Intelligent public transport combined scheduling method and device, and storage medium

Abstract

The present application relates to a kind of wisdom public transport combined scheduling method, device and storage medium, it is related to scheduling optimization field, call bus card record establishes card site feature set, establishes navigation site trigger and carries out navigation record matching analysis, establishes space-time heat forecast graph;Multi-source traffic flow data set is constructed to carry out road congestion state prediction and construct regional level road congestion state graph;According to space-time heat forecast graph, regional level road congestion state graph, establish site passenger flow demand, line travel time and congestion state;Configure multi-objective scheduling channel, and site passenger flow demand, line travel time and congestion state are used as input data, by passenger waiting time target, scheduling cost target, vehicle utilization rate target, congestion influence target, line bus scheduling optimization is carried out, the technical problem that the present application solves is that there is data utilization insufficient, prediction precision is limited and scheduling strategy lacks flexibility in bus scheduling.

Description

Technical Field

[0001] This invention relates to the field of scheduling optimization, and in particular to a smart bus combined scheduling method, device and storage medium. Background Technology

[0002] With the acceleration of urbanization and continuous population growth, public transportation plays a crucial role in urban travel. Traditional bus dispatching methods often rely on manual experience and static data, with dispatchers manually setting and adjusting bus departure times and routes based on historical data and current road conditions. However, with the rapid pace of urbanization and increased population mobility, traditional bus dispatching methods struggle to accurately reflect real-time passenger demand and road conditions, leading to problems such as low operational efficiency and long passenger waiting times. Therefore, based on the development of smart cities, an intelligent bus dispatching method has emerged, which leverages the internet to optimize bus dispatching.

[0003] However, existing bus dispatching methods also have certain limitations. On the one hand, existing bus dispatching methods lack real-time performance and accuracy. Due to limitations in data collection and processing methods, dispatchers struggle to obtain crucial information such as passenger demand and road congestion in a timely manner, causing dispatching plans to often lag behind actual conditions and fail to respond promptly to changes in passenger demand and road conditions. On the other hand, existing bus dispatching methods lack intelligence and automation, making the dispatching process susceptible to human factors. This results in suboptimal dispatching plans that fail to maximize the utilization of bus resources and improve operational efficiency and service quality. Summary of the Invention

[0004] This invention addresses the technical problems of insufficient data utilization, limited prediction accuracy, and lack of flexibility in scheduling strategies in existing public transport scheduling technologies by providing a smart public transport combined scheduling method, device, and storage medium.

[0005] The technical solution of the present invention to solve the above-mentioned technical problems is as follows:

[0006] In a first aspect, the present invention provides a smart bus combined scheduling method, the method comprising: calling bus card swiping records to establish a card swiping station feature set; establishing a navigation station trigger, using the navigation station trigger to perform navigation record matching analysis, and establishing a spatiotemporal heat prediction map based on the matching analysis results and the card swiping station feature set; constructing a multi-source traffic flow dataset, using the multi-source traffic flow dataset to predict road congestion status, and constructing a regional road congestion status map; establishing station passenger flow demand, route travel time, and congestion status based on the spatiotemporal heat prediction map and the regional road congestion status map; configuring a multi-objective scheduling channel, using the station passenger flow demand, route travel time, and congestion status as input data, and optimizing bus scheduling for routes through passenger waiting time objectives, scheduling cost objectives, vehicle utilization rate objectives, and congestion impact objectives, and establishing optimization results; and performing bus scheduling management based on the optimization results.

[0007] Secondly, the present invention provides a smart bus combined dispatching device, the device comprising: an information retrieval module for retrieving bus card swiping records and establishing a card swiping station feature set; a matching analysis module for establishing navigation station triggers, performing navigation record matching analysis using the navigation station triggers, and establishing a spatiotemporal heat prediction map based on the matching analysis results and the card swiping station feature set; a status prediction module for constructing a multi-source traffic flow dataset, performing road congestion status prediction using the multi-source traffic flow dataset, and constructing a regional-level road congestion status map; an information flow module for establishing station passenger flow demand, route travel time, and congestion status based on the spatiotemporal heat prediction map and the regional-level road congestion status map; a channel configuration module for configuring multi-objective dispatching channels, taking the station passenger flow demand, route travel time, and congestion status as input data, optimizing bus dispatching based on passenger waiting time targets, dispatching cost targets, vehicle utilization rate targets, and congestion impact targets, and establishing optimization results; and a dispatching management module for managing bus dispatching based on the optimization results.

[0008] Thirdly, the present invention provides a computer device, the computer device comprising:

[0009] Memory, used to store executable instructions;

[0010] The processor, when running the executable instructions stored in the memory, implements the intelligent bus combination scheduling method described in the first aspect.

[0011] Fourthly, the present invention provides a non-transitory computer-readable storage medium storing a computer software program, which, when executed by a processor, implements a smart bus combination scheduling method as described in the first aspect.

[0012] The beneficial effects of this invention are as follows: By establishing a feature set through bus card swiping records, combining navigation record matching analysis to construct a spatiotemporal heat map, and using multi-source traffic flow data to predict road congestion status, a model of station passenger demand, route travel time, and congestion status is established based on the prediction results. By configuring multi-objective scheduling channels for route bus scheduling optimization, bus scheduling efficiency can be effectively improved, passenger waiting time reduced, scheduling costs lowered, vehicle utilization increased, and the impact of traffic congestion mitigated. Attached Figure Description

[0013] Figure 1 This is a flowchart illustrating a smart bus combination scheduling method provided by the present invention.

