Urban service optimization system based on swarm intelligence

Abstract

The application discloses a kind of urban service optimization systems based on swarm intelligence, including obtaining historical ride data and urban road network data, and establishing database and urban road network coordinate system, the length of time of analyzing last bus delay, assesses delay deviation, analyzes the platform coinciding with other bus routes in remaining route, assesses shunt deviation, further according to historical ride data, the full load rate of target bus to remaining platform is predicted, according to predicted full load rate, the departure time of next bus is adjusted, the ride information of passenger is analyzed, assesses the passenger flow when bus stops target platform, judges whether to carry out early warning analysis, if necessary, further assesses the driving state of motor vehicle and non-motor vehicle near target platform, obtains early warning result, controls broadcast to issue safety reminder according to analyzed early warning result, the application has the characteristics of improving passenger travel efficiency and guaranteeing bus passenger safety.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of bus optimization, in particular to a city service optimization system based on swarm intelligence. BACKGROUND

[0002] With the rapid development of cities in recent years, the public transportation system has become an important tool for urban residents to travel. Currently, urban residents can solve their travel needs such as going to work, going to school, and buying groceries by taking the bus. However, with the rapid growth of residents and the expansion of road scale, the original fixed bus departure time interval can easily cause problems such as long waiting time for residents or not being able to get on the bus. Residents pay more attention to travel efficiency, and most of the area in front of the bus stop is a non-motorized lane. There are more and more motor vehicles and non-motorized vehicles on the road. When the bus stops, passengers, motor vehicles and non-motorized vehicles that are running cannot avoid in time due to the sudden opening of the bus door, which can easily cause accidents.

[0003] Therefore, it is necessary to design a city service optimization system based on swarm intelligence to improve passenger travel efficiency and ensure the safety of bus passengers. SUMMARY

[0004] The present application aims to provide a city service optimization system based on swarm intelligence to solve the problems raised in the background.

[0005] In order to solve the above technical problems, the present application provides the following technical scheme: a city service optimization system based on swarm intelligence, characterized by comprising 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 city road network data, establish a city road network database and a city road network coordinate system;

[0006] The departure time optimization module is used to analyze the late time of the last bus, evaluate the influence of the late time on the number of passengers getting on and off the bus, analyze the stations in the remaining route of the last bus that coincide with other bus routes, evaluate the influence of passenger diversion on the full load rate, predict the full load rate of the target bus arriving at the remaining stations according to the historical riding data combined with the late deviation and the diversion deviation, evaluate the running state of the target bus according to the predicted full load rate, 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 station, determine whether to perform warning analysis, and if necessary, further evaluate the driving state of motor vehicles and non-motorized vehicles near the target station, and obtain the warning result;

[0008] The broadcast reminding module is configured to control the broadcasting in the bus, the broadcasting at the bus stop and the broadcasting in the motor vehicle according to the analysis result of the early warning to send the arrival reminding and the safety reminding.

[0009] According to the technical scheme, the bus running state analysis module is configured to analyze the late time of the previous bus, evaluate the influence of the late time on the number of passengers getting on and off the bus, analyze the bus stops on the remaining route of the previous bus that coincide with other bus routes, evaluate the influence of the passenger diversion on the full load rate, and predict the full load rate of the target bus at the remaining bus stops according to the historical riding data and in combination with the late deviation and the diversion deviation.

[0010] According to the technical scheme, the bus running state analysis module includes a late deviation analysis submodule, a diversion deviation analysis submodule and a full load rate prediction submodule, the late deviation analysis submodule is configured to analyze the late time of the previous bus, and evaluate the influence of the late time on the number of passengers getting on and off the bus, the diversion deviation analysis submodule is configured to analyze the bus stops on the remaining route of the previous bus that coincide with other bus routes, and evaluate the influence of the passenger diversion on the full load rate, and the full load rate prediction submodule is configured to predict the full load rate of the target bus at the remaining bus stops according to the historical riding data and in combination with the late deviation and the diversion deviation.

[0011] According to the technical scheme, the early warning analysis module includes a bus arrival analysis unit and a bus stop early warning analysis unit, the bus arrival analysis unit is configured to analyze the distance between the bus and the bus stop, determine whether the bus stops at the bus stop, and send a stop signal, and the bus stop early warning analysis unit is configured to analyze the riding information features of the passengers, obtain the passenger flow when the bus stops at the bus stop, determine whether to perform the early warning analysis, and obtain the bus stop early warning result.

