Urban service optimization system based on group intelligence

Abstract

The invention discloses an urban service optimization system based on swarm intelligence, and the system comprises the steps: obtaining historical taking data and urban road network data, building a database and an urban road network coordinate system, analyzing the delay time of a previous bus, evaluating the delay deviation, analyzing the stations, which coincide with other bus routes, in remaining routes, and carrying out the optimization of the urban service. The method comprises the following steps: acquiring historical riding data of a target bus, evaluating shunting deviation, further predicting a full-load rate of the target bus arriving at remaining stations according to the historical riding data, adjusting departure time of a next bus according to the predicted full-load rate, analyzing riding information of passengers, evaluating passenger flow when the bus stops at the target station, and judging whether to carry out early warning analysis or not. If yes, the driving states of the motor vehicles and the non-motor vehicles near the target station are further evaluated, an early warning result is obtained, and broadcasting is controlled to send out safety reminding according to the analyzed early warning result, and the method has the advantages of improving the passenger travel efficiency and guaranteeing the bus passenger safety.

Description

Technical Field

[0001] The present invention relates to the technical field of bus optimization, and specifically to an urban service optimization system based on swarm intelligence. Background Technique

[0002] With the rapid development of cities in recent years, the public transportation system has become an important means for urban residents to travel. At present, urban residents can solve their travel needs such as going to work, school, and grocery shopping by taking the bus. However, with the rapid growth of residents and the expansion of the road scale, the original fixed bus departure time interval is likely to cause problems such as too long waiting time for residents or being unable to get on the bus. Residents pay more attention to travel efficiency. Moreover, most of the areas in front of bus stops are non-motorized lanes, and there are more and more motor vehicles and non-motor vehicles on the road. When the bus stops, due to the sudden opening of the door, passengers, moving motor vehicles and non-motor vehicles fail to notice and avoid in time, which is likely to cause accidental injury accidents.

[0003] Therefore, it is necessary to design an urban service optimization system based on swarm intelligence to improve the travel efficiency of passengers and ensure the safety of bus passengers. Summary of the Invention

[0004] The purpose of the present invention is to provide an urban service optimization system based on swarm intelligence to solve the problems raised in the above background technique.

[0005] To solve the above technical problems, the present invention provides the following technical solution: An urban service optimization system based on swarm intelligence, characterized in that: it includes a data collection module, a departure time optimization module, a warning analysis module, and a broadcast reminder module. The data collection module is used to obtain historical riding data, establish a historical database, obtain urban road network data, and establish an urban road network database and an urban road network coordinate system;

[0006] The departure time optimization module is used to analyze the delay duration of the previous bus, evaluate the impact of the delay duration on the number of boarding and alighting passengers, analyze the platforms on the remaining route of the previous bus that coincide with other bus routes, evaluate the impact of passenger diversion on the load factor, and according to the historical riding data, combined with the delay deviation and the diversion deviation, predict the load factor of the target bus arriving at the remaining platforms. According to the predicted load factor, evaluate the operating status of the target bus and adjust the departure time of the next bus;

[0007] The warning analysis module is used to analyze the riding information of passengers, evaluate the passenger flow when the bus stops at the target platform, judge whether to perform warning analysis, and if necessary, further evaluate the driving status of motor vehicles and non-motor vehicles near the target platform to obtain a warning result;

[0008] The broadcast reminder module is used to control the in-bus broadcast, platform broadcast, and on-vehicle broadcast of motor vehicles according to the analyzed early warning results, and issue arrival reminders and safety reminders.

[0009] According to the above technical solution, the departure time optimization module includes a bus operation status analysis module and a departure time adjustment module. The bus operation status analysis module is used to analyze the delay duration of the previous bus, evaluate the impact of the delay duration on the number of boarding and alighting passengers, analyze the platforms on the remaining route of the previous bus that coincide with other bus routes, evaluate the impact of passenger diversion on the load factor, and predict the load factor of the target bus arriving at the remaining platforms based on historical riding data, combined with the delay deviation and diversion deviation. The departure time adjustment module adjusts the departure time of the next bus according to the predicted load factor and evaluates the operation status of the target bus.

[0010] According to the above technical solution, the bus operation status analysis module includes a delay deviation analysis sub-module, a diversion deviation analysis sub-module, and a load factor prediction sub-module. The delay deviation analysis sub-module is used to analyze the delay duration of the previous bus and evaluate the impact of the delay duration on the number of boarding and alighting passengers. The diversion deviation analysis sub-module is used to analyze the platforms on the remaining route of the previous bus that coincide with other bus routes and evaluate the impact of passenger diversion on the load factor. The load factor prediction sub-module is used to predict the load factor of the target bus arriving at the remaining platforms based on historical riding data, combined with the delay deviation and diversion deviation.

