Demand response type scheduling management method and system applied to intelligent public transportation system

Abstract

The invention discloses a demand response type scheduling management method and system applied to an intelligent public transportation system, and particularly relates to the field of traffic transportation engineering. Comprising the steps of S1, collecting multi-source data of a demand response type bus, S2, integrating and storing the multi-source data, S3, analyzing the multi-source data in real time, S4, predicting and judging the demand condition of the bus, S5, monitoring the running state of the demand response type bus, S6, intelligently obtaining a scheduling decision, S7, collecting passenger feedback after a scheduling strategy is implemented, and S8, updating and maintaining a bus scheduling management system. According to the demand response type scheduling management method applied to the intelligent public transportation system, split data are integrated through the data integration module, and an advantage foundation of data collaboration is laid; a demand response type bus scheduling decision is obtained through an intelligent scheduling decision module, and a strategy is adjusted in time in response to sudden temporary passenger flow demands; and a real-time data updating channel is established through the system updating and maintaining module, so that the bus dispatching accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the field of transportation engineering technology, and more specifically, to a management method and system for demand-responsive scheduling applied to a smart public transportation system. Background Art

[0002] With the rapid development of information technology and intelligent transportation systems, the importance of smart public transportation systems has become increasingly prominent. Cutting-edge technologies such as big data, the Internet of Things, and artificial intelligence have been continuously integrated into the transportation field to optimize public transportation operations and improve service efficiency and passenger experience. This is one of the important indicators for measuring the level of urban modernization.

[0003] The smart bus system can accurately dispatch buses and optimize bus route planning based on real-time traffic conditions, passenger flow and other data, so that bus resources can more reasonably cover various areas of the city and enhance the attractiveness of the bus system. The smart bus system can also reduce empty driving through intelligent scheduling, reduce environmental pollution, and save energy, which has a positive impact on promoting green travel and sustainable urban development.

[0004] However, in actual use, it still has some shortcomings, such as the need for continuous investment and updating of large amounts of data; the fragmentation of multi-source data, which cannot give full play to the advantages of data collaboration, affecting the accuracy and timeliness of bus scheduling; and insufficient response to sudden and temporary passenger flow demands, resulting in passenger backlogs at some stations. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides a management method and system for demand-responsive scheduling applied to a smart public transportation system, and solves the problems raised in the above-mentioned background technology through the following scheme.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A management method for demand-responsive scheduling applied to a smart public transportation system, characterized by comprising:

[0008] S1: Collect multi-source data of demand-responsive public transportation: Collect multi-source data corresponding to demand-responsive public transportation in the smart public transportation system to obtain the first demand set;

[0009] S2: Integrate and store multi-source data: perform integration and storage processing on the first requirement set, and the integration and storage processing is used to obtain and store the first key requirement corresponding to the first requirement set;

[0010] S3: Real-time analysis of multi-source data: obtaining a demand response analysis model, and obtaining a second demand set through the first key demand according to the demand response analysis model;

[0011] S4: predicting and judging the demand for public transport vehicles: obtaining a demand judgment model, and obtaining a second key demand corresponding to the second demand set through the second demand set according to the demand judgment model;

[0012] S5: monitoring the running status of the demand-responsive bus: monitoring the running status of the demand-responsive bus in real time to obtain a third demand set, and performing a feedback operation on the monitored demand-responsive bus based on the second key demand, wherein the feedback operation is used to obtain a third key demand corresponding to the third demand set;

[0013] S6: Intelligently obtain scheduling decisions: obtain an intelligent scheduling decision model, and obtain a demand-responsive bus scheduling strategy based on the second key demand and the third key demand according to the intelligent scheduling decision model;

[0014] S7: Collecting passenger feedback after implementing the dispatch strategy: Collecting passenger feedback data corresponding to the implementation of the demand-responsive bus dispatch strategy;

[0015] S8: Update and maintain the bus dispatching management system: Continuously update and maintain the corresponding database of the demand-responsive bus dispatching management system.

[0016] Preferably, the S2, obtaining and storing the first key requirement corresponding to the first requirement set, specifically includes:

[0017] Data cleaning: Clean the data in the first requirement set to remove abnormal data and invalid data caused by signal interference;

[0018] Format unification: Unify the data formats of different data sources in the first requirement set;

[0019] Key feature fusion: associating and fusing various types of data in the first demand set. The associative fusion operation includes associating the vehicle's location data with the speed data, fusing the passenger boarding and alighting data with the vehicle's location data, associating the door opening and closing time with the passenger counting data, and fusing the traffic conditions with the vehicle's driving route information;

[0020] Key requirement identification: identify the first requirement set after association and fusion and extract the first key requirement;

[0021] Storage operation: Use a distributed database to store different types of key demand data in different tables.

[0022] Preferably, the step S3, obtaining a second requirement set, specifically includes:

[0023] Actual passenger demand S at different times t t-1 , S t-2 , …, S t-p, calculate the passenger flow peak intensity coefficient Rs of the station, which is specifically expressed as:

[0024] Rs=r1×S t-1 +r2×S t-2 +...+r p ×S t-p +∈ t ,

[0025] Among them, r1, r2, ..., r p It is represented as the weight of the impact of the pth lag time on the current passenger demand, t represents the current time, p represents the number of lag times, ∈ t Expressed as the difference in passenger demand;

[0026] Based on the number of passengers Q on line l1 l1 、The number of passengers on line l2 Q l2 , the average passenger capacity of idle buses S, the vehicle capacity C on line l1 l1 、Vehicle capacity C on line l2 l2 , calculate the line passenger flow balance adjustment coefficient Rl, which is specifically expressed as:

[0027]

[0028] Where c represents the number of buses that can be deployed, and its value range is [0, min (C l1 ,C l2 )].