[0012] According to the technical scheme, 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 configured to, after receiving the early warning analysis signal, analyze the non-motor vehicle driving state in front of the target bus stop, evaluate the safety index of the passengers getting off the bus when the bus stops at the target bus stop, and obtain the passenger early warning result, and the motor vehicle early warning analysis unit is configured to, after receiving the early warning analysis signal, analyze the position features of the motor vehicle and the target bus stop, and obtain the motor vehicle early warning result.

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

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

[0015] Step S2: analyzing the late departure time of the previous bus, evaluating the impact of the late departure time on the number of passengers getting on and off the bus, analyzing the stations on the remaining route of the previous bus that coincide with other bus routes, evaluating the impact of passenger diversion on the full load rate, predicting the full load rate of the target bus at the remaining stations based on the historical riding data, the late departure deviation and the diversion deviation, evaluating the running state of the target bus based on the predicted full load rate, and adjusting the departure time of the next bus;

[0016] Step S3: analyzing the riding information of passengers, evaluating the passenger flow when the bus stops at the target station, determining whether to perform early warning analysis, and if necessary, further evaluating the driving state of motor vehicles and non-motor vehicles near the target station to obtain early warning results;

[0017] Step S4: controlling the bus intercom, station intercom and motor vehicle intercom based on the analyzed early warning results to issue safety reminders.

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

[0019] Step S11: obtaining historical riding data, including the number of passengers getting on and off each station of each bus route in each time period, establishing a historical database and entering the data into the database;

[0020] Step S12: obtaining urban road network data, including an urban road network map, road names, road lengths, road curvatures, road slopes and road intersection positions, establishing an urban road network database, entering the data into the database, establishing an urban road network coordinate system, marking the target bus route, marking the coordinates of the turning points and the coordinates of each station point of the target bus route, and obtaining the coordinates of the bus position point, the coordinates of the motor vehicle position point and the coordinates of the non-motor vehicle position point in real time.

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

[0022] Step S21: obtaining the total number N of passengers in the previous bus 总 and the maximum passenger capacity N max , calculating the real-time full load rate of the previous bus

[0023] Step S22: marking a starting timestamp when the previous bus departs from the starting station, marking a station timestamp when the bus arrives at each station during the journey, and taking the difference between the station timestamp and the starting timestamp as the actual running time T of the previous bus to the stationi T i This represents the actual travel time of the bus from the starting platform to platform i. The threshold t for the travel time t from the starting platform to platform i is retrieved from the database. i If T i <t i If the bus is delayed, calculate the delay duration T. 晚点 =T i -t i According to the bus delay duration T 晚点 Retrieve the corresponding deviation coefficient μ of the number of passengers boarding from the database. i Deviation coefficient v of the number of people getting off the bus i Based on historical passenger data, the number of passengers N boarding the original target bus at each stop was statistically analyzed. i And the number of people getting off the bus M i The predicted number of passengers (μ) boarding the target bus at each stop is obtained based on the delay duration deviation. i N i And the predicted number of people getting off the bus v i M i ;

[0024] Step S23: Obtain the bus stops that overlap with other bus routes on the remaining route of the target bus. If the number of overlapping bus stops is N... 重 If the number of buses is ≥2, then the bus route is marked as a diversion bus route, and the buses corresponding to the diversion bus routes are diversion buses, based on the number of overlapping stops N. 重 Retrieve the corresponding dilution weight ε from the database j Obtain the number of diversion buses k at each station. j Calculate the diversion impact coefficient In the formula, j = 1, 2, ..., n, j represents the number of bus stops where the diversion bus and the target bus overlap, and k j This indicates that there are k diversion buses with overlapping platform number j, ε j This indicates that the dilution weight corresponding to the number of overlapping stations is j, and ε is the weight of the station.

