Urban rail transit passenger service quality optimization method, device, electronic device and storage medium

Abstract

The present disclosure relates to a method, device, electronic device and storage medium for optimizing the quality of service for urban rail transit passengers. The method comprises obtaining road network data, passenger flow data, a decision variable set and a guidance strategy set of a subway network within a specified time period; determining a passenger path selection set based on the road network data, passenger flow data and the guidance strategy set; determining the patience loss of passengers traveling from each starting station to each terminal station based on the road network data, the passenger path selection set and the passenger service coefficient set; determining the waiting time required for the target travel path selected by each passenger based on the passenger path selection set; optimizing the decision variable set and the guidance strategy set based on the patience loss and waiting time of passengers traveling from each starting station to each terminal station to obtain a target decision variable set and a target guidance strategy set. Thus, it is possible to shorten the waiting time and patience loss of passengers in the subway network and improve the passenger service quality of the subway network.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a method, device, electronic device, and storage medium for optimizing urban rail transit passenger service quality. Background Art

[0002] The subway is currently a major mode of urban rail transit, helping to alleviate ground traffic pressure, promote coordinated regional economic development, and provide significant improvements to people's livelihoods. However, there is still much room for improvement in the passenger experience. For example, during peak hours, carriages are prone to overcrowding, requiring multiple queues before boarding; during off-peak hours, long intervals between trains often result in lengthy waits before boarding. These issues create a negative passenger experience.

[0003] Train scheduling on subway lines typically uses a timetable, which controls the departure and arrival times of each train at various stations. These schedules are typically based on certain temporal, spatial, and equipment constraints, such as a safe operating speed limit; a minimum interval between departures to prevent rear-end collisions; and a maximum number of trains operating on the line at any one time.

[0004] Because current timetables are not based on actual subway passenger flow or the actual needs of passengers in choosing their routes, this can easily lead to the aforementioned poor riding experience. Therefore, optimizing train scheduling and guiding passenger flow across the subway network to ensure quality service, facilitate travel, and enhance the subway riding experience is an urgent issue that needs to be addressed. Summary of the Invention

[0005] In view of this, the present disclosure proposes a method, device, electronic device and storage medium for optimizing the passenger service quality of urban rail transit, which can shorten the waiting time and patience loss of passengers in the subway network and improve the passenger service quality of the subway network.

[0006] According to one aspect of the present disclosure, a method for optimizing the passenger service quality of urban rail transit is provided, comprising: obtaining network data, passenger flow data, a decision variable set, and a guidance strategy set of a subway network within a specified time period, wherein the network data comprises: line information, station information, and train information in the subway network; the passenger flow data comprises the number of passengers traveling from each starting station to each terminal station in the subway network within each unit time period of the specified time period; the specified time period comprises a plurality of sub-time periods, the decision variable set comprises the departure interval of trains in each sub-time period of the specified time period, and the guidance strategy set comprises the passenger flow guidance strategy set for each sub-time period of the specified time period. The passenger flow guidance strategy is a strategy for determining a passenger path selection set based on the network data, the passenger flow data, and the guidance strategy set. The passenger path selection set includes a passenger path selection matrix from each starting station to each terminal station, wherein the passenger path selection matrix from the s-th starting station to the v-th terminal station includes multiple passenger paths from the s-th starting station to the v-th terminal station. a target travel path selected by each passenger, wherein s∈[1,N], v∈[1,N], s≠v, and N is the total number of stations in the subway network; determining the patience loss of each passenger traveling from each starting station to each terminal station based on the network data, the passenger path selection set, and the passenger service coefficient set, wherein the passenger service coefficient set includes a passenger service coefficient matrix for traveling from each starting station to each terminal station, wherein the passenger service coefficient matrix for traveling from the s-th starting station to the v-th terminal station includes the service coefficient of each passenger traveling from the s-th starting station to the v-th terminal station, and the service coefficient represents the gradient of the patience loss The patience loss represents the patience lost by a passenger when selecting a target travel route; based on the passenger route selection set, the waiting time required for the target travel route selected by each passenger traveling from each starting station to each terminal station in the subway network is determined; based on the patience loss and the required waiting time of each passenger traveling from each starting station to each terminal station in the subway network, the decision variable set and the guidance strategy set are optimized to obtain an optimized target decision variable set and a target guidance strategy set, so as to improve the passenger service quality of the subway network within the specified time period by utilizing the optimized target decision variable set and the target guidance strategy set.

[0007] In one possible implementation, the passenger path selection set is determined based on the road network data, the passenger flow data and the guidance strategy set, including: for the sth starting station in the subway network, determining a path set from the sth starting station to the vth terminal station based on the road network data, wherein the path set from the sth starting station to the vth terminal station includes at least one selectable travel path from the sth starting station to the vth terminal station and the path length of each travel path; determining the number of passengers going from the sth starting station to the vth terminal station based on the passenger flow data; determining a passenger path selection matrix from the sth starting station to the vth terminal station based on the guidance strategy set, the path set from the sth starting station to the vth terminal station and the number of passengers going from the sth starting station to the vth terminal station within the specified time period.

[0008] In one possible implementation, the determination of the patience loss of each passenger traveling from each starting station to each terminal station based on the road network data, the passenger path selection set, and the passenger service coefficient set includes: for the s-th starting station in the subway network, based on the path set from the s-th starting station to the v-th terminal station, determining a path excess rate set from the s-th starting station to the v-th terminal station, wherein the path excess rate set includes the path excess rate of each riding path in at least one ride path that can be selected from the s-th starting station to the v-th terminal station. The path excess rate of each riding route is the ratio of the path length of each riding route to the path length of the shortest riding route minus 1, and the path set is determined based on the road network data; according to the path excess rate set from the s-th starting station to the v-th terminal station and the passenger service coefficient matrix from the s-th starting station to the v-th terminal station, the original patience loss of each passenger traveling from the s-th starting station to the v-th terminal station is determined, wherein the patience loss of each passenger traveling from the s-th starting station to the v-th terminal station includes the original patience loss of each passenger.

[0009] In a possible implementation, the step of determining the patience loss of each passenger traveling from each starting station to each terminal station based on the road network data, the passenger path selection set, and the passenger service coefficient set further includes: determining an expected value of the original patience loss of each passenger traveling from the s-th starting station to the v-th terminal station based on the original patience loss of each passenger traveling from the s-th starting station to the v-th terminal station, and determining the expected value as a tolerance threshold for traveling from the s-th starting station to the v-th terminal station; for the i-th passenger traveling from the s-th starting station to the v-th terminal station, if the original patience loss of the i-th passenger is greater than or equal to the tolerance threshold, based on a first weighting coefficient, The difference between the original patience loss of the i-th passenger and the tolerance threshold is weighted to obtain the weighted patience loss of the i-th passenger; or, when the original patience loss of the i-th passenger is less than the tolerance threshold, the difference between the original patience loss of the i-th passenger and the tolerance threshold is weighted based on a second weighting coefficient to obtain the weighted patience loss of the i-th passenger; wherein, i∈[1,M], M is the number of passengers going from the s-th starting station to the v-th terminal station, the first weighting coefficient is greater than the second weighting coefficient, and the patience loss of each passenger going from the s-th starting station to the v-th terminal station includes the weighted patience loss of each passenger.

[0010] In one possible implementation, the method of determining the waiting time required for the target travel path selected by each passenger traveling from each starting station to each terminal station in the subway network based on the passenger path selection set includes: for the target travel path selected by any passenger traveling from the sth starting station to the vth terminal station, if the target travel path includes a transfer station, dividing the target travel path into at least two path segments based on the transfer stations included in the target travel path; obtaining the waiting time required for the target travel path selected by the passenger based on the waiting time required to board a train from the starting station of each path segment of the at least two path segments; wherein the waiting time required to board a train from the starting station of each path segment is determined based on the departure time of each train passed by the starting station of each path segment; if the target travel path does not include a transfer station, determining the waiting time required for the target travel path selected by the passenger as the waiting time required.

[0011] In a possible implementation, the decision variable set and the guidance strategy set are optimized according to the patience loss and the required waiting time of each passenger traveling from each starting station to each terminal station in the subway network to obtain the optimized target decision variable set and target guidance strategy set, including: normalizing the patience loss of each passenger traveling from each starting station to each terminal station according to the maximum patience loss of a single passenger in the specified time period to obtain the normalized patience loss of each passenger, the maximum patience loss being the maximum value of the patience loss incurred by the passengers in the specified time period; normalizing the waiting time required for the target travel path selected by each passenger traveling from each starting station to each terminal station according to the maximum waiting time of a single passenger in the specified time period to obtain the normalized patience loss of each passenger. the normalized waiting time of each passenger, the maximum waiting time being the maximum time required for a passenger to wait to board the train within the specified time period; based on the time weights set for different passengers, the normalized patience loss and the normalized waiting time of each passenger traveling from each starting station to each terminal station are weightedly summed to obtain the service quality loss of each passenger traveling from each starting station to each terminal station; the service quality loss of each passenger traveling from each starting station to each terminal station on each subway line of the subway network within the specified time period is accumulated to obtain the comprehensive passenger service quality loss corresponding to the subway network; based on the specified constraints, the decision variable set and the guidance strategy set are optimized with the goal of minimizing the comprehensive passenger service quality loss to obtain the optimized target decision variable set and target guidance strategy set.

[0012] In one possible implementation, the method further includes: determining the system traction energy consumption based on the decision variable set, wherein the system traction energy consumption represents the total energy consumption required for the operation of each train on each subway line within the specified time period; wherein, based on the specified constraints, with the goal of minimizing the comprehensive loss of passenger service quality, optimizing the decision variable set and the guidance strategy set to obtain the optimized target decision variable set and target guidance strategy set, includes: based on the specified constraints, with the goal of minimizing the comprehensive loss of passenger service quality and minimizing the system traction energy consumption, optimizing the decision variable set and the guidance strategy set to obtain the optimized target decision variable set and target guidance strategy set.

[0013] In one possible implementation, the decision variable set and the guidance strategy set are optimized based on the patience loss and the required waiting time of each passenger traveling from each starting station to each terminal station in the subway network to obtain the optimized target decision variable set and target guidance strategy set, including: determining the total passenger patience loss of the subway network in the specified time period based on the patience loss of each passenger traveling from each starting station to each terminal station in the specified time period, and the total passenger patience loss represents the patience loss of all passengers at all stations on all subway lines in the subway network. the total value of ; determining the average waiting time of passengers in the subway network within the specified time period based on the waiting time required for the target travel route selected by each passenger traveling from each starting station to each terminal station within the specified time period, wherein the average waiting time of passengers represents the average time required for passengers to wait for boarding at all stations on all subway lines in the subway network; based on specified constraints, optimizing the decision variable set and the guidance strategy set with the goal of minimizing the total passenger patience loss and minimizing the average passenger waiting time, thereby obtaining an optimized target decision variable set and target guidance strategy set.

[0014] In a possible implementation, the decision variable set and the guidance strategy set are optimized based on the specified constraints, with the goal of minimizing the total passenger patience loss and minimizing the average passenger waiting time, to obtain the optimized target decision variable set and target guidance strategy set, including: based on the specified constraints, with the goal of minimizing the total passenger patience loss, minimizing the average passenger waiting time and minimizing the system traction energy consumption, the decision variable set and the guidance strategy set are optimized to obtain the optimized target decision variable set and target guidance strategy set; wherein the system traction energy consumption is determined based on the decision variable set and is used to characterize the total energy consumption required for the operation of each train on each subway line within the specified time period.

[0015] In one possible implementation, the constraints include: the departure interval of trains on each subway line is within the range of the maximum departure interval and the minimum departure interval preset for each subway line; the earliest departure time of the last train on each subway line is later than the preset end time of operation; the relative deviation between the path length of each selectable travel route from the sth starting station to the vth terminal station and the path length of the shortest travel route is less than or equal to a preset deviation threshold; the sum of the selection probabilities of each selectable travel route from the sth starting station to the vth terminal station is 1; and the remaining patience of each passenger is greater than or equal to a preset patience threshold, wherein the remaining patience of each passenger includes the difference between the initial patience set by each passenger and the patience loss of each passenger.

[0016] In one possible implementation, the method further includes: determining the period patience loss corresponding to each sub-period of the specified time period based on the patience loss of each passenger traveling from each starting station to each terminal station within the specified time period, wherein the period patience loss represents the total value of the patience loss of passengers entering all stations on all subway lines of the subway network within the sub-period; adjusting the initial duration of each sub-period in the specified time period based on the period patience loss corresponding to each sub-period of the specified time period to obtain each sub-period after the duration is adjusted, wherein the period patience loss of the sub-period is negatively correlated with the duration of the sub-period; and determining a period-adjusted decision variable set and a guidance strategy set based on each sub-period after the duration is adjusted, so as to optimize the period-adjusted decision variable set and guidance strategy set to obtain an optimized target decision variable set and target guidance strategy set.

