Methods and systems for determining passenger flow in urban rail transit sections
By using linear regression to fit the relationship between passenger flow in sections and passenger flow entering stations in urban rail transit, the problems of high solution difficulty and large prediction deviation in existing technologies have been solved, achieving efficient and accurate passenger flow control in sections and improving train service efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING JIAOTONG UNIV
- Filing Date
- 2022-11-09
- Publication Date
- 2026-05-26
AI Technical Summary
In urban rail transit, existing technologies, through sensitivity analysis and linear programming models for path selection, struggle to accurately predict nonlinear passenger flow between sections. This results in high solution difficulty and large prediction errors, especially during peak hours or large-scale event evacuations, failing to accurately reflect the impact of station entry passenger flow on section passenger flow.
By adopting a linear relationship between the station-section linear ratio matrix and the passenger flow entering the station, combined with correlation degree parameters and correlation margin parameters, the relationship between the passenger flow in the section and the passenger flow entering the station is fitted by a linear regression method to achieve real-time control.
It reduces the difficulty and complexity of model solving, improves computational efficiency, accurately reflects the impact of peak hours or large-scale event passenger flow evacuation, and ensures train service efficiency.
Smart Images
Figure CN115796442B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of urban rail transit operation and maintenance management technology, specifically to a method and system for determining passenger flow in urban rail transit sections. Background Technology
[0002] Urban rail transit networks often experience congestion during morning and evening rush hours or when dealing with the dispersal of large events. Uneven passenger flow between stations, coupled with limited train capacity, inevitably leads to passenger delays and a decline in service quality and passenger safety. Therefore, stations, as entrances to urban rail transit systems, must control passenger flow entering the station to quickly determine passenger flow at different times, ensuring that the station's capacity meets passenger boarding needs. However, the capacity of urban rail transit is discrete, influenced by train departure intervals. The dynamically changing passenger flow entering the station and the passenger flow between stations exhibit an unknown, non-linear relationship that cannot be directly predicted.
[0003] Currently, to ensure train service efficiency and supply-demand balance, passenger flow between stations is primarily determined through "sensitivity analysis" and "linear programming models for route selection." In "sensitivity analysis," a two-level programming model is established, aiming to achieve a balance between inbound passenger flow and station capacity based on the principle of "system optimization." An approximate linear relationship between inbound passenger flow and station passenger flow is established to approximate the actual nonlinear relationship. Through continuous iterative convergence, the optimal inbound passenger flow and station passenger flow are obtained. Using the LP control method, a quasi-dynamic control model is constructed to obtain inbound passenger flow at different times based on the proportion and correlation of passenger flow along each route.
[0004] The existing methods described above, which approximate the nonlinear relationship between station entry passenger flow and interval passenger flow using linear functions through sensitivity analysis, require multiple passenger flow allocations and iterations until an optimal solution is found. This method is difficult and complex, and the continuous model also places high demands on computation. While the LP-based passenger flow control method discretizes time compared to the first method, reducing the difficulty of the solution, it ignores the characteristics of passenger flow changes over time and cannot accurately reflect the impact of station entry passenger flow on interval passenger flow. This is especially true for peak hours or evacuation flows from large events, where the influence of stranded passengers on the weighted ratio further increases, leading to significant passenger flow prediction errors. Summary of the Invention
[0005] The purpose of this invention is to provide a method and system for determining passenger flow in urban rail transit sections by representing the through passenger flow in different time periods using a station-section linear ratio matrix and the linear relationship between the inbound passenger flow and the station-section passenger flow. This reduces the difficulty and complexity of model solving, is more in line with the research background of passenger flow dispersal during peak hours or large-scale events, and also takes into account the time-varying characteristics of passenger flow. This is beneficial for real-time control of inbound passenger flow and ensures the efficiency of train service. This aims to solve at least one of the technical problems existing in the background art.
[0006] To achieve the above objectives, the present invention adopts the following technical solution:
[0007] On one hand, the present invention provides a method for determining passenger flow in urban rail transit sections, comprising:
[0008] Based on the spatiotemporal correlation of passenger flow, the evolution process of passenger flow in the station is analyzed within the interval;
[0009] Based on the evolution of passenger flow in the station area, the relationship between passenger flow in the area and passenger flow in the station is linearly fitted.
