Train diagram optimization method and device based on passenger flow matching, equipment and medium

Abstract

The application provides a train diagram optimization method and device based on passenger flow matching, equipment and medium, relates to the field of rail transit technology, and comprises the following steps: obtaining first information, the first information comprising a train diagram and passenger flow data; constructing a passenger flow distribution model based on the influence of quantified comfort and the number of transfers on passengers, taking the first information as the input value of the passenger flow distribution model to calculate a passenger flow distribution result; calculating a capacity matching degree set according to the passenger flow distribution result, the first information and a preset capacity matching degree mathematical model; evaluating at least one operating enterprise expected index and at least one passenger expected index in the capacity matching degree calculation value to obtain an evaluation result; and optimizing the train diagram according to the evaluation result and a preset optimization rule. The application constructs a passenger flow distribution model by quantifying the influence of comfort and the number of transfers on passengers, and realizes balanced adjustment of the train diagram.

Description

Technical Field

[0001] This invention relates to the field of rail transit technology, and more specifically, to a method, apparatus, equipment, and medium for optimizing train schedules based on passenger flow matching. Background Technology

[0002] Train timetables serve as the foundation for urban rail transit companies' operational planning, a basis for passengers' travel arrangements, and a crucial reflection of the overall service level of the urban rail transit system. A scientifically sound and efficient train timetable not only ensures operational safety and contributes to the economic and social benefits of enterprises, but also provides passengers with high-quality and efficient travel services. Existing optimization methods for urban rail transit train timetables primarily focus on single-line operations, aiming to minimize passenger waiting time or travel costs. They fail to delve into the psychological costs passengers incur during their journeys due to transfers and comfort considerations, resulting in a lack of comprehensive factor consideration and ultimately, poor optimization outcomes. Therefore, a train timetable optimization method based on passenger flow matching is needed. This method should incorporate passengers' perceived psychological costs and construct a passenger flow allocation model based on transfer frequency limitations. Furthermore, it should propose optimization strategies for train timetables from three aspects: time period, section, and direction. Summary of the Invention

[0003] The purpose of this invention is to provide a method, apparatus, device, and medium for optimizing train timetables based on passenger flow matching, in order to improve the aforementioned problems. To achieve the above objective, the technical solution adopted by this invention is as follows:

[0004] Firstly, this application provides a train timetable optimization method based on passenger flow matching, including:

[0005] Obtain first information, which includes train timetable and passenger flow data, wherein the passenger flow data includes actual passenger flow data, historical passenger flow data, operating company expected passenger flow data, and passenger expected passenger flow data;

[0006] A passenger flow allocation model is constructed based on the impact of quantified comfort and transfer frequency on passengers. The first information is used as the input value of the passenger flow allocation model to calculate the passenger flow allocation result.

[0007] A capability matching degree set is calculated based on the passenger flow allocation result, the first information, and the preset capability matching degree mathematical model. The capability matching degree set includes capability matching degree results in at least two dimensions, wherein at least one dimension is the operating company's expected indicator and at least one dimension is the passenger's expected indicator.

[0008] The evaluation results are obtained by evaluating at least one of the operating company's expected indicators and at least one of the passenger's expected indicators in the calculated capability matching degree values.

[0009] The train timetable is optimized based on the evaluation results and preset optimization rules.

[0010] Secondly, this application also provides a train timetable optimization device based on passenger flow matching, comprising:

[0011] The acquisition module is used to acquire first information, which includes train timetable and passenger flow data. The passenger flow data includes actual passenger flow data, historical passenger flow data, operating company expected passenger flow data, and passenger expected passenger flow data.

[0012] The module constructs a passenger flow allocation model based on the impact of quantitative comfort and transfer frequency on passengers, and uses the first information as the input value of the passenger flow allocation model to calculate the passenger flow allocation result;

[0013] The calculation module is used to calculate a set of capability matching degrees based on the passenger flow allocation results, the first information and a preset capability matching degree mathematical model. The set of capability matching degrees includes capability matching degree results in at least two dimensions, wherein at least one dimension is an operating enterprise expectation indicator and at least one dimension is a passenger expectation indicator.