[0025] Step S24: Based on the predicted number of passengers μ i N i And the predicted number of people getting off the bus v i M i And the diversion impact coefficient ξ, predict the occupancy rate of the previous bus arriving at the remaining stops on the target route. In the formula, i = 1, 2, ..., n, N 总 It represents the total number of passengers on the bus, compared with the predicted occupancy rate P at each bus stop within the period. i And the full load rate threshold θ, if P occurs iIf > θ, the previous bus appears in an abnormal running state, and the next bus immediately sends out a bus running state coordination target bus route, and if P i ≤ θ, the previous bus is in a normal running state, and the next bus sends out according to the original period.

[0026] According to the above technical scheme, the step S3 further comprises the following steps:

[0027] Step S31: Obtain the bus position point coordinates in the urban road network coordinate system, traverse the target bus route according to the driving direction of the bus, stop when reaching the station point, and take it as the target station point, wherein the bus position point, the inflection point and the target station point are used as m+1 division nodes to divide the target route into m road segments, and the position coordinates (a i , b i ) of the m+1 division nodes are obtained 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, wherein Q m_m+1 represents the road curvature of the road segment between the mth division node and the m+1th division node, the corresponding curvature influence coefficient α 1_2 , α 2_3 ,..., α m_m+1 is obtained according to the road curvature, the road slopes P 1_2 , P 2_3 ,..., P m_m+1 of the road segments between the m+1 division nodes are obtained, wherein P m_m+1 represents the road slope of the road segment between the mth division node and the m+1th division node, and the corresponding slope influence coefficient β 1_2 , β 2_3 ,..., β m_m+1 is obtained.

[0029] Step S33: According to the position coordinates of each division node and the road curvatures and road slopes of the road segments between each division node, the distance L between the bus and the target station is calculated. In the formula, k=1, 2,..., m, if the distance L between the bus and the target station is less than or equal to the threshold value, it is judged that the bus will stop at the target station, and a bus will arrive at the station signal is sent out.

[0030] According to the above technical scheme, the step S33 further comprises the following steps:

[0031] Step S331: After receiving the signal that the bus is about to arrive at the station, retrieve the passenger information from the database and count the number M of passengers getting off the target bus at the target station. 下 And the number of passengers M 上 Calculate the passenger flow K = M at the target platform. 下 +M 上 If the passenger flow K is 0, no early warning analysis will be performed. If the passenger flow K is greater than 0, it will be determined that an early warning analysis is needed, an early warning analysis signal will be issued, and the target platform broadcast will be controlled to provide safety reminders to waiting passengers and non-motorized vehicles in front of the target platform.

[0032] Step S332: After receiving the early warning analysis signal, further obtain the target bus stop location coordinates (a1, b1), obtain the location coordinates (a2, b2) of all non-motorized vehicles on the road segment where the target bus is about to arrive, obtain the road curvature Q1 and road slope P1 of the road segment where the bus stop is located, retrieve the corresponding curvature influence coefficient α1 and slope influence coefficient β1, and calculate the distance between each non-motorized vehicle and the target bus stop. In the formula, (a1, b1) represents the position coordinates of the platform, (a2, b2) represents the position coordinates of the non-motorized vehicles, and the speed V of each non-motorized vehicle is identified. 非 According to the driving speed V 非 Retrieve the corresponding non-motorized vehicle warning distance thresholds between each non-motorized vehicle and the target bus stop from the database. Comparison of L1 and non-motorized vehicle warning distance thresholds If there are non-motorized vehicle traffic flows Then control the onboard announcements to send safety reminders to passengers;

[0033] Step S333: After receiving the early warning analysis signal, further obtain the coordinates (a3, b3) of all motor vehicles on the road segment where the bus is about to arrive, obtain the coordinates (a1, b1) of the target bus stop, obtain the road curvature Q1 and road slope P1 of the road segment where the bus stop 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 bus stop. In the formula, (a1, b1) represents the position coordinates of the platform, and (a3, b3) represents the position coordinates of the motor vehicle. By comparing L2 with the motor vehicle warning distance threshold φ, if L2 < φ, the motor vehicle is marked as being within the warning reminder range, and the vehicle's onboard broadcast is controlled to provide a safety reminder to the driver.