[0011] According to the above technical solution, the early warning analysis module includes a bus arrival analysis unit and a platform early warning analysis unit. The bus arrival analysis unit is used to analyze the distance between the bus and the platform, determine whether the bus stops at the platform, and issue a stop signal. The platform early warning analysis unit analyzes the riding information characteristics of passengers, obtains the passenger flow volume when the bus stops at the platform, determines whether to conduct early warning analysis, and obtains the platform early warning result.

[0012] According to the above technical solution, the early warning analysis module further includes a passenger early warning analysis unit and a motor vehicle early warning analysis unit. The passenger early warning analysis unit is used to analyze the driving state of non-motor vehicles in front of the target platform after receiving the early warning analysis signal, evaluate the safety index when passengers get off the bus at the target platform where the bus stops, and obtain the passenger early warning result. The motor vehicle early warning analysis unit is used to analyze the position characteristics of the motor vehicle and the target platform after receiving the early warning analysis signal and obtain the motor vehicle early warning result.

[0013] According to the above technical solution, the operation method of the urban service optimization system includes the following steps:

[0014] Step S1: Obtain historical riding data, establish a historical database, obtain urban road network data, and establish an urban road network database and an urban road network coordinate system;

[0015] Step S2: Analyze the delay duration of the previous bus, evaluate the impact of the delay duration on the number of boarding and alighting passengers, analyze the platforms on the remaining route of the previous bus that coincide with other bus routes, evaluate the impact of passenger diversion on the load factor, predict the load factor of the target bus arriving at the remaining platforms based on historical riding data, combined with the delay deviation and the diversion deviation, evaluate the operating status of the target bus according to the predicted load factor, and adjust the departure time of the next bus;

[0016] Step S3: Analyze the riding information of passengers, evaluate the passenger flow when the bus stops at the target platform, determine whether to conduct early warning analysis, and if necessary, further evaluate the driving status of motor vehicles and non-motor vehicles near the target platform to obtain the early warning result;

[0017] Step S4: Control the in-bus broadcast, platform broadcast, and motor vehicle on-vehicle broadcast according to the analyzed early warning result to issue safety reminders.

[0018] According to the above technical solution, the step S1 further includes the following steps:

[0019] Step S11: Obtain historical riding data, including the number of boarding and alighting passengers at each platform of each bus route in each time period, establish a historical database and enter the data into the database;

[0020] Step S12: Obtain urban road network data, including urban road network diagrams, road names, road lengths, road curvatures, road slopes, and road intersection positions, establish an urban road network database and enter the data into the database, establish an urban road network coordinate system, mark the target bus route, mark the inflection point coordinates and the coordinates of each platform point of the target bus route, and obtain the coordinates of the bus position point, motor vehicle position point, and non-motor vehicle position point in real time.

[0021] According to the above technical solution, the step S2 further includes the following steps:

[0022] Step S21: Obtain the total number of passengers N in the previous bus 总 and the maximum passenger capacity N max , and calculate the real-time load factor of the previous bus

[0023] Step S22: Mark a starting timestamp when the previous bus departs from the starting platform, and mark a platform timestamp every time it arrives at a platform during the driving process. The difference between the platform timestamp and the starting timestamp is used as the actual running time T of the previous bus arriving at this platformi , T i represents the actual running time of the bus from the starting platform to platform i. Retrieve the running time threshold t of the bus from the starting platform to platform i from the database i . If T i < t i , then the bus is late. Calculate the late duration T 晚点 = T i - t i . According to the late duration T of the bus 晚点 retrieve the corresponding boarding passenger number deviation coefficient μ and alighting passenger number deviation coefficient v from the database i and i . According to the historical riding data, count the boarding passenger number N and alighting passenger number M of the original target bus at each platform i and i . Obtain the predicted boarding passenger number μ i N i and predicted alighting passenger number v i M i ;

[0024] Step S23: Obtain the platforms where the remaining route of the target bus coincides with other bus routes. If the number of coincident platforms N 重 ≥2, then mark this bus route as a diverted bus route, and the bus corresponding to the diverted bus route as a diverted bus. According to the number of coincident platforms N 重 retrieve the corresponding dilution weight ε from the database j , obtain the number k of diverted buses at each platform j , and calculate the diversion influence coefficient where j = 1, 2…, n, j represents the number of platforms where the diverted bus coincides with the target bus, k j represents that there are k diverted buses with the number of coincident platforms j, and ε j represents that the dilution weight corresponding to the number of coincident platforms j is ε;

[0025] Step S24: According to the obtained predicted boarding passenger number μ i N i and predicted alighting passenger number v i M i and the diversion influence coefficient ξ, predict the full load rate of the previous bus on the target route when arriving at the remaining platforms where i = 1, 2,..., n, N 总 is the total number of passengers in the bus. Compare the predicted full load rate P i and the full load rate threshold θ at each platform within the cycle. If P iIf it is >θ, the previous bus is in an abnormal operation state, and the next bus is immediately dispatched to coordinate the bus operation state of the target bus route. If P remains unchanged throughout the cycle i ≤θ, the previous bus is in a normal operation state, and the next bus departs according to the original cycle.