[0014] The evaluation module is used to evaluate at least one of the operating company's expected indicators and at least one of the passenger's expected indicators in the calculated capability matching degree to obtain an evaluation result;

[0015] The optimization module is used to optimize the train timetable based on the evaluation results and preset optimization rules.

[0016] Thirdly, this application also provides a train timetable optimization device based on passenger flow matching, comprising:

[0017] Memory, used to store computer programs;

[0018] A processor is used to implement the steps of the train timetable optimization method based on passenger flow matching when executing the computer program.

[0019] Fourthly, this application also provides a readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described train timetable optimization method based on passenger flow matching.

[0020] The beneficial effects of this invention are as follows:

[0021] This invention studies the factors influencing passenger route selection, incorporating passengers' perceived psychological costs, quantifying the impact of comfort and transfer frequency on passengers to construct a passenger flow allocation model, and calculating the capacity matching degree using a multi-objective synthesis method based on the network passenger flow allocation results. Based on the capacity matching degree set, analysis is performed on indicators of operator expectations and passenger expectations, proposing targeted optimization strategies from three aspects: time period, section, and direction, to achieve balanced adjustments to the train timetable.

[0022] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing embodiments of the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0023] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of the train timetable optimization method based on passenger flow matching described in this embodiment of the invention;

[0025] Figure 2 This is a schematic diagram of the train timetable optimization device based on passenger flow matching described in an embodiment of the present invention;

[0026] Figure 3 This is a schematic diagram of the train timetable optimization device based on passenger flow matching as described in an embodiment of the present invention.

[0027] The diagram is labeled as follows: 1. Acquisition module; 2. Construction module; 21. First calculation unit; 22. Second calculation unit; 221. First processing unit; 222. Fourth calculation unit; 223. Fifth calculation unit; 224. Sixth calculation unit; 23. First construction unit; 24. Third calculation unit; 3. Calculation module; 31. Second construction unit; 32. Seventh calculation unit; 33. Eighth calculation unit; 4. Evaluation module; 41. Second processing unit; 42. First clustering unit; 43. Third processing unit; 44. Ninth calculation unit; 45. First evaluation unit; 5. Optimization module; 51. Fourth processing unit; 52. Fifth processing unit; 53. Sixth processing unit; 800. Train timetable optimization device based on passenger flow matching; 801. Processor; 802. Memory; 803. Multimedia component; 804. I / O interface; 805. Communication component. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0029] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0030] Example 1:

[0031] This embodiment provides a train timetable optimization method based on passenger flow matching.

[0032] See Figure 1 The figure shows that the method includes steps S100, S200, S300, S400 and S500.

[0033] Step S100: Obtain first information, which includes train timetable and passenger flow data. Passenger flow data includes actual passenger flow data, historical passenger flow data, operating company expected passenger flow data, and passenger expected passenger flow data.

[0034] Understandably, this step involves uploading and storing information such as train schedules and passenger flow data to facilitate subsequent analysis and processing.

[0035] Step S200: Construct a passenger flow allocation model based on the impact of quantitative comfort and transfer frequency on passengers, and calculate the passenger flow allocation result by using the first information as the input value of the passenger flow allocation model.

[0036] Understandably, this step is based on an analysis of the factors influencing passenger travel route selection, quantifies the impact of comfort and transfers on passenger psychological perception, constructs a generalized travel cost function, improves the efficient route search algorithm, builds a passenger flow allocation model, and uses the MSA algorithm to solve the model to obtain the passenger flow allocation results. It should be noted that step S200 includes steps S210, S220, S230, and S240.

[0037] Step S210: Construct a generalized travel cost formula based on quantified comfort, and calculate the set of travel costs based on the first information and the generalized travel cost formula.

[0038] It is understandable that the formula for the generalized travel cost of the route constructed in this step is:

[0039]

[0040] Where r and s represent the passenger's origin and destination; w represents the route the passenger chooses within the origin and destination (r, s); N represents the number of segments in the route; and M represents the number of stations in the route. This indicates the time the train spends traveling on segment i; This indicates the stopping time of the train at station j; This indicates the number of transfers a passenger makes on path w; t represents the walking time for passengers on path w to pass through transfer station k; f π represents the train interval of the line; π represents a parameter related to the time it takes for passengers to walk to the transfer platform and the train interval, taken as 0.5; α represents the penalty factor for transfer time; β represents the penalty factor for the number of transfers; Y i (x i x represents the perceived psychological cost due to the degree of crowding. i p represents the passenger flow at the section cross-section. i C represents the number of train seats. i Let x represent the maximum number of passengers the train can accommodate. i <p i At that time, Y i (x i ) = 0; when p i <x i ≤C i hour, A represents the additional cost factor under normal congestion conditions, and η is the exponential parameter; when x i >C i hour, B represents the additional cost factor under overload, and γ is the exponential parameter.