[0017] According to another aspect of the present disclosure, an urban rail transit passenger service quality optimization device is provided, comprising: an acquisition module for acquiring network data, passenger flow data, a decision variable set, and a guidance strategy set of a subway network within a specified time period, wherein the network data comprises line information, station information, and train information in the subway network; the passenger flow data comprises the number of passengers traveling from each starting station to each terminal station in the subway network within each unit time period of the specified time period; the specified time period comprises multiple sub-time periods, the decision variable set comprises the departure interval of trains in each sub-time period of the specified time period, and the guidance strategy set comprises the passenger flow guidance strategy for each sub-time period of the specified time period. The departure intervals of trains in the same departure direction and the same sub-time period on the same subway line are the same and the passenger flow guidance strategy is the same. The passenger flow guidance strategy is used to indicate the selection probability of each of the at least one travel routes that passengers can choose from each starting station to each terminal station within the sub-time period; a route selection determination module is used to determine a passenger route selection set based on the road network data, the passenger flow data and the guidance strategy set. The passenger route selection set includes a passenger route selection matrix from each starting station to each terminal station, wherein the passenger route selection matrix from the s-th starting station to the v-th terminal station includes each of the multiple passengers from the s-th starting station to the v-th terminal station. The target travel path selected by the passenger, wherein s∈[1,N], v∈[1,N], s≠v, and N is the total number of stations in the subway network; a patience loss determination module, for determining the patience loss of each passenger traveling from each starting station to each terminal station based on the network data, the passenger path selection set, and the passenger service coefficient set, wherein the passenger service coefficient set includes a passenger service coefficient matrix from each starting station to each terminal station, wherein the passenger service coefficient matrix from the s-th starting station to the v-th terminal station includes the service coefficient of each passenger traveling from the s-th starting station to the v-th terminal station, wherein the service coefficient represents the gradient of the patience loss, and the patience loss The loss represents the patience lost by the passenger when choosing the target travel route; a waiting time determination module is used to determine the waiting time required for the target travel route selected by each passenger traveling from each starting station to each terminal station in the subway network based on the passenger route selection set; an optimization module is used to optimize the decision variable set and the guidance strategy set based on the patience loss and the required waiting time of each passenger traveling from each starting station to each terminal station in the subway network, so as to obtain the optimized target decision variable set and target guidance strategy set, so as to improve the passenger service quality of the subway network within the specified time period by using the optimized target decision variable set and target guidance strategy set.

[0018] According to another aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0019] According to another aspect of the present disclosure, a non-volatile computer-readable storage medium is provided, on which computer program instructions are stored, wherein the computer program instructions implement the above method when executed by a processor.

[0020] According to another aspect of the present disclosure, a computer program product is provided, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0021] According to various aspects of the present disclosure, by determining the passengers' patience loss and waiting time based on the subway network data, passenger flow data, decision variable set and guidance strategy set within a specified time period, and then optimizing the decision variable set and guidance decision set based on the passengers' patience loss and waiting time, the train departure time can be scheduled and passengers can be guided to choose a suitable travel route based on the optimized target decision variable set and target guidance strategy set, which is conducive to shortening the waiting time and patience loss of passengers in the subway network and improving the passenger service quality of the entire subway network.

[0022] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0024] Figure 1 A flowchart of a method for optimizing urban rail transit passenger service quality according to an embodiment of the present disclosure is shown.

[0025] Figure 2 A schematic diagram of a subway network according to an embodiment of the present disclosure is shown.

[0026] Figure 3 A schematic diagram of a road network model according to an embodiment of the present disclosure is shown.

[0027] Figure 4 A schematic diagram illustrating a decision variable set adjustment process according to an embodiment of the present disclosure is shown.

[0028] Figure 5A schematic diagram illustrating passenger patience loss and its changing rate from 6:00 to 22:00 according to an embodiment of the present disclosure is shown.

[0029] Figure 6a 、 Figure 6b and Figure 6c Schematic diagrams showing the ET Pareto front, PT Pareto front, PE Pareto front and their fitting curves according to an embodiment of the present disclosure are shown respectively.

[0030] Figure 6d A schematic diagram showing the PET Pareto front and its fitting surface in three-dimensional space according to an embodiment of the present disclosure is shown.

[0031] Figure 6e A schematic diagram illustrating points in the PET Pareto front on the ET plane according to an embodiment of the present disclosure.

[0032] Figure 7 The SE Pareto front formed based on the comprehensive loss value of passenger service quality and system traction energy consumption according to an embodiment of the present disclosure is shown.

[0033] Figure 8 A schematic diagram showing the departure interval in the upward direction of Line 1 in the Pareto front solution according to an embodiment of the present disclosure.

[0034] Figure 9 A schematic diagram illustrating a departure schedule for Line 1 in a Pareto front solution according to an embodiment of the present disclosure is shown.

[0035] Figure 10 A partial passenger flow path distribution diagram of 100 pairs of ODs (starting points and ending points) randomly selected after passenger flow guidance according to an embodiment of the present disclosure is shown.

[0036] Figure 11 A block diagram of an apparatus for optimizing urban rail transit passenger service quality according to an embodiment of the present disclosure is shown.

[0037] Figure 12 A block diagram of an electronic device 1900 according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0038] Various exemplary embodiments, features, and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise indicated.

[0039] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0040] The term "and / or" herein simply describes an association relationship between associated objects, indicating that three relationships can exist. For example, "A and / or B" can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. Furthermore, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of items. For example, "at least one of A, B, and C" can represent any one or more elements selected from the set consisting of A, B, and C. In the description of this disclosure, "plurality" means two or more, unless otherwise specifically defined.

[0041] It should be understood that the terms "first," "second," and the like in the claims, specification, and drawings of the present disclosure are used to distinguish between different objects, rather than to describe a specific order. The terms "include" and "comprising" used in the specification and claims of the present disclosure indicate the presence of the described features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or combinations thereof.

[0042] In addition, numerous specific details are provided in the following detailed description to better illustrate the present disclosure. Those skilled in the art will appreciate that the present disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art are not described in detail in order to highlight the main points of the present disclosure.

[0043] The urban rail transit passenger service quality optimization method of the embodiment of the present disclosure can be deployed on various terminal devices through software or hardware modification. The terminal device involved in the embodiment of the present disclosure may refer to a device with a wireless connection function and / or a wired connection function. The wireless connection function means that it can be connected to other devices through wireless connection methods such as wifi and Bluetooth. The terminal device involved in the embodiment of the present disclosure can also communicate with other devices through a wired connection function. The terminal device involved in the embodiment of the present disclosure can be a touch screen, a non-touch screen, or a screenless terminal device. The touch screen terminal device can be controlled by clicking, sliding, etc. on the display screen with a finger or a stylus. The non-touch screen device can be connected to an input device such as a mouse, keyboard, touch panel, etc., and the terminal device can be controlled by the input device. For example, a device without a screen can be a Bluetooth speaker without a screen. For example, the terminal device of the present application can include but is not limited to user equipment (UE), mobile device, user terminal, terminal, handheld device, tablet computer, laptop computer, PDA, computing device, etc.

[0044] The urban rail transit passenger service quality optimization method of the embodiment of the present disclosure can also be deployed on a server, which can be located in the cloud or locally, and can be a physical device or a virtual device, such as a virtual machine, a container, etc., with a wireless communication function, wherein the wireless communication function can be set in the chip (system) or other parts or components of the server. It can refer to a device with a wireless connection function, and the wireless connection function means that it can be connected to other servers or terminal devices through wireless connection methods such as Wi-Fi and Bluetooth. The server involved in the embodiment of the present disclosure can also have the function of communicating with a wired connection. For example, the server of the embodiment of the present disclosure can be located in the cloud, communicate with the terminal device, receive the network data, passenger flow data, decision variable set and guidance strategy set of the subway network sent by the terminal device, and use the optimization method deployed on the server to output the optimized target decision variable set and target guidance strategy set, and return them to the terminal device, so that the terminal device can use the target decision variable set returned by the server to formulate the scheduling schedule of trains in the subway network and use the returned target guidance strategy set to guide passengers to choose a suitable travel route.

[0045] Figure 1 The flowchart of the method for optimizing the quality of urban rail transit passenger service according to an embodiment of the present disclosure is shown. The method can be executed by the above-mentioned terminal device or electronic device such as the server, such as Figure 1 As shown, the method includes: steps S11 to S15.

[0046] In step S11, the network data, passenger flow data, decision variable set and guidance strategy set of the subway network within a specified time period are obtained.

[0047] The network data includes: line information in the subway network (such as the line number of the subway line, the direction of operation on the subway line, usually including the up direction and the down direction), station information (such as the station number of each station on the subway line, whether it is a transfer station, etc.) and train information (such as the train number of trains in different directions on the subway line, the running time between two adjacent stations, the length of time the train stops at the station, etc.). Figure 2 For example, a subway network is shown. The subway network includes 4 subway lines (i.e., Line 1, Line 2, Line 3, and Line 4). Each subway line has two running directions. There are 17 stations on the 4 subway lines, of which 1 3 Represents the station number 3 on subway line 1, 2 1 Represents the station numbered 1 on subway line 2, 1 3 (2 2 ) is a transfer station between Metro Line 1 and Metro Line 2.

[0048] Among them, the passenger flow data includes the number of passengers going from each starting station to each terminal station in the subway network in each unit time period of a specified time period; optionally, the passenger flow data can be described by a start-end matrix (OD matrix), that is, the OD matrix can be used to record the number of passengers entering the station from any starting station to any destination station in the subway network in each unit time period. In practical applications, by analyzing the AFC data (including the arrival time, starting station and terminal station of each passenger) generated by the real automatic ticketing system (Automatic Farecollection, AFC) in the subway network during a specified time period, the number of passengers entering the station from each starting station to each terminal station in different unit time periods can be learned, that is, the starting station and terminal station and the number of passengers entering the station for all passenger groups in each unit time period can be mastered. When initializing the OD matrix that has not been guided by passenger flow, it can be assumed that all passengers in the OD matrix choose the shortest travel route to travel, and thus the passenger flow number of each path from the starting station to the terminal station can be calculated in each unit time period. For example, assuming the definition is the sampling period of the OD matrix (e.g. 10 minutes). The passenger flow data within a specified period can have a total of OD matrices of Ω unit periods, so we can define For line l The number of passengers from the starting station o to the terminal station d in each unit time period, where T begin Indicates the start time of the specified period.

[0049] In order to reduce the optimization dimension of the decision variable set and the guidance strategy set, it can be set that trains with similar departure times in the same direction on the same subway line can adopt the same departure interval and the same passenger guidance strategy. Specifically, the designated time period can be divided into multiple sub-periods, and the departure intervals and passenger flow guidance strategies of trains in the same sub-period on the same subway line and the same departure direction in each sub-period are set to be the same. On this basis, the departure intervals and passenger flow guidance strategies are set for trains in the same sub-period on the same subway line and the same departure direction in each sub-period. Thus, the designated time period includes multiple sub-periods, the decision variable set includes the departure intervals of trains in each sub-period of the designated time period, and the guidance strategy set includes the passenger flow guidance strategy for each sub-period of the designated time period. In this way, when optimizing the decision variable set and the guidance strategy set, optimization can be performed in the sub-period dimension, greatly improving the optimization efficiency of train departure intervals and guidance strategies in the entire subway network.

[0050] It should be understood that those skilled in the art can set the duration of the sub-period according to actual needs, that is, set the time range defined by each divided sub-period. For example, if the designated time period is 7:00 to 22:00, the designated time period can be evenly divided according to the unit time length (such as every 1 hour) (for example, 7:00 to 22:00 can be evenly divided into 15 sub-periods such as 7:00-8:00, ..., 21:00-22:00, etc. every 1 hour). Of course, based on passenger flow characteristics such as morning peak and evening peak, the indicated time period can be divided into multi-scale sub-periods according to different unit time lengths for time periods with different passenger flow characteristics. For example, the morning peak period 7:00-9:00 and the evening peak period 17:00-19:00 can be divided into multiple sub-periods every 30 minutes, and the regular time periods of 9:00-17:00 and 19:00-22:00 can be divided into multiple sub-periods every 1 hour. The embodiments of the present disclosure are not limited to this.

[0051] The passenger flow guidance strategy is used to indicate the selection probability of each of the at least one travel path that passengers can choose from each starting station to each terminal station within the sub-time period. It should be understood that there can be at least one travel path from any starting station to any terminal station, for example Figure 2 In, from 1 1 Station to 4 3 Station can have "1 1 →1 2 →1 3 →1 4 →1 5 →3 3 →3 4 →4 3 ” and “1 1 →1 2 →1 3 →2 3 →2 4 →4 3 "These two travel paths. The selection probability indicated in the passenger flow guidance strategy describes the expected distribution ratio of passengers on each travel path between the starting point and the end point at the macro level, or in other words, it refers to the expected proportion of passengers in the passenger flow data to each travel path. At the micro level, the selection probability is reflected as the probability of prompting a single passenger to choose a specific travel path. For example, the ordered set Prob of the selection probabilities of each travel path from the starting station s to the end station v can be expressed by formula (1): s,v .

[0052]

[0053] Among them, γ s,v =|Prob s,v| represents the total number of travel paths from the starting station s to the terminal station v, represents the probability of selecting the γth bus route from the starting station s to the ending station v.

[0054] In practical applications, a passenger model can be established based on the above-mentioned passenger flow data, path data and passenger guidance strategies. In order to clearly describe the specific situation of each passenger in the subway network, attributes such as entry time, starting station, end station (also known as the destination station), number of people and travel route (also known as the riding route) can also be defined in the passenger model. In addition, the passenger's entry, exit, boarding, disembarking and transfer behaviors can be recorded, as well as the specific location status of the passenger group at different time points, such as whether they are waiting for the train at the station or already on the train. Among them, in order to simplify the calculation process, some simplifications can be made to the passenger model, including: assuming that passengers go directly to the platform to wait for the train upon entering the station, omitting the movement process from the station entrance to the platform; assuming that passengers' boarding and disembarking behaviors are completed instantly; and the transfer passenger flow can be equivalently represented by the non-transfer passenger flow, thereby simplifying the passenger flow analysis of the entire network. For example, for a certain passenger, 1 is used 1 →1 2 →1 3 →2 3 →2 4 →4 3 This riding route can be decomposed into 1 1 →1 2 →1 3 , 2 3 →2 3 →2 4 , 4 2 →4 3 The riding behaviors of these three path segments are as follows: It can refer to the path segment on line l. The number of passengers entering the station from the starting station to the destination station.

