Operation management and control method and system based on intelligent bus shelter

Abstract

The invention discloses an intelligent bus shelter-based operation management and control method and system, and the method comprises the steps: generating operation prompt information which comprises the predicted arrival time of a bus, unoccupied seats and passenger congestion degree information; when the first bus enters the queuing time, the passenger flow density of passengers in the first queuing area is calculated according to the queuing condition, and whether the passenger flow density is smaller than a preset density value is judged; if yes, whether the first queuing area needs to be scheduled or not is judged according to the passenger crowding degree of the first bus, the passenger flow density of the next stop and the getting-on and getting-off behavior mode, and the first target passenger is drained to the first queuing area within the schedulable range of the first queuing area when scheduling is needed; and if not, traversing the operation prompt information to find a second bus associated with the first bus, and scheduling the second target passenger to a second queuing area of the second bus. Through intelligent display and passenger flow scheduling, the bus taking order of the bus shelter is optimized, and the utilization efficiency of vehicle resources is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of public transportation management, and in particular to an operation control method and system based on a smart public transportation shelter. Background Art

[0002] In the existing public transportation system, especially in large cities, traffic congestion and a large number of passengers have increased the uncertainty of bus arrival time, making it difficult to accurately predict the waiting time for passengers. In addition, passengers often lack effective information guidance and cannot timely understand the crowdedness and remaining seats in the bus, which leads to passengers blindly waiting for the first bus to arrive during peak hours, while ignoring the subsequent buses that may have more empty seats. At the same time, the passenger management at the station also lacks refined means, making it difficult to balance the distribution of passengers between different buses in the smart bus shelter, resulting in poor order at the station, and easily causing some vehicles to be overcrowded while other vehicles have low seat utilization, reducing the utilization rate of vehicle resources. Summary of the invention

[0003] In order to solve at least one of the technical problems mentioned above, the present invention provides an operation control method and system based on a smart bus shelter.

[0004] In a first aspect, the present invention provides an operation control method based on a smart bus shelter, the method comprising:

[0005] Generate bus operation prompt information on the digital display screen of the smart bus shelter, and lock the bus with the shortest arrival time at the current time as the first bus according to the operation prompt information; the operation prompt information includes the estimated arrival time of the vehicle, available seats and passenger congestion information;

[0006] When the queue time for entering the first bus is determined, the passengers are guided to move from the waiting area to the first queue area at the boarding entrance to queue; the passenger flow density of the passengers in the first queue area is calculated according to the queue situation, and it is determined whether the passenger flow density is less than a preset density value;

[0007] If yes, predict the boarding and alighting behavior pattern of passengers according to the historical operation data of the first bus, and determine whether the first queue area needs to be dispatched according to the passenger congestion of the first bus, the passenger flow density of the next stop, and the boarding and alighting behavior pattern; if dispatching is required, monitor and identify the first target passengers who can be dispatched in other queue areas, and guide the first target passengers to the first queue area within the dispatchable range of the first queue area;

[0008] If not, determine the second target passenger to be dispatched from the first queuing area, traverse the bus operation prompt information on the digital display screen to find the second bus associated with the first bus, and dispatch the second target passenger to the second queuing area of ​​the second bus.

[0009] Preferably, the method further comprises:

[0010] When the first bus completes a trip, the operation data of each stop is obtained; the operation data includes the time deviation between the expected arrival time of the first bus and the actual arrival time, the passenger flow density in the queuing area, the number of passengers in the bus, and the predicted boarding and alighting behavior pattern;

[0011] Calculate the comprehensive vehicle dispatch index based on the station's operating data:

[0012]

[0013] Where i represents the i-th stop, I i represents the comprehensive vehicle dispatch index, ΔT i It represents the time difference between the expected arrival time and the actual arrival time, W i represents the passenger flow density in the queuing area, P i represents the number of passengers in the car, U i , D i They represent the predicted number of people getting on and the predicted number of people getting off, respectively. max represents the maximum passenger capacity of the vehicle, α, β, and γ represent adjustment factors, and their value ranges are all (0.1, 1);

[0014] Determine the comprehensive vehicle dispatch index I i With ideal index I t relationship;

[0015] When I i >I t When , execute the vehicle dispatch strategy;

[0016] When I i ≤I t The current departure plan remains unchanged.

[0017] Preferably, the executing vehicle dispatching strategy includes reducing the departure interval, increasing the number of vehicles or adjusting the departure time.

[0018] Preferably, the first target passenger is a passenger who can meet the destination arrival requirement by taking the first bus;

[0019] The estimated arrival time of the second bus is later than that of the first bus, and the time difference between the estimated arrival times is less than a preset time; the overlap between the stop sites of the second bus and the first bus is greater than a preset overlap.

