Intelligent people flow sensing and bus route self-adaptive adjusting system and intelligent people flow sensing and bus route self-adaptive adjusting device

Abstract

The invention relates to the technical field of urban public transportation, and discloses an intelligent passenger flow perception and bus route adaptive adjustment system and device, and the adjustment system is composed of a data collection module, a data processing module, a passenger flow prediction and event detection module, a dynamic scheduling and route adjustment module, and an information release and user interaction module. According to the method, the characteristics of passenger flow density, flow direction, peak period and the like are extracted, the passenger flow change from a few minutes to a few hours in the future is predicted based on real-time data, and the passenger flow trend from a few days to a few weeks in the future is predicted in combination with historical data and special event information such as large-scale activities, traffic congestion and weather change. By automatically identifying the influence of the special event on the passenger flow, the passenger flow peak or the abnormal passenger flow condition can be predicted in advance, the module automatically adjusts the bus route and the departure time according to the passenger flow prediction result, and the beneficial effect of adjusting the bus route in real time according to the passenger flow distribution in the high stage or the special event period is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of urban public transportation, and in particular to an intelligent passenger flow sensing and bus line adaptive adjustment system and a device thereof. Background Art

[0002] The optimization of bus departure schedule is a complex process. On the one hand, when the total number of bus departures is too small, although it will reduce the operating costs of bus companies, it will also cause passengers to wait too long, and may also cause buses to be too crowded, reducing travelers' satisfaction with bus travel. When the number of bus departures is too large, it may aggravate traffic congestion on urban roads, causing buses to arrive at bus stops continuously, resulting in a "string of buses" phenomenon, which not only cannot effectively reduce travelers' waiting time, but also causes a waste of social resources and increases bus operating costs. On the other hand, based on the determined number of bus departures, unreasonable departure intervals will lead to the bus capacity being unable to meet the residents' bus travel needs, resulting in buses being too crowded at local times or having many empty seats, resulting in a waste of bus capacity.

[0003] In order to solve the above-mentioned problem, a method for dynamically optimizing an adaptive bus departure schedule is disclosed in the prior art with a publication number of CN 104157132 A, and the steps are as follows: determining the full-day working period T of bus line l, the rated passenger capacity C of the bus service vehicle, the maximum passenger capacity Cs and the bus departure interval tm; determining the distribution of the cross-sectional passenger flow Pijlk of bus line l between station i and adjacent station j in the kth period; matching the cross-sectional passenger flow data Pijlk(1) of the first bus fed back in real time during the operation of bus line l between station i and station j with the historical bus station passenger flow cross-sectional cumulative distribution curve on bus line l, predicting the cross-sectional passenger flow demand distribution Pijlk(2) of the second bus, and determining the departure time T12 of the second bus; and using a recursive method to determine the bus departure schedule for the full-day working period T of bus line l.

[0004] Although historical passenger flow data is used for matching and prediction, changes in passenger flow demand are often complex and prediction models may have errors, especially during peak passenger flow periods or special events. The distribution of passenger flow will change significantly in different time periods, weather conditions, holidays and other special circumstances. The model cannot fully adapt to all situations, resulting in errors in bus route adjustments. Summary of the invention

[0005] Technical issues solved:

[0006] In view of the deficiencies of the prior art, the present invention provides an intelligent passenger flow perception and bus route adaptive adjustment system and device thereof, which has the advantages of real-time adjustment of bus routes according to passenger flow distribution during high-frequency periods or special events, and wider adaptability of bus route adjustment optimization, thereby solving the problems of the above-mentioned technologies.