[0055] In step S12, a passenger path selection set is determined based on the road network data, passenger flow data, and guidance strategy set. The passenger path selection set includes a passenger path selection matrix from each starting station to each terminal station, wherein the passenger path selection matrix from the s-th starting station to the v-th terminal station includes the target travel path selected by each passenger among multiple passengers traveling from the s-th starting station to the v-th terminal station, wherein s∈[1,N], v∈[1,N], s≠v, and N is the total number of stations in the subway network.

[0056] In one possible implementation, determining the passenger route selection set based on the road network data, passenger flow data, and guidance strategy set includes:

[0057] Step S121: For the sth starting station in the subway network, determine a set of paths from the sth starting station to the vth terminal station based on the network data, wherein the set of paths from the sth starting station to the vth terminal station includes at least one selectable travel path from the sth starting station to the vth terminal station and the path length of each travel path;

[0058] Step S122, determining the number of passengers traveling from the sth starting station to the vth terminal station based on the passenger flow data;

[0059] Step S123, determining the passenger path selection matrix from the sth starting station to the vth terminal station based on the guidance strategy set, the path set from the sth starting station to the vth terminal station, and the number of passengers traveling from the sth starting station to the vth terminal station within the specified time period.

[0060] In practical applications, a road network model can be established based on road network data, such as Figure 3 A road network model is shown. In this road network model, each station is regarded as a node, and the direct connection between stations is regarded as an edge. The path set can be obtained based on the road network model, that is, the corresponding travel path can be obtained through the starting station and the end station. Specifically, an adjacency matrix A can be used to represent the road network model G(V,E), where the element A[a][b] of the adjacency matrix A, if not zero, indicates that any station a in the subway network has a direct connection to any station b (that is, adjacent), and its element value is represented by the distance dis between the two stations. a,b For a subway network with N stations, the adjacency matrix A is an N×N matrix, defined as shown in formula (2).

[0061]

[0062] It is known that in urban rail transit, a passenger starts from a departure station (starting station) and goes to a terminal station (terminal station), and will not pass through the same station twice during the journey. Therefore, what can be found is a loop-free path (simple path) between each pair of starting points and terminal points. For example, the depth-first search (DFS) algorithm can be used to find all possible passenger paths between each pair of starting points and terminal points. DFS is an algorithm for traversing or searching a tree or graph. It walks along a possible branch to the end until it can no longer continue, and then backtracks to the nearest fork point to try another possibility. This method can meet the needs of finding all possible paths. When implementing DFS, the algorithm establishes a current path list path and a visited node set visited to avoid repeated visits and loops. Whenever DFS reaches the terminal station, the current path is recorded. Through the DFS algorithm, all possible paths from the starting station to the terminal station can be collected.

[0063] For example, for the starting station s, the path set from the starting station s to the terminal station v (v≠s) can be expressed as the ordered set Path shown in formula (3): s,v .

[0064]

[0065] Among them, γ s,v =|Path s,v |,|Path s,v | represents the total number of travel paths from the starting station s to the terminal station v, represents the γth travel path from the starting station s to the terminal station v, represents the length of the γth ride path from the starting station s to the terminal station v, The path length representing the γth bus route is equal to the cumulative sum of the distances between the stations on the γth bus route.

[0066] It should be understood that based on the passenger flow data, the number of passengers going from the sth starting station to the vth terminal station can be known. Then, based on the various travel routes indicated by the path set from the sth starting station to the vth terminal station, combined with the selection probability of each travel route from the sth starting station to the vth terminal station indicated by the passenger flow guidance strategy in the guidance strategy set, the target travel route selected by each passenger can be randomly assigned to each passenger indicated by the number of passengers going from the sth starting station to the vth terminal station, thereby obtaining the passenger path selection matrix from the sth starting station to the vth terminal station.

[0067] As mentioned above, each sub-period within the specified time period corresponds to a passenger flow guidance strategy. Therefore, based on the path set from the s-th starting station to the v-th terminal station and the passenger flow guidance strategy corresponding to each sub-period, each passenger indicated by the number of passengers going from the s-th starting station to the v-th terminal station in each sub-period can be randomly assigned the target travel path selected by each passenger, and the passenger path selection matrix from the s-th starting station to the v-th terminal station can be obtained, that is, the target travel path selected by each passenger from the s-th starting station to the v-th terminal station in the entire specified time period can be obtained.

[0068] The passenger path selection matrix from the sth starting station to the vth terminal station can be expressed as a 0-1 matrix. For example, let the passenger path selection matrix Φ s,v It is represented as a 0-1 matrix as shown in formula (4-1), where each row represents a passenger from the s-th starting station to the v-th terminal station, and each column represents a possible riding path, where Φ s,v The elements in the matrix are defined as follows: If the i-th passenger chooses the j-th route from the s-th starting station to the v-th terminal station, the matrix element If the i-th passenger does not choose the j-th route, the matrix element

[0069]

[0070] Above Φ s,v The matrix satisfies the constraints shown in formula (4-2):

[0071]

[0072] Where M represents the number of passengers going from the sth starting station to the vth terminal station, The target travel route selected by each passenger traveling from the sth starting station to the vth terminal station conforms to the selection probability distribution of each travel route corresponding to the sth starting station to the vth terminal station.

[0073] It should be understood that for each starting station and each terminal station in the subway network, the passenger path selection matrix from each starting station to each terminal station in the subway network can be obtained according to the above steps S121 to S123.

[0074] In step S13, the patience loss of each passenger traveling from each starting station to each terminal station is determined based on the road network data, the passenger path selection set and the passenger service coefficient set. The passenger service coefficient set includes a passenger service coefficient matrix for traveling from each starting station to each terminal station, wherein the passenger service coefficient matrix for traveling from the sth starting station to the vth terminal station includes the service coefficient of each passenger traveling from the sth starting station to the vth terminal station. The service coefficient represents the gradient of the patience loss, and the patience loss represents the patience lost by the passenger when choosing the target riding path.

[0075] In one possible implementation, determining the patience loss of each passenger traveling from each starting station to each terminal station based on the road network data, the passenger route selection set, and the passenger service coefficient set includes:

[0076] Step S131: For the sth starting station in the subway network, based on the set of paths from the sth starting station to the vth terminal station, determine a set of path excess rates from the sth starting station to the vth terminal station, where the set of path excess rates includes the path excess rate of each of at least one selectable travel path from the sth starting station to the vth terminal station, and the path excess rate of each travel path is the ratio of the path length of each travel path to the path length of the shortest travel path minus 1;

[0077] Step S132: Determine the original patience loss of each passenger traveling from the s-th starting station to the v-th terminal station based on the set of path excess rates from the s-th starting station to the v-th terminal station and the passenger service coefficient matrix from the s-th starting station to the v-th terminal station, wherein the patience loss of each passenger traveling from the s-th starting station to the v-th terminal station includes the original patience loss of each passenger.

[0078] Referring to step S121 above, the path set is determined based on the road network data. In practical applications, the path set from the s-th starting station to the v-th terminal station is usually an ordered set. Therefore, the elements in the path set can be arranged in ascending order, that is, the path lengths of the various riding paths from the s-th starting station to the v-th terminal station increase in sequence, that is, Therefore, in step S131, the ratio of the path length of each bus route from the sth starting station to the vth terminal station to the path length of the shortest bus route can be calculated minus 1 to obtain the path excess rate of each bus route. For example, it can be expressed as the path excess rate set R from the sth starting station to the vth terminal station as shown in formula (5-1): s,v :

[0079]

[0080] in, represents the path excess rate of the γth bus route from the sth starting station to the vth terminal station, γ s,v =|Path s,v |=|R s,v | represents the total number of travel paths from the starting station s to the terminal station v, It can represent the shortest travel route from the sth starting station to the vth terminal station. represents the path length of the shortest route from the sth starting station to the vth terminal station, represents the length of the γth bus route from the sth starting station to the vth terminal station. The corresponding numerical vector can be expressed as formula (5-2):

[0081]

[0082] In step S132, passenger patience (which can also be understood as passenger satisfaction, or satisfaction with the metro network's service quality) is an inherent attribute of passengers. Each passenger has an initial patience before boarding the train, represented by a positive real number. This patience decreases during the ride, meaning that each passenger's satisfaction with the subway ride decreases as the ride progresses. This loss is also known as patience loss. For example, assume that at entry time t0, there are M passengers entering station s (i.e., the s-th starting station) and heading to station v (i.e., the v-th terminal station). The set of initial patience levels of passengers entering the station through the AFC system can be defined as follows:

[0083]

[0084] The corresponding numerical vector can be expressed as formula (6-2):

[0085]

[0086] in, represents the initial patience of the i-th passenger entering from station s (i.e., the s-th starting station) and going to station v (i.e., the v-th terminal station), represent belongs to positive real numbers, |P s,v |=M represents the set capacity of the initial patience equal to the number of passengers entering the station M.

[0087] Assuming that each passenger hopes to travel along the shortest route between the starting station and the terminal station, if the passenger chooses a route that is longer than the shortest route, it will cause the route to be too long. The passenger service coefficient is the loss gradient of passenger patience, which represents the passenger's tolerance for the additional travel path length. The loss gradient is determined by the passenger's own type attributes, and its mathematical definition can be shown in formula (7-1):

[0088]

[0089] Using the vector-to-vector derivative formula, the passenger service coefficient matrix K from station s to station v is s,v It can also be expressed as formula (7-2):

[0090]

[0091] in, represents the passenger service coefficient of each passenger on the first bus path from station s to station v, It represents the passenger service coefficient of the first passenger on the first bus route from station s to station v, and so on.

[0092] Among them, the passenger service coefficient matrix K s,v The physical meaning of can be understood as each passenger starting from station s to station v on the path The sensitivity of the loss of satisfaction to the path length rate is quantified. While this representation is detailed, the high dimensionality of the matrix significantly increases the complexity of the problem. To simplify the calculation, it can be assumed that the same passenger's sensitivity to the path length rate (i.e., the passenger service coefficient) is the same for different routes between the same starting and ending stations.

[0093] The original patience loss of the passenger can be defined as the difference in the passenger's patience before and after passenger flow guidance, that is, the remaining patience P of the passenger after the path guidance (recorded as time t1) s,v (t1) and the initial patience P of the passenger when he just passed through the AFC system (recorded as time t1) s,v The difference between (t0) and the passenger service coefficient can be calculated by integrating the passenger's route excess rate. Its mathematical expression can be expressed as formula (8):

[0094] ΔP s,v =P s,v (t1)-P s,v (t0)=∫K s,v dR s,v =K s,v ·R s,v (8)

[0095] Where ΔP s,vrepresents the original patience loss of each passenger going from the s-th starting station to the v-th terminal station, that is, in step S132, the above formula (8) can be used to determine the original patience loss of each passenger going from the s-th starting station to the v-th terminal station based on the path excess rate set from the s-th starting station to the v-th terminal station and the passenger service coefficient matrix from the s-th starting station to the v-th terminal station.

[0096] Considering that different passengers have different expectations for subway service quality, we can classify passengers and set an initial patience level, a passenger service coefficient, and a time weight (the time weight is used to weight the passenger's waiting time) for each type of passenger. This results in the passenger classification information table shown in Table 1. This not only simplifies the calculation process but also facilitates analysis of the behavioral characteristics of different types of passengers.

[0097] Table 1 Passenger classification information

[0098]

[0099] Among them, U(20,30) represents a randomly distributed number between 20 and 30. For example, for a certain standard commuting passenger, the passenger service coefficient can be randomly 25 and the initial patience can be 42 at any time. Other values ​​are similar and will not be elaborated on.

[0100] In practical applications, considering that passengers have a certain tolerance threshold for path overlength and waiting time, if the path overlength or waiting time exceeds this tolerance threshold, the passenger service quality may be deducted; if it does not exceed this tolerance threshold, a small amount of bonus points may be given to the passenger service quality. In order to implement the above-mentioned weighted method for passenger service quality, a Leaky-ReLU function may be used to dynamically weight the original patience loss based on whether the original patience loss exceeds the tolerance threshold. Thus, in one possible implementation, after calculating the original patience loss of each passenger through steps S131 to S132, the above-mentioned determination of the patience loss of each passenger traveling from each starting station to each terminal station based on the road network data, the passenger path selection set, and the passenger service coefficient set may also include:

[0101] Step S133: determining an expected value of the original patience loss of each passenger traveling from the s-th starting station to the v-th terminal station based on the original patience loss of each passenger traveling from the s-th starting station to the v-th terminal station, and determining the expected value as the tolerance threshold for traveling from the s-th starting station to the v-th terminal station;

[0102] Step S134: For the i-th passenger traveling from the s-th starting station to the v-th terminal station, if the i-th passenger's original patience loss is greater than or equal to the tolerance threshold, weight the difference between the i-th passenger's original patience loss and the tolerance threshold based on the first weighting coefficient to obtain the i-th passenger's weighted patience loss; or

[0103] Step S135: If the original patience loss of the i-th passenger is less than the tolerance threshold, weight the difference between the original patience loss of the i-th passenger and the tolerance threshold based on the second weighting coefficient to obtain the weighted patience loss of the i-th passenger;

[0104] Wherein, i∈[1,M], M is the number of passengers traveling from the sth starting station to the vth terminal station, the first weighted coefficient is greater than the second weighted coefficient, and the patience loss of each passenger traveling from the sth starting station to the vth terminal station includes the weighted patience loss of each passenger.