[0026] According to the above technical solution, step S3 further includes the following steps:

[0027] Step S31: Obtain the coordinate of the bus position point in the urban road network coordinate system, traverse the target bus route according to the driving direction of the bus, stop when reaching the platform point, and use it as the target platform point. Among them, the bus position point, the inflection point, and the target platform point are used as m + 1 division nodes to divide the target route into m road segments, and obtain the position coordinates (a i , b i ) of the m + 1 division nodes according to the traversal order;

[0028] Step S32: Obtain the road curvatures Q 1_2 , Q 2_3 , ……, Q m_m+1 of the road segments between the m + 1 division nodes, where Q m_m+1 refers to the road curvature of the road segment between the mth division node and the (m + 1)th division node. Retrieve the corresponding curvature influence coefficients α 1_2 , α 2_3 , ……, α m_m+1 from the database according to the road curvature, and obtain the road slopes P 1_2 , P 2_3 , ……, P m_m+1 of the road segments between the m + 1 division nodes, where P m_m+1 refers to the road slope of the road segment between the mth division node and the (m + 1)th division node. Retrieve the corresponding slope influence coefficients β 1_2 , β 2_3 , ……, β m_m+1 from the database;

[0029] Step S33: Calculate the distance between the bus and the target platform according to the position coordinates of each division node and the road curvature and road slope of the road segments between each division node In the formula, k = 1, 2,..., m. If the distance L between the bus and the target platform is less than or equal to the threshold, it is determined that the bus is about to stop at the target platform, and a signal that the bus is about to arrive at the station is issued.

[0030] According to the above technical solution, step S33 further includes the following steps:

[0031] Step S331: After receiving the signal that the bus is about to arrive at the station, obtain the riding information of passengers in the database, and count the number of people getting off the target bus at the target station as M 下 and the number of people getting on the bus as M 上 , calculate the passenger flow at the target station K = M 下 +M 上 . If the passenger flow K is 0, no early warning analysis is carried out. If the passenger flow K is greater than 0, it is judged that early warning analysis is required, an early warning analysis signal is sent, and the broadcast of the target station is controlled to give safety reminders to the waiting passengers at the target station and the non-motor vehicles in front of the target station;

[0032] Step S332: After receiving the early warning analysis signal, further obtain the position coordinates (a1, b1) of the target station, obtain the position coordinates (a2, b2) of all non-motor vehicles on the road section where the target bus is about to arrive at the station, obtain the road curvature Q1 and road slope P1 of the road section where the station is located, retrieve the corresponding curvature influence coefficient α1 and slope influence coefficient β1, and calculate the distance between each non-motor vehicle and the target station In the formula, (a1, b1) represents the position coordinates of the station, (a2, b2) represents the position coordinates of the non-motor vehicle, identify the driving speed V of each non-motor vehicle 非 , according to the driving speed V 非 retrieve the corresponding non-motor vehicle early warning distance threshold between each non-motor vehicle and the target station from the database Compare L1 with the non-motor vehicle early warning distance threshold If there is in the non-motor vehicle flow, then control the in-bus broadcast to give safety reminders to passengers;

[0033] Step S333: After receiving the early warning analysis signal, further obtain the position coordinates (a3, b3) of all motor vehicles on the road section where the bus is about to arrive at the station, obtain the position coordinates (a1, b1) of the target station, obtain the road curvature Q1 and road slope P1 of the road section where the station is located, retrieve the corresponding curvature influence coefficient α1 and slope influence coefficient β1, and calculate the distance between each motor vehicle and the target station In the formula, (a1, b1) represents the position coordinates of the station, (a3, b3) represents the position coordinates of the motor vehicle. Compare L2 with the motor vehicle early warning distance threshold φ. If L2 < φ, mark the motor vehicle as within the early warning reminder range and control the in-vehicle broadcast of the motor vehicle to give safety reminders to the motor vehicle driver.