[0034] Compared with the prior art, the present application has the beneficial effects that: the present application predicts the full load rate of the bus according to the historical riding data by analyzing the late impact and the shunt impact, evaluates the running state of the last bus according to the predicted full load rate, adjusts the departure time of the next bus, relieves the running pressure, improves the travel efficiency of the passengers, reduces the problem of long waiting time of the passengers caused by too large passenger flow, optimizes the bus resource allocation, effectively improves the running efficiency of the bus, issues a safety reminder to the passengers by analyzing the non-motor vehicle flow state between the bus and the platform when the passengers get off the bus, ensures the safety of the passengers getting off the bus, issues a safety reminder to the non-motor vehicle running between the bus and the platform by analyzing whether the bus stops at the platform and the passenger flow getting on and off the bus when stopping at the platform, the non-motor vehicle can slow down and avoid the passenger flow in time, ensuring the safety of the passengers and the non-motor vehicle, and issuing a safety reminder to the motor vehicle by analyzing the distance between the motor vehicle and the platform, the motor vehicle can avoid in time, facilitates the bus to stop at the platform, and ensures the safety of the motor vehicle and the bus. BRIEF DESCRIPTION OF DRAWINGS

[0035] The accompanying drawings are included to provide a further understanding of the present application, and constitute a part of the specification, illustrate the present application and explain the technical scheme of the present application, and do not constitute a limitation on the present application. In the drawings:

[0036] Figure 1 It is a system module composition schematic diagram of the present application. DETAILED DESCRIPTION

[0037] The technical scheme in the embodiments of the present application will be described clearly and completely below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0038] Please refer to Figure 1 The present application provides a technical scheme: a city service optimization system based on swarm intelligence, comprising a data collection module, a departure time optimization module, a early warning analysis module and a broadcast reminder module, the data collection module is used for obtaining historical riding data, establishing a historical database, obtaining city road network data, establishing a city road network database and a city road network coordinate system;

[0039] The departure time optimization module is configured to analyze the late time of the previous bus, evaluate the influence of the late time on the number of passengers getting on and off the bus, analyze the stations on the remaining route of the previous bus that coincide with other bus routes, evaluate the influence of passenger diversion on the full load rate, predict the full load rate of the target bus at the remaining stations according to historical riding data, in combination with the late deviation and the diversion deviation, evaluate the running state of the target bus according to the predicted full load rate, and adjust the departure time of the next bus.

[0040] The early warning analysis module is configured to analyze the riding information of passengers, evaluate the passenger flow when the bus stops at the target station, determine whether to perform early warning analysis, and if so, further evaluate the driving state of motor vehicles and non-motor vehicles near the target station, and obtain early warning results.

[0041] The broadcast reminder module is configured to control the bus interior broadcast, the station broadcast, and the motor vehicle on-board broadcast according to the analyzed early warning results, and issue a station arrival reminder and a safety reminder.

[0042] The departure time optimization module includes a bus running state analysis module and a departure time adjustment module. The bus running state analysis module is configured to analyze the late time of the previous bus, evaluate the influence of the late time on the number of passengers getting on and off the bus, analyze the stations on the remaining route of the previous bus that coincide with other bus routes, evaluate the influence of passenger diversion on the full load rate, and predict the full load rate of the target bus at the remaining stations according to historical riding data, in combination with the late deviation and the diversion deviation. The departure time adjustment module is configured to evaluate the running state of the target bus according to the predicted full load rate, and adjust the departure time of the next bus.

[0043] The bus running state analysis module includes a late deviation analysis submodule, a diversion deviation analysis submodule, and a full load rate prediction submodule. The late deviation analysis submodule is configured to analyze the late time of the previous bus, and evaluate the influence of the late time on the number of passengers getting on and off the bus. The diversion deviation analysis submodule is configured to analyze the stations on the remaining route of the previous bus that coincide with other bus routes, and evaluate the influence of passenger diversion on the full load rate. The full load rate prediction submodule is configured to predict the full load rate of the target bus at the remaining stations according to historical riding data, in combination with the late deviation and the diversion deviation.

[0044] The early warning analysis module includes a bus arrival analysis unit and a station early warning analysis unit. The bus arrival analysis unit is configured to analyze the distance between the bus and the station, determine whether the bus stops at the station, and issue a stop signal. The station early warning analysis unit is configured to analyze the riding information characteristics of passengers, obtain the passenger flow when the bus stops at the station, determine whether to perform early warning analysis, and obtain a station early warning result.