[0010] Based on the relationship between the interval passenger flow and the station passenger flow after linear fitting, the correlation degree parameter and correlation margin parameter are calibrated.
[0011] Based on correlation degree parameters and correlation margin parameters, passenger flow allocation methods are used to obtain station entry volume and train section passenger flow data.
[0012] Preferably, based on the spatiotemporal correlation of passenger flow, the evolution process of passenger flow in the station is analyzed within the interval, including: based on the changes in the full load and flow of the interval caused by the changes in passenger flow, the evolution process of passenger flow in the station within the interval is obtained; the continuous passenger flow evolution state is discretized and the spatiotemporal correlation of passenger flow is calibrated.
[0013] Preferably, the continuous passenger flow evolution state is discretized, including: establishing an urban rail transit physical topology network G<N,A>, where N={s1,..,s k ,...} represents the station object, s represents the station, A={a(s1,s2),..,a(s k ,s k+1 ),...} represents an interval object, and 'a' represents an interval; the time range T is discretized to form M time intervals t of length T / M. i For each time period t, i = 0, 1, ..., M-1, the passenger flow entering the station and the passenger flow between sections are discretized. i Inside, each station k The collection of inbound passenger flow Q sk ={Q sk (ti )|i=0,1,...,M-1}, and each interval a(s k ,s k+1 Set of passenger flow in intervals The passenger flow of a section is the sum of the number of passengers carried by trains passing through the section within a time period.
[0014] Preferably, a fitting relationship is established using linear regression; wherein, the passenger flow entering the station during a certain time period is gradually distributed to the subsequent passenger flow according to the different destination stations of the travelers, in a certain proportion; as station s k Passenger flow at the station Entering the interval a(s) within a certain time period k ,s k+1 As the probability increases, the passenger flow in that interval increases accordingly; before time period t0, the passenger flow in the interval prior to the study time range is generated, and this part of the passenger flow affects the interval passenger flow as a bias term.
[0015] Preferably, in each time period t i Internally, through the correlation degree parameter and correlation margin parameters The correlation between passenger flow in the designated section and passenger flow entering each station:
[0016]
[0017] in, Indicates the t-th j Stations within a time period k Passenger flow at the station During time period t i Entering the interval a(s) k ,s k+1 The probability of ) represents the degree of influence of inbound passenger flow on inter-section passenger flow during the road network evolution process; This represents the interval a(s) within the time period ti prior to the study time range. k ,s k+1 The interval passenger flow represents the range of disturbance to the interval passenger flow caused by the prior cumulative passenger flow that has entered the station before the research time range.
[0018] Preferably, assuming there are n intervals and k stations on the road network, then during the Mth time period, the following discrete linear relationship is formed between the passenger flow of the intervals and the passenger flow entering the stations:
[0019]
[0020] in, Indicates the time period t M Passing through interval a n Passenger flow in the area Indicates the time period t i Entering the station k The number of passengers entering the station; Indicates the t-th i Stations within a time period k Passenger flow entering the station during time period tM enters interval a n The probability, Indicates the time period t before the research time range M Inner interval a n Passenger flow in the area;
[0021] By inputting historical passenger flow data, the station entry volume and train section passenger flow data are obtained using passenger flow allocation methods. Then, the parameters are fitted using linear regression. and
[0022] Secondly, the present invention provides a system for determining passenger flow in urban rail transit sections, comprising:
[0023] The analysis module is used to analyze the evolution of passenger flow in the interval based on the spatiotemporal correlation of passenger flow points and lines.
[0024] The fitting module is used to linearly fit the relationship between the passenger flow in the interval and the passenger flow in the station based on the evolution of the passenger flow in the interval.
[0025] The calibration module is used to calibrate the correlation degree parameters and correlation margin parameters based on the relationship between the linearly fitted interval passenger flow and the inbound passenger flow.
[0026] The determination module is used to obtain station entry volume and train section passenger flow data based on correlation degree parameters and correlation margin parameters, using passenger flow allocation methods.
[0027] Thirdly, the present invention provides a non-transitory computer-readable storage medium for storing computer instructions, which, when executed by a processor, implement the method for determining passenger flow in urban rail transit sections as described above.
[0028] Fourthly, the present invention provides a computer program product, including a computer program that, when run on one or more processors, is used to implement the method for determining passenger flow in urban rail transit sections as described above.