[0034] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: By analyzing the impact of delays and diversions, predicting the full load rate of buses based on historical riding data, evaluating the operating status of the previous bus according to the predicted full load rate, adjusting the departure time of the next bus, alleviating the operating pressure, improving the travel efficiency of passengers, reducing problems such as long waiting times for passengers due to excessive passenger flow, optimizing the allocation of bus resources, effectively improving the operating efficiency of buses, issuing safety reminders to passengers by analyzing the non-motor vehicle traffic flow state between the bus and the platform when passengers get off the bus, ensuring the safety of passengers getting off the bus, issuing safety reminders to non-motor vehicles traveling between the bus and the platform by analyzing whether the bus stops at the platform and the passenger flow getting on and off at the platform, enabling non-motor vehicles to have time to slow down and pay attention to avoiding the flow of people, ensuring the safety of passengers and non-motor vehicles, and issuing safety reminders to moving motor vehicles by analyzing the distance between the motor vehicle and the platform, enabling the motor vehicle to avoid in time, facilitating the bus to stop at the platform, and ensuring the safety of motor vehicles and buses. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0036] Figure 1 is a schematic diagram of the system module composition of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0037] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0038] Please refer to Figure 1 , the present invention provides a technical solution: An urban service optimization system based on swarm intelligence, including a data collection module, a departure time optimization module, a warning analysis module, and a broadcast reminder module. The data collection module is used to obtain historical riding data, establish a historical database, obtain urban road network data, and establish an urban road network database and an urban road network coordinate system;

[0039] The departure time optimization module is used to analyze the delay duration of the previous bus, evaluate the impact of the delay duration on the number of boarding and alighting passengers, analyze the platforms on the remaining route of the previous bus that coincide with other bus routes, evaluate the impact of passenger diversion on the load factor, predict the load factor of the target bus arriving at the remaining platforms based on historical riding data, combined with the delay deviation and diversion deviation, evaluate the operating status of the target bus based on the predicted load factor, and adjust the departure time of the next bus;

[0040] The early warning analysis module is used to analyze the riding information of passengers, evaluate the passenger flow when the bus stops at the target platform, determine whether to conduct early warning analysis, and if necessary, further evaluate the driving status of motor vehicles and non-motor vehicles near the target platform to obtain the early warning result;

[0041] The broadcast reminder module is used to control the in-bus broadcast, platform broadcast, and vehicle-mounted broadcast of motor vehicles according to the analyzed early warning result, and issue arrival reminders and safety reminders.

[0042] The departure time optimization module includes a bus operating status analysis module and a departure time adjustment module. The bus operating status analysis module is used to analyze the delay duration of the previous bus, evaluate the impact of the delay duration on the number of boarding and alighting passengers, analyze the platforms on the remaining route of the previous bus that coincide with other bus routes, evaluate the impact of passenger diversion on the load factor, predict the load factor of the target bus arriving at the remaining platforms based on historical riding data, combined with the delay deviation and diversion deviation. The departure time adjustment module evaluates the operating status of the target bus based on the predicted load factor and adjusts the departure time of the next bus.

[0043] The bus operating status analysis module includes a delay deviation analysis sub-module, a diversion deviation analysis sub-module, and a load factor prediction sub-module. The delay deviation analysis sub-module is used to analyze the delay duration of the previous bus and evaluate the impact of the delay duration on the number of boarding and alighting passengers. The diversion deviation analysis sub-module is used to analyze the platforms on the remaining route of the previous bus that coincide with other bus routes and evaluate the impact of passenger diversion on the load factor. The load factor prediction sub-module is used to predict the load factor of the target bus arriving at the remaining platforms based on historical riding data, combined with the delay deviation and diversion deviation.

[0044] The early warning analysis module includes a bus arrival analysis unit and a platform early warning analysis unit. The bus arrival analysis unit is used to analyze the distance between the bus and the platform, determine that the bus stops at the platform, and issue a stop signal. The platform early warning analysis unit analyzes the characteristics of the riding information of passengers, obtains the passenger flow when the bus stops at the platform, determines whether to conduct early warning analysis, and obtains the platform early warning result.

[0045] The early warning analysis module further includes a passenger early warning analysis unit and a motor vehicle early warning analysis unit. The passenger early warning analysis unit is used to analyze the driving state of non-motor vehicles in front of the target platform after receiving the early warning analysis signal, evaluate the safety index when passengers get off the bus at the target platform, and obtain the passenger early warning result. The motor vehicle early warning analysis unit is used to analyze the position characteristics of the motor vehicle and the target platform after receiving the early warning analysis signal, and obtain the motor vehicle early warning result.