[0041] Step S220: Construct an effective path search algorithm based on the impact of transfer times. Calculate the effective path set based on the first information, the path travel cost set, and the effective path search algorithm.

[0042] Understandably, this step takes into account the impact of passenger transfer frequency, and the minimum number of passenger transfers on the road network is n. min Number of transfers n≤n min The effective path search algorithm is constructed using constraints as conditions for the effective paths, and the set of effective paths is obtained. It should be noted that step S220 includes steps S221, S222, S223, and S224.

[0043] Step S221: Select any node in the train time map as the initial vertex and mark the initial vertex as visited.

[0044] Understandably, this step is to initialize the data, select the starting vertex i, and mark it as visited.

[0045] Step S222: Calculate the minimum cost of generalized travel costs for all valid paths within the interval based on Dijkstra's algorithm. The interval includes nodes.

[0046] Understandably, this step involves calculating the minimum cost c between intervals using Dijkstra's algorithm. min .

[0047] Step S223: Starting from the initial vertex, traverse its adjacent nodes in turn to calculate the set of path costs.

[0048] Understandably, this step starts from the initial vertex i, traverses its adjacent nodes, obtains the set of paths, and calculates the path cost corresponding to each path.

[0049] Step S224: Based on the preset limit on the number of transfers, determine the set of path costs and the minimum cost to obtain the set of valid paths, and calculate the generalized cost corresponding to each valid path in the set of valid paths.

[0050] Understandably, in this step, we determine whether the path costs within the path cost set satisfy c ≤ c. min Do the conditions and the number of transfers satisfy n≤n? min If all constraints are met, the corresponding path is entered into the set of valid paths and its generalized cost is calculated.

[0051] Step S230: Construct a passenger flow allocation model based on the first information, the set of valid routes, and the preset passenger route selection model.

[0052] It is understandable that the passenger flow allocation model constructed in this step is as follows:

[0053]

[0054] Where r and s represent the passenger's origin and destination; θ represents the probability of choosing path w; n represents the number of transfers; w represents the passenger's choice of path within the origin and destination points (r, s); θ is an evaluation index that measures the passenger's familiarity with the rail transit network. It is represented as the minimum cost of generalized travel for all valid paths in the interval (r, s); The cost of a passenger's journey on route w.

[0055] Step S240: Solve the passenger flow allocation model based on the MSA algorithm to obtain the passenger flow allocation result.

[0056] Understandably, in this step, the MSA algorithm is used to design the passenger flow allocation algorithm for the passenger flow allocation model to obtain the passenger flow allocation results.

[0057] Step S300: Calculate the capability matching degree set based on the passenger flow allocation result, the first information and the preset capability matching degree mathematical model. The capability matching degree set includes capability matching degree results in at least two dimensions, wherein at least one dimension is the operating company's expected indicator and at least one dimension is the passenger's expected indicator.

[0058] Understandably, this step involves constructing formulas for relevant operational indicators describing the degree of matching between train schedules and passenger flow demand, and obtaining a set of matching degrees based on the operational indicator algorithm. It should be noted that step S300 includes steps S310, S320, and S330.

[0059] Step S310: Construct an operational indicator formula based on the matching degree between train operation data and passenger flow demand.