[0029] Fifthly, the present invention provides an electronic device, comprising: a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to cause the electronic device to execute instructions for implementing the urban rail transit section passenger flow determination method as described above.
[0030] The beneficial effects of this invention are as follows: Compared with existing methods for extrapolating passenger flow in the same scenario, this invention ensures the accuracy and reliability of passenger flow calculation by fitting the quantitative relationship between passenger flow in the interval and station entry volume in the spatiotemporal network. On the one hand, it avoids the high complexity of solving continuous mathematical models and improves computational efficiency; on the other hand, it avoids the impact of fixed proportional coefficients on the accuracy of prediction results.
[0031] The advantages of additional aspects of the invention will be set forth more clearly in the following description or will be learned by practice of the invention. Attached Figure Description
[0032] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0033] Figure 1 This is a schematic diagram illustrating the evolution of station entry volume within a section, as described in an embodiment of the present invention. Detailed Implementation
[0034] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.
[0035] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.
[0036] It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with their meanings in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless defined as here.
[0037] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, and / or groups thereof.
[0038] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.
[0039] To facilitate understanding of the present invention, the present invention will be further explained and described below with reference to the accompanying drawings and specific embodiments. However, the specific embodiments do not constitute a limitation on the embodiments of the present invention.
[0040] Those skilled in the art should understand that the accompanying drawings are merely schematic diagrams of embodiments, and the components in the drawings are not necessarily essential for implementing the present invention.
[0041] Example 1
[0042] This embodiment 1 provides a system for determining passenger flow in urban rail transit sections, including:
[0043] The analysis module is used to analyze the evolution of passenger flow in the interval based on the spatiotemporal correlation of passenger flow points and lines.
[0044] The fitting module is used to linearly fit the relationship between the passenger flow in the interval and the passenger flow in the station based on the evolution of the passenger flow in the interval.
[0045] The calibration module is used to calibrate the correlation degree parameters and correlation margin parameters based on the relationship between the linearly fitted interval passenger flow and the inbound passenger flow.
[0046] The determination module is used to obtain station entry volume and train section passenger flow data based on correlation degree parameters and correlation margin parameters, using passenger flow allocation methods.
[0047] In this embodiment 1, the above-described system is used to implement a method for determining passenger flow in urban rail transit sections, including:
[0048] Based on the spatiotemporal correlation of passenger flow, the evolution process of passenger flow in the station is analyzed within the interval;
[0049] Based on the evolution of passenger flow in the station area, the relationship between passenger flow in the area and passenger flow in the station is linearly fitted.
[0050] Based on the relationship between the interval passenger flow and the station passenger flow after linear fitting, the correlation degree parameter and correlation margin parameter are calibrated.
[0051] Based on correlation degree parameters and correlation margin parameters, passenger flow allocation methods are used to obtain station entry volume and train section passenger flow data.
[0052] Among them, based on the spatiotemporal correlation of passenger flow, the evolution process of passenger flow in the station is analyzed in the interval, including: based on the changes in the full load and flow of the interval caused by the changes in passenger flow, the evolution process of passenger flow in the station in the interval is obtained; the continuous passenger flow evolution state is discretized and the spatiotemporal correlation of passenger flow is calibrated.
[0053] Discretizing the continuous passenger flow evolution process includes: establishing a physical topology network G<N,A> for urban rail transit, where N={s1,..,s k ,...} represents the station object, s represents the station, A={a(s1,s2),..,a(s k ,s k+1 ),...} represents an interval object, and 'a' represents an interval; the time range T is discretized to form M time intervals t of length T / M. i For each time period t, i = 0, 1, ..., M-1, the passenger flow entering the station and the passenger flow between sections are discretized. i Inside, each station k The collection of inbound passenger flow Q sk ={Q sk (t i )|i=0,1,...,M-1}, and each interval a(s k ,s k+1 Set of passenger flow in intervals The passenger flow of a section is the sum of the number of passengers carried by trains passing through the section within a time period.
[0054] A fitting relationship is established using linear regression; the passenger flow entering the station during a certain time period is distributed to subsequent interval passenger flow according to the different destination stations of travelers, in a certain proportion; as station s k Passenger flow at the station Entering the interval a(s) within a certain time period k ,s k+1As the probability increases, the passenger flow in that interval increases accordingly; before time period t0, the passenger flow in the interval prior to the study time range is generated, and this part of the passenger flow affects the interval passenger flow as a bias term.