[0029] Preferably, the step S3, obtaining a second requirement set, specifically includes:

[0030] Based on the number of passengers arriving per unit time λ and the vehicle's passenger capacity per unit time μ, the bus idle probability P0 is calculated, which can be expressed as:

[0031]

[0032] Where n is the index of the number of buses that can be deployed, n! is the factorial of n, and c is the number of buses that can be deployed, with a value range of [0, min(C l1 ,C l2 )];

[0033] Based on the number of passengers arriving per unit time λ, the passenger capacity of the vehicle per unit time μ, and the bus idle probability P0, the active passenger flow evacuation demand coefficient Vd is calculated, which is specifically expressed as:

[0034]

[0035] Where (c-1)! represents the factorial of (c-1), c represents the number of buses that can be deployed, and the value range is [0, min(C l1 ,C l2 )].

[0036] Preferably, the step S4, obtaining the second key requirement corresponding to the second requirement set, specifically includes:

[0037] The weight of each site is determined by building a hierarchical model;

[0038] Determine the weight of passenger flow adjustment between routes and routes on the degree of regional passenger flow aggregation based on route coverage and connection relationship;

[0039] Based on the station passenger flow peak intensity coefficient Rs and the line passenger flow balance adjustment coefficient Rl, the regional passenger flow concentration degree RTD is calculated, which is specifically expressed as:

[0040]

[0041] Among them, ω s It is represented as the weight vector of the peak passenger flow intensity of the station, ω s (s) represents the weight of site s, S represents the set of sites, ω l It is represented as the weight matrix of line passenger flow balance adjustment, ω l (l1, l2) represents the passenger flow adjustment weight between line l1 and line l2, L1 represents the set of lines l1, and L2 represents the set of lines l2.

[0042] Preferably, the step S4, obtaining the second key requirement corresponding to the second requirement set, specifically includes:

[0043] Based on the number of vehicles required for evacuating passenger flow during large-scale activities Vd and the number of buses that can be deployed c, the quantitative value of comprehensive emergency response capacity IER is calculated, which is specifically expressed as:

[0044]

[0045] Wherein, α represents the evacuation threshold coefficient, and its value range is (0, 1).

[0046] Preferably, the step S6, obtaining a demand-responsive public transport vehicle dispatching strategy, specifically includes:

[0047] The second key demand and the third key demand are passed as input data to the intelligent scheduling decision model, and the relationship between the second key demand and the third key demand is comprehensively analyzed;

[0048] Determine feedback instructions to generate demand-responsive bus dispatch strategies;

[0049] Vehicle deployment decision: clearly indicate the source of the vehicle to be deployed and the specific vehicle number to be deployed;

[0050] Departure interval adjustment decision: adjust the specific departure interval value according to the increase in passenger flow and the operation status of the vehicle;

[0051] Driving route adjustment decision: Plan the vehicles that need to change their driving routes and the new driving routes, including the sequence of stops and the stop time at each stop. For vehicles that need to detour, clearly define the starting and end points of the detour as well as the main sections and intersections in between.

[0052] Preferably, the step S8, updating and maintaining the public transportation dispatching management system, specifically includes:

[0053] Establish a real-time data update channel to continuously update the first key demand, the second key demand, the third key demand, and the demand-responsive bus dispatch strategy to the preset management database every 2 minutes;

[0054] Test the data recovery mechanism regularly, simulate different types of failure scenarios, and verify the backup data.

[0055] To achieve the above object, the present invention provides the following technical solution: a management system for demand-responsive scheduling applied to a smart public transportation system, comprising a system operation database, a system central processing module and a user information terminal, and implementing the above-mentioned management method for demand-responsive scheduling applied to a smart public transportation system, comprising:

[0056] Data collection module: used to collect multi-source data corresponding to demand-responsive public transportation in the smart public transportation system to obtain the first demand set and transmit it to the data integration module;

[0057] Data integration module: used for integrating and storing the first requirement set collected by the data collection module, and the integrated storage processing is used for acquiring and storing the first key requirement corresponding to the first requirement set, and transmitting it to the real-time data analysis module;

[0058] Real-time data analysis module: used to obtain a demand response analysis model, obtain a second demand set through the first key demand in the data integration module according to the demand response analysis model, and transmit it to the demand prediction and judgment module;

[0059] Demand prediction and judgment module: used to obtain a demand judgment model, obtain the second key demand corresponding to the second demand set through the second demand set in the real-time data analysis module according to the demand judgment model, and transmit it to the vehicle monitoring module and the intelligent scheduling decision module;

[0060] Vehicle monitoring module: used to monitor the operating status of the demand-responsive public transport vehicle in real time to obtain the third demand set, and perform feedback operation on the monitored demand-responsive public transport vehicle based on the second key demand of the demand prediction and judgment module. The feedback operation is used to obtain the third key demand corresponding to the third demand set and transmit it to the intelligent scheduling decision module;