[0105] The above process of weighting the original patience can be expressed as formula (9):

[0106]

[0107] Among them, x i represents the original patience loss of the i-th passenger, x c represents the expected value of the original patience loss of multiple passengers going from the s-th starting station to the v-th terminal station; a1 represents the first weighting coefficient, a2 represents the second weighting coefficient, optionally, a2=0.2a1; L(x i ) represents the weighted patience loss of the i-th passenger. This approach allows for dynamic adjustment of each passenger's patience loss, increasing the weight of passengers with higher initial patience losses in service quality optimization, thereby further improving the service quality of the entire subway network for all passengers.

[0108] It should be understood that for each passenger traveling from each starting station to each terminal station in the subway network, the patience loss of each passenger traveling from each starting station to each terminal station can be calculated according to the above steps S131 to S132, or the above steps S131 to S135.

[0109] In step S14, based on the passenger route selection set, the waiting time required for the target travel route selected by each passenger traveling from each starting station to each terminal station in the subway network is determined.

[0110] In one possible implementation, determining the waiting time required for the target travel path selected by each passenger traveling from each starting station to each destination station in the subway network based on the passenger route selection set includes:

[0111] Step S141: For a target travel route selected by any passenger traveling from the sth starting station to the vth destination station, if the target travel route includes a transfer station, the target travel route is divided into at least two route segments based on the transfer station included in the target travel route;

[0112] Step S142: Obtaining the required waiting time for the target route selected by the passenger based on the required waiting time for boarding a train at the starting station of each of the at least two route segments; wherein the required waiting time for boarding a train at the starting station of each route segment is determined based on the departure times of each train passing through the starting station of each route segment;

[0113] In step S143, when the target boarding route does not include a transfer station, the waiting time required to board a bus from the starting station of the target boarding route is determined as the waiting time required for the target boarding route selected by the passenger.

[0114] It is understandable that if the target route selected by the passenger includes a transfer station, the waiting time for boarding will also be incurred when transferring at the transfer station. Therefore, the waiting time required for the entire target route can be obtained by accumulating the waiting time of the transfer stations on the target route. For example, if a passenger selects 1 1 →1 2 →1 3 →2 3 →2 4 →4 3 This target travel path can be decomposed into 1 1 →1 2 →1 1 , 2 3 →2 3 →2 4 , 4 2 →4 3 The riding behaviors of these three path segments can then be assumed to have three passengers P(1 1 →1 1 ),P(2 3 →2 4 ),P(4 2 →4 3 ) choose these three route segments to travel respectively, then the starting stations of the three route segments, i.e., 1 1 , 2 3 , 4 2The waiting time required for taking the bus is accumulated to get the passenger P(1 1 →4 3 )Select 1 1 →1 2 →1 3 →2 3 →2 4 →4 3 The required waiting time. Similarly, if the passenger chooses 1 1 →1 2 →1 3 →1 4 →1 5 →3 3 →3 4 →4 3 This target riding route can be decomposed into “1 1 →1 2 →1 3 、1 3 →1 4 →1 5 , 3 2 →3 3 →3 4 , 4 4 →4 3 "The riding behavior of the four path segments, then we can assume that there are four passengers P(1 1 →1 3 ),P(1 3 →1 5 ),P(3 2 →3 4 ) and P(4 4 →4 3 ) choose these four route segments to travel, then we can calculate the starting stations of these four passengers at the four route segments, that is, 1 1 、1 3 , 3 2 , 4 4 The waiting time required for taking the bus is calculated by adding up the waiting time of the four passengers to get the number of passengers P(1 1 →4 3 )Select 1 1 →1 2 →1 3 →1 4 →1 5 →3 3 →3 4 →4 3 The required waiting time.

[0115] It can be understood that, given the departure intervals of each train on each subway line in each sub-time period in the decision variable set, the departure time of each train on each subway line can be obtained. Combined with the running time of each train between two adjacent stations and the stop time of the train at the station, the arrival time and departure time of each train passing through each path segment of any travel route at the starting station of each path segment can be calculated. Furthermore, combined with the entry time of each passenger entering the station from the starting station of each path segment, the waiting time required for each passenger entering the station from the starting station of each path segment to board the train can be calculated. For example, if a passenger enters the station between the arrival time and departure time of a train, the waiting time of the passenger can be considered to be 0. If the passenger enters the station after the departure time of the previous train, the waiting time of the passenger can be the difference between the entry time of the passenger and the arrival time of the next train.

[0116] It can be understood that if the target travel route does not include a transfer station, it means that the passenger does not need to change trains. Therefore, the waiting time required to board the train from the starting station of the target travel route can be directly determined as the waiting time required for the target travel route selected by the passenger. Among them, the waiting time required to board the train from the starting station of the target travel route can be calculated based on the arrival and departure times of each train passing through the starting station of the target travel route, as well as the entry time of each passenger entering the station from the starting station of the target travel route.

[0117] It should be understood that the waiting time required for each passenger's target travel route selected from each starting station to each terminal station in the subway network can be calculated according to the above steps S141 to S143. Of course, those skilled in the art may also use any other known algorithm for calculating passenger waiting time to calculate the above waiting time, and the present embodiment does not limit this.

[0118] In step S15, the decision variable set and the guidance strategy set are optimized based on the patience loss and the required waiting time of each passenger traveling from each starting station to each terminal station in the subway network to obtain an optimized target decision variable set and a target guidance strategy set, so as to improve the passenger service quality of the subway network within a specified time period using the optimized target decision variable set and the target guidance strategy set.

[0119] In practical applications, as shown in formula (10), the passenger service quality Y(i) of a certain passenger can be equal to the passenger's initial patience p i Plus the passenger path excess rate r i Weighted coefficient b1, plus the waiting time Weighted by its coefficient b2, Indicates weighted gain.

[0120]

[0121] In order to improve the passenger service quality of the subway network within a specified period, the above formula (10) can be referred to establish an optimization model to optimize the decision variable set and the guidance strategy set.

[0122] As can be seen above, the passenger route excess rate affects the loss of passengers' patience. Therefore, when optimizing passenger service quality, we can primarily consider each passenger's service quality from two perspectives: waiting time and passenger patience. Passenger waiting time primarily refers to the time spent waiting for a bus at the station, which can be considered the cost of waiting. Passenger patience, on the other hand, reflects the passenger's satisfaction with the length of their chosen travel route exceeding the shortest route, as this affects their travel costs, including onboard time and fare. Different types of passengers place varying levels of importance on these two indicators. Therefore, to more accurately assess passenger service quality, we can assign weights to each passenger's card type, thereby constructing a comprehensive passenger service quality loss function. This function can then be used to optimize the decision variable set and guidance strategy set based on the passenger service quality loss.

[0123] Therefore, in one possible implementation, step S15 above optimizes the decision variable set and the guidance strategy set based on the patience loss and required waiting time of each passenger traveling from each starting station to each terminal station in the subway network to obtain the optimized target decision variable set and target guidance strategy set, which may include:

[0124] Step S151: normalizing the patience loss of each passenger traveling from each starting station to each terminal station based on the maximum patience loss of a single passenger during a specified time period to obtain the normalized patience loss of each passenger, where the maximum patience loss is the maximum value of the patience loss incurred by the passengers during the specified time period.

[0125] Step S152: Normalize the waiting time required for each passenger to board the bus on the target route selected by each passenger from each starting station to each terminal station based on the maximum waiting time of a single passenger during the specified time period to obtain the normalized waiting time of each passenger. The maximum waiting time is the maximum waiting time required for a passenger to board the bus during the specified time period.

[0126] Step S153 , based on the time weights set for different passengers, a weighted sum is taken of the normalized patience loss and the normalized waiting time of each passenger traveling from each starting station to each terminal station to obtain the service quality loss of each passenger traveling from each starting station to each terminal station;

[0127] Step S154, accumulating the service quality loss of each passenger traveling from each starting station to each terminal station on each subway line in the inland railway network during the specified time period to obtain a comprehensive passenger service quality loss corresponding to the subway network;

[0128] Step S155 , based on the specified constraints and with the goal of minimizing the comprehensive loss of passenger service quality, optimize the decision variable set and the guidance strategy set to obtain an optimized target decision variable set and target guidance strategy set.

[0129] The comprehensive loss of passenger service quality corresponding to the subway network can be calculated using the passenger service quality comprehensive loss function FITNESS shown in formula (11):

[0130]

[0131] Among them, l represents any subway line in the subway network, l max is the total number of subway lines in the subway network, s represents any starting station on subway line l, s max is the total number of starting stations on subway line l, ρ represents any train on subway line l, is the total number of trains departing in any direction on subway line l during a specified period, represents the departure time of the ρ-1th train from the starting station s, represents the departure time of the ρth train from the starting station s, v represents any terminal station in the subway network, N is the set of stations in the subway network, trace() represents the diagonal summation operation of the matrix, λ1 is the time weight set for different passengers, is the maximum waiting time of a single passenger in a specified period, E represents the unit matrix, diag[] represents the function of constructing a diagonal matrix, and Ediag[] represents the function of constructing a unit diagonal matrix. represents the waiting time required for each passenger to choose the target route from the sth starting station to the vth terminal station, ΔP max Represents the maximum patience loss of a single passenger within a specified period of time, represents the transpose of the passenger route choice matrix from the sth starting station to the vth terminal station, L(∫K s,v dR s,v ) represents the weighted patience loss of each passenger going from the s-th starting station to the v-th terminal station, and M(t) represents the number of passengers entering the station between the departure times of any two trains from the s-th starting station to the v-th terminal station.

[0132] in, represents the normalized patience loss of each passenger traveling from the starting station to the terminal station. Represents the normalized waiting time of each passenger's target route from the starting station to the terminal station, and uses λ1 to A weighted sum is performed to obtain the service quality loss of each passenger traveling from the starting station to the terminal station. FITNESS represents the accumulation of the service quality loss of each passenger traveling from each starting station to each terminal station on each subway line in the mainland railway network during a specified period of time to obtain the corresponding comprehensive passenger service quality loss of the subway network.

[0133] The time weight λ1 = [0, 1] is a real number representing the proportion of time cost in the overall evaluation. A higher λ1 indicates that passengers place greater emphasis on waiting time at the platform during the evaluation process. This is suitable for time-sensitive passengers, such as time-pressed office workers and students. For example, you can refer to the passenger classification information shown in Table 1 to set corresponding time weights for different passengers.

[0134] In practical applications, the passenger entry behavior can be simulated to construct a group of passengers about to enter the station, that is, to calculate the number of passengers entering the station between the departure times of any two trains leaving the starting station. Specifically, the passenger entry rate from the s-th starting station on any subway line l to the v-th terminal station can be analyzed in each unit time period, and the passenger entry rate can be integrated over the time period represented by the departure times of each two trains to estimate the number of new passengers entering the station in a specific time period. For example, the passenger entry rate from the s-th starting station to the v-th terminal station in each unit time period can be calculated using formula (12):

[0135]

[0136] in, represents the number of passengers going from station s to station v on subway line l in each unit time period, enter(t; l, s, v) represents the unit time period The passenger entry rate from the sth starting station to the vth terminal station on subway line l at each time t. Formula (12) can be understood as the number of passengers going from the sth starting station to the vth terminal station in each unit time period divided by the duration of the unit time period. (i.e., the sampling period duration) is used to obtain the passenger entry rate from the s-th starting station to the v-th terminal station in each unit time period. In other words, the passenger entry rate from the s-th starting station to the v-th terminal station in each unit time period can be determined based on the number of passengers going from the s-th starting station to the v-th terminal station in each unit time period of the specified time period. Formula (13) is then used to calculate the number of passengers entering the station between the departure times of any two trains from the s-th starting station to the v-th terminal station on subway line l based on the above passenger entry rate:

[0137]

[0138] Among them, During the time period, by integrating the passenger entry rate of passengers entering the subway line l from the s-th starting station to the v-th terminal station, we can obtain the change in the number of passengers entering the station from the time the ρ-1-th train leaves the s-th starting station to the time the ρ-th train leaves the s-th starting station, that is, calculate the number of passengers who can get on the train from the time the previous train leaves to the time the next train leaves.

[0139] As described above, given the departure intervals of each train on each subway line within each sub-period in the decision variable set, the departure times of each train on each subway line can be obtained. That is, based on the decision variable set and train information, the departure times of each train from the sth starting station to the vth terminal station can be obtained. Combined with the time each train travels between two adjacent stations and the time it stops at a station, the departure times of each train from the sth starting station to the vth terminal station within each unit time period can be calculated. Therefore, based on the departure times of each train from the sth starting station to the vth terminal station within each unit time period and the passenger entry rate from the sth starting station to the vth terminal station within each unit time period, the number of passengers entering the station between the departure times of every two trains from the sth starting station to the vth terminal station can be determined.

[0140] In a possible implementation, in step S155, the constraint conditions may include:

[0141] The departure interval of trains on each subway line is within the range of the maximum departure interval and the minimum departure interval preset for each subway line;

[0142] The earliest departure time of the last train on each subway line is later than the preset end time of operation;

[0143] The relative deviation between the length of each route that can be selected from the s-th starting station to the v-th terminal station and the length of the shortest route is less than or equal to a preset deviation threshold;

[0144] The sum of the selection probabilities of all the routes that can be chosen from the sth starting station to the vth terminal station is 1;

[0145] The remaining patience of each passenger is greater than or equal to a preset patience threshold, wherein the remaining patience of each passenger includes a difference between an initial patience set by each passenger and a patience loss of each passenger.