[0055] In each time period t i Internally, through the correlation degree parameter and correlation margin parameters The correlation between passenger flow in the designated section and passenger flow entering each station:
[0056]
[0057] in, Indicates the t-th j Stations within a time period k Passenger flow at the station During time period t i Entering the interval a(s) k ,s k+1 The probability of ) represents the degree of influence of inbound passenger flow on inter-section passenger flow during the road network evolution process; Indicates the time period t before the research time range i Inner interval a(s) k ,s k+1 The interval passenger flow represents the range of disturbance to the interval passenger flow caused by the prior cumulative passenger flow that has entered the station before the research time range.
[0058] Suppose there are n intervals and k stations on the road network, then the following discrete linear relationship exists between the passenger flow of each interval and the passenger flow entering the station during the Mth time period:
[0059]
[0060] in, Indicates the time period t M Passing through interval a n Passenger flow in the area Indicates the time period t i Entering the station k The number of passengers entering the station; Indicates the t-th i Stations within a time period k Passenger flow entering the station during time period t M Enter interval a n The probability, Indicates the time period t before the research time range M Inner interval a n Passenger flow in the area;
[0061] By inputting historical passenger flow data, the station entry volume and train section passenger flow data are obtained using passenger flow allocation methods. Then, the parameters are fitted using linear regression. and
[0062] Example 2
[0063] The refined management of passenger flow is fundamental to much research in the field of urban rail transit. Under congestion conditions, accurately establishing the relationship between interval passenger flow and station entry passenger flow is particularly important. For example, due to the dynamic evolution of passenger flow, as passenger flow enters a station or section along a line, it occupies the spatiotemporal capacity resources of that section or other lines. When the capacity of the interval cannot match the excess passenger demand, it will result in excessively high interval occupancy rates, which in turn affects the passenger flow rate and line capacity allocation of the entire network. Therefore, by studying the point-to-line spatiotemporal correlation of network passenger flow, extrapolating interval passenger flow based on historical passenger flow data, and combining optimization theories and methods, it is possible to achieve balanced and reasonable control of station entry passenger flow, quantify the number of stations with flow restrictions, passenger flow control periods, and passenger flow entry rates, maximize the network entry rate while maximizing the utilization of train capacity to achieve the highest network transportation efficiency.
[0064] Based on the above, this embodiment 2 provides a method for obtaining the relationship between interval passenger flow and station entry passenger flow. Based on the networked operation of urban rail transit and considering time-varying passenger flow, and according to the point-to-line spatiotemporal correlation of passenger flow, the correlation degree parameter and correlation margin parameter of the two are obtained through a linear fitting method, thereby achieving the purpose of dimensionality reduction of passenger flow data and realizing the estimation of interval passenger flow.
[0065] The method includes the following steps:
[0066] 1. Based on the spatiotemporal correlation of passenger flow points and lines, analyze the evolution of passenger flow in the station within the interval.
[0067] Based on the spatiotemporal correlation of passenger flow, i.e., the changes in station load and flow caused by changes in inbound passenger flow, this invention obtains the evolution process of inbound passenger flow within a station. To calibrate the spatiotemporal correlation of passenger flow, this invention discretizes the continuous passenger flow evolution state. First, a physical topology network G<N,A> for urban rail transit is established, where N={s1,..,s k ,...} represents the station object, s represents the station, A={a(s1,s2),..,a(s k ,s k+1 ), ...} represent interval objects, and a represents an interval. This invention discretizes the time range T under study, forming M time intervals t of length T / M. iFor each time period t, i = 0, 1, ..., M-1, the passenger flow entering the station and the passenger flow between sections are discretized. i Inside, each station k The collection of inbound passenger flow and each interval a(s) k ,s k+1 Set of passenger flow in intervals The passenger flow of a section is the sum of the number of passengers carried by trains passing through the section within a time period.
[0068] like Figure 1 As shown, the passenger flow entering station s0 within time period t0. Different trains, Tr1, Tr2, or Tr3, can be selected. As the trains travel, passenger flow will sequentially pass through network intervals a(s1,s2)...a(s... k ,s k+1 ...and this affects the passenger flow in these intervals at various time periods after t0, therefore the passenger flow in these intervals... and passenger flow There is a certain correlation between them in space and time. Specifically: in the spatial dimension, as passengers travel by train through different sections sequentially, passenger flow evolution exhibits spatial sequential characteristics; in the temporal dimension, if passengers entering the station in the current time period do not exit, they will influence the sections in subsequent time periods over time, meaning that the impact of entering passenger flow on section flow has a time lag. Due to the discrete nature of train transportation modes, it is difficult to describe the relationship between section passenger flow and entering passenger flow using a continuous and unified analytical function.