[0046] The operation method of the urban service optimization system includes the following steps:

[0047] Step S1: Obtain historical riding data, establish a historical database, obtain urban road network data, and establish an urban road network database and an urban road network coordinate system;

[0048] Step S2: Analyze the delay duration of the previous bus, evaluate the impact of the delay duration on the number of passengers getting on and off, analyze the platforms on the remaining route of the previous bus that coincide with other bus routes, evaluate the impact of passenger diversion on the full load rate, predict the full load rate of the target bus arriving at the remaining platforms according to the historical riding data, combined with the delay deviation and the diversion deviation, evaluate the operating state of the target bus according to the predicted full load rate, and adjust the departure time of the next bus;

[0049] Step S3: Analyze the riding information of passengers, evaluate the passenger flow when the bus stops at the target platform, determine whether to perform early warning analysis, and if necessary, further evaluate the driving states of motor vehicles and non-motor vehicles near the target platform to obtain the early warning result;

[0050] Step S4: Control the in-bus broadcast, platform broadcast, and motor vehicle on-vehicle broadcast according to the analyzed early warning result to issue a safety reminder.

[0051] Step S1 further includes the following steps:

[0052] Step S11: Obtain historical riding data, including the number of passengers getting on and off at each platform of each bus route in each time period, establish a historical database and enter the data into the database;

[0053] Step S12: Obtain urban road network data, including urban road network diagrams, road names, road lengths, road curvatures, road slopes, and road intersection positions, establish an urban road network database, enter the data into the database, establish an urban road network coordinate system, mark the target bus route, mark the inflection point coordinates and the coordinates of each platform point of the target bus route, and obtain the bus position point coordinates, motor vehicle position point coordinates, and non-motor vehicle position point coordinates in real time.

[0054] Step S2 further includes the following steps:

[0055] Step S21: Obtain the total number N of passengers in the previous bus and the maximum passenger capacity N, and calculate the real-time full-load rate of the previous bus. 总 and the maximum passenger capacity N max , calculate the real-time full-load rate of the previous bus

[0056] Step S22: When the previous bus departs from the starting platform, mark a starting timestamp. When it arrives at each platform during the driving process, mark a platform timestamp. The difference between the platform timestamp and the starting timestamp is used as the actual running time T of the previous bus to reach this platform. T represents the actual running time of the bus from the starting platform to platform i. Retrieve the running time threshold t of the bus from the starting platform to platform i in the database. If T < t, it means the bus is late. Calculate the late duration T = T - t. According to the late duration T of the bus, retrieve the corresponding boarding number deviation coefficient μ and alighting number deviation coefficient v from the database. According to the historical riding data, count the boarding number N and alighting number M of the original target bus at each platform. According to the deviation of the late duration, obtain the predicted boarding number μN and predicted alighting number vM of the target bus at each platform. The late arrival affects the boarding number at each platform, and the change in the boarding number leads to the update of the alighting number. By calculating the late duration of the bus, the deviation of the boarding and alighting numbers at each platform is compensated, improving the accuracy of predicting the boarding and alighting numbers at each platform. i , T i represents the actual running time of the bus from the starting platform to platform i. Retrieve the running time threshold t of the bus from the starting platform to platform i in the database. If T i , if T i < t i , the bus is late. Calculate the late duration T 晚点 = T i - t i , according to the late duration T of the bus 晚点 retrieve the corresponding boarding number deviation coefficient μ i and alighting number deviation coefficient v i , according to the historical riding data, count the boarding number N i and alighting number M i of the original target bus at each platform. According to the deviation of the late duration, obtain the predicted boarding number μ i N i and predicted alighting number v i M i , the late arrival affects the boarding number at each platform, and the change in the boarding number leads to the update of the alighting number. By calculating the late duration of the bus, the deviation of the boarding and alighting numbers at each platform is compensated, improving the accuracy of predicting the boarding and alighting numbers at each platform;

[0057] Step S23: Obtain the platforms where the remaining route of the target bus coincides with other bus routes. If the number of coincident platforms N ≥ 2, mark this bus route as a diverted bus route, and the bus corresponding to the diverted bus route is a diverted bus. According to the number of coincident platforms N, retrieve the corresponding dilution weight ε from the database. Obtain the number k of diverted buses at each platform, and calculate the diversion influence coefficient 重 ≥ 2, mark this bus route as a diverted bus route, and the bus corresponding to the diverted bus route is a diverted bus. According to the number of coincident platforms N 重 retrieve the corresponding dilution weight ε from the database. Obtain the number k of diverted buses at each platform j , calculate the diversion influence coefficient j In the formula, j = 1, 2,..., n, j represents the number of platforms where the diverted bus coincides with the target bus, k represents that there are k diverted buses with the number of coincident platforms j, and ε j represents the dilution weight corresponding to the number of coincident platforms j, and k jIt is indicated that the dilution weight corresponding to the number of overlapping platforms being \(j\) is \(\varepsilon\). By analyzing the platforms overlapping with other bus routes, the degree of diversion of other buses to the target bus is evaluated. For example, if Bus A has two overlapping platforms with the remaining route of the target bus, and a certain passenger's bus travel plan's waiting platform and destination platform are those two overlapping platforms, then they can also choose to take Bus A, which relieves the riding pressure on the target bus. Bus A plays a role in diversion. By analyzing the diversion impact, the accuracy of predicting the full-load rate is improved;