[0061] Intelligent dispatching decision module: used to obtain an intelligent dispatching decision model, and obtain a demand-responsive public transport dispatching strategy based on the intelligent dispatching decision model through the second key requirement of the demand prediction and judgment module and the third key requirement of the vehicle monitoring module;

[0062] Passenger feedback module: used to collect passenger feedback data corresponding to the demand-responsive bus dispatch strategy implemented in the intelligent dispatch decision module, and transmit it to the system update and maintenance module;

[0063] System update and maintenance module: used to receive passenger feedback data from the passenger feedback module, continuously update and maintain the corresponding database of the demand-responsive bus dispatch management system, and transmit the updated maintenance data to the data integration module for storage;

[0064] The system operation database includes all data texts of the demand-responsive bus scheduling management system, and collects information texts output by each module in real time. The system central processing module is used for information text instructions output by each module in the central control method, and the user information terminal is an information output device for receiving the demand-responsive bus scheduling management system.

[0065] Preferably, the passenger feedback module collects passenger feedback data corresponding to the implementation of the demand-responsive public transport vehicle dispatching strategy, specifically including:

[0066] Collecting passenger feedback data through passenger feedback terminals, including touch terminals installed inside demand-responsive buses, mobile applications, and social media;

[0067] Passenger feedback data includes the degree of crowding in the vehicle, vehicle punctuality, riding comfort, and abnormal problems;

[0068] Abnormal problems include but are not limited to abnormal vehicle shaking and severe odor.

[0069] Technical effects and advantages of the present invention:

[0070] 1. The present invention uses a data integration module to remove abnormal data and invalid data and integrate key features, thereby integrating fragmented data and laying a foundation for the advantages of data collaboration;

[0071] 2. The present invention uses the intelligent dispatching decision module to comprehensively analyze the second key demand of the demand forecasting and judgment module and the third key demand of the vehicle monitoring module to obtain demand-responsive public transport vehicle dispatching decisions, and can also adjust strategies in time to cope with sudden temporary passenger flow demands;

[0072] 3. The present invention establishes a real-time data update channel through the system update and maintenance module, timely updates data and maintains the database to ensure the normal operation of the system, and improves the accuracy of public transportation scheduling and the ability to respond to emergencies. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 It is a diagram of the method steps of the present invention.

[0074] Figure 2 The figure is a flow chart of the method of the present invention.

[0075] Figure 3 It is a schematic diagram of the structure of the method of the present invention. DETAILED DESCRIPTION

[0076] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0077] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to and includes any or all possible combinations of one or more listed items.

[0078] In the following, the terms "first", "second", and "third" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", and "third" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0079] As attached Figure 1A management method for demand-responsive scheduling applied to a smart public transportation system is shown, including S1: collecting multi-source data of demand-responsive public transportation, S2: integrating and storing multi-source data, S3: real-time analysis of multi-source data, S4: predicting and judging the demand situation of public transportation vehicles, S5: monitoring the operating status of demand-responsive vehicles, S6: intelligently obtaining scheduling decisions, S7: collecting passenger feedback after implementing the scheduling strategy, and S8: updating and maintaining the public transportation scheduling management system.

[0080] S1: Collect multi-source data of demand-responsive public transportation: Collect multi-source data corresponding to demand-responsive public transportation in the smart public transportation system to obtain the first demand set.

[0081] Specifically, the smart public transportation system collects data on the corresponding terminal platform by setting up demand-responsive public transportation vehicles, and the terminal platform includes but is not limited to: a high-precision GPS positioning system, an on-board speed sensor, a passenger counting sensor, etc.; the data of different terminal platforms are received using corresponding communication protocols and data formats; the first demand set is obtained, and the first demand set includes the number of buses that can be deployed, the number of passengers per unit time, the passenger capacity of vehicles per unit time, the total number of passengers on each line, the average passenger capacity of idle public transportation vehicles, and the total vehicle capacity C on each line. l1 , the actual number of passengers demanded at different times.

[0082] In one possible implementation, obtaining the first demand set includes: outputting the three-dimensional coordinate information of the vehicle every 10 seconds through a high-precision GPS positioning system installed on a demand-responsive public bus; collecting real-time driving speed data of the vehicle through an on-board speed sensor; counting the number of passengers getting on and off each time the door is opened and closed through a passenger counting sensor installed at the door; obtaining real-time traffic information of the urban road network through microwave radars distributed on the road, including traffic volume and speed data on the road; and collecting information on large-scale events from social media platforms and large-scale event ticket sales websites, including event time, event location, and the expected number of participants in the event.

[0083] S2: Integrate and store multi-source data: perform integration and storage processing on the first requirement set, and the integration and storage processing is used to obtain and store the first key requirement corresponding to the first requirement set.

[0084] Specifically, after obtaining the first demand set, the demand-responsive bus dispatching and management system obtains multiple demand features corresponding to the first demand set, namely, the first key demand, through integrated storage and processing operations.