[0146] Among them, and represent the minimum departure interval and the maximum departure interval of subway line l in the running direction d, respectively. Then the departure interval of any train ρ in the decision variable set is The constraints should be met: These two constraints play an important role in urban rail transit systems. The setting of the minimum departure interval takes into account multiple factors, including passenger safety, train speed, and track crowding effects. By ensuring the minimum departure interval, we can effectively prevent trains from being too close to each other, reduce the probability of accidents, and ensure the safety of passengers. On the other hand, the setting of the maximum departure interval is to meet the travel needs of passengers and reduce waiting time. If the departure interval is too large, passengers may have to wait too long, which not only reduces travel efficiency but also may cause congestion and inconvenience. Therefore, by setting the maximum departure interval, we can ensure that passengers can catch the train within a reasonable time frame, improving their travel comfort and satisfaction.

[0147] Among them, the scheduled end time of operation of the local railway network is T end , then the constraint that the earliest departure time of the last train on each subway line is later than the preset operation end time can be expressed as formula (14-1) and formula (14-2):

[0148]

[0149] Among them, T begin represents the start time of the subway network operation, or the start time of the specified time period, K l,d represents the total number of trains departing from subway line l in direction d, Represents the cumulative departure intervals from the second train to the last train. Representative K l,d The departure time of the last train is greater than or equal to the end of operation time. Represents trains 2 to K l,d-The accumulation of the departure intervals of 1 train (i.e. the second to last train), Representative K l,d -The departure time of one train is less than the end time of operation.

[0150] It should be understood that the specified time period may include the above-mentioned end time of operation, and the earliest departure time of the last train represented by the decision variable set should be later than the above-mentioned end time of operation. This is because in actual situations, although the subway network is specified at T end The operation ends at T (passengers can no longer enter the station), but there may be situations where passengers cannot complete their trips normally between the departure of the previous train and the end of the subway system operation. Considering the safety and travel convenience of passengers, the earliest departure time of the last train on each line should be later than T end This is to ensure that those end Passengers who arrive at the station before T will have enough time to catch the last train, avoiding being forced to stay at the station. end Therefore, in order to ensure the safety of passengers and smooth travel, the earliest departure time of the last train on the line must be later than T end In this way, if passengers arrive at the station before the end of the normal operating hours of the subway system, they can still take the last train and complete their travel purpose.

[0151] The relative deviation between the length of each route that can be selected from the sth starting station to the vth terminal station and the length of the shortest route is less than or equal to the preset deviation threshold, which can be expressed as the constraint condition indicated by formula (15):

[0152]

[0153] in, represents the path length of the jth bus route from station s to station v, and represents the path length of the shortest route from station s to station v, represents the relative deviation between the length of the jth route and the shortest route, and θ is a preset deviation threshold. Persons skilled in the art may set the specific value of the preset deviation threshold based on practical needs, and this is not a limitation of the present disclosure. The purpose of this constraint is to avoid directing passengers onto routes that are excessively long, thereby reducing the total travel time for a particular passenger and improving travel efficiency and satisfaction.

[0154] The sum of the selection probabilities of all the routes that can be chosen from the sth starting station to the vth terminal station is 1, which can be expressed as the constraint shown in formula (16-1):

[0155]

[0156] in, represents the probability of a passenger choosing route j from the sth starting station to the vth destination station within a sub-period [m, (m+1)]. This means that for all routes from station s to station v, the sum of the proportions of routes with the same starting and ending points must be 1. This constraint ensures that each passenger is correctly assigned to the appropriate target route, avoiding omissions and duplications. This approach ensures diversity in passenger route selection and promotes balanced utilization of the entire urban rail transit network.

[0157] The constraint condition that the remaining patience of each passenger is greater than or equal to the preset patience threshold can be expressed as shown in formula (16-2):

[0158]

[0159] Among them, the remaining patience P of any passenger s,v (t1) is equal to the passenger's initial patience minus the passenger's patience loss, that is, P s,v (t1) = P s,v (t0)-ΔP s,v , C s,v represents the set of preset patience thresholds corresponding to each passenger, represents the preset patience threshold corresponding to the first passenger, and other values ​​are similar and will not be elaborated on. This constraint can be understood as that after passenger flow guidance, the remaining patience of the passenger must not be lower than a certain limit. It should be understood that those skilled in the art can set the preset patience threshold for different passengers according to actual needs. Optionally, in order to simplify the calculation, it can be set to that the remaining patience of each passenger is greater than 0, that is: P s,v (t1)≥0.

[0160] Considering that optimizing the decision variable set and the guidance strategy set with the goal of minimizing the above-mentioned comprehensive loss in passenger service quality is likely to result in a decision variable set with a shorter departure interval (i.e., a greater number of departures), and that the shorter the departure interval (i.e., the greater the number of departures), the greater the traction energy consumption generated by the entire subway network. Traction energy consumption can be expressed as the amount of electrical energy input from a DC traction substation to the subway network. Therefore, in order to balance the traction energy consumption consumed by the entire subway network system with the passenger service quality, in one possible implementation, the method further includes:

[0161] According to the decision variable set, the system traction energy consumption is determined. The system traction energy consumption represents the total energy consumption required for the operation of each train on each subway line within a specified period of time.

[0162] Based on this, the above-mentioned step S155, based on the specified constraints, with the goal of minimizing the comprehensive loss of passenger service quality, optimizes the decision variable set and the guidance strategy set to obtain the optimized target decision variable set and target guidance strategy set, which may include: based on the specified constraints, with the goal of minimizing the comprehensive loss of passenger service quality and minimizing the system traction energy consumption, optimizes the decision variable set and the guidance strategy set to obtain the optimized target decision variable set and target guidance strategy set.

[0163] It should be understood that, given the departure intervals of each train on each subway line within each sub-period in the decision variable set, as well as the line information and train information in the road network data, the number of trains departing from each subway line within each sub-period can be determined. Furthermore, combined with the average traction energy consumption of a single train on the subway line (this average traction energy consumption can be an empirical value), the total energy consumption required for each train operation on each subway line within the specified time period can be calculated. Of course, those skilled in the art can also use any known train energy consumption estimation technology in the art to estimate the system traction energy consumption under different decision variable sets, and this is not limited to the embodiments of the present disclosure.

[0164] In step S155, based on the above-specified constraints, any known search optimization algorithm in the art can be used to achieve the goal of minimizing the comprehensive loss of passenger service quality (i.e., min FITNESS), or minimizing the comprehensive loss of passenger service quality and minimizing the system traction energy consumption En (i.e., min FITNESS and min En), and iteratively optimize the decision variable set and the guidance strategy set, wherein the optimized decision variable set can be the train departure interval corresponding to each sub-time period, and the optimized guidance strategy set can be the passenger guidance strategy corresponding to each sub-time period.

[0165] It should be understood that the optimization of the decision variable set and the guiding strategy set can be iteratively performed in multiple rounds, and each round of the optimization process can be implemented with reference to the above steps S11 to S15 (including the above steps S151 to S155). That is, the optimization process of the above steps S11 to S15 (including the above steps S151 to S155) can be performed in multiple rounds, and the decision variable set and guiding strategy set used in each round of optimization can be the results of the previous round of optimization output. Those skilled in the art can set the end conditions of the iterative optimization, for example, they can set it to reach a specified round, the comprehensive loss of passenger service quality reaches a certain threshold, the system traction energy consumption reaches a certain threshold, etc., and then select an appropriate target decision variable set and target guiding strategy set from the decision variable set and guiding strategy set obtained after multiple rounds of optimization.

[0166] In practical applications, the decision variable set and the guidance strategy set can also be directly optimized based on the passenger waiting time and the loss of passenger patience. Specifically, in one possible implementation, step S15 above optimizes the decision variable set and the guidance strategy set based on the patience loss and the required waiting time of each passenger traveling from each starting station to each terminal station in the subway network. The optimized target decision variable set and target guidance strategy set can include:

[0167] Step S156: determining the total passenger patience loss of the metro network during the specified time period based on the patience loss of each passenger traveling from each starting station to each terminal station during the specified time period. The total passenger patience loss represents the total value of the patience loss of all passengers at all stations on all subway lines in the metro network.

[0168] Step S157: Determine the average waiting time of passengers on the metro network during the specified time period based on the waiting time required for each passenger to travel from each starting station to each destination station during the specified time period. The average waiting time represents the average waiting time required for passengers to board trains at all stations on all subway lines in the metro network.

[0169] Step S158 , based on the specified constraints, with the goal of minimizing the total passenger patience loss and minimizing the average waiting time of passengers, optimize the decision variable set and the guidance strategy set to obtain the optimized target decision variable set and target guidance strategy set.

[0170] In step S156, when calculating the total value of passenger patience loss after passenger flow guidance (i.e., the difference in passenger patience before and after passenger flow guidance), the patience loss of all passengers at each station can be calculated first, and then the patience losses of each station can be aggregated to obtain the total passenger patience loss for the entire subway network. That is, for a particular station s, the passenger patience loss of each passenger at the station can be calculated by time-integrating M(t), where M(t) describes the change in the number of passengers at the station s (i.e., the change in the number of passengers entering the station) in different time periods after the train leaves the station. Furthermore, when calculating the passenger patience loss at the station s, the patience loss of passengers entering the station during each time period (i.e., the period between the departure times of two trains) can be calculated. The patience losses of these entering passengers are then accumulated to obtain the patience loss of all passengers at the station. The patience losses of all passengers at all stations on all subway lines are then accumulated to obtain the total passenger patience loss for the subway network during the specified time period.

[0171] Among them, the cumulative value of patience loss of all passengers traveling in the upward direction up from the starting station s at any time t in any sub-period can be calculated using formula (17-1):

[0172]

[0173] Then use formula (17-2) to calculate the cumulative value of patience loss of all passengers traveling in the upward direction from the starting station s during the specified time period That is, the patience loss of passengers entering the station between the departure times of every two trains passing through the starting station s in the upward direction can be accumulated to obtain the cumulative value of the patience loss of all passengers traveling in the upward direction from the starting station s in the specified period.

[0174]

[0175] Then, the total passenger satisfaction loss of all stations on all subway lines in the subway network can be calculated using formula (17-3):

[0176]

[0177] in, Represents the cumulative value of patience loss of all passengers traveling in the down direction from the starting station s during the specified period, and The calculation method is the same, that is, it can be calculated by referring to the above formula (17-1) and formula (17-2) represents the cumulative value of the patience loss of all passengers traveling in the upward and downward directions from the starting station s during the indicated period, and PLOSS represents the cumulative value of the patience loss of all passengers traveling in the upward and downward directions from all stations on all subway lines during the specified period (that is, the total passenger patience loss of the subway network during the specified period).

[0178] In step S157, the waiting time required for the target travel route selected by each passenger from each starting station to each terminal station within the specified time period can be accumulated to obtain the total waiting time of passengers in the subway network within the specified time period. The total waiting time of passengers is then divided by the total number of passengers from each starting station to each terminal station within the specified time period to obtain the average waiting time of passengers t w The waiting time required for the target route selected by any passenger can be calculated by referring to the above steps S141 to S143, which will not be described in detail here.

[0179] In step S158, as described above, the constraints may include: and P s,v (t1)≥C s,v .

[0180] Considering that the total passenger patience loss (i.e., min PLOSS) and the average waiting time of passengers (i.e., min t w ) as the goal, it is likely to obtain a decision variable set with a smaller departure interval (i.e., more departures). However, the smaller the departure interval (i.e., more departures), the greater the traction energy consumption of the entire subway network. Therefore, in order to balance the traction energy consumption of the entire subway network system with the passenger service quality, in one possible implementation, the above step S158 optimizes the decision variable set and the guidance strategy set based on specified constraints and with the goal of minimizing the total passenger patience loss and minimizing the average passenger waiting time, to obtain the optimized target decision variable set and target guidance strategy set, including:

[0181] Based on the specified constraints, the decision variable set and the guidance strategy set are optimized with the goal of minimizing the total passenger patience loss, minimizing the average passenger waiting time, and minimizing the system traction energy consumption, and the optimized target decision variable set and target guidance strategy set are obtained.

[0182] As described above, the system traction energy consumption may be determined based on the decision variable set to characterize the total energy consumption required for each train running on each subway line within the specified time period. The embodiment of the present disclosure does not limit the method for determining the system traction energy consumption.

[0183] In step S158, based on the above-specified constraints, any search optimization algorithm known in the art can be used to achieve the goal of minimizing the total passenger patience loss and minimizing the average passenger waiting time (i.e., minPLOSS and mint w ), or the goal is to minimize the total passenger patience loss, minimize the average waiting time of passengers, and minimize the system traction energy consumption (i.e., minPLOSS and min t w And min En), iteratively optimize the decision variable set and the guidance strategy set, wherein the optimized decision variable set can be to optimize the departure interval of trains in each sub-period, and the optimized guidance strategy set can be to optimize the passenger guidance strategy corresponding to each sub-period.

[0184] As described above, the optimization of the decision variable set and the guidance strategy set can be iterated for multiple rounds, and each round of optimization process can be implemented with reference to the above steps S11 to S15 (including the above steps S156 to S158), that is, the optimization process of the above steps S11 to S15 (including the above steps S156 to S158) can be performed for multiple rounds, and the decision variable set and guidance strategy set used in each round of optimization can be the result of the previous round of optimization output. Those skilled in the art can set the end conditions of the iterative optimization, for example, it can be set to reach a specified round, the total passenger patience loss reaches a certain threshold, the average passenger waiting time reaches a certain threshold, the system traction energy consumption reaches a certain threshold, etc., and then select a suitable target decision variable set and target guidance strategy set from the decision variable set and guidance strategy set obtained after multiple rounds of optimization.