[0020] In a second aspect, the present invention further provides an operation control system based on a smart bus shelter, the system comprising:

[0021] A prompt information generating unit is used to generate bus operation prompt information on the digital display screen of the smart bus shelter, and lock the bus with the shortest arrival time at the current time as the first bus according to the operation prompt information; the operation prompt information includes the estimated arrival time of the vehicle, the available seats and the passenger congestion information;

[0022] A passenger flow density calculation unit is used to guide passengers to move from the waiting area to the first queue area at the boarding entrance to queue up when the queue time for entering the first bus is determined; calculate the passenger flow density of passengers in the first queue area according to the queue situation, and determine whether the passenger flow density is less than a preset density value;

[0023] The passenger diversion planning unit is used to predict the passenger boarding and alighting behavior pattern according to the historical operation data of the first bus when the passenger flow density is less than the preset density value, and determine whether the first queue area needs to be dispatched according to the passenger congestion of the first bus, the passenger flow density of the next stop, and the boarding and alighting behavior pattern; if dispatching is required, monitor and identify the dispatchable first target passengers in other queue areas, and divert the first target passengers to the first queue area within the dispatchable range of the first queue area;

[0024] The passenger dispatch planning unit is used to determine the second target passenger to be dispatched from the first queuing area when the passenger flow density is greater than or equal to the preset density value, traverse the bus operation prompt information on the digital display screen to find the second bus associated with the first bus, and dispatch the second target passenger to the second queuing area of ​​the second bus.

[0025] Preferably, the system further comprises a vehicle dispatch planning unit, which is used to:

[0026] When the first bus completes a trip, the operation data of each stop is obtained; the operation data includes the time deviation between the expected arrival time of the first bus and the actual arrival time, the passenger flow density in the queuing area, the number of passengers in the bus, and the predicted boarding and alighting behavior pattern;

[0027] Calculate the comprehensive vehicle dispatch index based on the station's operating data:

[0028]

[0029] Where i represents the i-th stop, I i represents the comprehensive vehicle dispatch index, ΔT i It represents the time difference between the expected arrival time and the actual arrival time, W i represents the passenger flow density in the queuing area, P i represents the number of passengers in the car, U i , D i They represent the predicted number of people getting on and the predicted number of people getting off, respectively. maxrepresents the maximum passenger capacity of the vehicle, α, β, and γ represent adjustment factors, and their value ranges are all (0.1, 1);

[0030] Determine the comprehensive vehicle dispatch index I i With ideal index I t relationship;

[0031] When I i >I t When , execute the vehicle dispatch strategy;

[0032] When I i ≤I t The current departure plan remains unchanged.

[0033] Preferably, the executing vehicle dispatching strategy includes reducing the departure interval, increasing the number of vehicles or adjusting the departure time.

[0034] Preferably, the first target passenger is a passenger who can meet the destination arrival requirement by taking the first bus;

[0035] The estimated arrival time of the second bus is later than that of the first bus, and the time difference between the estimated arrival times is less than a preset time; the overlap between the stop sites of the second bus and the first bus is greater than a preset overlap.

[0036] In a third aspect, the present invention further provides an electronic device comprising a processor and a memory, wherein the memory is used to store computer program code, and the computer program code comprises computer instructions. When the processor executes the computer instructions, the electronic device executes the method as described in the first aspect above and any possible implementation thereof.

[0037] In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, wherein the computer program includes program instructions, and when the program instructions are executed by a processor of an electronic device, the processor executes the method as described in the first aspect above and any possible implementation thereof.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] 1) The present invention solves the problem of information opacity in the traditional public transportation system by updating the operation prompt information of the bus in real time on the digital display screen of the smart bus shelter, including the estimated arrival time of the vehicle, the number of available seats, and the degree of congestion in the bus. Through this information, passengers can be prompted and guided to conduct autonomous diversion, such as changing the type of bus they are waiting for in time, reducing the problem of some buses being too crowded and some buses being too idle, which can improve the passenger experience and improve the utilization rate of vehicle resources.

[0040] 2) In addition to providing detailed vehicle operation information to prompt users to independently dispatch passenger flow in the queue area, the present invention also introduces a passenger flow density monitoring mechanism. When it is detected that the passenger flow density in the first queue area is lower than the preset threshold, the behavior pattern of passengers getting on and off the bus can be predicted by analyzing historical data, and it is determined whether the distribution of passengers in the queue area needs to be adjusted. If adjustment is required, passengers in other queue areas can be intelligently guided to the first queue area, and vice versa, some passengers will be guided to the queue areas corresponding to other relatively idle vehicles to achieve the purpose of evenly distributing passengers. Through passenger flow density monitoring and historical data analysis, reasonable dispatch of passengers is achieved, station order is optimized, passengers' queuing experience is improved, and the efficiency of vehicle resource utilization is improved.