[0085] In a possible implementation, the steps of integrating the storage processing operation are as follows: data cleaning: cleaning the data in the first demand set to remove abnormal data and invalid data generated due to signal interference;

[0086] In this embodiment, when the GPS coordinates are compared with the normal driving trajectory of the vehicle, if they exceed the bus operation area, they are determined to be abnormal data and are eliminated; when the passenger counts have the same value continuously in a short period of time and do not conform to the actual situation, they are corrected by comparing and analyzing the data of the adjacent time periods;

[0087] Format unification: Unify the data formats of different data sources in the first requirement set;

[0088] In this embodiment, the format of the road condition data and the format of the activity information obtained from the Internet platform are converted into a representation format preset within the demand-responsive bus dispatch management system;

[0089] Key feature fusion: associating and fusing various types of data in the first demand set. The associative fusion operation includes associating the vehicle's location data with the speed data, fusing the passenger boarding and alighting data with the vehicle's location data, associating the door opening and closing time with the passenger counting data, and fusing the traffic conditions with the vehicle's driving route information;

[0090] In this embodiment, at the same time point, the driving state of the vehicle is judged based on the driving speed of the vehicle at a specific location; the passenger boarding and alighting data is integrated with the vehicle location data to determine the passenger flow at each station; when the vehicle arrives at a station, the number of boarding and alighting at the station is recorded in combination with the door opening and closing time and the passenger counting data, and is associated with the station information to form the station passenger flow information; the traffic conditions are integrated with the vehicle driving route information to understand the traffic conditions faced by the vehicle at different sections;

[0091] Key requirement identification: identify the first requirement set after association and fusion and extract the first key requirement;

[0092] In this embodiment, the positions, speeds, number of passengers in the vehicles and the road congestion ahead of all vehicles on the route at the same time are extracted to determine the expected peak passenger flow time of the station and the surrounding vehicle resources that can be deployed;

[0093] Storage operation: Use a distributed database to store different types of key demand data in different tables;

[0094] In this embodiment, the bus line number, station name, and time are used as index fields, and the real-time vehicle status data and station passenger flow forecast data are stored in a single data table respectively. Through index query, the key needs of a certain line in a specific time period can be quickly queried.

[0095] S3: Real-time analysis of multi-source data: obtaining a demand response analysis model, and obtaining a second demand set based on the first key demand according to the demand response analysis model.

[0096] Specifically, the demand response analysis model is a pre-constructed learning model. By inputting the first key demand into the demand response analysis model, the demand response analysis model obtains a second demand set based on the first key demand. The second demand set includes the site passenger flow peak intensity coefficient, the line passenger flow balance adjustment coefficient, the bus idle probability, and the active passenger flow evacuation demand coefficient.

[0097] In a possible implementation, obtaining the second demand set includes: arranging the historical passenger demands in time series according to the historical passenger flow data covering different time periods and different stations stored in the preset management database, taking the time when the passenger flow peak of the station occurs as the node, determining the influence weight of each lag time on the current passenger demand by calculating the Pearson correlation coefficient, and calculating the actual passenger demand S at different times t. t-1 , S t-2 , …, S t-p , calculate the passenger flow peak intensity coefficient Rs of the station, which is specifically expressed as:

[0098] Rs=r1×S t-1 +r2×S t-2 +...+r p ×S t-p +∈ t ,

[0099] Among them, r1, r2, ..., r p It is represented as the weight of the impact of the pth lag time on the current passenger demand, t represents the current time, p represents the number of lag times, ∈ t Expressed as the difference in passenger demand;

[0100] In a possible implementation, obtaining the second demand set includes: determining the range of the number of buses to be deployed based on the historical deployment data stored in the preset management database, and then determining the actual number of buses that can be deployed based on the binary search method; based on the number of passengers Q on line l1 l1 、The number of passengers on line l2 Q l2 , the average passenger capacity of idle buses S, the vehicle capacity C on line l1 l1 、Vehicle capacity C on line l2 l2 , calculate the line passenger flow balance adjustment coefficient Rl, which is specifically expressed as:

[0101]

[0102] Where c represents the number of buses that can be deployed, and its value range is [0, min (C l1 ,C l2 )].

[0103] In this embodiment, when the passenger flow of the lines is unbalanced and the vehicle capacities of the two lines are similar, 10% more vehicles are allocated to the line with the smaller vehicle capacity.

[0104] In a possible implementation, obtaining the second demand set includes: determining the range of the number of buses to be deployed according to the historical deployment data stored in the preset management database, and then determining the actual number of buses that can be deployed according to the binary search method; and calculating the bus idle probability P0 based on the number of passengers arriving per unit time λ and the passenger capacity of the vehicle per unit time μ, which is specifically expressed as:

[0105]

[0106] Where n is the index of the number of buses that can be deployed, n! is the factorial of n, and c is the number of buses that can be deployed, with a value range of [0, min(C l1 ,C l2 )];

[0107] Based on the number of passengers arriving per unit time λ, the passenger capacity of the vehicle per unit time μ, and the bus idle probability P0, the active passenger flow evacuation demand coefficient Vd is calculated, which is specifically expressed as:

[0108]

[0109] Where (c-1)! represents the factorial of (c-1), c represents the number of buses that can be deployed, and the value range is [0, min(C l1 ,C l2 )].

[0110] S4: Predict and judge the demand situation of public transportation vehicles: obtain a demand judgment model, and obtain a second key demand corresponding to the second demand set through the second demand set according to the demand judgment model.

[0111] Specifically, the demand judgment model is a pre-constructed learning model. By inputting the second demand set into the demand judgment model, the demand judgment model obtains the second key demand based on the second demand set. The second key demand includes the weight vector of the peak passenger flow intensity at the station, the weight matrix of the line passenger flow balance adjustment, the regional passenger flow concentration degree, the evacuation threshold coefficient, and the quantitative value of the comprehensive emergency capability.