[0045] The early warning analysis module further comprises a passenger early warning analysis unit and a motor vehicle early warning analysis unit, the passenger early warning analysis unit is used for analyzing the non-motor vehicle driving state in front of the target station after receiving the early warning analysis signal, evaluating the safety index of the passengers getting off the bus when the bus stops at the target station, and obtaining the passenger early warning result, and the motor vehicle early warning analysis unit is used for analyzing the position characteristics of the motor vehicle and the target station after receiving the early warning analysis signal, and obtaining the motor vehicle early warning result.

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

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

[0048] Step S2: analyzing the late departure time of the previous bus, evaluating the influence of the late departure time on the number of passengers getting on and off the bus, analyzing the stations on the remaining route of the previous bus that coincide with other bus routes, evaluating the influence of passenger diversion on the full load rate, predicting the full load rate of the target bus at the remaining stations according to the historical riding data, combining the late deviation and the diversion deviation, evaluating the operation state of the target bus according to the predicted full load rate, and adjusting the departure time of the next bus;

[0049] Step S3: analyzing the riding information of the passengers, evaluating the passenger flow when the bus stops at the target station, judging whether to perform early warning analysis, and if necessary, further evaluating the driving state of the motor vehicle and the non-motor vehicle near the target station, and obtaining the early warning result;

[0050] Step S4: controlling the bus interior broadcast, the station broadcast and the motor vehicle on-board broadcast according to the analyzed early warning result, and issuing a safety reminder.

[0051] Step S1 further comprises the following steps:

[0052] Step S11: obtaining historical riding data, including the number of passengers getting on and off each station of each bus route in each time period, establishing a historical database and entering the data into the database;

[0053] Step S12: obtaining urban road network data, including an urban road network map, road names, road lengths, road curvatures, road slopes and road intersection positions, establishing an urban road network database, entering the data into the database, establishing an urban road network coordinate system, marking the target bus route, marking the coordinates of the turning points and the coordinates of each station point of the target bus route, and obtaining the coordinates of the bus position point, the coordinates of the motor vehicle position point and the coordinates of the non-motor vehicle position point in real time.

[0054] Step S2 further comprises the following steps:

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

[0056] Step S22: Mark a starting timestamp when the last bus departs from the starting platform, and mark a platform timestamp every time the bus arrives at a platform during the journey. The difference between the platform timestamp and the starting timestamp is the actual running time T of the last bus to reach the platform i , T i represents the actual running time of the bus from the starting platform to the i-th platform, and the running time threshold t of the bus from the starting platform to the i-th platform in the database is retrieved i , if T i < t i , the bus is late, the length of the delay T 晚点 = T i -t i is calculated, the corresponding boarding number deviation coefficient μ 晚点 and the alighting number deviation coefficient v i are retrieved from the database according to the length of the delay T i , the original target bus boarding number N i and the alighting number M i are calculated according to the historical riding data statistics, the predicted boarding number μ i N i and the predicted alighting number v i M i are obtained according to the deviation of the delay, the length of the delay affects the boarding number of each platform, the change of the boarding number leads to the update of the alighting number, by calculating the length of the delay of the bus, the deviation of the boarding and alighting numbers of each platform is compensated, and the accuracy of predicting the boarding and alighting numbers of each platform is improved

[0057] Step S23: Obtain the platforms that coincide with other bus routes in the remaining route of the target bus, if the number of coinciding platforms N 重 ≥ 2, mark the bus route as a shunt bus route, the bus corresponding to the shunt bus route is a shunt bus, retrieve the corresponding dilution weight ε 重 from the database according to the number of coinciding platforms N j , obtain the number of shunt buses k j at each platform, and calculate the shunt influence coefficient wherein, j = 1, 2,..., n, j represents the number of coinciding platforms of the shunt bus and the target bus, k j represents that there are k shunt buses with j coinciding platforms, and ε jε represents the dilution weight corresponding to the number of coinciding stations j, by analyzing the stations coinciding with other bus routes, the degree of diversion of other buses to the target bus is evaluated, for example, if the A bus route coincides with the target bus route at two stations, a passenger's travel plan is to wait at the two coinciding stations and the destination station, then the passenger can also choose to take the A bus, which relieves the pressure on the target bus, and the A bus plays a role in diversion, and by analyzing the diversion effect, the accuracy of the predicted full load rate is improved;