[0041] 3) In addition to scheduling the passenger flow distribution in the queue area, the present invention also considers reasonable scheduling of vehicle flow, including obtaining the operation data of each station after the first bus completes a trip, including the time deviation between the expected arrival time of the first bus and the actual arrival time, the passenger flow density in the queue area, the number of passengers in the car, and the predicted boarding and alighting behavior pattern; then calculating the vehicle comprehensive scheduling index based on the operation data of the station, and then comparing it with the ideal index to analyze whether to implement a vehicle scheduling strategy, such as reducing the departure interval, increasing the number of vehicles, or adjusting the departure time. By dynamically scheduling the operation plan of the vehicle, the rationality of the operation frequency and cycle is increased, the passengers' riding needs are met, the traffic pressure during peak hours is alleviated, and the problem of low vehicle utilization during off-peak hours causing waste of resources is avoided.

[0042] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the background technology, the drawings required for use in the embodiments of the present invention or the background technology will be described below.

[0044] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used to illustrate the technical solutions of the present disclosure together with the specification.

[0045] Figure 1 A schematic diagram of a flow chart of an operation control method based on a smart bus shelter provided in an embodiment of the present invention;

[0046] Figure 2 A schematic structural diagram of an operation control system based on a smart bus shelter provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0049] At present, the smart bus shelters in cities lack effective and reasonable management and control methods, and usually have some problems such as low information transparency, poor riding order, and large differences in passenger flow distribution, resulting in uneven utilization of different vehicles. To this end, the present invention aims to provide an operation control method based on a smart bus shelter, which can reasonably dispatch the passenger flow distribution in the queuing area and dynamically adjust the operation plan of the vehicle itself, thereby optimizing the riding order of the shelter, improving the passenger riding experience, and enhancing the utilization of vehicle resources.

[0050] See also Figure 1 , Figure 1 The present invention provides a flow chart of an operation control method based on a smart bus shelter. Figure 1 As shown, the method includes:

[0051] S10. Generate bus operation prompt information on the digital display screen of the smart bus shelter, and lock the bus with the shortest arrival time at the current time as the first bus according to the operation prompt information; the operation prompt information includes the vehicle's estimated arrival time, available seats and passenger congestion information.

[0052] In this embodiment, when obtaining the operation prompt information, it is necessary to establish or access the existing public transport GPS positioning system to obtain the location information of each bus in real time. The time for each bus to arrive at the designated station is calculated based on the real-time location information, and its arrival time is predicted, so that the estimated arrival time of the vehicle can be updated in real time on the digital display screen. When obtaining the vacant seat information, the number of passengers in the vehicle and the seat usage are collected through the on-board sensors, and the passenger crowding can be obtained by calculating the ratio of the number of passengers on the vehicle to the maximum passenger capacity.

[0053] It can be understood that the operation prompt information is mainly for all buses that can stop at the current smart bus shelter. For example, if there are 15 different bus routes that can stop at the station, the operation prompt information will include the operation information of these 15 buses. In order to carry out scheduling planning, first lock the bus with the shortest arrival time as the first bus according to the operation prompt information; for example, bus No. 101 will arrive at the station in 5 minutes, and other vehicles will take more than 5 minutes to arrive at the station, then you can first consider the scheduling planning of the queue area for bus No. 101, which can arrive at the station the fastest.

[0054] Bus shelters are usually divided into waiting areas and queuing areas. The waiting area mainly provides seats and a rest area for passengers who have been waiting for a long time, while the queuing area is set up to optimize the order of riding. When the vehicle arrives at the stop in a short time, in order to avoid passengers cutting in line or rushing to increase safety hazards, it is necessary to queue up in an orderly manner before the vehicle arrives at the station. For example, if the vehicle arrives in 3 minutes, the bus shelter will issue a queuing reminder to remind users to move from the waiting area to the queuing area to queue up, so that they can board the bus in an orderly manner.

[0055] In actual applications, passengers waiting for a bus usually choose the first one or two buses that arrive at the station. This is because most passengers have the highest demand for travel time and hope to get on the bus smoothly with the shortest waiting time. However, some passengers have a greater demand for travel experience than time. For example, there are two travel options: waiting a little longer to get on a bus with a seat, and waiting less to get on a crowded bus. These passengers will choose the first option because they are not in a hurry to travel and can sacrifice a certain waiting time to improve ride comfort.