[0112] In one possible implementation, obtaining the second key demand corresponding to the second demand set includes: continuously optimizing the parameters of the demand judgment model through a large amount of historical public transportation operation data and external data, including but not limited to passenger flow data in different time periods, road construction and control data, various large-scale event data, and weather data; obtaining the demand judgment model corresponding to the second demand set in a preset management database, and the preset management database is used to save the correspondence between the second demand set and the demand judgment model.

[0113] In a possible implementation, obtaining the second key demand corresponding to the second demand set includes: determining the weight of each site by establishing a hierarchical model; determining the weight of passenger flow adjustment between lines on the degree of regional passenger flow aggregation based on line coverage and connection relationship; calculating the degree of regional passenger flow aggregation RTD based on the site passenger flow peak intensity coefficient Rs and the line passenger flow balance adjustment coefficient Rl, which is specifically expressed as:

[0114]

[0115] Among them, ω s It is represented as the weight vector of the peak passenger flow intensity of the station, ω s (s) represents the weight of site s, S represents the set of sites, ω l It is represented as the weight matrix of line passenger flow balance adjustment, ω l (l1, l2) represents the passenger flow adjustment weight between line l1 and line l2, L1 represents the set of lines l1, and L2 represents the set of lines l2.

[0116] In this embodiment, the degree of regional passenger flow concentration is taken as the target layer, the site-related factors are taken as the criterion layer, and the specific site is taken as the scheme layer. The criterion layer includes the transportation hub attributes of the site, the surrounding land use type, and the passenger flow; for each factor in the criterion layer, the relative importance of each site under the factor is compared pairwise to form a judgment matrix; then, by calculating the eigenvalue and eigenvector of the judgment matrix, the weight vector of each site under each criterion is obtained; according to the importance of each criterion layer factor to the target layer, pairwise comparison is performed to determine the weight of each criterion layer factor, and the weight vector of each site under each criterion is comprehensively calculated with the weight of the criterion layer factor to finally obtain the weight of each site.

[0117] In this embodiment, by calculating the overlap degree of the coverage area of ​​the two lines l1 and l2 in the area, if the overlap ratio reaches above 60, the weight is set to 0.7, and if the overlap ratio is lower than 30, it is set to 0.3.

[0118] In a possible implementation, obtaining the second key demand corresponding to the second demand set includes: presetting a series of different temporary evacuation threshold coefficients, calculating IER values ​​for different temporary evacuation threshold coefficients, setting the evacuation threshold coefficient with the shortest average passenger evacuation time as the initial value of the evacuation threshold coefficient, and calculating the comprehensive emergency capacity quantitative value IER based on the number of evacuation vehicles required for large-scale activities Vd and the number of buses that can be deployed c, which is specifically expressed as:

[0119]

[0120] Wherein, α represents the evacuation threshold coefficient, and its value range is (0, 1).

[0121] S5: Monitor the operating status of demand-responsive vehicles: monitor the operating status of demand-responsive public buses in real time to obtain a third demand set, and perform feedback operations on the monitored demand-responsive public buses based on the second key demand, and the feedback operation is used to obtain a third key demand corresponding to the third demand set.

[0122] Specifically, the demand-responsive bus dispatching and management system continuously obtains the precise geographic location information of the vehicle through the high-precision GPS positioning device installed on the bus; uses the on-board inertial measurement to monitor the vehicle's driving direction and posture in real time; measures the vehicle's driving speed in real time through the speed sensor; obtains the speed limit information of the road section where the vehicle is located through the on-board communication equipment; continuously counts the number of passengers in the car; and summarizes the data of the demand-responsive bus during the driving process to form a third demand set.

[0123] In this embodiment, the third requirement set includes that vehicle A on line l1 is currently at intersection s1, has a speed of 30 km / h, has 40 passengers in the vehicle, has closed doors, and operates the air conditioner normally, as well as similar detailed status information of other vehicles on the same line.

[0124] Specifically, after obtaining the second key demand, the demand-responsive bus dispatching and management system can obtain multiple demand characteristics corresponding to the third demand set, namely, the third key demand, through a feedback operation.

[0125] In a possible implementation, the steps of the feedback operation are as follows: Comparative analysis of the second key demand and the third demand set: after obtaining the second key demand, the demand-responsive bus dispatching and management system immediately reviews the data in the third demand set; when it is found through the third demand set that the passenger capacity of the vehicle is close to or exceeds the rated passenger capacity, and at this time the second key demand indicates that the corresponding line needs to increase the capacity within a specific time period, the system will send a feedback instruction to the demand-responsive bus dispatching and management system;

[0126] In this embodiment, the second key demand of line l1 in period t shows that there is expected to be a passenger flow peak, and it is necessary to add more vehicles to meet the travel needs of passengers. At this time, it is monitored that some vehicles on the line are close to full load, so a feedback instruction is triggered to adjust the transport capacity;

[0127] Set feedback instructions: Set simple feedback instructions to quickly adjust capacity;

[0128] In this embodiment, for vehicles whose passenger capacity is close to or exceeds the rated passenger capacity and whose line needs to increase capacity, the instruction is set to A; to adjust the departure interval, the instruction is set to B; to change the vehicle's route, the instruction is set to C.