[0007] Technical solution:

[0008] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an intelligent passenger flow perception and bus route adaptive adjustment system, wherein the adjustment system is composed of a data acquisition module, a data processing module, a passenger flow prediction and event detection module, a dynamic scheduling and route adjustment module, and an information release and user interaction module;

[0009] The data collection module collects passenger flow data in real time through sensors deployed at bus stops, hubs, and key sections: cameras, infrared sensors, and Wi-Fi probes;

[0010] The data processing module is used to merge data from different data sources to generate a unified passenger flow data set, use a stream processing engine to process and analyze the passenger flow data in real time, and extract the characteristics of the passenger flow data, including passenger flow density, flow direction, and peak hours;

[0011] The passenger flow prediction and event detection module predicts passenger flow changes in the next few minutes to hours based on real-time data, and predicts passenger flow trends in the next few days to weeks based on historical data and special event information, and automatically identifies special events: the impact of large-scale events, traffic congestion, and weather changes on passenger flow;

[0012] The dynamic scheduling and route adjustment module automatically adjusts bus routes and departure times according to passenger flow prediction results, updates bus scheduling plans in real time, and adjusts bus routes and departure times;

[0013] The information publishing and user interaction module publishes real-time updated bus information through display screens at bus stops, mobile applications, and website channels.

[0014] Preferably, the crowd flow data in the data collection module is calculated as follows: Where ρ is the crowd density, number of people / area; A is the area of ​​the detection area, and N is the number of people;

[0015] The flow rate is calculated as: Among them: v is the average speed of people flow, t is a certain distance; d is time;

[0016] The crowd flow is calculated as: Q = ρ × v × A; where: Q is the crowd flow;

[0017] Calculation of crowd residence time: Where: τ is the average stay time of the crowd.

[0018] Preferably, the flow direction calculation in the data processing module is:

[0019]

[0020] It is used to calculate the movement of people from point P1 (x1, y1) to point P2 (x2, y2) within a certain period of time, and θ is the flow direction.

[0021] Preferably, the data processing module also calculates the peak hours, the different time periods T in a certain day i The corresponding passenger flow is Q i , then the peak period T calculation formula is:

[0022]

[0023] in: is the index corresponding to the maximum value, that is, time period T i .

[0024] Preferably, the real-time passenger flow prediction calculation in the passenger flow prediction and time detection module is:

[0025]

[0026] Among them: the current time is t, and the passenger flow data at the past n time points is Q t -1,Q t -2,…,Q t -n, the passenger flow at the next k time points is is the predicted passenger flow at the kth time point in the future; θ j are the parameters of the MA model;

[0027] Historical data combined with special event information is calculated as:

[0028]

[0029] Among them: historical passenger flow data is Q h , special event information is E, including large-scale activities, traffic congestion, and weather changes. The regression model is used to predict the passenger flow trend. The predicted passenger flow in the next m days is is the predicted passenger flow for the next m days; E h+m Special event information for the future mth day.

[0030] Preferably, the automatic identification of special events in the passenger flow prediction and event detection module is calculated as follows:

[0031]

[0032] Where: μ is the mean of historical data; τ is the threshold for anomaly detection.

[0033] Preferably, the formula for adjusting bus routes based on passenger flow density in the dynamic scheduling and route adjustment module is:

[0034]

[0035] Where: f new is the adjusted departure frequency; ρ is the passenger flow density in the current area; k is the adjustment coefficient, which is 1;

[0036] The predicted peak passenger flow period is T peak , adjust the departure time to cope with the passenger flow during peak hours, assuming that the original departure timetable is t i , the adjusted departure timetable is t' i , the adjustment formula is:

[0037]

[0038] Where: t' i is the adjusted departure time; Δt is the adjustment time interval.

[0039] Preferably, the real-time scheduling plan update calculation in the dynamic scheduling and line adjustment module is:

[0040]

[0041] Among them: passenger flow data is Q t , the predicted future passenger flow is The adjustment factor of the scheduling plan is α, which is 0.5.

[0042] Preferably, the real-time bus information update expression in the information release and user interaction module is:

[0043] t next =t+Δt

[0044] Where: t next is the time of the next information update; Δt is the information update frequency, in seconds or minutes.

[0045] An intelligent crowd flow sensing and bus route adaptive adjustment device, the device is used to run an adjustment system, the device includes a display screen and a terminal connected to the display screen, the terminal is used to run the adjustment system and project its output results onto the display screen.