[0185] As mentioned above, the departure intervals of trains in the same sub-time period in the same departure direction of the same subway line are the same, and the passenger flow guidance strategies in the same sub-time period are the same. Therefore, the decision variable set T can be divided into several non-overlapping subsets, hereinafter referred to as T-subsets. Each T-subset corresponds to a sub-time period, and each T-subset contains several decision variables (that is, the departure intervals of each train in the sub-time period), and all decision variable values ​​in each T-subset are set to be the same (that is, the departure intervals of each train in each sub-time period are the same). It should be understood that the guidance strategy set can also be divided into multiple subsets in the above manner, each subset corresponds to a sub-time period, and the passenger flow guidance strategies in each subset are the same. In this way, the dimension of the decision variable set can be adjusted. For example, let T represent the decision variable set (also called the train departure interval table), It represents the time interval between the departure of the ρth train and the departure of the ρ-1th train on subway line l. Since the subway network usually adopts an asymmetric departure scheme for up and down trains, an additional subscript d∈{0,1} is set, where 0 represents the up direction and 1 represents the down direction. represents the maximum number of trains that can be dispatched in a specified time period (such as a day's running time) in the direction d of subway line l according to the minimum interval. Then T can be expressed as In order to reduce the dimension of decision variables, the trains with similar departure times in the same direction are divided into the same departure interval, and the passenger guidance strategy in this period is the same, that is, the decision variables are divided into multiple subsets (i.e., the departure intervals of multiple sub-periods). Then T can also be expressed as in, represents any sub-period, S0 represents the total number of sub-periods in the uplink direction, Represents the sub-period in the upward direction The corresponding subset, represents the union of all subsets of uplink sub-intervals, S1 represents the total number of downlink sub-intervals, represents the union of all subsets of the downlink sub-intervals, The intersection between the subsets representing each sub-period in the uplink direction is empty. The intersection between the subsets representing each sub-period in the downlink direction is empty.

[0186] Generally speaking, if the capacity of these T-subsets is evenly distributed, which is the so-called uniform time scale optimization, it may not be able to effectively cope with the dynamic changes in passenger patience in different time periods. In order to optimize passenger patience more finely, the embodiment of the present disclosure proposes a sequential optimization method based on the characteristics of passenger patience loss, which is based on the multi-time scale adaptive adjustment of the decision variable dimension. The core idea of ​​this optimization method is to dynamically divide and adjust the decision variable set to adapt to the changes in passenger patience in different time periods. Specifically, for the sub-period with a large loss of passenger patience, the capacity of the T-subset corresponding to the sub-period can be appropriately reduced, that is, the dimension of the decision variable can be increased, so as to more flexibly adjust the train departure interval; on the contrary, for the sub-period with a small loss of passenger patience, the capacity of the T-subset corresponding to the sub-period can be appropriately increased, and the dimension of the decision variable can be reduced. This adaptive adjustment mechanism based on multiple time scales can more effectively cope with changes in passenger patience in various time periods, thereby optimizing passenger service quality from multiple time scales. Based on this, in a possible implementation method, the method also includes:

[0187] Step S16: determining the patience loss corresponding to each sub-period of the specified period based on the patience loss of each passenger traveling from each starting station to each terminal station within the specified period, wherein the patience loss of each sub-period represents the total patience loss of passengers entering all stations on all subway lines of the subway network within the sub-period;

[0188] Step S17, adjusting the initial duration of each sub-period within the specified time period according to the time period patience loss corresponding to each sub-period within the specified time period, to obtain each sub-period after the adjustment, wherein the time period patience loss of the sub-period is negatively correlated with the duration of the sub-period;

[0189] Step S18, based on each sub-period after the adjustment of the duration, determine the period-adjusted decision variable set and guidance strategy set, so as to optimize the period-adjusted decision variable set and guidance strategy set to obtain the optimized target decision variable set and target guidance strategy set.

[0190] The cumulative value of patience loss of all passengers traveling in the upward direction up from station s at any time t in any sub-period can be calculated by referring to the above formula (17-1): The cumulative value of patience loss of all passengers traveling in the down direction from station s Will and The cumulative value of patience loss of all passengers at the station s in the sub-period is obtained by adding them up. Then, the cumulative value of patience loss of all passengers at all stations on all subway lines in the subway network in the sub-period can be calculated, that is, The patience loss of the period corresponding to the sub-period is obtained.

[0191] According to the patience loss of each sub-period in the specified period, the initial duration of each sub-period in the specified period is adjusted to obtain each sub-period after the duration adjustment, which may include: calculating the patience loss of each sub-period and the preset maximum passenger total satisfaction loss PLOSS max The ratio between them is used to obtain the normalized length weight corresponding to each sub-period; then, based on the normalized length weight corresponding to each sub-period and the preset capacity growth upper limit, the initial length of each sub-period is adjusted to obtain the adjusted length of each sub-period; then, based on the adjusted length of each sub-period, the sub-periods after the length adjustment are determined. For example, PLOSS can be preset max =70000 as a normalization parameter to use the passenger's patience loss as feedback to adjust the initial duration of the sub-period.

[0192] The normalized length weight μ2(t) corresponding to each sub-period can be calculated using formula (18):

[0193]

[0194] Formula (19) can be used to adjust the initial duration of each sub-period:

[0195]

[0196] Wherein, μ2 represents the normalized length weight of any sub-period x, |T0| represents the initial duration of any sub-period x (i.e., subset) (i.e., the initial capacity of any subset). For example, |T0| can be set to 10; k is a coefficient greater than 1, for example, it can be set to 1.5, and k represents the upper limit of duration growth (i.e., the upper limit of capacity growth). Represents the adjusted duration (i.e., adjusted capacity) corresponding to any sub-period x.

[0197] It should be understood that if the adjusted duration of each sub-period is known, the adjusted sub-periods can be calculated. For example, if the initial duration of a sub-period from 10:00 to 11:00 is 1 hour and the adjusted duration is 2 hours, then the sub-period after the adjustment can be 10:00 to 12:00. This means that the same departure interval and passenger flow guidance strategy used in the sub-period from 10:00 to 11:00 will be adjusted to the same departure interval and passenger flow guidance strategy used in the sub-period from 10:00 to 12:00.

[0198] For example, Figure 4 A schematic diagram showing a decision variable set adjustment process is shown as follows: Figure 4 As shown, each T-subset can be initialized in a uniformly divided manner (i.e., the duration of each sub-period divided by initialization is the same), and a feedback loop can be established from the passenger's real-time patience loss to the T-subset. When the passenger flow passes through the AFC system, a path selection is performed, resulting in patience loss, which is normalized to obtain a normalized length weight. Then, the capacity of each T-subset is adjusted according to the normalized length weight (i.e., the length of each sub-period is adjusted), resulting in each T-subset with adjusted capacity (i.e., adjusted subset 1, subset 2, subset 3, etc.).

[0199] For example, Figure 5 The diagram shows the passenger satisfaction loss and its change rate from 6:00 to 22:00, where the change rate is the first-order difference of the passenger satisfaction loss. Figure 5 The results show visually which times of the day passengers lose the most patience. Figure 5The key periods with the greatest loss of patience can be identified as the morning peak of 7:00-9:00 and the evening peak of 17:00-19:00. Therefore, the capacity of each subset within the morning peak of 7:00-9:00 and the evening peak of 17:00-19:00, where the loss of passenger patience is greatest, can be adjusted. For example, if the decision variable set originally included the train departure intervals of the sub-periods 7:00-8:00 and 8:00-9:00, the decision variable set after period adjustment can include the train departure intervals of the sub-periods 7:00-7:30, 7:30-8:00, 8:00-8:30, and 8:30-9:00.

[0200] Among them, the above steps S11 to S15 can be used to optimize the decision variable set and guidance strategy set after the time period adjustment to obtain the optimized target decision variable set and target guidance strategy set; it should be understood that the above steps S16 to S18 are equivalent to optimizing the granularity of the division of sub-time periods in the decision variable set and guidance strategy set, and the above steps S11 to S15 are equivalent to optimizing the specific departure intervals and passenger flow guidance strategies within each sub-time period. In actual applications, during the iterative optimization process of the decision variable set and guidance strategy set, steps S16 to S18 can be first executed to optimize the granularity of the division of sub-time periods in the decision variable set and guidance strategy set, and then steps S11 to S15 can be executed to optimize the specific departure intervals and passenger flow guidance strategies within each sub-time period in the decision variable set and guidance strategy set, so as to realize a sequential optimization method for adaptively adjusting the decision variable dimensions at multiple time scales.

[0201] In practical applications, after obtaining the optimized departure intervals corresponding to each train in any direction of operation on any subway line based on the target decision variable set, a scheduling schedule for the trains in that direction of operation on the subway network can be formulated based on the optimized departure intervals. This schedule with the optimized departure intervals can be used to schedule each train on the subway line in that direction of operation, thereby reducing the waiting time required for passengers to board the train, improving subway operation efficiency, and enhancing the passenger experience. Furthermore, based on the target guidance strategy set, each passenger who is about to take the subway can be guided on the travel route (for example, based on the target guidance strategy set, a suitable target travel route can be recommended to passengers inquiring about travel in different time periods through relevant map navigation software, etc.), so as to more comprehensively improve the passenger travel experience and enhance the passenger service quality of the entire subway network.

[0202] According to the embodiments of the present disclosure, the passengers' patience loss and waiting time are determined based on the network data, passenger flow data, decision variable set and guidance strategy set of the subway railway network within a specified time period, and the decision variable set and guidance decision set are optimized based on the passengers' patience loss and waiting time. Based on the optimized target decision variable set and target guidance strategy set, train departure times can be scheduled and passengers can be guided to choose appropriate travel routes, which is conducive to shortening the waiting time and patience loss of passengers in the subway railway network and improving the passenger service quality of the entire subway railway network.

[0203] According to the embodiments of the present disclosure, the train departure interval decision variables can be grouped using uniform time intervals, resulting in a clear step-by-step nature in the decision results. This addresses the issue of a single time scale resulting from direct optimization using uniform time intervals, optimizes passenger service quality from multiple time scales, and implements a sequential optimization method that adaptively adjusts the dimensions of decision variables based on multiple time scales. By dynamically dividing and adjusting the decision variable set to accommodate changes in passenger patience loss within different time periods, the optimization problem is decomposed into several sub-problems of different dimensions based on multiple time scales. Furthermore, the optimization algorithm can obtain the Pareto frontier of multiple objectives, achieving effective optimization for multiple objectives.

[0204] In addition, the embodiment of the present disclosure also verifies the efficiency and effectiveness of the optimization algorithm through numerical experiments, designs comparative verification cases and demonstrates the verification results. Specifically, the embodiment of the present disclosure uses 10 lines, namely Lines 1, 2, 3, 4, 5, 6, 7, 8, 9 and 10, 168 stations and 362 sections in the subway network of a certain area to construct a road network model and a passenger model. The DFS algorithm is used to find the set of all OD paths and calculate the path excess rate. Because the road network model and passenger model are large in scale, only Lines 1, 2 and 3 are selected as numerical examples in the optimization problem. Based on the above-mentioned road network model and passenger model, the embodiment of the present disclosure will give two different forms of optimization results. The first form of optimization measures the optimization effect through three evaluation indicators: system traction energy consumption, average passenger waiting time (i.e., average passenger waiting time) and passenger patience loss (i.e., passenger satisfaction loss); while the second form of optimization reflects the optimization effect through two indicators: system traction energy consumption and comprehensive loss of passenger service quality.

[0205] In the first form, the three evaluation indicators of system traction energy consumption, average passenger waiting time, and passenger patience loss are all extremely small indicators. The Pareto frontier formed by system traction energy consumption and average passenger waiting time can be called the ET Pareto frontier, the Pareto frontier formed by passenger satisfaction loss and average passenger waiting time can be called the PT Pareto frontier, and the Pareto frontier formed by passenger satisfaction loss and system traction energy consumption can be called the PE Pareto frontier. The Pareto frontier formed by the three together can be called the PET Pareto frontier. Figure 6a 、 Figure 6b and Figure 6c The ET Pareto front, PT Pareto front and PE Pareto front and their fitting curves are shown respectively. Figure 6d The PET Pareto front and its fitting surface in three-dimensional space are shown. Figure 6e Shown are the points in the PET Pareto front on the ET plane.

[0206] In the second form, the two evaluation indicators of system traction energy consumption and comprehensive loss of passenger service quality are also extremely small indicators, and the Pareto front formed by them is called SE Pareto front. Figure 7 The SE Pareto frontier, formed based on the comprehensive loss of passenger service quality and system traction energy consumption, is shown. It can be seen that the feasible solution for dispatching trains based on passenger flow experience is not on the Pareto frontier, while the feasible solution obtained by the disclosed embodiment is closer to the Pareto frontier. A solution obtained from the Pareto frontier was compared with a baseline solution. Compared with the baseline solution, the Pareto frontier solution reduced system traction energy consumption by 2.83% and the comprehensive passenger service quality evaluation value by 6.54%. The experimental results fully validate the effectiveness of the optimization method proposed in the disclosed embodiment.

[0207] from Figure 8 The Pareto front solution for the upward direction of Line 1 shows that the train departure interval changes less frequently during off-peak hours, such as 10:00-16:00, which means the decision variable dimension is low. However, during peak hours, such as 16:00-19:00, the train departure interval changes more frequently, which means the decision variable dimension is high. Based on the above departure intervals, the following can be formed: Figure 9 The departure schedule for Line 1 in the Pareto front scenario is shown.

[0208] Figure 10 The following figure shows the distribution of some passenger flow paths for 100 pairs of ODs (starting and ending points) randomly selected after passenger flow guidance. The horizontal axis is the number of the OD, and the vertical axis is the number of the selectable route. Different colors represent the probability of the current OD selecting the route. The corresponding relationship between color and selection probability is shown in the legend on the right. It should be understood that Figure 10Only some of the path selection probabilities under passenger flow guidance are displayed. Due to the huge number of ODs, they are not displayed one by one due to space limitations.