[0056] However, the current bus booths only update the arrival time of different vehicles, but cannot provide information such as the congestion of the vehicles and the number of seats remaining in the vehicles. This will cause passengers in the waiting area to not understand the relevant situation of the bus and cannot choose a more suitable travel method. For example, bus B is only 2 minutes later than bus A. Both buses can meet the destination needs of passenger A. However, because passenger A does not know the situation of bus B, he directly gets on bus A. Bus A is crowded with many people, which brings a bad experience to passenger A. Although bus B is only 2 minutes late, the vehicle is relatively spacious. If passenger A can obtain the riding situation of bus B in advance, he is likely to choose to wait for 2 more minutes to take bus B, which also avoids further increasing the congestion of bus A and improves the riding comfort of passenger A.

[0057] Therefore, in this embodiment, the three kinds of information, namely the estimated arrival time of the vehicle, the available seats and the passenger congestion information, are used as operation prompt information and generated and displayed on the digital display screen of the smart bus shelter. In this way, the autonomous dispatch process of passengers can be realized, avoiding some queuing areas being very crowded and some being very sparse, and reasonably realizing the dispatch of passenger flow distribution to improve the utilization rate of different bus resources.

[0058] S20. When the queuing time for entering the first bus is determined, the passengers are guided to move from the waiting area to the first queuing area at the boarding entrance to queue up; the passenger flow density of the passengers in the first queuing area is calculated according to the queuing situation, and it is determined whether the passenger flow density is less than a preset density value.

[0059] It is understandable that since bus shelters are usually divided into waiting areas and queuing areas, although the first bus is the fastest among all vehicles to reach the station, if the waiting time is still relatively long, such as 10 minutes, then for the comfort of passengers it is usually recommended to wait in the waiting area. Once the queuing time begins, for example, if the first bus starts queuing within 3 minutes before the expected arrival, passengers can be guided from the waiting area to the first queuing area at the boarding entrance to queue. This can manage the waiting order of the bus shelter in a more orderly manner, avoiding early queuing that increases passenger fatigue, thereby reducing user experience; it can also avoid the lack of reasonable queuing control when the vehicle arrives, resulting in queue jumping and crowded boarding that cause dangerous accidents, thereby enhancing the safety control efficiency of the shelter.

[0060] Furthermore, when calculating the passenger flow density of the passengers in the first queue area according to the queuing situation, first determine the scope of the first queue area to be monitored, and use ground markings or physical isolation facilities to clearly define the boundaries of the queue area. Install appropriate monitoring equipment in the first queue area, such as cameras, infrared sensors or other people counting equipment, to ensure that the equipment covers the entire queue area and can accurately identify the number of people entering and leaving the queue area. Then, the monitoring equipment continuously collects information on changes in the number of people in the queue area, and the data is transmitted to the central processing server or cloud for processing via a wired or wireless network. Measure or know the area of ​​the queue area, and use the monitoring equipment to count the total number of people in the queue area in real time. The passenger flow density is equal to the ratio of the total number of people in the queue area to the area of ​​the queue area, in units of people / square meter.

[0061] After calculating the passenger flow density, set a reasonable preset density value based on safety standards, comfort requirements or past experience. This value should take into account the best practices in different scenarios, such as the minimum space requirements recommended in emergency evacuation situations. Compare the calculated actual passenger flow density with the preset density value. If the actual passenger flow density is less than the preset density value, it indicates that the queue is in good condition; if it is greater than the preset density value, there may be a risk of congestion. For queue-jumping, congestion or dangerous behavior found during the queuing process, an early warning signal should be issued to notify the management staff to take measures.

[0062] S30. If yes, predict the boarding and alighting behavior pattern of the passengers according to the historical operation data of the first bus, and determine whether the first queuing area needs to be dispatched according to the passenger congestion of the first bus, the passenger flow density of the next stop, and the boarding and alighting behavior pattern; if dispatching is required, monitor and identify the first target passengers who can be dispatched in other queuing areas, and guide the first target passengers to the first queuing area within the dispatchable range of the first queuing area.

[0063] When the passenger flow density is less than the preset density value, the historical operation data of the first bus is first collected, including but not limited to the number of passengers getting on and off at each stop, the distribution of travel time, etc. Then, machine learning methods (such as time series analysis, cluster analysis, etc.) are used to analyze these data to find out the behavior patterns of passengers getting on and off the bus. A boarding and alighting prediction model is established based on historical data, which can predict the number of passengers getting on and off the first bus at each stop within a specific time period. Combined with the historical data of the next stop that the first bus is about to arrive at, the passenger flow density of the next stop is predicted.