[0046] Compared with the prior art, the present invention provides an intelligent passenger flow sensing and bus route adaptive adjustment system and device thereof, which has the following beneficial effects:

[0047] 1. The present invention uses a data acquisition module to collect real-time passenger flow data through sensors deployed at bus stops, hubs, and key sections. These data include key information such as passenger flow, passenger flow speed, and crowd residence time. The data processing module integrates data from different data sources to generate a unified passenger flow data set, and uses a stream processing engine to process and analyze passenger flow data in real time to extract characteristics such as passenger flow density, flow direction, and peak hours. Based on real-time data, the passenger flow changes in the next few minutes to hours are predicted, and combined with historical data and special event information: large-scale activities, traffic congestion, weather changes, the passenger flow trend in the next few days to weeks is predicted. By automatically identifying the impact of special events on passenger flow, passenger flow peaks or abnormal passenger flow conditions can be predicted in advance. According to the passenger flow prediction results, the module automatically adjusts the bus routes and departure times, achieving the beneficial effect of real-time adjustment of bus routes according to the passenger flow distribution during high-frequency periods or special events.

[0048] 2. The present invention uses a stream processing engine through a data processing module to process and analyze passenger flow data in real time, and extracts key features such as passenger flow density, flow direction, peak hours, etc. The system can respond to passenger flow changes in a short time and has stronger adaptability. The passenger flow prediction and event detection module predicts future passenger flow changes based on real-time data, and combines historical data and special event information: large-scale activities, traffic congestion, weather changes, and predicts passenger flow trends in the next few days to weeks. The dynamic scheduling and route adjustment module automatically adjusts bus routes and departure times according to passenger flow prediction results. The information release and user interaction module releases real-time updated bus information through the display screen, mobile application, and website channels of the bus station. Passengers can obtain the latest bus route and departure time information in time, effectively reducing waiting time and improving travel experience, achieving the beneficial effect of wider adaptability of bus route adjustment and optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 Schematic diagram of the system of the present invention. DETAILED DESCRIPTION

[0050] 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.

[0051] See also Figure 1, intelligent passenger flow perception and bus route adaptive adjustment system, the adjustment system consists of a data acquisition module, a data processing module, a passenger flow prediction and event detection module, a dynamic scheduling and route adjustment module and an information release and user interaction module;

[0052] The data collection module collects passenger flow data in real time through sensors deployed at bus stops, hubs, and key sections: cameras, infrared sensors, and Wi-Fi probes;

[0053] The data processing module is used to merge data from different data sources to generate a unified passenger flow data set, use a stream processing engine to process and analyze the passenger flow data in real time, and extract the characteristics of the passenger flow data, including passenger flow density, flow direction, and peak hours;

[0054] The passenger flow prediction and event detection module predicts passenger flow changes in the next few minutes to hours based on real-time data, and predicts passenger flow trends in the next few days to weeks based on historical data and special event information, and automatically identifies special events: the impact of large-scale events, traffic congestion, and weather changes on passenger flow;

[0055] The dynamic scheduling and route adjustment module automatically adjusts bus routes and departure times according to passenger flow prediction results, updates bus scheduling plans in real time, and adjusts bus routes and departure times;

[0056] The information publishing and user interaction module publishes real-time updated bus information through display screens at bus stops, mobile applications, and website channels.

[0057] The data collection module collects passenger flow data in real time through sensors deployed at bus stops, hubs, and key sections of roads. These data include key information such as passenger volume, passenger flow speed, and crowd residence time. The data processing module integrates data from different data sources to generate a unified passenger flow data set. The stream processing engine is used to process and analyze passenger flow data in real time, extract characteristics such as passenger flow density, flow direction, and peak hours, and predict passenger flow changes in the next few minutes to hours based on real-time data.

[0058] Preferably, the crowd flow data in the data collection module is calculated as follows: Where ρ is the crowd density, number of people / area; A is the area of ​​the detection area, and N is the number of people;

[0059] The flow rate is calculated as: Among them: v is the average speed of people flow, t is a certain distance; d is time;

[0060] The crowd flow is calculated as: Q = ρ × v × A; where: Q is the crowd flow;

[0061] Calculation of crowd residence time: Where: τ is the average stay time of the crowd.

[0062] Preferably, the flow direction calculation in the data processing module is:

[0063]

[0064] It is used to calculate the movement of people from point P1 (x1, y1) to point P2 (x2, y2) within a certain period of time, and θ is the flow direction.