[0060] Understandably, the formula for the operational metrics constructed in this step is:

[0061]

[0062]

[0063]

[0064]

[0065]

[0066]

[0067]

[0068]

[0069] Where i represents a station along the line, i∈[1,M]; j is the train number, j∈[1,N]; N represents N sections within the route; M represents M stations within the route; L represents L stations within the route; l is the train line, l∈[1,L]; The number of passengers remaining at station i after train j on line l departs station i. The passenger flow between (r, s) is determined based on the passenger flow allocation result of S1. This indicates the number of people waiting at station i for train j on line l; This represents the number of people who disembarked at station i on train j on line l. This indicates the number of people who boarded train j on line l at station i; This represents the number of passengers remaining at station i after train j on line l departs from station i; C represents the number of cars in the train; Q represents the capacity of each train; and k represents the maximum passenger capacity the train can handle. Let represent the cross-sectional passenger flow of train j in the interval (i, i+1); This represents the section load factor of train j in the section (i, i+1); Indicates the maximum cross-sectional load factor of line l; Γ i δ represents the average waiting time for passengers at station i; δ is the passenger delay penalty coefficient, which is generally taken as 1.7; μ represents the network load intensity; and D represents the total length of the line. This indicates the departure time of train j at station i; This indicates the departure time of train j-1 at station i; Q represents the departure time of train j+1 at station i; i,i+x (t) represents the passenger flow between OD pairs (i, i+x); Q x,i (t) represents the passenger flow between OD pairs (x, i); This represents the passenger flow of train j in the interval (i-1, i); Passenger flow of train j on section (i-1, i) of line l; Q 全日 This indicates the total daily passenger volume.

[0070] Step S320: Calculate the operational indicators based on the train timetable, passenger flow distribution results, and operational indicator formula.

[0071] Understandably, the values ​​of each operational indicator are calculated using an operational indicator algorithm in this step.

[0072] Step S330: Construct a capability matching degree mathematical model based on the matching relationship between corporate interests and passenger interests, and use the calculation results of operational indicators as the input values ​​of the capability matching degree mathematical model to calculate the capability matching degree set.

[0073] It is understandable that the mathematical model for capability matching constructed in this step is as follows:

[0074]

[0075]

[0076]

[0077]

[0078]

[0079]

[0080] Where W represents the capacity matching degree; X represents the line utilization rate; and Δ represents the number of evaluation units, when 0 < ω ≤ ω a When ω = 0, u1(ω) = 0; when ω a <ω≤ω b hour, When ω>ω b When u1(ω) = 1, u1(ω) represents the full load rate judgment function of the tolerance interval; ω a This represents the minimum acceptable load factor for a transportation company's routes; ω b This represents the ideal occupancy rate of a transportation route, as desired by the transportation company. Y represents passenger flow characteristics; when 0... max a hour, When Q a max b hour, This represents the function for determining cross-sectional passenger flow; when Q... max Q b hour, Q a Q represents the minimum and maximum cross-sectional passenger flow that a transportation company can tolerate; max This represents the actual cross-sectional passenger flow; Q b This represents the maximum cross-sectional passenger flow expected by the transportation company under ideal conditions. Z represents the overall network efficiency, when 0 < μ ≤ μ a When μ = 0, u3(μ) = 0; when μ = 0, u3(μ) = 0. a <μ≤μ b hour, u3(μ) represents the load strength judgment function of the power grid; when μ > μ b ​​​​At that time, u3(μ)=1; μ a μ represents the minimum network load intensity that the transportation company can tolerate; μ represents the actual network load intensity; μ b This represents the network load intensity that transportation companies expect to achieve. U represents the passenger's travel environment comfort, when 0 < S ≤ S a When u4(S) = 1; when S a <S≤S c hour, u4(S) represents the train passenger capacity judgment function; when S > S b At that time, u4(S) = 0; S a S represents the number of train seats; S represents the actual number of seats used; S b This represents the train's rated passenger capacity. V represents the reliability of travel time; when 0 < Γ ≤ Γ a When Γ = 1, u5(Γ) = 1; when Γ = 1 a <Γ≤Γ b hour, u5(Γ) represents the passenger waiting time judgment function; when Γ < Γ b At that time, u5(Γ)=0; Γ a Γ represents the average waiting time under ideal conditions as expected by passengers; Γ represents the actual average waiting time for passengers; b This represents the longest average waiting time that passengers can tolerate. ξ1 and ξ2 represent the weights of enterprise satisfaction and passenger satisfaction in the capacity matching evaluation; δ1 represents the weight of route utilization rate in the enterprise satisfaction evaluation; δ2 represents the weight of passenger flow characteristics in the enterprise satisfaction evaluation; δ3 represents the weight of overall network efficiency in the enterprise satisfaction evaluation; δ4 represents the weight of travel environment comfort in the passenger satisfaction evaluation; δ5 represents the weight of travel time reliability in the passenger satisfaction evaluation. This represents the section load factor of train j in the interval (i, i+1).