[0064] Furthermore, according to the passenger congestion of the first bus, the passenger flow density of the next stop, and the boarding and alighting behavior pattern, it is determined whether the first queue area needs to be dispatched. Specifically, a multi-input neural network model is constructed, preferably a model is trained based on an LSTM network, including:

[0065] Input layer: data corresponding to passenger congestion, passenger flow density, and boarding and alighting behavior patterns.

[0066] Passenger crowding input: It can be a set of values, indicating the number of passengers or the degree of crowding on the current bus.

[0067] Passenger flow density input: It is also a set of values, reflecting the passenger density of the next stop.

[0068] Boarding and alighting behavior pattern input: It can be a multidimensional array or sequence data, containing the changes in the number of boarding and alighting passengers over a period of time.

[0069] Data processing layer: For passenger congestion and passenger flow density, a simple fully connected layer can be used to convert the congestion value into a higher-dimensional feature representation. For the time series data of boarding and alighting behavior patterns, a gated recurrent unit (GRU) is used to capture temporal dependencies.

[0070] Integration layer: completes the vector splicing of different processing layers;

[0071] Fully connected layer: learns higher-level abstract features from the features extracted by the integration layer;

[0072] Activation function: Use the Sigmoid function to output a probability value between 0 and 1, indicating the possibility of scheduling.

[0073] Based on the above structure, a LSTM prediction model is trained using a large amount of data from historical operations. When applied, it is only necessary to input the passenger congestion of the first bus, the passenger flow density of the next stop, and the boarding and alighting behavior pattern into the prediction model to quickly analyze whether scheduling is needed.

[0074] If dispatching is required, monitor and identify the first target passengers who can be dispatched in other queue areas, and guide the first target passengers to the first queue area within the dispatchable range of the first queue area.

[0075] Preferably, the first target passenger is a passenger who can meet the destination arrival requirement by taking the first bus;

[0076] First, the video stream is processed using computer vision technology to identify passengers in the queue area. Passengers are classified into different groups based on their behavioral characteristics such as waiting time and movement direction, such as passengers waiting to get on the bus, passengers who have just gotten off the bus and are looking for the exit, etc. The algorithm selects the first target passengers who have been waiting for a long time, have the same destination and are willing to accept the dispatch. Finally, dispatch information is released to passengers through multiple channels such as digital display screens and mobile phone applications to guide the first target passengers to the first queue area.

[0077] If no dispatch is required, just maintain the current number of people and order in the queue area.

[0078] S40: If not, determine the second target passenger to be dispatched from the first queuing area, traverse the bus operation prompt information on the digital display screen to find the second bus associated with the first bus, and dispatch the second target passenger to the second queuing area of ​​the second bus.

[0079] When the passenger flow density is greater than or equal to the preset density value, in order to optimize the passenger flow distribution, it is necessary to determine the second target passengers to be called out from the first queue area. The second target passengers are usually passengers at the back of the queue. For example, the first row area can normally queue 30 people, but there are 40 people in the queue at this time. In this case, the last 10 passengers can be regarded as the second target passengers, and then find a second bus for them to replace, so as to divert these passengers to the second queue area of ​​the second bus.

[0080] Preferably, the second bus is expected to arrive at the station later than the first bus, and the time difference between the expected arrival times is less than a preset time; the overlap between the stops of the second bus and the first bus is greater than a preset overlap. It can be understood that the time difference between the expected arrival times is less than the preset time, which can avoid the second target passenger from waiting for too long after being dispatched, thereby alleviating the negative emotions of the second target passenger while waiting for the bus, and the overlap between the stops of the second bus and the first bus is greater than the preset overlap, which can ensure that the destination needs of the second target passenger can be met after changing buses.

[0081] In summary, this embodiment solves the problem of information opacity in the traditional public transportation system by updating the operation prompt information of the bus in real time on the digital display screen of the smart bus shelter, including the estimated arrival time of the vehicle, the number of empty seats, and the degree of crowding in the bus. Through this information, passengers can be prompted and guided to conduct autonomous diversion, such as changing the type of bus they are waiting for in time, reducing the problem of some buses being too crowded and some buses being too idle, which can improve the passenger experience and improve the utilization rate of vehicle resources.