[0129] S6: Intelligently obtain scheduling decisions: obtain an intelligent scheduling decision model, and obtain a demand-responsive bus scheduling strategy based on the second key demand and the third key demand according to the intelligent scheduling decision model.

[0130] Specifically, the intelligent question and answer model is a pre-constructed learning model. By inputting the second key demand and the third key demand into the intelligent question and answer model, the intelligent question and answer model obtains a demand-responsive bus scheduling strategy based on the second key demand and the third key demand.

[0131] In a possible implementation, obtaining a demand-responsive bus dispatching strategy includes: passing the second key demand and the third key demand as input data to an intelligent dispatching decision model, comprehensively analyzing the relationship between the second key demand and the third key demand; and judging feedback instructions to generate a demand-responsive bus dispatching strategy, the demand-responsive bus dispatching strategy including vehicle allocation decisions, departure interval adjustment decisions, and driving route adjustment decisions.

[0132] In this embodiment, the passenger flow prediction information in the second key requirement is used to analyze the temporal and spatial distribution characteristics of the passenger flow; and the real-time operating status data of the vehicle in the third key requirement is used to evaluate the specific impact of factors such as the vehicle's current position, speed, and passenger load on the scheduling decision.

[0133] In a possible implementation, obtaining a demand-responsive public transport vehicle dispatching strategy includes: vehicle dispatching decision: clearly indicating the source of the vehicle to be dispatched and the specific vehicle number to be dispatched;

[0134] In this embodiment, the second key demand shows that there will be a passenger flow peak on line l1 within a specific time period, and the third key demand shows that the vehicle capacity on the current line can no longer meet the demand, so spare vehicles are dispatched from the bus parking lot to increase the overall capacity of the line;

[0135] Departure interval adjustment decision: adjust the specific departure interval value according to the increase in passenger flow and the operation status of the vehicle;

[0136] In this embodiment, the original 10-minute departure interval of line l1 is shortened to 8 minutes;

[0137] Driving route adjustment decision: Plan the vehicles that need to change their driving routes and the new driving routes, including the sequence of stops and the stop time at each stop. For vehicles that need to detour, clearly define the starting and end points of the detour as well as the main sections and intersections in between.

[0138] S7: Collect passenger feedback after implementing the dispatch strategy: Collect passenger feedback data corresponding to the implementation of the demand-responsive bus dispatch strategy.

[0139] Specifically, passenger feedback data is collected through a passenger feedback terminal, which includes a touch terminal, mobile application, and social media installed inside the demand-responsive bus. The passenger feedback data includes the degree of crowding in the bus, vehicle punctuality, riding comfort, and abnormal problems; abnormal problems include but are not limited to abnormal vehicle bumps and severe odor.

[0140] S8: Update and maintain the bus dispatching management system: Continuously update and maintain the corresponding database of the demand-responsive bus dispatching management system.

[0141] Specifically, a real-time data update channel is established to continuously update the first key demand, the second key demand, the third key demand, and the demand-responsive bus dispatch strategy to the preset management database every 2 minutes; the data recovery mechanism is tested regularly, different types of failure scenarios are simulated, and backup data is verified.

[0142] As attached Figure 2 A management system for demand-responsive scheduling applied to a smart public transportation system is shown, including a system operation database, a system central processing module and a user information terminal, and also includes: a data acquisition module, a data integration module, a real-time data analysis module, a demand prediction and judgment module, a vehicle monitoring module, an intelligent scheduling decision module, a passenger feedback module, and a system update and maintenance module.

[0143] Data collection module: used to collect multi-source data corresponding to demand-responsive public transportation in the smart public transportation system to obtain the first demand set and transmit it to the data integration module;

[0144] Data integration module: used for integrating and storing the first requirement set collected by the data collection module, and the integrated storage processing is used for acquiring and storing the first key requirement corresponding to the first requirement set, and transmitting it to the real-time data analysis module;

[0145] Real-time data analysis module: used to obtain a demand response analysis model, obtain a second demand set through the first key demand in the data integration module according to the demand response analysis model, and transmit it to the demand prediction and judgment module;

[0146] Demand prediction and judgment module: used to obtain a demand judgment model, obtain the second key demand corresponding to the second demand set through the second demand set in the real-time data analysis module according to the demand judgment model, and transmit it to the vehicle monitoring module and the intelligent scheduling decision module;

[0147] Vehicle monitoring module: used to monitor the operating status of the demand-responsive public transport vehicle in real time to obtain the third demand set, and perform feedback operation on the monitored demand-responsive public transport vehicle based on the second key demand of the demand prediction and judgment module. The feedback operation is used to obtain the third key demand corresponding to the third demand set and transmit it to the intelligent scheduling decision module;

[0148] Intelligent dispatching decision module: used to obtain an intelligent dispatching decision model, and obtain a demand-responsive public transport dispatching strategy based on the intelligent dispatching decision model through the second key requirement of the demand prediction and judgment module and the third key requirement of the vehicle monitoring module;

[0149] Passenger feedback module: used to collect passenger feedback data corresponding to the demand-responsive bus dispatch strategy implemented in the intelligent dispatch decision module, and transmit it to the system update and maintenance module;

[0150] System update and maintenance module: used to receive passenger feedback data from the passenger feedback module, continuously update and maintain the corresponding database of the demand-responsive bus dispatch management system, and transmit the updated maintenance data to the data integration module for storage;

[0151] The system operation database includes all data texts of the demand-responsive bus scheduling management system, and collects information texts output by each module in real time. The system central processing module is used for information text instructions output by each module in the central control method, and the user information terminal is an information output device for receiving the demand-responsive bus scheduling management system.