[0058] Step S24: according to the predicted number of passengers μ i N i and the predicted number of passengers v i M i and the diversion influence coefficient ξ, the full load rate of the last bus on the target route is predicted In the formula, i=1, 2,..., n, N 总 is the total number of passengers in the bus, and the predicted full load rate P i of each station in the period is compared with the full load rate threshold θ, if P i > θ, the last bus is in an abnormal running state, and the next bus is immediately dispatched to coordinate the bus running state of the target bus route, if P i ≤ θ all the time in the period, the last bus is in a normal running state, and the next bus is dispatched according to the original period, by analyzing the running state of the last bus, when the running state is abnormal, the next bus receives the instruction and is immediately dispatched to relieve the running pressure of the last bus, for example, if the target bus is delayed by half an hour, and the number of waiting passengers at the following station increases by 15 in half an hour, the target bus cannot carry all the waiting passengers, and the next bus needs to be dispatched early to relieve the running pressure, improve the travel efficiency of passengers, reduce the problem of long waiting time of passengers due to large passenger flow, optimize the allocation of bus resources, and effectively improve the running efficiency of the bus.

[0059] Step S3 further includes the following steps:

[0060] Step S31: obtain the coordinates 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 the station point is reached, and take it as the target station point, wherein the bus position point, the inflection point and the target station point are taken as m+1 division nodes to divide the target route into m road segments, and the position coordinates (a i , b i ) of the m+1 division nodes are obtained according to the traversal order;

[0061] Step S32: obtain the road curvature Q of the road segment between the m+1 division nodes1_2 , Q 2_3 , …, Q m_m+1 , wherein Q m_m+1 denotes the road curvature of the road segment between the mth division node and the m+1th division node, the corresponding curvature influence coefficient a is retrieved from the database according to the road curvature 1_2 , a 2_3 , …, a m_m+1 , the road slope P of the road segment between the mth division node and the m+1th division node is obtained 1_2 , P 2_3 , …, P m_m+1 , wherein P m_m+1 denotes the road slope of the road segment between the mth division node and the m+1th division node, the corresponding slope influence coefficient b is retrieved from the database 1_2 , b 2_3 , …, b m_m+1 ;

[0062] Step S33: According to the position coordinates of each division node and the road curvature and road slope of the road segment between each division node, the distance between the bus and the target platform is calculated 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 judged that the bus will stop at the target platform, and a signal that the bus will arrive at the station is sent.

[0063] Step S33 further comprises the following steps:

[0064] Step S331: After receiving the signal that the bus will arrive at the station, the riding information of the passengers in the database is obtained, the number of passengers M getting off the target bus at the target platform is counted 下 and the number of passengers M 上 getting on the target bus, the passenger flow K of the target platform is calculated =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 judged that early warning analysis is needed, a warning analysis signal is sent, and the target platform broadcast is controlled to remind the waiting passengers at the target platform and the non-motor vehicles in front of the target platform of safety;

[0065] Step S332: After receiving the early warning analysis signal, the position coordinates (a1, b1) of the target platform are further obtained, the position coordinates (a2, b2) of all non-motor vehicles on the road segment where the target bus is located when the target bus arrives at the station are obtained, the road curvature Q1 and the road slope P1 of the road segment where the target platform is located are obtained, the corresponding curvature influence coefficient a1 and the slope influence coefficient b1 are retrieved, and the distance between each non-motor vehicle and the target platform is calculated Wherein (a1, b1) represents the position coordinates of the station, (a2, b2) represents the position coordinates of the non-motor vehicle, and V represents the driving speed of each non-motor vehicle 非 According to the driving speed V 非 , the non-motor vehicle early warning distance threshold value corresponding to each non-motor vehicle and the target station in the database is called The L1 is compared with the non-motor vehicle early warning distance threshold value If there is a non-motor vehicle in the non-motor vehicle flow , the safety reminder is issued to the passengers in the bus through the bus internal broadcast control;