[0082] In addition, in addition to providing detailed vehicle operation information to prompt users to independently dispatch passenger flow in the queue area, this embodiment also introduces a passenger flow density monitoring mechanism. When it is detected that the passenger flow density in the first queue area is lower than the preset threshold, the behavior pattern of passengers getting on and off the bus can be predicted by analyzing historical data, and it is determined whether the distribution of passengers in the queue area needs to be adjusted. If adjustment is required, passengers in other queue areas can be intelligently guided to the first queue area, and vice versa, some passengers will be guided to the queue areas corresponding to other relatively idle vehicles to achieve the purpose of evenly distributing passengers. Through passenger flow density monitoring and historical data analysis, reasonable dispatch of passengers is achieved, station order is optimized, and the queuing waiting experience of passengers is improved, while the efficiency of vehicle resource utilization is improved.

[0083] In one embodiment, the method further comprises:

[0084] When the first bus completes a trip, the operation data of each stop is obtained; the operation data includes the time deviation between the expected arrival time of the first bus and the actual arrival time, the passenger flow density in the queuing area, the number of passengers in the bus, and the predicted boarding and alighting behavior pattern;

[0085] Calculate the comprehensive vehicle dispatch index based on the station's operating data:

[0086]

[0087] Where i represents the i-th stop, I i represents the comprehensive vehicle dispatch index, ΔT i It represents the time difference between the expected arrival time and the actual arrival time, W i represents the passenger flow density in the queuing area, P i represents the number of passengers in the car, U i , D i They represent the predicted number of people getting on and the predicted number of people getting off, respectively. max represents the maximum passenger capacity of the vehicle, α, β, and γ represent adjustment factors, and their value ranges are all (0.1, 1);

[0088] Determine the comprehensive vehicle dispatch index I i With ideal index I t relationship;

[0089] When I i >I t When , execute the vehicle dispatch strategy;

[0090] When I i ≤I t The current departure plan remains unchanged.

[0091] Preferably, the executing vehicle dispatching strategy includes reducing the departure interval, increasing the number of vehicles or adjusting the departure time.

[0092] In this embodiment, 1+αln(1+W i ) uses a logarithmic function to reflect the impact of passenger flow density. As W i With the increase of the amount of water, its influence gradually increases. Consider the current congestion of the vehicle and the difference between the number of people getting on and getting off. If the number of people getting on is much greater than the number of people getting off, the congestion will increase; vice versa. 1+γΔT i It reflects that the greater the time deviation, the greater the scheduling difficulty, so a proportional relationship is used to reflect its impact.

[0093] Therefore, the above formula introduces nonlinear relationships through logarithmic functions and absolute value functions, so that the formula can better adapt to complex situations in actual scenarios. By adjusting factors α, β, and γ, the importance of each factor can be flexibly adjusted according to actual conditions. Since the three main factors of queue passenger flow density, in-vehicle congestion, and time deviation are considered at the same time, the key points in the scheduling decision are reflected, which can increase the rationality and accuracy of the scheduling decision.

[0094] In summary, in addition to the scheduling of passenger flow distribution in the queue area in the aforementioned embodiment, this embodiment also considers reasonable scheduling of vehicle flow, including obtaining the operation data of each station after the first bus completes a trip, including the time deviation between the expected arrival time of the first bus and the actual arrival time, the passenger flow density in the queue area, the number of passengers in the car, and the predicted boarding and alighting behavior pattern; then calculating the vehicle comprehensive scheduling index based on the operation data of the station, and then comparing it with the ideal index to analyze whether to implement a vehicle scheduling strategy, such as reducing the departure interval, increasing the number of vehicles, or adjusting the departure time. By dynamically scheduling the operation plan of the vehicle, the rationality of the operation frequency and cycle is increased, the passengers' riding needs are met, the traffic pressure during peak hours is alleviated, and the problem of low vehicle utilization during off-peak hours causing waste of resources is avoided.

[0095] See also Figure 2 In one embodiment, the present invention further provides an operation control system based on a smart bus shelter, the system comprising:

[0096] The prompt information generating unit 100 is used to generate bus operation prompt information on the digital display screen of the smart bus shelter, and lock the bus with the shortest arrival time at the current time as the first bus according to the operation prompt information; the operation prompt information includes the estimated arrival time of the vehicle, the available seats and the passenger congestion information;

[0097] The passenger flow density calculation unit 200 is used to guide passengers to move from the waiting area to the first queue area at the boarding entrance to queue up when the queue time for entering the first bus is determined; calculate the passenger flow density of passengers in the first queue area according to the queue situation, and determine whether the passenger flow density is less than a preset density value;

[0098] The passenger diversion planning unit 300 is used to predict the passenger boarding and alighting behavior pattern according to the historical operation data of the first bus when the passenger flow density is less than the preset density value, and determine whether the first queue area needs to be dispatched according to the passenger congestion of the first bus, the passenger flow density of the next stop, and the boarding and alighting behavior pattern; if dispatching is required, monitor and identify the dispatchable first target passengers in other queue areas, and divert the first target passengers to the first queue area within the dispatchable range of the first queue area;

[0099] The passenger dispatch planning unit 400 is used to determine the second target passenger to be dispatched from the first queuing area when the passenger flow density is greater than or equal to a preset density value, traverse the bus operation prompt information on the digital display screen to find the second bus associated with the first bus, and dispatch the second target passenger to the second queuing area of ​​the second bus.