[0069] 2. Linear fitting of the relationship between passenger flow in the interval and passenger flow entering the station.
[0070] To accurately and concisely describe the relationship between inter-station passenger flow and inbound passenger flow, this invention establishes a fitting relationship using linear regression. The regression coefficients and bias terms in the linear equation have clear physical meanings, thus achieving data dimensionality reduction. Inbound passenger flow generated within a certain time period will be distributed to subsequent inter-station passenger flow according to a certain proportion, based on the different destinations of travelers. Historical passenger flow data shows that when the time period is appropriately divided and the OD structure of passenger flow is relatively stable, this proportion is equivalent to a relatively fixed probability. As station s... k Passenger flow at the station Entering the interval a(s) within a certain time period k ,s k+1As the probability increases, the passenger flow in that interval also increases. Furthermore, before time period t0, passenger flow from the period prior to the study time range will inevitably occur; this passenger flow will act as a bias term, affecting the overall passenger flow in that interval. Based on the above analysis, in each time period t... i Within this invention, a correlation parameter (regression coefficient term) is proposed. And the associated margin parameter (bias term) The correlation between passenger flow in the designated section and passenger flow entering each station:
[0071]
[0072] In formula (1) Indicates the t-th j Stations within a time period k Passenger flow at the station During time period t i Entering the interval a(s) k ,s k+1 The probability of ) represents the degree of influence of inbound passenger flow on inter-section passenger flow during the road network evolution process; Indicates the time period t before the research time range i Inner interval a(s) k ,s k+1 The interval passenger flow represents the range of disturbance to the interval passenger flow caused by the prior cumulative passenger flow that has entered the station before the study time range. The time discretization method essentially employs linear fitting to describe the relationship between the inbound passenger flow and the interval passenger flow. The higher the linear fit, the more stable the passenger flow origin-destination (OD) structure and the closer the OD ratios.
[0073] 3. Calibration of correlation degree parameters and correlation margin parameters
[0074] The correlation parameter of the analytical function of interval passenger flow with respect to inbound passenger flow. and correlation margin parameters There are currently two approaches to solving this problem. One approach is to use sensitivity analysis to find the continuous derivative of the passenger flow in the interval with respect to the passenger flow entering the station. This is then used to obtain the passenger flow in the interval through multiple passenger flow allocations, followed by an inverse function iteration to calculate the passenger flow entering the station until convergence to the optimal solution. The other approach is to calculate the proportion of passenger flow allocated along the path based on the Logit path selection model. Based on the relationship between the path and the interval, and combined with the allocation proportion, the proportion of passenger flow entering the station that passes through the interval is calculated, thus solving the optimization model. The former approach requires passenger flow allocation for each solution, making the solution of the continuous model more complex. The latter approach uses a path selection probability function to reduce the algorithmic difficulty, but using a fixed proportion cannot accurately reflect the impact of the station's passenger flow on the passenger flow in the interval, especially during peak hours. Due to high train occupancy rates, passenger dwell times can cause the passenger flow evolution in the interval to change over time as the train runs, thus affecting the accuracy of the solution parameters.
[0075] In this embodiment, the calibration of these two parameters is achieved by comprehensively considering the advantages and disadvantages of the two approaches. Based on the autonomous choice of passenger travel, and through the passenger flow evolution calculation of the daily variation evolution model, when the road network traffic will tend to be balanced, the two parameters are calculated based on the inbound passenger flow and the calculated interval passenger flow of the previous d days. According to formula (1), assuming there are n intervals and k stations on the road network, the following discrete linear relationship between interval passenger flow and inbound passenger flow is formed in the Mth time period:
[0076]
[0077] In formula (2), Indicates the time period t M Passing through interval a n Passenger flow in the area Indicates the time period t i Entering the station k The number of passengers entering the station; Indicates the t-th i Stations within a time period k Passenger flow entering the station during time period t M Enter interval a n The probability, Indicates the time period t before the research time range M Inner interval a n Passenger flow in the area.