[0152] In this example, the passenger feedback data corresponding to the implementation of the demand-responsive bus dispatch strategy is collected, including:

[0153] Specifically, passenger feedback data is collected through a passenger feedback terminal, which includes a touch terminal, mobile application, and social media installed inside the demand-responsive bus. The passenger feedback data includes the degree of crowding in the bus, vehicle punctuality, riding comfort, and abnormal problems; abnormal problems include but are not limited to abnormal vehicle bumps and severe odor.

[0154] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0155] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A management method for demand-responsive scheduling applied to a smart public transportation system, characterized in that: include: S1: Collect multi-source data of demand-responsive public transportation: Collect multi-source data corresponding to demand-responsive public transportation in the smart public transportation system to obtain the first demand set; S2: Integrate and store multi-source data: perform integration and storage processing on the first requirement set, and the integration and storage processing is used to obtain and store the first key requirement corresponding to the first requirement set; S3: Real-time analysis of multi-source data: obtaining a demand response analysis model, and obtaining a second demand set through the first key demand according to the demand response analysis model; S4: predicting and judging the demand for public transport vehicles: obtaining a demand judgment model, and obtaining a second key demand corresponding to the second demand set through the second demand set according to the demand judgment model; S5: monitoring the running status of the demand-responsive bus: monitoring the running status of the demand-responsive bus in real time to obtain a third demand set, and performing a feedback operation on the monitored demand-responsive bus based on the second key demand, wherein the feedback operation is used to obtain a third key demand corresponding to the third demand set; S6: Intelligently obtain scheduling decisions: obtain an intelligent scheduling decision model, and obtain a demand-responsive bus scheduling strategy based on the second key demand and the third key demand according to the intelligent scheduling decision model; S7: Collecting passenger feedback after implementing the dispatch strategy: Collecting passenger feedback data corresponding to the implementation of the demand-responsive bus dispatch strategy; S8: Update and maintain the bus dispatching management system: Continuously update and maintain the corresponding database of the demand-responsive bus dispatching management system.

2. A management method for demand-responsive scheduling applied to a smart public transportation system according to claim 1, characterized in that: The step S2, obtaining and storing the first key requirement corresponding to the first requirement set, specifically includes: Data cleaning: Clean the data in the first requirement set to remove abnormal data and invalid data caused by signal interference; Format unification: Unify the data formats of different data sources in the first requirement set; Key feature fusion: associating and fusing various types of data in the first demand set. The associative fusion operation includes associating the vehicle's location data with the speed data, fusing the passenger boarding and alighting data with the vehicle's location data, associating the door opening and closing time with the passenger counting data, and fusing the traffic conditions with the vehicle's driving route information; Key requirement identification: identify the first requirement set after association and fusion and extract the first key requirement; Storage operation: Use a distributed database to store different types of key demand data in different tables.

3. A management method for demand-responsive scheduling applied to a smart public transportation system according to claim 1, characterized in that: The step S3, obtaining a second requirement set, specifically includes: Based on the actual passenger demand S at different times t t-1 , S t-2 , …, S t-p , calculate the passenger flow peak intensity coefficient Rs of the station, which is specifically expressed as: Rs=r1×S t-1 +r2×S t-2 +...+r p ×S t-p +∈ t , Among them, r1, r2, ..., r p It is represented as the weight of the impact of the pth lag time on the current passenger demand, t represents the current time, p represents the number of lag times, ∈ t Expressed as the difference in passenger demand; Based on the number of passengers Q on line l1 l1 、The number of passengers on line l2 Q l2 , the average passenger capacity of idle buses S, the vehicle capacity C on line l1 l1 、Vehicle capacity C on line l2 l2 , calculate the line passenger flow balance adjustment coefficient Rl, which is specifically expressed as: Where c represents the number of buses that can be deployed, and its value range is [0, min (C l1 ,C l2 )].

4. The management method for demand-responsive scheduling applied to a smart public transportation system according to claim 1, characterized in that: The step S3, obtaining a second requirement set, specifically includes: Based on the number of passengers arriving per unit time λ and the vehicle's passenger capacity per unit time μ, the bus idle probability P0 is calculated, which can be expressed as: Where n is the index of the number of buses that can be deployed, n! is the factorial of n, and c is the number of buses that can be deployed, with a value range of [0, min(C l1 ,C l2 )]; Based on the number of passengers arriving per unit time λ, the passenger capacity of the vehicle per unit time μ, and the bus idle probability P0, the active passenger flow evacuation demand coefficient Vd is calculated, which is specifically expressed as: Where (c-1)! represents the factorial of (c-1), c represents the number of buses that can be deployed, and the value range is [0, min(C l1 ,C l2 )].