[0058] Step S24: According to the obtained predicted boarding number \(\mu\) i N i and the predicted alighting number \(v\) i M i and the diversion impact coefficient \(\xi\), predict the full-load rate of the previous bus arriving at the remaining platforms on the target route In the formula, \(i = 1, 2, \cdots, n\), \(N\) 总 is the total number of passengers in the bus. During the period, compare the predicted full-load rate \(P\) of each platform i and the full-load rate threshold \(\theta\). If the situation of \(P\) i \(>\theta\) occurs, then the previous bus is in an abnormal operation state, and the next bus is immediately dispatched to coordinate the bus operation state of the target bus route. If \(P\) i \(\leq\theta\) always holds during the period, then the previous bus is in a normal operation state, and the next bus departs according to the original period. By analyzing the operation state of the previous bus, when an abnormal operation state occurs, the next bus receives the instruction and is immediately dispatched. The early departure relieves the operation pressure of the previous bus. For example, if the target bus is half an hour late and the number of waiting passengers at the subsequent platforms increases by 15 within half an hour, and the target bus cannot carry all the waiting passengers, the next bus needs to depart earlier to relieve the operation pressure, improve the travel efficiency of passengers, reduce problems such as long waiting times for passengers due to large passenger flows, optimize the allocation of bus resources, and effectively improve the operation efficiency of buses.

[0059] Step S3 further includes the following steps:

[0060] Step S31: Obtain the coordinate of the bus position point in the urban road network coordinate system. Traverse the target bus route according to the bus driving direction and stop when reaching the platform point, and use it as the target platform point. Among them, the bus position point, the inflection point, and the target platform point are used as \(m + 1\) division nodes to divide the target route into \(m\) road segments. Obtain the position coordinates \((a\) i , \(b\) i ) of the \(m + 1\) division nodes according to the traversal order;

[0061] Step S32: Obtain the road curvature \(Q\) of the road segments between the \(m + 1\) division nodes1_2 , Q 2_3 , ……, Q m_m+1 , where Q m_m+1 refers to the road curvature of the road segment between the m-th division node and the (m + 1)-th division node, and retrieves the corresponding curvature influence coefficient α from the database 1_2 , α 2_3 , ……, α m_m+1 , and obtains the road slope P of the road segment between the m + 1 division nodes 1_2 , P 2_3 , ……, P m_m+1 , where P m_m+1 refers to the road slope of the road segment between the m-th division node and the (m + 1)-th division node, and retrieves the corresponding slope influence coefficient β from the database 1_2 , β 2_3 , ……, β m_m+1 ;

[0062] Step S33: Calculate the distance between the bus and the target platform according to the position coordinates of each division node, the road curvature and road slope of the road segments between each division node In the formula, k = 1, 2,..., m. If the distance L between the bus and the target platform is less than or equal to the threshold, it is determined that the bus is about to stop at the target platform, and a signal that the bus is about to arrive at the station is sent

[0063] Step S33 further includes the following steps:

[0064] Step S331: After receiving the signal that the bus is about to arrive at the station, obtain the riding information of the passengers in the database, count the number of people getting off the target bus at the target platform M 下 and the number of people getting on the bus M 上 , calculate the passenger flow K of the target platform = M 下 + M 上 . If the passenger flow K is 0, no early warning analysis is performed. If the passenger flow K is greater than 0, it is determined that early warning analysis is required, a signal for early warning analysis is sent, and the target platform broadcast is controlled to give safety reminders to the waiting passengers at the target platform and the non-motor vehicles in front of the target platform;

[0065] Step S332: After receiving the early warning analysis signal, further obtain the position coordinates (a1, b1) of the target platform, obtain the position coordinates (a2, b2) of all non-motor vehicles on the road segment where the target bus is about to arrive at the station, obtain the road curvature Q1 and road slope P1 of the road segment where the platform is located, retrieve the corresponding curvature influence coefficient α1 and slope influence coefficient β1, and calculate the distance between each non-motor vehicle and the target platform Where (a1, b1) represents the position coordinates of the platform, (a2, b2) represents the position coordinates of the non-motor vehicle, and the driving speed V of each non-motor vehicle is identified 非 , according to the driving speed V 非 Retrieve the non-motor vehicle warning distance thresholds between each non-motor vehicle and the target platform in the database Compare L1 with the non-motor vehicle warning distance threshold If there is any in the non-motor vehicle flow Then control the in-bus broadcast to issue a safety reminder to the passengers;