[0065] Preferably, the data processing module also calculates the peak hours, the different time periods T in a certain day i The corresponding passenger flow is Q i , then the peak period T calculation formula is:

[0066]

[0067] in: is the index corresponding to the maximum value, that is, time period T i .

[0068] Preferably, the real-time passenger flow prediction calculation in the passenger flow prediction and time detection module is:

[0069]

[0070] Among them: the current time is t, and the passenger flow data at the past n time points is Q t -1,Q t -2,…,Q t -n, the passenger flow at the next k time points is is the predicted passenger flow at the kth time point in the future; θ j are the parameters of the MA model;

[0071] Historical data combined with special event information is calculated as:

[0072]

[0073] Among them: historical passenger flow data is Q h , special event information is E, including large-scale activities, traffic congestion, and weather changes. The regression model is used to predict the passenger flow trend. The predicted passenger flow in the next m days is is the predicted passenger flow for the next m days; E h+m Special event information for the future mth day.

[0074] Preferably, the automatic identification of special events in the passenger flow prediction and event detection module is calculated as follows:

[0075]

[0076] Where: μ is the mean of historical data; τ is the threshold for anomaly detection.

[0077] Preferably, the formula for adjusting bus routes based on passenger flow density in the dynamic scheduling and route adjustment module is:

[0078]

[0079] Where: f new is the adjusted departure frequency; ρ is the passenger flow density in the current area; k is the adjustment coefficient, which is 1;

[0080] The predicted peak passenger flow period is T peak , adjust the departure time to cope with the passenger flow during peak hours, assuming that the original departure timetable is t i , the adjusted departure timetable is t' i , the adjustment formula is:

[0081]

[0082] Where: t' i is the adjusted departure time; Δt is the adjustment time interval.

[0083] Preferably, the real-time scheduling plan update calculation in the dynamic scheduling and line adjustment module is:

[0084]

[0085] Among them: passenger flow data is Q t , the predicted future passenger flow is The adjustment factor of the scheduling plan is α, which is 0.5.

[0086] Combining historical data and special event information: large-scale events, traffic congestion, weather changes, the module predicts passenger flow trends in the next few days to weeks. By automatically identifying the impact of special events on passenger flow, peak or abnormal passenger flow conditions can be predicted in advance. Based on the passenger flow prediction results, the module automatically adjusts bus routes and departure times.

[0087] Preferably, the real-time bus information update expression in the information release and user interaction module is:

[0088] t next =t+Δt

[0089] Where: t next is the time of the next information update; Δt is the information update frequency, in seconds or minutes.

[0090] An intelligent crowd flow sensing and bus route adaptive adjustment device, the device is used to run an adjustment system, the device includes a display screen and a terminal connected to the display screen, the terminal is used to run the adjustment system and project its output results onto the display screen.

[0091] The data processing module uses the stream processing engine to process and analyze passenger flow data in real time, extracting key features such as passenger flow density, flow direction, peak hours, etc. The system can respond to passenger flow changes in a short time and is more adaptable. The passenger flow prediction and event detection module predicts future passenger flow changes based on real-time data, and combines historical data and special event information: large-scale events, traffic congestion, weather changes, to predict passenger flow trends in the next few days to weeks. The dynamic scheduling and route adjustment module automatically adjusts bus routes and departure times according to passenger flow prediction results. The information release and user interaction module releases real-time updated bus information through the display screens, mobile applications, and website channels at bus stops.

[0092] Passengers can obtain the latest bus routes and departure time information in a timely manner, effectively reducing waiting time and improving travel experience

[0093] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. Intelligent passenger flow perception and bus route adaptive adjustment system, characterized by: The adjustment system is composed of a data acquisition module, a data processing module, a passenger flow prediction and event detection module, a dynamic scheduling and route adjustment module, and an information release and user interaction module; The data collection module collects passenger flow data in real time through sensors deployed at bus stops, hubs, and key sections: cameras, infrared sensors, and Wi-Fi probes; The data processing module is used to merge data from different data sources to generate a unified passenger flow data set, use a stream processing engine to process and analyze the passenger flow data in real time, and extract the characteristics of the passenger flow data, including passenger flow density, flow direction, and peak hours; The passenger flow prediction and event detection module predicts passenger flow changes in the next few minutes to hours based on real-time data, and predicts passenger flow trends in the next few days to weeks based on historical data and special event information, and automatically identifies special events: large-scale events, traffic congestion, and the impact of weather changes on passenger flow; The dynamic scheduling and route adjustment module automatically adjusts bus routes and departure times according to passenger flow prediction results, updates bus scheduling plans in real time, and adjusts bus routes and departure times; The information publishing and user interaction module publishes real-time updated bus information through display screens at bus stops, mobile applications, and website channels.