[0081] Step S400: Evaluate at least one operating company expectation indicator and at least one passenger expectation indicator in the capability matching set to obtain the evaluation result.

[0082] Understandably, this step compares the numerical values ​​of the indicators in the capability matching set with the standard indicators, and obtains an evaluation result of "high" or "low" based on the comparison result. It should be noted that step S400 includes steps S410, S420, S430, S440, and S450.

[0083] Step S410: Standardize the historical passenger flow data to obtain a standard dataset.

[0084] Understandably, this step involves standardizing historical passenger flow data and extracting input data for calculating evaluation indicators.

[0085] Step S420: Perform clustering operations on the standard dataset to obtain the clustering results.

[0086] Understandably, this step uses distance-based clustering to obtain the clustering results.

[0087] Step S430: Retain the points with the highest approximation in the clustering results to obtain the normal dataset.

[0088] Understandably, the point with the highest approximation in this step is taken as the information that is closest to the actual situation.

[0089] Step S440: Calculate the set of average capability matching scores based on the normal dataset.

[0090] Understandably, the standard values ​​of the capability matching indexes are calculated based on the normal dataset in this step.

[0091] Step S450: Compare the values ​​of the corresponding dimensions in the capability matching set with the values ​​of each constituent dimension in the capability matching average set to obtain the evaluation result.

[0092] Understandably, in this step, the indicator values ​​in the capability matching set are compared with the corresponding indicator standard values ​​in the capability matching average set to obtain an evaluation result of "high" or "low".

[0093] Step S500: Optimize the train timetable based on the evaluation results and preset optimization rules.

[0094] Understandably, this step categorizes the different permutations and combinations of the constituent indicators of capability matching and proposes optimization schemes from various levels. It should be noted that step S500 includes steps S510, S520, and S530.

[0095] Step S510: Annotate the evaluation results based on the overall analysis of the matching relationship between corporate interests and passenger interests.

[0096] It is understandable that the annotations in this step are descriptions of the actual situation corresponding to the values ​​of each indicator in the evaluation results.

[0097] Step S520: Analyze the evaluation results after annotation based on three aspects: time-segment optimization, segment optimization, and direction optimization to obtain the optimization scheme.

[0098] Understandably, this step aims to achieve a coordinated match between train schedule capacity and passenger demand through optimization at various levels.

[0099] Step S530: Optimize the train timetable according to the optimization scheme.

[0100] It is understandable that the evaluation results in this step have the following permutations and combinations:

[0101]

[0102]

[0103] The following methods are used to optimize train timetables for different combinations of evaluation results:

[0104] 1. Category I: X High, Z High, U Low, V Low. For time-of-day optimization, this can be achieved by adjusting departure intervals and train formation schemes. For section-of-day optimization, this can be achieved by adjusting train route schemes in conjunction with passenger flow demand to achieve reasonable capacity allocation, selecting appropriate long and short routes. For direction-of-day optimization, the unbalanced transport organization method is considered.

[0105] 2. Category II: X High, Z Low, U Low, V Low. For time-of-day optimization, capacity is increased through adjusting departure intervals and train formation schemes. For section-of-day optimization, the focus is on adjusting route schemes. Based on understanding passenger flow distribution characteristics, appropriate multi-route schemes are selected. For directional optimization, the approach is to address uneven transport organization, focusing on scheduling trains in sections with uneven passenger flow.

[0106] 3. Category III: X High Z High U Low V High and X High Z Low U Low V High. Similar to Category I, for this type of situation, multiple measures are taken to improve system performance by using time-segmented, region-segmented, and direction-segmented optimization methods.

[0107] 4. Category IV: X-low, Z-high, U-high, V-low and X-low, Z-low, U-high, V-low. Regarding time-segmentation optimization, the number of train pairs can be adjusted appropriately. Under certain conditions, a mixed-run mode of two trains coupled together with large and small train sets can be adopted.