[0066] Step S333: After receiving the warning analysis signal, further obtain the position coordinates (a3, b3) of all motor vehicles on the road section where the bus is about to arrive at the station, obtain the position coordinates (a1, b1) of the target platform, obtain the road curvature Q1 and road slope P1 of the road section where the platform is located, retrieve the corresponding curvature influence coefficient α1 and slope influence coefficient β1, and calculate the distance between each motor vehicle and the target platform Where (a1, b1) represents the position coordinates of the platform, (a3, b3) represents the position coordinates of the motor vehicle. Compare L2 with the motor vehicle warning distance threshold φ. If L2 < φ, mark the motor vehicle as within the warning reminder range, control the in-vehicle broadcast of the motor vehicle, and issue a safety reminder to the motor vehicle driver. Through the safety reminders of the in-bus broadcast, platform broadcast and in-vehicle broadcast, the non-motor vehicle and motor vehicle drivers learn that there is a bus stopping at the nearby platform and whether there are people getting on or off, and adjust the driving speed in time to pay attention to avoidance, improving the travel efficiency and safety of motor vehicles. Passengers can understand the state of the non-motor vehicle flow in front of the platform in advance and pay attention to observing left and right when getting off, ensuring the safety of passengers getting off the bus.

[0067] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device.

[0068] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions recorded in the foregoing embodiments or perform equivalent replacements for some of the technical features. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An urban service optimization system based on swarm intelligence, characterized in that: The operation method of the urban service optimization system includes the following steps: Step S1: Obtain historical riding data, establish a historical database, obtain urban road network data, establish an urban road network database and an urban road network coordinate system; Step S2: Analyze the delay duration of the previous bus, evaluate the impact of the delay duration on the number of boarding and alighting passengers, analyze the platforms where the remaining route of the previous bus coincides with other bus routes, evaluate the impact of passenger diversion on the full load rate, predict the full load rate of the target bus arriving at the remaining platforms based on historical riding data, combined with the delay deviation and the diversion deviation, evaluate the operating status of the target bus according to the predicted full load rate, and adjust the departure time of the next bus; Step S3: Analyze the riding information of passengers, evaluate the passenger flow volume when the bus stops at the target platform, determine whether to conduct early warning analysis, and if necessary, further evaluate the driving status of motor vehicles and non-motor vehicles near the target platform to obtain the early warning result; Step S4: Control the in-vehicle broadcast, platform broadcast and in-vehicle broadcast of motor vehicles according to the analyzed early warning result to issue safety reminders; The said Step S1 further includes the following steps: Step S11: Obtain historical riding data, including the number of boarding and alighting passengers at each platform of each bus route in each time period, establish a historical database and enter the data into the database; Step S12: Obtain urban road network data, including urban road network diagrams, road names, road lengths, road curvatures, road gradients and road intersection positions, establish an urban road network database and enter the data into the database, establish an urban road network coordinate system, mark the target bus route, mark the inflection point coordinates and the coordinates of each platform point of the target bus route, and obtain the coordinates of the bus position point, the motor vehicle position point and the non-motor vehicle position point in real time; The said Step S2 further includes the following steps: Step S21: Obtain the total number N of passengers in the previous bus 总 and the maximum passenger capacity N max , and calculate the real-time full-load rate of the previous bus Step S22: When the previous bus departs from the starting platform, mark a starting timestamp. When it arrives at each platform during the journey, mark a platform timestamp. The difference between the platform timestamp and the starting timestamp is used as the actual running time T of the previous bus to reach this platform i , T i represents the actual running time of the bus from the starting platform to platform i. Retrieve the running time threshold t of the bus from the starting platform to platform i from the database i , if T i <t i , then the bus is late. Calculate the late duration T 晚点 =T i -t i . According to the late duration T of the bus 晚点 , retrieve the corresponding boarding passenger number deviation coefficient μ i and alighting passenger number deviation coefficient v i from the database. According to the historical riding data, count the boarding passenger number N i and alighting passenger number M i of the original target bus at each platform. Obtain the predicted boarding passenger number μ i N i and predicted alighting passenger number v i M i ; Step S23: Obtain the platforms on the remaining route of the target bus that overlap with other bus routes. If the number of overlapping platforms N 重 ≥ 2, mark this bus route as a diverted bus route, the bus corresponding to the diverted bus route as a diverted bus, and according to the number of overlapping platforms N 重 retrieve the corresponding dilution weight ε in the database j , obtain the number k of diverted buses at each platform j , and calculate the diversion influence coefficient In the formula, j = 1, 2,..., n, where j represents the number of platforms where the diverted bus overlaps with the target bus, and k j represents that there are k diverted buses with the number of overlapping platforms j, and ε j represents that the dilution weight corresponding to the number of overlapping platforms j is ε; Step S24: According to the obtained predicted number of boarding passengers μ i N i and the predicted number of alighting passengers v i M i and the shunt influence coefficient ξ, predict the full-load rate P of the previous bus arriving at the remaining stations on the target route i = where i = 1, 2,..., n, N 总 is the total number of passengers in the bus. Compare the predicted full-load rate P i of each station within the period with the full-load rate threshold θ. If P i > θ occurs, it means that the previous bus is in an abnormal operation state, and the next bus will depart immediately to coordinate the bus operation state of the target bus route. If P i ≤ θ always holds within the period, it means that the previous bus is in a normal operation state, and the next bus will depart according to the original period.