[0209] Figure 11 A block diagram of a device for optimizing the quality of service for urban rail transit passengers according to an embodiment of the present disclosure is shown. Figure 11 As shown, the device includes:

[0210] Acquisition module 111 is configured to acquire network data, passenger flow data, a decision variable set, and a guidance strategy set of a subway network within a specified time period, wherein the network data includes: line information, station information, and train information within the subway network; the passenger flow data includes the number of passengers traveling from each starting station to each terminal station within each unit time period of the specified time period; the specified time period includes multiple sub-time periods; the decision variable set includes the departure interval of trains within each sub-time period of the specified time period; the guidance strategy set includes the passenger flow guidance strategy for each sub-time period of the specified time period; the departure intervals of trains within the same sub-time period in the same departure direction on the same subway line are the same and the passenger flow guidance strategy is the same; the passenger flow guidance strategy is used to indicate the selection probability of each of at least one travel route that can be selected by passengers traveling from each starting station to each terminal station within the sub-time period;

[0211] a route selection determination module 112 for determining a passenger route selection set based on the road network data, the passenger flow data, and the guidance strategy set, wherein the passenger route selection set includes a passenger route selection matrix from each starting station to each terminal station, wherein the passenger route selection matrix from the s-th starting station to the v-th terminal station includes a target travel route selected by each of a plurality of passengers traveling from the s-th starting station to the v-th terminal station, wherein s∈[1,N], v∈[1,N], s≠v, and N is the total number of stations in the subway network;

[0212] a patience loss determination module 113 configured to determine the patience loss of each passenger traveling from each starting station to each terminal station based on the road network data, the passenger route selection set, and the passenger service coefficient set, wherein the passenger service coefficient set includes a service coefficient matrix for passengers traveling from each starting station to each terminal station, wherein the service coefficient matrix for passengers traveling from the s-th starting station to the v-th terminal station includes the service coefficients for each passenger traveling from the s-th starting station to the v-th terminal station, wherein the service coefficients represent the gradient of patience loss, and the patience loss represents the patience lost by a passenger who chooses a target route to travel;

[0213] A waiting time determination module 114 is configured to determine, based on the passenger route selection set, the waiting time required for each target route selected by each passenger traveling from each starting station to each terminal station in the subway network;

[0214] The optimization module 115 is used to optimize the decision variable set and the guidance strategy set based on the patience loss and waiting time of each passenger traveling from each starting station to each terminal station in the subway network, to obtain an optimized target decision variable set and target guidance strategy set, so as to improve the passenger service quality of the subway network within the specified time period using the optimized target decision variable set and target guidance strategy set.

[0215] In one possible implementation, the passenger path selection set is determined based on the road network data, the passenger flow data and the guidance strategy set, including: for the sth starting station in the subway network, determining a path set from the sth starting station to the vth terminal station based on the road network data, wherein the path set from the sth starting station to the vth terminal station includes at least one selectable travel path from the sth starting station to the vth terminal station and the path length of each travel path; determining the number of passengers going from the sth starting station to the vth terminal station based on the passenger flow data; determining a passenger path selection matrix from the sth starting station to the vth terminal station based on the guidance strategy set, the path set from the sth starting station to the vth terminal station and the number of passengers going from the sth starting station to the vth terminal station within the specified time period.

[0216] In one possible implementation, the determination of the patience loss of each passenger traveling from each starting station to each terminal station based on the road network data, the passenger path selection set, and the passenger service coefficient set includes: for the s-th starting station in the subway network, based on the path set from the s-th starting station to the v-th terminal station, determining a path excess rate set from the s-th starting station to the v-th terminal station, wherein the path excess rate set includes the path excess rate of each riding path in at least one ride path that can be selected from the s-th starting station to the v-th terminal station. The path excess rate of each riding route is the ratio of the path length of each riding route to the path length of the shortest riding route minus 1, and the path set is determined based on the road network data; according to the path excess rate set from the s-th starting station to the v-th terminal station and the passenger service coefficient matrix from the s-th starting station to the v-th terminal station, the original patience loss of each passenger traveling from the s-th starting station to the v-th terminal station is determined, wherein the patience loss of each passenger traveling from the s-th starting station to the v-th terminal station includes the original patience loss of each passenger.

[0217] In a possible implementation, determining the patience loss of each passenger traveling from each starting station to each terminal station based on the road network data, the passenger path selection set, and the passenger service coefficient set further includes: determining an expected value of the original patience loss of each passenger traveling from the s-th starting station to the v-th terminal station based on the original patience loss of each passenger traveling from the s-th starting station to the v-th terminal station, and determining the expected value as a tolerance threshold for traveling from the s-th starting station to the v-th terminal station; for the i-th passenger traveling from the s-th starting station to the v-th terminal station, if the original patience loss of the i-th passenger is greater than or equal to the tolerance threshold, based on a first weighting coefficient, The difference between the original patience loss of the i-th passenger and the tolerance threshold is weighted to obtain the weighted patience loss of the i-th passenger; or, when the original patience loss of the i-th passenger is less than the tolerance threshold, the difference between the original patience loss of the i-th passenger and the tolerance threshold is weighted based on a second weighting coefficient to obtain the weighted patience loss of the i-th passenger; wherein, i∈[1,M], M is the number of passengers going from the s-th starting station to the v-th terminal station, the first weighting coefficient is greater than the second weighting coefficient, and the patience loss of each passenger going from the s-th starting station to the v-th terminal station includes the weighted patience loss of each passenger.

[0218] In one possible implementation, the method of determining the waiting time required for the target travel path selected by each passenger traveling from each starting station to each terminal station in the subway network based on the passenger path selection set includes: for the target travel path selected by any passenger traveling from the sth starting station to the vth terminal station, if the target travel path includes a transfer station, dividing the target travel path into at least two path segments based on the transfer stations included in the target travel path; obtaining the waiting time required for the target travel path selected by the passenger based on the waiting time required to board a train from the starting station of each path segment of the at least two path segments; wherein the waiting time required to board a train from the starting station of each path segment is determined based on the departure time of each train passed by the starting station of each path segment; if the target travel path does not include a transfer station, determining the waiting time required for the target travel path selected by the passenger as the waiting time required.

[0219] In a possible implementation, the decision variable set and the guidance strategy set are optimized according to the patience loss and the required waiting time of each passenger traveling from each starting station to each terminal station in the subway network to obtain the optimized target decision variable set and target guidance strategy set, including: normalizing the patience loss of each passenger traveling from each starting station to each terminal station according to the maximum patience loss of a single passenger in the specified time period to obtain the normalized patience loss of each passenger, the maximum patience loss being the maximum value of the patience loss incurred by the passengers in the specified time period; normalizing the waiting time required for the target travel path selected by each passenger traveling from each starting station to each terminal station according to the maximum waiting time of a single passenger in the specified time period to obtain the normalized patience loss of each passenger. the normalized waiting time of each passenger, the maximum waiting time being the maximum time required for a passenger to wait to board the train within the specified time period; based on the time weights set for different passengers, the normalized patience loss and the normalized waiting time of each passenger traveling from each starting station to each terminal station are weightedly summed to obtain the service quality loss of each passenger traveling from each starting station to each terminal station; the service quality loss of each passenger traveling from each starting station to each terminal station on each subway line of the subway network within the specified time period is accumulated to obtain the comprehensive passenger service quality loss corresponding to the subway network; based on the specified constraints, the decision variable set and the guidance strategy set are optimized with the goal of minimizing the comprehensive passenger service quality loss to obtain the optimized target decision variable set and target guidance strategy set.

[0220] In one possible implementation, the device further includes: an energy consumption determination module, configured to determine the system traction energy consumption based on the decision variable set, wherein the system traction energy consumption represents the total energy consumption required for the operation of each train on each subway line within the specified time period; wherein, based on the specified constraints, with the goal of minimizing the comprehensive loss of passenger service quality, the decision variable set and the guidance strategy set are optimized to obtain the optimized target decision variable set and target guidance strategy set, including: based on the specified constraints, with the goal of minimizing the comprehensive loss of passenger service quality and minimizing the system traction energy consumption, the decision variable set and the guidance strategy set are optimized to obtain the optimized target decision variable set and target guidance strategy set.

[0221] In one possible implementation, the decision variable set and the guidance strategy set are optimized based on the patience loss and the required waiting time of each passenger traveling from each starting station to each terminal station in the subway network to obtain the optimized target decision variable set and target guidance strategy set, including: determining the total passenger patience loss of the subway network in the specified time period based on the patience loss of each passenger traveling from each starting station to each terminal station in the specified time period, and the total passenger patience loss represents the patience loss of all passengers at all stations on all subway lines in the subway network. the total value of ; determining the average waiting time of passengers in the subway network within the specified time period based on the waiting time required for the target travel route selected by each passenger traveling from each starting station to each terminal station within the specified time period, wherein the average waiting time of passengers represents the average time required for passengers to wait for boarding at all stations on all subway lines in the subway network; based on specified constraints, optimizing the decision variable set and the guidance strategy set with the goal of minimizing the total passenger patience loss and minimizing the average passenger waiting time, thereby obtaining an optimized target decision variable set and target guidance strategy set.

[0222] In a possible implementation, the decision variable set and the guidance strategy set are optimized based on the specified constraints, with the goal of minimizing the total passenger patience loss and minimizing the average passenger waiting time, to obtain the optimized target decision variable set and target guidance strategy set, including: based on the specified constraints, with the goal of minimizing the total passenger patience loss, minimizing the average passenger waiting time and minimizing the system traction energy consumption, the decision variable set and the guidance strategy set are optimized to obtain the optimized target decision variable set and target guidance strategy set; wherein the system traction energy consumption is determined based on the decision variable set and is used to characterize the total energy consumption required for the operation of each train on each subway line within the specified time period.

[0223] In one possible implementation, the constraints include: the departure interval of trains on each subway line is within the range of the maximum departure interval and the minimum departure interval preset for each subway line; the earliest departure time of the last train on each subway line is later than the preset end time of operation; the relative deviation between the path length of each selectable travel route from the sth starting station to the vth terminal station and the path length of the shortest travel route is less than or equal to a preset deviation threshold; the sum of the selection probabilities of each selectable travel route from the sth starting station to the vth terminal station is 1; and the remaining patience of each passenger is greater than or equal to a preset patience threshold, wherein the remaining patience of each passenger includes the difference between the initial patience set by each passenger and the patience loss of each passenger.

[0224] In one possible implementation, the apparatus further includes: a time period patience loss determination module, configured to determine, based on the patience loss of each passenger traveling from each starting station to each terminal station within the specified time period, a time period patience loss corresponding to each sub-time period of the specified time period, wherein the time period patience loss represents the total value of the patience loss of passengers entering all stations on all subway lines of the subway network within the sub-time period; a time period adjustment module, configured to adjust, based on the time period patience loss corresponding to each sub-time period of the specified time period, the initial duration of each sub-time period within the specified time period, to obtain each sub-time period after the duration is adjusted, wherein the time period patience loss of the sub-time period is negatively correlated with the duration of the sub-time period; and an adjustment module, configured to determine, based on each sub-time period after the duration is adjusted, a time period adjusted decision variable set and a guidance strategy set, so as to optimize the time period adjusted decision variable set and guidance strategy set to obtain an optimized target decision variable set and target guidance strategy set.

[0225] According to the device of the embodiment of the present disclosure, the passengers' patience loss and waiting time are determined based on the network data, passenger flow data, decision variable set and guidance strategy set of the subway railway network within a specified time period, and the decision variable set and guidance decision set are optimized based on the passengers' patience loss and waiting time. Based on the optimized target decision variable set and target guidance strategy set, train departure times can be scheduled and passengers can be guided to choose appropriate travel routes, which is conducive to shortening the waiting time and patience loss of passengers in the subway railway network and improving the passenger service quality of the entire subway railway network.

[0226] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments. For the sake of brevity, it will not be repeated here.

[0227] The present disclosure also provides a computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions implement the above method when executed by a processor. The computer-readable storage medium may be a volatile or non-volatile computer-readable storage medium.

[0228] An embodiment of the present disclosure further proposes an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0229] An embodiment of the present disclosure also provides a computer program product, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0230] Figure 12 FIG1 shows a block diagram of an electronic device 1900 according to an embodiment of the present disclosure. For example, the electronic device 1900 can be provided as a server or a terminal device. Figure 12 The electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions executable by the processing component 1922, such as an application. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute the instructions to perform the above-described method.

[0231] The electronic device 1900 may further include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input / output interface 1958 (I / O interface). The electronic device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server 2003. TM , Mac OS X TM , Unix TM ,Linux TM , FreeBSD TM or similar.

[0232] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions that can be executed by the processing component 1922 of the electronic device 1900 to perform the above method.

[0233] The present disclosure may be a system, method and / or computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0234] A computer-readable storage medium can be a tangible device that can hold and store instructions for use by an instruction execution device. A computer-readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination thereof. As used herein, a computer-readable storage medium is not to be construed as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through an electrical wire.

[0235] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in the computer-readable storage medium in each computing / processing device.