[0100] In one embodiment, the system further comprises a vehicle dispatch planning unit, configured to:

[0101] When the first bus completes a trip, the operation data of each stop is obtained; the operation data includes the time deviation between the expected arrival time of the first bus and the actual arrival time, the passenger flow density in the queuing area, the number of passengers in the bus, and the predicted boarding and alighting behavior pattern;

[0102] Calculate the comprehensive vehicle dispatch index based on the station's operating data:

[0103]

[0104] Where i represents the i-th stop, I i represents the comprehensive vehicle dispatch index, ΔT i It represents the time difference between the expected arrival time and the actual arrival time, W i represents the passenger flow density in the queuing area, P i represents the number of passengers in the car, U i , D i They represent the predicted number of people getting on and the predicted number of people getting off, respectively. max represents the maximum passenger capacity of the vehicle, α, β, and γ represent adjustment factors, and their value ranges are all (0.1, 1);

[0105] Determine the comprehensive vehicle dispatch index I i With ideal index I t relationship;

[0106] When I i >I t When , execute the vehicle dispatch strategy;

[0107] When I i ≤I t The current departure plan remains unchanged.

[0108] In one embodiment, executing the vehicle dispatching strategy includes reducing the departure interval, increasing the number of vehicles, or adjusting the departure time.

[0109] In one embodiment, the first target passenger is a passenger who can meet the destination arrival requirement by taking the first bus;

[0110] The estimated arrival time of the second bus is later than that of the first bus, and the time difference between the estimated arrival times is less than a preset time; the overlap between the stop sites of the second bus and the first bus is greater than a preset overlap.

[0111] It can be understood that the functions or modules included in the system provided in this embodiment can be used to execute the method described in the above method embodiment. Its specific implementation can refer to the description of the above method embodiment. For the sake of brevity, it will not be repeated here.

[0112] The present invention also provides an electronic device, including a processor and a memory, wherein the memory is used to store computer program code, and the computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device executes a method as described in any possible implementation manner.

[0113] The present invention also provides a computer-readable storage medium, in which a computer program is stored. The computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes a method as described in any possible implementation manner.

[0114] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0115] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. Those skilled in the art can also clearly understand that the descriptions of the various embodiments of the present invention have different focuses. For the convenience and brevity of description, the same or similar parts may not be repeated in different embodiments. Therefore, for parts not described or not described in detail in a certain embodiment, refer to the records of other embodiments.

Claims

1. An operation control method based on a smart bus shelter, characterized in that: The method comprises: Generate bus operation prompt information on the digital display screen of the smart bus shelter, and lock the bus with the shortest arrival time at the current time as the first bus according to the operation prompt information; the operation prompt information includes the estimated arrival time of the vehicle, available seats and passenger congestion information; When the queue time for entering the first bus is determined, the passengers are guided to move from the waiting area to the first queue area at the boarding entrance to queue; the passenger flow density of the passengers in the first queue area is calculated according to the queue situation, and it is determined whether the passenger flow density is less than a preset density value; If yes, predict the boarding and alighting behavior pattern of passengers according to the historical operation data of the first bus, and determine whether the first queue area needs to be dispatched according to the passenger congestion of the first bus, the passenger flow density of the next stop, and the boarding and alighting behavior pattern; if dispatching is required, monitor and identify the first target passengers who can be dispatched in other queue areas, and guide the first target passengers to the first queue area within the dispatchable range of the first queue area; If not, determine the second target passenger to be dispatched from the first queuing area, traverse the bus operation prompt information on the digital display screen to find the second bus associated with the first bus, and dispatch the second target passenger to the second queuing area of ​​the second bus.