2. The intelligent crowd flow sensing and bus route adaptive adjustment system according to claim 1 is characterized by: The flow data in the data collection module is calculated as: Where ρ is the crowd density, number of people / area; A is the area of ​​the detection area, and N is the number of people; The flow rate is calculated as: Among them: v is the average speed of people flow, t is a certain distance; A is time; The crowd flow is calculated as: Q = ρ × v × A; where: Q is the crowd flow; Calculation of crowd residence time: Where: τ is the average stay time of the crowd.

3. The intelligent crowd flow sensing and bus route adaptive adjustment system according to claim 1 is characterized by: The flow direction calculation in the data processing module is calculated as: It is used to calculate the movement of people from point P1 (x1, y1) to point P2 (x2, y2) within a certain period of time, and θ is the flow direction.

4. The intelligent crowd flow sensing and bus route adaptive adjustment system according to claim 3 is characterized by: The data processing module also calculates the peak hours, the different time periods T in a certain day i The corresponding passenger flow is Q i , then the peak period T calculation formula is: in: is the index corresponding to the maximum value, that is, time period T i .

5. The intelligent crowd flow sensing and bus route adaptive adjustment system according to claim 4 is characterized by: The real-time passenger flow prediction calculation in the passenger flow prediction and time detection module is: Among them: the current time is t, and the passenger flow data at the past n time points is Q t -1,Q t -2,…,Q t -n, the passenger flow at the next k time points is is the predicted passenger flow at the kth time point in the future; θ j are the parameters of the MA model; Historical data combined with special event information is calculated as: Among them: historical passenger flow data is Q h , special event information is E, including large-scale activities, traffic congestion, and weather changes. The regression model is used to predict the passenger flow trend. The predicted passenger flow in the next m days is is the predicted passenger flow for the next m days; E h+m Special event information for the future mth day.

6. The intelligent crowd flow sensing and bus route adaptive adjustment system according to claim 5 is characterized by: The calculation of automatically identifying special events in the passenger flow prediction and event detection module is: Where: μ is the mean of historical data; τ is the threshold for anomaly detection.

7. The intelligent crowd flow sensing and bus route adaptive adjustment system according to claim 6 is characterized by: The formula for adjusting bus routes based on passenger flow density in the dynamic scheduling and route adjustment module is: Where: f new is the adjusted departure frequency; ρ is the passenger flow density in the current area; k is the adjustment coefficient, which is 1; The predicted peak passenger flow period is T peak , adjust the departure time to cope with the passenger flow during peak hours, assuming that the original departure timetable is t i , the adjusted departure timetable is t' i , the adjustment formula is: Where: t' i is the adjusted departure time; Δt is the adjustment time interval.

8. The intelligent crowd flow sensing and bus route adaptive adjustment system according to claim 1 is characterized by: The real-time scheduling plan update calculation in the dynamic scheduling and line adjustment module is: Among them: passenger flow data is Q t , the predicted future passenger flow is The adjustment factor of the scheduling plan is α, which is 0.

5.

9. The intelligent crowd flow sensing and bus route adaptive adjustment system according to claim 1 is characterized by: The real-time bus information update expression in the information release and user interaction module is: t next =t+Δt Where: t next is the time of the next information update; Δt is the information update frequency, in seconds or minutes.

10. Intelligent crowd flow sensing and bus route adaptive adjustment device, characterized in that: The device is used to run the adjustment system described in claim 1, and the device includes a display screen and a terminal connected to the display screen. The terminal is used to run the adjustment system and project its output results onto the display screen.

Images