution is used as the hot start; Cutting plane library pre-generation, 20% of the Pareto cutting plane library is pre-generated, and the cutting plane of the common path combination is loaded in advance into the ticket dynamic threshold clearing system of the interconnection of the urban line and the subway line; Cutting plane screening, cutting plane screening is performed every five iterations, the top 10% efficient cutting planes are retained, and redundant cutting planes are removed.

10. The method of claim 3, wherein the method is characterized by, Step S105 includes: Step S1051, clearly defining the passenger-selected boarding path information, including path ID and line composition sequence; Step S1052, outputting the matching probability of the actual travel time and the path reference time, and quantifying the confidence of path determination through probability evaluation; Step S1053, listing all candidate paths and their corresponding probability values that meet the conditions to form a candidate path set; Step S1054, detailed recording of the processing method and the final determination result in the case of multiple matching or no candidate path; Step S1055, visualizing the clearing output result.

Images