[0236] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, and conventional procedural programming languages ​​such as "C" language or similar programming languages. Computer-readable program instructions may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., utilizing an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be personalized by utilizing the state information of the computer-readable program instructions. The electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0237] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0238] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0239] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0240] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and the part of the module, program segment or instruction contains one or more executable instructions for realizing the prescribed logical function. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the prescribed function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0241] While various embodiments of the present disclosure have been described above, the foregoing description is intended to be illustrative, non-exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, their practical applications, or technological improvements in the marketplace, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for optimizing the passenger service quality of urban rail transit, characterized in that: include: Obtaining network data, passenger flow data, a decision variable set, and a guidance strategy set for a subway network within a specified time period, wherein the network data includes: line information, station information, and train information in the subway network; the passenger flow data includes the number of passengers traveling from each starting station to each terminal station in the subway network within each unit time period of the specified time period; the specified time period includes multiple sub-time periods, the decision variable set includes the departure interval of trains in each sub-time period of the specified time period, and the guidance strategy set includes the passenger flow guidance strategy for each sub-time period of the specified time period, wherein the departure intervals of trains in the same departure direction and the same sub-time period of the same subway line are the same and the passenger flow guidance strategy is the same, and the passenger flow guidance strategy is used to indicate the selection probability of each of at least one travel route that can be selected by passengers traveling from each starting station to each terminal station within the sub-time period; Determine a passenger path selection set based on the road network data, the passenger flow data, and the guidance strategy set, wherein the passenger path selection set includes a passenger path selection matrix from each starting station to each terminal station, wherein the passenger path selection matrix from the s-th starting station to the v-th terminal station includes a target travel path selected by each passenger from the s-th starting station to the v-th terminal station, wherein s∈[1,N], v∈[1,N], s≠v, and N is the total number of stations in the subway network; Determining the patience loss of each passenger traveling from each starting station to each terminal station based on the road network data, the passenger route selection set, and the passenger service coefficient set, wherein the passenger service coefficient set includes a service coefficient matrix for passengers traveling from each starting station to each terminal station, wherein the service coefficient matrix for passengers traveling from the s-th starting station to the v-th terminal station includes the service coefficients of each passenger traveling from the s-th starting station to the v-th terminal station, wherein the service coefficient represents a gradient of the patience loss, and the patience loss represents the patience lost by a passenger who chooses a target route to travel; Determining, based on the passenger route selection set, the waiting time required for each target travel route selected by each passenger traveling from each starting station to each terminal station in the subway network; The decision variable set and the guidance strategy set are optimized according to the patience loss and the required waiting time of each passenger traveling from each starting station to each terminal station in the subway network to obtain an optimized target decision variable set and a target guidance strategy set, so as to improve the passenger service quality of the subway network within the specified time period by utilizing the optimized target decision variable set and the target guidance strategy set.

2. The method according to claim 1, characterized in that The determining of the passenger path selection set based on the road network data, the passenger flow data and the guidance strategy set includes: For the sth starting station in the subway network, determining, based on the network data, a set of paths from the sth starting station to the vth terminal station, wherein the set of paths from the sth starting station to the vth terminal station includes at least one selectable travel path from the sth starting station to the vth terminal station and the length of each travel path; Determine the number of passengers traveling from the sth starting station to the vth ending station based on the passenger flow data; Determine a passenger path selection matrix from the sth starting station to the vth terminal station based on the guidance strategy set, the path set from the sth starting station to the vth terminal station, and the number of passengers traveling from the sth starting station to the vth terminal station within the specified time period.

3. The method according to claim 2, characterized in that Determining the patience loss of each passenger traveling from each starting station to each terminal station based on the road network data, the passenger route selection set, and the passenger service coefficient set includes: For an s-th starting station in the subway network, determining a set of path excess rates from the s-th starting station to the v-th terminal station based on a set of paths from the s-th starting station to the v-th terminal station, wherein the set of path excess rates includes the path excess rate of each of at least one selectable travel path from the s-th starting station to the v-th terminal station, the path excess rate of each travel path being the ratio of the path length of each travel path to the path length of the shortest travel path minus 1, and the path set being determined based on the road network data; Based on the set of path excess rates from the s-th starting station to the v-th terminal station and the passenger service coefficient matrix from the s-th starting station to the v-th terminal station, the original patience loss of each passenger going from the s-th starting station to the v-th terminal station is determined, wherein the patience loss of each passenger going from the s-th starting station to the v-th terminal station includes the original patience loss of each passenger.

4. The method according to claim 3, characterized in that The determining of the patience loss of each passenger traveling from each starting station to each terminal station based on the road network data, the passenger route selection set, and the passenger service coefficient set further includes: Determine an expected value of the original patience loss of each passenger going from the s-th starting station to the v-th terminal station based on the original patience loss of each passenger going from the s-th starting station to the v-th terminal station, and determine the expected value as the tolerance threshold for going from the s-th starting station to the v-th terminal station; For the i-th passenger traveling from the s-th starting station to the v-th terminal station, if the original patience loss of the i-th passenger is greater than or equal to the tolerance threshold, weighting the difference between the original patience loss of the i-th passenger and the tolerance threshold based on a first weighting coefficient to obtain a weighted patience loss of the i-th passenger; or If the original patience loss of the i-th passenger is less than the tolerance threshold, weighting the difference between the original patience loss of the i-th passenger and the tolerance threshold based on a second weighting coefficient to obtain a weighted patience loss of the i-th passenger; Wherein, i∈[1,M], M is the number of passengers traveling from the sth starting station to the vth terminal station, the first weighting coefficient is greater than the second weighting coefficient, and the patience loss of each passenger traveling from the sth starting station to the vth terminal station includes the weighted patience loss of each passenger.

5. The method according to claim 1, wherein Determining the waiting time required for the target travel path selected by each passenger traveling from each starting station to each terminal station in the subway network based on the passenger route selection set includes: For a target travel route selected by any passenger traveling from the sth starting station to the vth destination station, if the target travel route includes a transfer station, the target travel route is divided into at least two route segments based on the transfer station included in the target travel route; Obtaining a waiting time required for a target route selected by the passenger based on the waiting time required to board a train from the starting station of each of the at least two route segments; wherein the waiting time required to board a train from the starting station of each route segment is determined based on the departure times of each train passing through the starting station of each route segment; When the target boarding route does not include a transfer station, the waiting time required to board a train from the starting station of the target boarding route is determined as the waiting time required for the target boarding route selected by the passenger.

6. The method according to claim 1, characterized in that The decision variable set and the guidance strategy set are optimized according to the patience loss and the required waiting time of each passenger traveling from each starting station to each terminal station in the subway network to obtain an optimized target decision variable set and target guidance strategy set, including: Normalizing the patience loss of each passenger traveling from each starting station to each terminal station according to the maximum patience loss of a single passenger during the specified time period to obtain the normalized patience loss of each passenger, wherein the maximum patience loss is the maximum value of the patience loss incurred by the passengers during the specified time period; Normalizing the waiting time required for the target bus route selected by each passenger traveling from each starting station to each terminal station based on the maximum waiting time of a single passenger during the specified time period to obtain the normalized waiting time of each passenger, where the maximum waiting time is the maximum time required for a passenger to wait for boarding during the specified time period; Based on the time weights set for different passengers, the normalized patience loss and normalized waiting time of each passenger traveling from each starting station to each terminal station are weighted and summed to obtain the service quality loss of each passenger traveling from each starting station to each terminal station; Accumulating the service quality loss of each passenger traveling from each starting station to each terminal station on each subway line of the subway network within the specified time period to obtain a comprehensive passenger service quality loss corresponding to the subway network; Based on specified constraints and with the goal of minimizing the comprehensive loss of passenger service quality, the decision variable set and the guidance strategy set are optimized to obtain an optimized target decision variable set and target guidance strategy set.

7. The method according to claim 6, characterized in that The method further comprises: determining a system traction energy consumption according to the decision variable set, wherein the system traction energy consumption represents the total energy consumption required for the operation of each train on each subway line within the specified time period; The step of optimizing the decision variable set and the guidance strategy set based on the specified constraints and aiming at minimizing the comprehensive loss of passenger service quality to obtain the optimized target decision variable set and target guidance strategy set includes: Based on specified constraints, with the goal of minimizing the comprehensive loss of passenger service quality and minimizing the system traction energy consumption, the decision variable set and the guidance strategy set are optimized to obtain an optimized target decision variable set and target guidance strategy set.

8. The method according to claim 1, characterized in that The decision variable set and the guidance strategy set are optimized according to the patience loss and the required waiting time of each passenger traveling from each starting station to each terminal station in the subway network to obtain an optimized target decision variable set and target guidance strategy set, including: determining a total passenger patience loss of the subway network during the specified time period based on the patience loss of each passenger traveling from each starting station to each terminal station during the specified time period, wherein the total passenger patience loss represents the total value of the patience loss of all passengers at all stations on all subway lines in the subway network; Determining an average passenger waiting time for the subway network during the specified time period based on the waiting time required for each passenger to travel from each starting station to each terminal station during the specified time period, wherein the average passenger waiting time represents the average waiting time required for passengers to board a train at all stations on all subway lines in the subway network; Based on specified constraints, with the goal of minimizing the total passenger patience loss and minimizing the average waiting time of the passengers, the decision variable set and the guidance strategy set are optimized to obtain an optimized target decision variable set and target guidance strategy set.

9. The method according to claim 8, characterized in that The method optimizes the decision variable set and the guidance strategy set based on the specified constraints with the goal of minimizing the total passenger patience loss and minimizing the average passenger waiting time to obtain an optimized target decision variable set and target guidance strategy set, including: Based on specified constraints, the decision variable set and the guidance strategy set are optimized with the goal of minimizing the total passenger patience loss, minimizing the average passenger waiting time, and minimizing the system traction energy consumption, thereby obtaining an optimized target decision variable set and target guidance strategy set; wherein the system traction energy consumption is determined based on the decision variable set and is used to characterize the total energy consumption required for the operation of each train on each subway line within the specified time period.

10. The method according to any one of claims 6 to 9, characterized in that The constraints include: The departure interval of trains on each subway line is within the range of the maximum departure interval and the minimum departure interval preset for each subway line; The earliest departure time of the last train on each subway line is later than the preset end time of operation; The relative deviation between the length of each route that can be selected from the s-th starting station to the v-th terminal station and the length of the shortest route is less than or equal to a preset deviation threshold; The sum of the selection probabilities of all the routes that can be chosen from the sth starting station to the vth terminal station is 1; The remaining patience of each passenger is greater than or equal to a preset patience threshold, wherein the remaining patience of each passenger includes a difference between an initial patience set by each passenger and a patience loss of each passenger.

11. The method according to any one of claims 1 to 9, characterized in that The method further comprises: Determining, based on the patience loss of each passenger traveling from each starting station to each terminal station within the specified time period, a period patience loss corresponding to each sub-period of the specified time period, wherein the period patience loss represents the total value of the patience loss of passengers entering all stations on all subway lines of the subway network within the sub-period; adjusting the initial duration of each sub-period within the specified time period according to the time period patience loss corresponding to each sub-period within the specified time period to obtain each sub-period after the duration is adjusted, wherein the time period patience loss of the sub-period is negatively correlated with the duration of the sub-period; Based on each sub-period after the adjustment of the duration, a decision variable set and a guiding strategy set after the period adjustment are determined, so as to optimize the decision variable set and the guiding strategy set after the period adjustment to obtain an optimized target decision variable set and a target guiding strategy set.

12. An urban rail transit passenger service quality optimization device, characterized in that: include: an acquisition module, configured to acquire network data, passenger flow data, a decision variable set, and a guidance strategy set of a subway network within a specified time period, wherein the network data includes: line information, station information, and train information within the subway network; the passenger flow data includes the number of passengers traveling from each starting station to each terminal station within each unit time period of the specified time period; the specified time period includes multiple sub-time periods; the decision variable set includes the departure interval of trains within each sub-time period of the specified time period; the guidance strategy set includes the passenger flow guidance strategy for each sub-time period of the specified time period; the departure intervals of trains within the same sub-time period in the same departure direction on the same subway line are the same and the passenger flow guidance strategy is the same; the passenger flow guidance strategy is used to indicate the selection probability of each of at least one travel route that can be selected by passengers traveling from each starting station to each terminal station within the sub-time period; a path selection determination module, configured to determine a passenger path selection set based on the road network data, the passenger flow data, and the guidance strategy set, wherein the passenger path selection set includes a passenger path selection matrix from each starting station to each terminal station, wherein the passenger path selection matrix from the s-th starting station to the v-th terminal station includes a target travel path selected by each of a plurality of passengers traveling from the s-th starting station to the v-th terminal station, wherein s∈[1,N], v∈[1,N], s≠v, and N is the total number of stations in the subway network; a patience loss determination module, configured to determine the patience loss of each passenger traveling from each starting station to each terminal station based on the road network data, the passenger route selection set, and the passenger service coefficient set, wherein the passenger service coefficient set includes a service coefficient matrix for passengers traveling from each starting station to each terminal station, wherein the service coefficient matrix for passengers traveling from the s-th starting station to the v-th terminal station includes the service coefficients for each passenger traveling from the s-th starting station to the v-th terminal station, wherein the service coefficients represent the gradient of the patience loss, and the patience loss represents the patience lost by a passenger who chooses a target route to travel; a waiting time determination module, configured to determine, based on the passenger path selection set, the waiting time required for each target travel path selected by each passenger traveling from each starting station to each terminal station in the subway network; The optimization module is used to optimize the decision variable set and the guidance strategy set according to the patience loss and the required waiting time of each passenger traveling from each starting station to each terminal station in the subway network, so as to obtain an optimized target decision variable set and a target guidance strategy set, so as to improve the passenger service quality of the subway network within the specified time period by using the optimized target decision variable set and the target guidance strategy set.

13. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to implement the method according to any one of claims 1 to 11 when executing the instructions stored in the memory.

14. A non-volatile computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 11 is implemented.

Images