[0108] 5. Category V: X-low, Z-high, U-high, V-high and X-low, Z-low, U-high, V-high. Similar to Category IV, optimization in this category aims to improve capacity utilization efficiency and avoid capacity waste while ensuring passenger travel needs are met. Based on considerations of sustainable system development, routes in the initial stages of passenger flow development should plan ahead and reserve a certain amount of capacity in advance to meet the growing passenger demand in the later stages.

[0109] Example 2:

[0110] like Figure 2 As shown, this embodiment provides a train timetable optimization device based on passenger flow matching. The device includes:

[0111] The acquisition module 1 is used to acquire first information, which includes train timetable and passenger flow data. The passenger flow data includes actual passenger flow data, historical passenger flow data, operating company expected passenger flow data, and passenger expected passenger flow data.

[0112] Module 2 is used to construct a passenger flow allocation model based on the impact of quantified comfort and transfer frequency on passengers. The first information is used as the input value of the passenger flow allocation model to calculate the passenger flow allocation result.

[0113] The calculation module 3 is used to calculate a set of capability matching degrees based on the passenger flow allocation results, the first information and the preset capability matching degree mathematical model. The set of capability matching degrees includes capability matching degree results in at least two dimensions, wherein at least one dimension is the operating enterprise's expected indicator and at least one dimension is the passenger's expected indicator.

[0114] Evaluation module 4 is used to evaluate at least one of the operating company's expected indicators and at least one of the passenger's expected indicators in the capability matching set, and obtain an evaluation result.

[0115] The optimization module 5 is used to optimize the train timetable based on the evaluation results and preset optimization rules.

[0116] In one specific embodiment of this disclosure, the construction module 2 includes:

[0117] The first calculation unit 21 constructs a generalized travel cost formula based on quantified comfort, and calculates a set of travel costs based on the first information and the generalized travel cost formula.

[0118] The second calculation unit 22 constructs an effective path search algorithm based on the influence of the number of transfers, and calculates the effective path set according to the first information, the path travel cost set, and the effective path search algorithm.

[0119] The first construction unit 23 is used to construct a passenger flow allocation model based on the first information, the set of effective paths, and the preset passenger path selection model.

[0120] The third calculation unit 24 solves the passenger flow allocation model based on the MSA algorithm and calculates the passenger flow allocation result.

[0121] In one specific embodiment of this disclosure, the second computing unit 22 includes:

[0122] The first processing unit 221 is used to select any node in the train time map as an initial vertex and mark the initial vertex as visited.

[0123] The fourth calculation unit 222 calculates the minimum cost of generalized travel costs for all valid paths within the interval based on Dijkstra's algorithm, where the interval includes the node.

[0124] The fifth calculation unit 223 is used to calculate the path cost set by traversing its adjacent nodes sequentially from the initial vertex.

[0125] The sixth calculation unit 224, based on a preset limit on the number of transfers, judges the set of path costs and the minimum cost to obtain a set of valid paths and calculates the generalized cost corresponding to each valid path in the set of valid paths.

[0126] In one specific embodiment of this disclosure, the computing module 3 includes:

[0127] The second building unit 31 constructs an operational indicator formula based on the matching degree between train operation data and passenger flow demand.

[0128] The seventh calculation unit 32 is used to calculate the operation index calculation result based on the train timetable, the passenger flow allocation result and the operation index formula.

[0129] The eighth calculation unit 33 constructs a capability matching degree mathematical model based on the matching relationship between corporate interests and passenger interests, and uses the calculation results of the operation indicators as the input values ​​of the capability matching degree mathematical model to calculate the capability matching degree set.

[0130] In one specific embodiment of this disclosure, the evaluation module 4 includes:

[0131] The second processing unit 41 is used to standardize the historical passenger flow data to obtain a standard dataset.

[0132] The first clustering unit 42 is used to perform clustering operations on the standard dataset to obtain clustering results.

[0133] The third processing unit 43 is used to retain the points with the highest approximation in the clustering results to obtain a normal dataset.

[0134] The ninth calculation unit 44 is used to calculate the set of average capability matching degrees based on the normal dataset.