[0078] By inputting a large amount of historical passenger flow data, the station entry volume and train section passenger flow data are obtained using the passenger flow allocation method. The parameters are then fitted using the linear regression method. and
[0079] Example 3
[0080] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium for storing computer instructions. When executed by a processor, the computer instructions implement a method for determining passenger flow in urban rail transit sections. The method includes:
[0081] Based on the spatiotemporal correlation of passenger flow, the evolution process of passenger flow in the station is analyzed within the interval;
[0082] Based on the evolution of passenger flow in the station area, the relationship between passenger flow in the area and passenger flow in the station is linearly fitted.
[0083] Based on the relationship between the interval passenger flow and the station passenger flow after linear fitting, the correlation degree parameter and correlation margin parameter are calibrated.
[0084] Based on correlation degree parameters and correlation margin parameters, passenger flow allocation methods are used to obtain station entry volume and train section passenger flow data.
[0085] Example 4
[0086] Embodiment 4 of the present invention provides a computer program (product), including a computer program that, when run on one or more processors, is used to implement a method for determining passenger flow in urban rail transit sections. The method includes:
[0087] Based on the spatiotemporal correlation of passenger flow, the evolution process of passenger flow in the station is analyzed within the interval;
[0088] Based on the evolution of passenger flow in the station area, the relationship between passenger flow in the area and passenger flow in the station is linearly fitted.
[0089] Based on the relationship between the interval passenger flow and the station passenger flow after linear fitting, the correlation degree parameter and correlation margin parameter are calibrated.
[0090] Based on correlation degree parameters and correlation margin parameters, passenger flow allocation methods are used to obtain station entry volume and train section passenger flow data.
[0091] Example 5
[0092] Embodiment 5 of the present invention provides an electronic device, including: a processor, a memory, and a computer program; wherein, the processor is connected to the memory, and the computer program is stored in the memory. When the electronic device is running, the processor executes the computer program stored in the memory to cause the electronic device to execute instructions for implementing a method for determining passenger flow in urban rail transit sections, the method including:
[0093] Based on the spatiotemporal correlation of passenger flow, the evolution process of passenger flow in the station is analyzed within the interval;
[0094] Based on the evolution of passenger flow in the station area, the relationship between passenger flow in the area and passenger flow in the station is linearly fitted.
[0095] Based on the relationship between the interval passenger flow and the station passenger flow after linear fitting, the correlation degree parameter and correlation margin parameter are calibrated.
[0096] Based on correlation degree parameters and correlation margin parameters, passenger flow allocation methods are used to obtain station entry volume and train section passenger flow data.
[0097] In summary, the key point of the urban rail transit section passenger flow determination method and system described in this invention is to characterize the quantitative relationship between urban rail transit section passenger flow and station entry volume at different time periods using a linearized dimensionality reduction method based on the daily evolution law of passenger flow. This proposes a low-complexity method that can quickly and accurately obtain section passenger flow. Technical implementation details include, but are not limited to: obtaining the entry passenger flow of each station at different time periods through data cleaning; obtaining section passenger flow using a passenger flow allocation method based on historical passenger flow data and train timetable information, and using a binary regression analysis prediction method to fit and obtain relevant parameters; based on the cleaned entry passenger flow, and according to the correlation parameters between section passenger flow and station entry volume, the through passenger flow of each section at different time periods can be obtained. Specifically: 1) Regarding section passenger flow prediction, constructing an urban rail transit network passenger flow allocation model by analyzing passenger travel behavior is a widely used quantitative prediction method for estimating network passenger flow distribution. However, this method has a long calculation time, especially when facing real-time prediction needs, requiring the design of a more efficient method. 2) Regarding passenger flow allocation, simulation has become a commonly used technical means. Given the train operation schedule and passenger flow demand of the network, it can accurately reflect the allocation effect and has strong applicability. However, each possible allocation scheme requires a simulation, which takes a long time. When facing large-scale networks and large passenger flows, the simulation efficiency will be significantly reduced.
[0098] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0099] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0100] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0101] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment, whereby a series of operational steps are performed to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0102] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that, based on the technical solutions disclosed in the present invention, various modifications or variations that can be made by those skilled in the art without creative effort should be included within the scope of protection of the present invention.