5. The management method for demand-responsive scheduling applied to a smart public transportation system according to claim 1 is characterized in that: The step S4, obtaining the second key requirement corresponding to the second requirement set, specifically includes: The weight of each site is determined by building a hierarchical model; Determine the weight of passenger flow adjustment between routes and routes on the degree of regional passenger flow aggregation based on route coverage and connection relationship; Based on the station passenger flow peak intensity coefficient Rs and the line passenger flow balance adjustment coefficient Rl, the regional passenger flow concentration degree RTD is calculated, which is specifically expressed as: Among them, ω s It is represented as the weight vector of the peak passenger flow intensity of the station, ω s (s) represents the weight of site s, S represents the set of sites, ω l It is represented as the weight matrix of line passenger flow balance adjustment, ω l (l1, l2) represents the passenger flow adjustment weight between line l1 and line l2, L1 represents the set of lines l1, and L2 represents the set of lines l2.

6. The management method for demand-responsive scheduling applied to a smart public transportation system according to claim 1, characterized in that: The step S4, obtaining the second key requirement corresponding to the second requirement set, specifically includes: Based on the number of vehicles required for evacuating passenger flow during large-scale activities Vd and the number of buses that can be deployed c, the quantitative value of comprehensive emergency response capacity IER is calculated, which is specifically expressed as: Wherein, α represents the evacuation threshold coefficient, and its value range is (0, 1).

7. The management method for demand-responsive scheduling applied to a smart public transportation system according to claim 1 is characterized in that: The step S6, obtaining a demand-responsive public transport vehicle dispatching strategy, specifically includes: The second key demand and the third key demand are passed as input data to the intelligent scheduling decision model, and the relationship between the second key demand and the third key demand is comprehensively analyzed; Determine feedback instructions to generate demand-responsive bus dispatch strategies; Vehicle deployment decision: clearly indicate the source of the vehicle to be deployed and the specific vehicle number to be deployed; Departure interval adjustment decision: adjust the specific departure interval value according to the increase in passenger flow and the operation status of the vehicle; Driving route adjustment decision: Plan the vehicles that need to change their driving routes and the new driving routes, including the sequence of stops and the stop time at each stop. For vehicles that need to detour, clearly define the starting and end points of the detour as well as the main sections and intersections in between.

8. The management method for demand-responsive scheduling applied to a smart public transportation system according to claim 1, characterized in that: The S8, updating and maintaining the public transportation dispatching management system, specifically includes: Establish a real-time data update channel to continuously update the first key demand, the second key demand, the third key demand, and the demand-responsive bus dispatch strategy to the preset management database every 2 minutes; Test the data recovery mechanism regularly, simulate different types of failure scenarios, and verify the backup data.

9. A management system for demand-responsive scheduling applied to a smart public transportation system, comprising a system operation database, a system central processing module and a user information terminal, and a management method for demand-responsive scheduling applied to a smart public transportation system according to any one of claims 1 to 8, characterized in that: Also includes: Data collection module: used to collect multi-source data corresponding to demand-responsive public transportation in the smart public transportation system to obtain the first demand set and transmit it to the data integration module; Data integration module: used for integrating and storing the first requirement set collected by the data collection module, and the integrated storage processing is used for acquiring and storing the first key requirement corresponding to the first requirement set, and transmitting it to the real-time data analysis module; Real-time data analysis module: used to obtain a demand response analysis model, obtain a second demand set through the first key demand in the data integration module according to the demand response analysis model, and transmit it to the demand prediction and judgment module; Demand prediction and judgment module: used to obtain a demand judgment model, obtain the second key demand corresponding to the second demand set through the second demand set in the real-time data analysis module according to the demand judgment model, and transmit it to the vehicle monitoring module and the intelligent scheduling decision module; Vehicle monitoring module: used to monitor the operating status of the demand-responsive public transport vehicle in real time to obtain the third demand set, and perform feedback operation on the monitored demand-responsive public transport vehicle based on the second key demand of the demand prediction and judgment module. The feedback operation is used to obtain the third key demand corresponding to the third demand set and transmit it to the intelligent scheduling decision module; Intelligent dispatching decision module: used to obtain an intelligent dispatching decision model, and obtain a demand-responsive public transport dispatching strategy based on the intelligent dispatching decision model through the second key requirement of the demand prediction and judgment module and the third key requirement of the vehicle monitoring module; Passenger feedback module: used to collect passenger feedback data corresponding to the demand-responsive bus dispatch strategy implemented in the intelligent dispatch decision module, and transmit it to the system update and maintenance module; System update and maintenance module: used to receive passenger feedback data from the passenger feedback module, continuously update and maintain the corresponding database of the demand-responsive bus dispatch management system, and transmit the updated maintenance data to the data integration module for storage; The system operation database includes all data texts of the demand-responsive bus scheduling management system, and collects information texts output by each module in real time. The system central processing module is used for information text instructions output by each module in the central control method, and the user information terminal is an information output device for receiving the demand-responsive bus scheduling management system.

10. A management system for demand-responsive scheduling applied to a smart public transportation system according to claim 9, characterized in that: The passenger feedback module collects passenger feedback data corresponding to the implementation of the demand-responsive public transport vehicle dispatching strategy, specifically including: Collecting passenger feedback data through passenger feedback terminals, including touch terminals installed inside demand-responsive buses, mobile applications, and social media; Passenger feedback data includes the degree of crowding in the vehicle, vehicle punctuality, riding comfort, and abnormal problems; Abnormal problems include but are not limited to abnormal vehicle shaking and severe odor.

Images