2. The urban service optimization system based on swarm intelligence according to claim 1, wherein: The said Step S3 further includes the following steps: Step S31: Obtain the coordinate of the bus position point in the urban road network coordinate system, traverse the target bus route according to the driving direction of the bus, stop when reaching the platform point, and use it as the target platform point. The bus position point, the inflection point, and the target platform point are used as m+1 division nodes to divide the target route into m road segments, and obtain the position coordinates (a i , b i ) of the m+1 division nodes according to the traversal order; Step S32: Obtain the road curvature Q of the road segments between m + 1 division nodes 12 , Q 23 , ……, Q m_m+1 , where Q m_m+1 refers to the road curvature of the road segment between the m-th division node and the (m + 1)-th division node, and retrieve the corresponding curvature influence coefficient α 1_2 , α 2_3 , ……, α m_m+1 , obtain the road gradient P of the road segments between m + 1 division nodes 1_2 , P 2_3 , ……, P m_ m +1 , where P m_m+1 refers to the road gradient of the road segment between the m-th division node and the (m + 1)-th division node, and retrieve the corresponding gradient influence coefficient β 1_2 , β 2_3 , ……, β m_m+1 ; Step S33: Calculate the distance between the bus and the target platform according to the position coordinates of each division node and the road curvature and road slope of the road segments between the division nodes In the formula, k = 1, 2,..., m. If the distance L between the bus and the target platform is less than or equal to the threshold value, it is determined that the bus is about to dock at the target platform, and a signal that the bus is about to arrive at the station is sent out.

3. The urban service optimization system based on swarm intelligence according to claim 2, characterized in that: The said Step S33 further includes the following steps: Step S331: After receiving the signal that the bus is about to arrive at the station, obtain the riding information of passengers in the database, and count the number of people getting off the target bus at the target platform as M 下 and the number of people getting on the bus as M 上 , calculate the passenger flow at the target platform K = M 下 + M 上 . If the passenger flow K is 0, no early warning analysis is performed. If the passenger flow K is greater than 0, it is determined that early warning analysis is required, an early warning analysis signal is sent, and the broadcast at the target platform is controlled to give safety reminders to the waiting passengers at the target platform and the non-motor vehicles in front of the target platform; Step S332: After receiving the warning analysis signal, further obtain the position coordinates (a1, b1) of the target platform, obtain the position coordinates (a2, b2) of all non-motor vehicles on the road section where the target bus is about to arrive, obtain the road curvature Q1 and road slope P1 of the road section where the platform is located, retrieve the corresponding curvature influence coefficient α1 and slope influence coefficient β1, and calculate the distance between each non-motor vehicle and the target platform In the formula, (a1, b1) represents the position coordinates of the platform, (a2, b2) represents the position coordinates of the non-motor vehicle, and identify the driving speed V of each non-motor vehicle 非 , according to the driving speed V 非 Retrieve the non-motor vehicle warning distance threshold between each non-motor vehicle and the target platform corresponding in the database Compare L1 with the non-motor vehicle warning distance threshold If there is in the non-motor vehicle traffic flow, then control the in-bus broadcast to send a safety reminder to passengers; Step S333: After receiving the warning analysis signal, further obtain the position coordinates (a3, b3) of all motor vehicles on the road section where the bus is about to arrive at the station, obtain the position coordinates (a1, b1) of the target platform, obtain the road curvature Q1 and road slope P1 of the road section where the platform is located, retrieve the corresponding curvature influence coefficient α1 and slope influence coefficient β1, and calculate the distance between each motor vehicle and the target platform. In the formula, (a1, b1) represents the position coordinates of the platform, and (a3, b3) represents the position coordinates of the motor vehicle. Compare L2 with the motor vehicle warning distance threshold φ. If L2 < φ, then mark the motor vehicle as within the warning reminder range, control the on-vehicle broadcast of the motor vehicle, and give a safety reminder to the motor vehicle driver.

Images