[0066] Step S333: After receiving the early warning analysis signal, further obtain all the motor vehicle position coordinates (a3, b3) on the road section where the bus is about to stop, obtain the position coordinates (a1, b1) of the target station, obtain the road curvature Q1 and the road slope P1 of the road section where the station is located, call the corresponding curvature influence coefficient α1 and the slope influence coefficient β1, and calculate the distance between each motor vehicle and the target station Wherein (a1, b1) represents the position coordinates of the station, (a3, b3) represents the position coordinates of the motor vehicle, L2 is compared with the motor vehicle early warning distance threshold value φ, if L2<φ, the motor vehicle is marked as within the early warning reminder range, the motor vehicle driver is reminded of safety through the motor vehicle on-board broadcast control, through the safety reminders of the bus internal broadcast, the station broadcast and the on-board broadcast, the non-motor vehicle and the motor vehicle driver know that there is a bus stopping at the nearby station and whether there is a passenger getting on or off the bus, and timely adjust the driving speed to avoid, improve the motor vehicle travel efficiency and safety, and the passengers know the non-motor vehicle flow state in front of the station in advance, and observe left and right when getting off the bus, thereby ensuring the safety of the passengers getting off the bus.

[0067] It should be noted that, in this text, the relationship 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 such actual relationship or order between the entities or operations. Moreover, the term "includes", "contains" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or equipment.

[0068] Finally, it should be noted that the above only describes the preferred embodiments of the present application and is not intended to limit the present application. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art will appreciate that the technical solutions described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalent ones. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for optimizing urban services based on swarm intelligence, characterized in that: The urban service optimization method includes the following steps: Step S1: Obtain historical ride data, establish a historical database, obtain urban road network data, and establish an urban road network database and urban road network coordinate system; Step S2: Analyze the delay duration of the previous bus, assess the impact of the delay duration on the number of passengers getting on and off the bus, analyze the stations that overlap with other bus routes on the remaining route of the previous bus, assess the impact of passenger diversion on the load factor, and based on historical riding data, combined with delay deviation and diversion deviation, predict the load factor of the target bus when it arrives at the remaining stations. Based on the predicted load factor, assess the operating status of the target bus and adjust the departure time of the next bus. Step S3: Analyze passenger travel information, assess passenger flow when the bus stops at the target station, determine whether to conduct early warning analysis, and if necessary, further assess the driving status of motor vehicles and non-motor vehicles near the target station to obtain early warning results. Step S4: Based on the analyzed warning results, control the in-bus broadcast, station broadcast, and vehicle-mounted broadcast to issue safety reminders; Step S1 further includes the following steps: Step S11: Obtain historical ride data, including the number of passengers boarding and alighting at each stop for each bus route at different times, establish a historical database and enter the data into the database; Step S12: Obtain urban road network data, including urban road network map, road name, road length, road curvature, road slope and road intersection location, establish urban road network database, enter the data into the database, establish urban road network coordinate system, mark target bus routes, mark turning point coordinates and the coordinates of each bus stop on the target bus routes, and obtain the real-time coordinates of bus location points, motor vehicle location points and non-motor vehicle location points. Step S2 further includes the following steps: Step S21: Obtain the total number of passengers on the previous bus. and maximum passenger capacity Calculate the real-time occupancy rate of the previous bus. ; Step S22: When the previous bus departs from the starting platform, it marks a start timestamp. During the journey, it marks a platform timestamp at each platform it arrives at. The difference between the platform timestamp and the start timestamp is the actual travel time of the previous bus to that platform. , This represents the arrival of the bus from the starting platform. The actual travel time of the bus at the station is retrieved from the database, showing the bus arrival time from the starting station. Platform running time threshold ,like If the bus is delayed, the delay duration will be calculated. According to the duration of bus delays Retrieve the corresponding boarding number deviation coefficient from the database. Deviation coefficient of the number of people getting off the bus Based on historical passenger data, the number of passengers boarding the original target bus at each stop was statistically analyzed. and the number of people getting off Based on the delay time deviation, the predicted number of passengers boarding the target bus at each stop is obtained. And predicted number of people getting off ; Step S23: Obtain the stops that overlap with other bus routes on the remaining route of the target bus. If the number of overlapping stops... If the number of overlapping stops is used, then the bus route is marked as a diversion bus route, and the bus corresponding to the diversion bus route is a diversion bus. Retrieve the corresponding dilution weights from the database Obtain the number of diversion buses at each station. Calculate the diversion impact coefficient In the formula, , This indicates the number of bus stops where the diversion buses and the target buses overlap. Indicates the number of overlapping platforms. The diversion buses have indivual, Indicates the number of overlapping platforms. The corresponding dilution weight is ; Step S24: Based on the predicted number of passengers boarding... And predicted number of people getting off and diversion influence coefficient Predict the occupancy rate of the previous bus arriving at the remaining stops on the target route. In the formula, , It represents the total number of passengers on the bus, compared with the predicted occupancy rate of each bus stop within the specified period. and full load threshold If it appears In such cases, if the previous bus experiences an abnormal operating status, the next bus will immediately depart, coordinating the bus operation status of the target bus route. If this continues within the cycle... If the previous bus is running normally, the next bus will depart according to the original schedule.