[0135] The first evaluation unit 45 is used to compare the values ​​of the corresponding dimensions in the capability matching degree set with the values ​​of each constituent dimension in the capability matching degree average value set to obtain the evaluation result.

[0136] In one specific embodiment of this disclosure, the optimization module 5 includes:

[0137] The fourth processing unit 51 annotates the evaluation results based on an overall analysis of the matching relationship between corporate interests and passenger interests.

[0138] The fifth processing unit 52 analyzes the annotated evaluation results based on three aspects: time-segment optimization, segment-segment optimization, and direction-segment optimization to obtain an optimization scheme.

[0139] The sixth processing unit 53 is used to optimize the train timetable according to the optimization scheme.

[0140] Example 3:

[0141] Corresponding to the above method embodiments, this embodiment also provides a train timetable optimization device based on passenger flow matching. The train timetable optimization device based on passenger flow matching described below and the train timetable optimization method based on passenger flow matching described above can be referred to in correspondence.

[0142] Figure 3 This is a block diagram illustrating a train timetable optimization device 800 based on passenger flow matching, according to an exemplary embodiment. Figure 3 As shown, the train timetable optimization device 800 based on passenger flow matching may include: a processor 801 and a memory 802. The train timetable optimization device 800 based on passenger flow matching may also include one or more of the following: a multimedia component 803, an I / O interface 804, and a communication component 805.

[0143] The processor 801 controls the overall operation of the passenger flow matching-based train timetable optimization device 800 to complete all or part of the steps in the aforementioned passenger flow matching-based train timetable optimization method. The memory 802 stores various types of data to support the operation of the passenger flow matching-based train timetable optimization device 800. This data may include, for example, instructions for any application or method operating on the passenger flow matching-based train timetable optimization device 800, as well as application-related data such as contact data, sent and received messages, images, audio, video, etc. The memory 802 can be implemented using any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 802 or transmitted via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. I / O interface 804 provides an interface between processor 801 and other interface modules, such as keyboards, mice, and buttons. These buttons can be virtual or physical. Communication component 805 is used for wired or wireless communication between the passenger flow matching-based train timetable optimization device 800 and other devices. Wireless communication includes, for example, Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination thereof. Therefore, the corresponding communication component 805 may include a Wi-Fi module, a Bluetooth module, and an NFC module.

[0144] In an exemplary embodiment, the train timetable optimization device 800 based on passenger flow matching can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described train timetable optimization method based on passenger flow matching.

[0145] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the above-described train timetable optimization method based on passenger flow matching. For example, the computer-readable storage medium may be the memory 802 including the program instructions, which may be executed by the processor 801 of the train timetable optimization device 800 based on passenger flow matching to complete the above-described train timetable optimization method based on passenger flow matching.

[0146] Example 4:

[0147] Corresponding to the above method embodiments, this embodiment also provides a readable storage medium. The readable storage medium described below can be referred to in conjunction with the train timetable optimization method based on passenger flow matching described above.

[0148] A readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the train timetable optimization method based on passenger flow matching described in the above method embodiments.

[0149] Specifically, the readable storage medium can be a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or any other readable storage medium capable of storing program code.

[0150] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A train timetable optimization method based on passenger flow matching, characterized in that, include: Obtain first information, which includes train timetable and passenger flow data, wherein the passenger flow data includes actual passenger flow data, historical passenger flow data, operating company expected passenger flow data, and passenger expected passenger flow data; A passenger flow allocation model is constructed based on the impact of quantified comfort and transfer frequency on passengers. The first information is used as the input value of the passenger flow allocation model to calculate the passenger flow allocation result. The passenger flow allocation model constructed based on the impact of quantified comfort and transfer frequency on passengers includes: Based on quantitative comfort, a generalized travel cost formula for a route is constructed, and a set of route travel costs is calculated according to the first information and the generalized travel cost formula for a route. An effective path search algorithm is constructed based on the impact of the number of transfers, and an effective path set is calculated based on the first information, the path travel cost set, and the effective path search algorithm. A passenger flow allocation model is constructed based on the first information, the set of effective paths, and the preset passenger path selection model. The passenger flow allocation model is solved based on the MSA algorithm to obtain the passenger flow allocation result; A capability matching degree set is calculated based on the passenger flow allocation result, the first information, and the preset capability matching degree mathematical model. The capability matching degree set includes capability matching degree results in at least two dimensions, wherein at least one dimension is the operating company's expected indicator and at least one dimension is the passenger's expected indicator. The capability matching degree set is calculated based on the passenger flow allocation result, the first information, and a preset capability matching degree mathematical model, including: Formulas for operational indicators are constructed based on the matching degree between train operation data and passenger flow demand. The operational indicator calculation results are obtained based on the train timetable, the passenger flow allocation results, and the operational indicator formula. A capability matching degree mathematical model is constructed based on the matching relationship between corporate interests and passenger interests. The calculation results of the operational indicators are used as the input values ​​of the capability matching degree mathematical model to calculate the capability matching degree set. The evaluation results are obtained by evaluating at least one of the operating company's expected indicators and at least one of the passenger's expected indicators in the set of capability matching degrees. The train timetable is optimized based on the evaluation results and preset optimization rules.