2. The operation control method based on the smart bus shelter according to claim 1 is characterized in that: The method further comprises: When the first bus completes a trip, the operation data of each stop is obtained; the operation data includes the time deviation between the expected arrival time of the first bus and the actual arrival time, the passenger flow density in the queuing area, the number of passengers in the bus, and the predicted boarding and alighting behavior pattern; Calculate the comprehensive vehicle dispatch index based on the station's operating data: Where i represents the i-th stop, I i represents the comprehensive vehicle dispatch index, ΔT i It represents the time difference between the expected arrival time and the actual arrival time, W i represents the passenger flow density in the queuing area, P i represents the number of passengers in the car, U i , D i They represent the predicted number of people getting on and the predicted number of people getting off, respectively. max represents the maximum passenger capacity of the vehicle, α, β, and γ represent adjustment factors, and their value ranges are all (0.1, 1); Determine the comprehensive vehicle dispatch index I i With ideal index I t relationship; When I i >I t When , execute the vehicle dispatch strategy; When I i ≤I t The current departure plan remains unchanged.

3. The operation control method based on the smart bus shelter according to claim 2 is characterized in that: The implementation of the vehicle dispatching strategy includes reducing the departure interval, increasing the number of vehicles or adjusting the departure time.

4. The operation control method based on the smart bus shelter according to claim 1 is characterized in that: The first target passenger is a passenger who can meet the demand of reaching the destination by taking the first bus; The estimated arrival time of the second bus is later than that of the first bus, and the time difference between the estimated arrival times is less than a preset time; the overlap between the stop sites of the second bus and the first bus is greater than a preset overlap.

5. An operation control system based on a smart bus shelter, characterized in that: The system comprises: A prompt information generating unit is used to generate bus operation prompt information on the digital display screen of the smart bus shelter, and lock the bus with the shortest arrival time at the current time as the first bus according to the operation prompt information; the operation prompt information includes the estimated arrival time of the vehicle, the available seats and the passenger congestion information; A passenger flow density calculation unit is used to guide passengers to move from the waiting area to the first queue area at the boarding entrance to queue up when the queue time for entering the first bus is determined; calculate the passenger flow density of passengers in the first queue area according to the queue situation, and determine whether the passenger flow density is less than a preset density value; The passenger diversion planning unit is used to predict the passenger boarding and alighting behavior pattern according to the historical operation data of the first bus when the passenger flow density is less than the preset density value, and determine whether the first queue area needs to be dispatched according to the passenger congestion of the first bus, the passenger flow density of the next stop, and the boarding and alighting behavior pattern; if dispatching is required, monitor and identify the dispatchable first target passengers in other queue areas, and divert the first target passengers to the first queue area within the dispatchable range of the first queue area; The passenger dispatch planning unit is used to determine the second target passenger to be dispatched from the first queuing area when the passenger flow density is greater than or equal to the preset density value, traverse the bus operation prompt information on the digital display screen to find the second bus associated with the first bus, and dispatch the second target passenger to the second queuing area of ​​the second bus.

6. The operation control system based on the smart bus shelter according to claim 5 is characterized in that: The system also includes a vehicle dispatch planning unit, which is used to: When the first bus completes a trip, the operation data of each stop is obtained; the operation data includes the time deviation between the expected arrival time of the first bus and the actual arrival time, the passenger flow density in the queuing area, the number of passengers in the bus, and the predicted boarding and alighting behavior pattern; Calculate the comprehensive vehicle dispatch index based on the station's operating data: Where i represents the i-th stop, I i represents the comprehensive vehicle dispatch index, ΔT i It represents the time difference between the expected arrival time and the actual arrival time, W i represents the passenger flow density in the queuing area, P i represents the number of passengers in the car, U i , D i They represent the predicted number of people getting on and the predicted number of people getting off, respectively. max represents the maximum passenger capacity of the vehicle, α, β, and γ represent adjustment factors, and their value ranges are all (0.1, 1); Determine the comprehensive vehicle dispatch index I i With ideal index I t relationship; When I i >I t When , execute the vehicle dispatch strategy; When I i ≤I t The current departure plan remains unchanged.

7. The operation control system based on the smart bus shelter according to claim 6 is characterized in that: The implementation of the vehicle dispatching strategy includes reducing the departure interval, increasing the number of vehicles or adjusting the departure time.

8. The operation control system based on the smart bus shelter according to claim 5 is characterized in that: The first target passenger is a passenger who can meet the demand of reaching the destination by taking the first bus; The estimated arrival time of the second bus is later than that of the first bus, and the time difference between the estimated arrival times is less than a preset time; the overlap between the stop sites of the second bus and the first bus is greater than a preset overlap.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory is used to store computer program codes, wherein the computer program codes include computer instructions. When the processor executes the computer instructions, the electronic device executes the operation control method based on the smart bus shelter as described in any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes the operation control method based on a smart bus shelter as described in any one of claims 1 to 4.

Images