2. The urban service optimization method based on swarm intelligence according to claim 1, characterized in that: Step S3 further includes the following steps: Step S31: Obtain the coordinates of the bus location points in the urban road network coordinate system. Traverse the target bus route according to the bus's direction of travel, stopping when a bus stop is reached and setting it as the target bus stop point. The bus location point, turning point, and target bus stop point are used as... Each dividing node divides the target route into... Each road segment is obtained according to the traversal order. The position coordinates of each dividing node ; Step S32: Obtain Road curvature between the dividing nodes , , ..., ,in Refers to the first The partition node and the first The road curvature of the road segments between the dividing nodes is used to retrieve the corresponding curvature influence coefficient from the database. , , ..., , obtain Road slope between the dividing nodes , , ..., ,in Refers to the first The partition node and the first The road slope between each dividing node is used to retrieve the corresponding slope influence coefficient from the database. , , ..., ; Step S33: Calculate the distance between the bus and the target bus stop based on the location coordinates of each dividing node and the road curvature and slope of the road segments between each dividing node. In the formula, If the distance between the bus and the target bus stop If the value is less than or equal to the threshold, it is determined that the bus is about to stop at the target station, and a signal indicating that the bus is about to arrive is issued.

3. The urban service optimization method based on swarm intelligence according to claim 2, characterized in that: Step S33 further includes the following steps: Step S331: After receiving the signal that the bus is about to arrive at the station, retrieve the passenger boarding information from the database and count the number of passengers alighting from the target bus at the target station. and the number of passengers Calculate the passenger flow at the target platform. If the passenger flow If the value is 0, no early warning analysis will be performed; if the passenger flow... If the value is greater than 0, it is determined that an early warning analysis is needed, an early warning analysis signal is issued, and the target platform broadcast is controlled to provide safety reminders to waiting passengers and non-motorized vehicles in front of the target platform. Step S332: After receiving the early warning analysis signal, further obtain the target station location coordinates. Obtain the coordinates of all non-motorized vehicles on the road segment where the target bus is about to arrive at the station. Obtain the road curvature of the road segment where the platform is located. and road slope Retrieve the corresponding curvature influence coefficient and slope influence coefficient Calculate the distance between each non-motorized vehicle and the target station. In the formula, Indicates the coordinates of the platform's location. It represents the position coordinates of non-motorized vehicles and identifies the speed of each non-motorized vehicle. According to driving speed Retrieve the corresponding non-motorized vehicle warning distance thresholds between each non-motorized vehicle and the target bus stop from the database. , Non-motorized vehicle warning distance threshold If there are non-motorized vehicle traffic Then, control the onboard announcements to send safety reminders to passengers; Step S333: After receiving the early warning analysis signal, further obtain the coordinates of all motor vehicles on the road segment where the bus is about to arrive at the station. Obtain the coordinates of the target platform. Obtain the road curvature of the road segment where the platform is located. and road slope Retrieve the corresponding curvature influence coefficient and slope influence coefficient Calculate the distance between each motor vehicle and the target platform. In the formula, Indicates the coordinates of the platform's location. Indicates the position coordinates of the motor vehicle, for comparison Warning distance threshold for motor vehicles ,like If the vehicle is marked as being within the warning range, the vehicle's onboard broadcast will be controlled to provide safety reminders to the driver.

Images