2. The train timetable optimization method based on passenger flow matching according to claim 1, characterized in that, The train timetable is optimized based on the evaluation results and preset optimization rules, including: The evaluation results are annotated based on an overall analysis of the matching relationship between corporate interests and passenger interests; An optimization scheme is obtained by analyzing the evaluation results after annotation based on three aspects: time-segment optimization, segment-segment optimization, and direction-segment optimization. The train timetable is optimized according to the optimization scheme.

3. A train timetable optimization device based on passenger flow matching, characterized in that, include: The acquisition module is used to acquire first information, which includes train timetable and passenger flow data. The passenger flow data includes actual passenger flow data, historical passenger flow data, operating company expected passenger flow data, and passenger expected passenger flow data. The module constructs a passenger flow allocation model based on the impact of quantitative comfort and transfer frequency on passengers, and uses the first information as the input value of the passenger flow allocation model to calculate the passenger flow allocation result; The building module includes: The first calculation unit constructs a generalized travel cost formula based on quantified comfort, and calculates a set of travel costs based on the first information and the generalized travel cost formula. The second calculation unit constructs an effective path search algorithm based on the impact of the number of transfers, and calculates the effective path set according to the first information, the path travel cost set, and the effective path search algorithm. The first construction unit is used to construct a passenger flow allocation model based on the first information, the set of effective paths, and the preset passenger path selection model. The third calculation unit solves the passenger flow allocation model based on the MSA algorithm and calculates the passenger flow allocation result; The calculation module is used to calculate a set of capability matching degrees based on the passenger flow allocation results, the first information and a preset capability matching degree mathematical model. The set of capability matching degrees includes capability matching degree results in at least two dimensions, wherein at least one dimension is an operating enterprise expectation indicator and at least one dimension is a passenger expectation indicator. The calculation module includes: The second building unit is to construct operational indicator formulas based on the matching degree between train operation data and passenger flow demand. The seventh calculation unit is used to calculate the operation index calculation result based on the train timetable, the passenger flow allocation result and the operation index formula; The eighth calculation unit constructs a capability matching degree mathematical model based on the matching relationship between corporate interests and passenger interests, and uses the calculation results of the operation indicators as the input values ​​of the capability matching degree mathematical model to calculate the capability matching degree set. The evaluation module is used to evaluate at least one of the operating company's expected indicators and at least one of the passenger's expected indicators in the capability matching set, and obtain the evaluation result; The optimization module is used to optimize the train timetable based on the evaluation results and preset optimization rules.

4. The train timetable optimization device based on passenger flow matching according to claim 3, characterized in that, The optimization module includes: The fourth processing unit annotates the evaluation results based on an overall analysis of the matching relationship between corporate interests and passenger interests; The fifth processing unit analyzes the annotated evaluation results based on three aspects: time-segment optimization, segment-segment optimization, and direction-segment optimization to obtain an optimization scheme; The sixth processing unit is used to optimize the train timetable according to the optimization scheme.

5. A train timetable optimization device based on passenger flow matching, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the steps of the train timetable optimization method based on passenger flow matching as described in any one of claims 1 to 2 when executing the computer program.

6. A medium, characterized in that: The medium stores a computer program, which, when executed by a processor, implements the steps of the train timetable optimization method based on passenger flow matching as described in any one of claims 1 to 2.

Images