Claims
1. A method for determining the passenger flow in an urban rail transit section, characterized in that, include: Based on the point-line spatio-temporal correlation relationship of passenger flow, analyze the evolution process of the inbound passenger flow in the interval, including: obtaining the evolution process of the inbound passenger flow in the interval based on the full-load and flow changes in the interval caused by the change of inbound passenger flow; discretizing the continuous passenger flow evolution state and calibrating the point-line spatio-temporal correlation relationship of passenger flow; discretizing the continuous passenger flow evolution state, including: establishing the physical topology network of urban rail transit , where represents the station object, represents the station, represents the interval object, represents the interval; discretize the time range to form M time periods with a length of . In each time period, discretize the inbound passenger flow of the station and the passenger flow of the interval to form the inbound passenger flow set of each station in each time period , and the interval passenger flow set of each interval . The interval passenger flow is the sum of the number of passengers carried by the trains passing through the interval within the time period; , and the interval passenger flow set of each interval . The interval passenger flow is the sum of the number of passengers carried by the trains passing through the interval within the time period; The interval passenger flow is the sum of the number of passengers carried by the trains passing through the interval within the time period; Based on the evolution process of the inbound passenger flow in the interval, linearly fit the relationship between the interval passenger flow and the inbound passenger flow; among which, establish the fitting relationship through the method of linear regression; among which, the inbound passenger flow generated in a certain time period is successively allocated to the subsequent interval passenger flow according to a certain proportion according to the different final stations of the travelers; as the inbound passenger flow entering the interval in a certain time period probability increases, the passenger flow of this interval increases accordingly; before the time period before, generate the interval passenger flow before the research time range, and this part of the passenger flow affects the interval passenger flow as an offset term; Based on the relationship between the interval passenger flow and the inbound passenger flow after linear fitting, calibrate the correlation degree parameter and the correlation margin parameter; among them, in each time period within, through the correlation degree parameter and the correlation margin parameter calibrate the correlation relationship between the interval passenger flow and the inbound passenger flow of each station: ; in, Indicates the first Stations within a certain time period Passenger flow at the station During the time period Entering the interval The probability represents the degree of influence of inbound passenger flow on inter-section passenger flow during the road network evolution process; Indicates the period prior to the research time range inner interval The interval passenger flow represents the range of disturbance to the interval passenger flow caused by the prior cumulative passenger flow that has entered the station before the research time range. Based on correlation degree parameters and correlation margin parameters, passenger flow allocation methods are used to obtain station entry volume and train section passenger flow data.
2. The method for determining passenger flow in urban rail transit sections according to claim 1, characterized in that, Assuming there is a road network Each interval The station, then at the... Within a given time period, the following discrete linear relationship is formed between the interval passenger flow and the station entry passenger flow: ； in, Indicates time period Inner Passage Interval Passenger flow in the area Indicates time period Enter the station The number of passengers entering the station; Indicates the first Stations within a certain time period Passenger flow at the station during the time period Entering the interval The probability, Indicates the period prior to the research time range inner interval Passenger flow in the area; By inputting historical passenger flow data, the station entry volume and train section passenger flow data are obtained using a passenger flow allocation method. Parameters are then fitted using a linear regression method. and .
3. A system for determining passenger flow in urban rail transit sections, used to implement the method for determining passenger flow in urban rail transit sections as described in claim 1 or 2, characterized in that, include: The analysis module is used to analyze the evolution of passenger flow in the interval based on the spatiotemporal correlation of passenger flow points and lines. The fitting module is used to linearly fit the relationship between the passenger flow in the interval and the passenger flow in the station based on the evolution of the passenger flow in the interval. The calibration module is used to calibrate the correlation degree parameters and correlation margin parameters based on the relationship between the linearly fitted interval passenger flow and the inbound passenger flow. The determination module is used to obtain station entry volume and train section passenger flow data based on correlation degree parameters and correlation margin parameters, using passenger flow allocation methods.
4. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium is used to store computer instructions, which, when executed by a processor, implement the method for determining passenger flow in urban rail transit sections as described in claim 1 or 2.
5. A computer program product, characterized in that, It includes a computer program, which, when run on one or more processors, is used to implement the method for determining passenger flow in urban rail transit sections as described in claim 1 or 2.
6. An electronic device, characterized in that, include: The device includes a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to cause the electronic device to execute instructions to implement the method for determining passenger flow in urban rail transit sections as described in claim 1 or 2.