[0014] Figure 2 This is a schematic diagram of the structure of a smart bus combined dispatching device provided by the present invention.

[0015] Figure 3 This is a schematic diagram of the structure of a computer-readable storage medium provided by the present invention.

[0016] Explanation of reference numerals in the attached figures: Information retrieval module 11, matching analysis module 12, status prediction module 13, information flow module 14, channel configuration module 15, scheduling management module 16, computer-readable storage medium 600, first computer program 611. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0019] In the description of this invention, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed herein.

[0020] Example 1:

[0021] like Figure 1 As shown in the figure, an embodiment of the present invention provides a smart bus combination scheduling method, the method comprising:

[0022] S10: Retrieve bus card swiping records and establish a feature set of card swiping stations.

[0023] For example, in intelligent bus scheduling, the first step is to access bus card swipe records, which form the basis of data collection. These records contain information such as the boarding and alighting points and times for each passenger's bus ride. By organizing and analyzing these records, a card swipe station feature set can be established. This feature set is a dataset containing multiple feature terms, primarily reflecting passenger travel patterns and station preferences. For instance, if a station experiences a large number of passengers swiping their cards to board during morning and evening rush hours, it might be labeled a "peak-hour hotspot station"; conversely, if a station consistently sees a fixed number of passengers swiping their cards to board and alight, it might be labeled a "stable passenger flow station." The feature set can be adaptively adjusted based on actual needs during its establishment. For example, during specific holidays or events, passenger flow at certain stations may change significantly. Updating the feature set reflects these changes, better adapting to the actual situation. Furthermore, in-depth analysis of the feature set can uncover potential travel patterns and trends, providing more accurate data support for subsequent bus scheduling.

[0024] S20: Establish a navigation site trigger, use the navigation site trigger to perform navigation record matching analysis, and establish a spatiotemporal heat prediction map based on the matching analysis results and the card swiping site feature set.

[0025] Optionally, a navigation site trigger can be established. This trigger mechanism is activated when a passenger uses specific navigation software, based on their location and selected destination. For example, if a passenger in location A uses a travel navigation app to navigate to location B, the navigation site trigger mechanism is activated based on their location and destination information. Subsequently, the data obtained from this navigation site trigger is used for navigation record matching analysis. The system compares the navigation records of different passengers, analyzing similarities and correlations, such as analyzing navigation records from similar departure points to similar destinations within the same time period. Furthermore, based on the results of the matching analysis, and combined with a card-swiping station feature set, which covers multi-dimensional information such as card-swiping time, card-swiping location, pedestrian traffic around the station, and station type (e.g., whether it is a transfer station), the card-swiping records of a large transfer station will show characteristics such as concentrated card-swiping times and high pedestrian traffic during weekday morning rush hours. By combining this information, a spatiotemporal heat map is created. This map can intuitively show the popularity of public transportation stations in different regions and time periods. For example, it can predict that the popularity of bus stations near a commercial area will increase significantly on weekend afternoons, providing a strong basis for public transportation operation scheduling, resource allocation, and passenger travel planning.

[0026] S30: Construct a multi-source traffic flow dataset, use the multi-source traffic flow dataset to predict road congestion status, and construct a regional road congestion status map.

[0027] Specifically, a multi-source traffic flow dataset is constructed. This dataset integrates traffic data from different channels and of different types. For example, real-time traffic flow video data from traffic cameras can be analyzed to obtain the number of vehicles passing through a specific road segment per unit time; vehicle speed data collected by induction coils installed on the road can accurately reflect the speed of vehicles; and GPS positioning data from floating cars (such as taxis and ride-hailing vehicles) can track vehicle trajectories and dwell times. These data sources are extensive and diverse, constituting a rich information dimension for the multi-source traffic flow dataset.

[0028] After constructing a multi-source traffic flow dataset, this dataset is used to predict road congestion. Data analysis algorithms and models are employed to perform in-depth mining and analysis of the multi-source data. For example, by analyzing the changing patterns of historical traffic flow data over different time periods, combined with current real-time traffic flow, vehicle speed, and construction information on surrounding roads, road congestion can be predicted for a future period. If a road historically experiences consistently high traffic flow during weekday morning and evening rush hours, and current real-time data shows a continuous increase in traffic flow, while construction is underway in the surrounding area, then congestion on that road can be predicted.

[0029] Finally, based on the road congestion prediction results, a regional road congestion map is constructed. This map visually displays the congestion status of various roads within a specific area, using different colors to represent different levels of congestion: red for severe congestion, yellow for mild congestion, and green for unobstructed traffic. Taking a city's core commercial district as an example, the regional road congestion map clearly shows the congestion status of main roads, secondary roads, and branch roads at different times. Traffic management departments can use this map to adjust traffic light durations, plan traffic diversion routes, and guide vehicles to flow more efficiently, thereby effectively alleviating regional traffic congestion.

[0030] S40: Establish station passenger flow demand, route travel time, and congestion status based on the spatiotemporal heat map and the regional road congestion status map.

[0031] Furthermore, subsequent analysis is conducted based on the previously obtained spatiotemporal heat map and regional road congestion map. The spatiotemporal heat map is generated based on a comprehensive analysis of various traffic-related data. It integrates temporal and spatial dimensions, clearly showing the traffic heat of different areas at different times. For example, a commercial area may experience high heat during weekday evening rush hours, indicating a large flow of people and vehicles. The regional road congestion map focuses on the road level, presenting the congestion status of various roads within a specific area through real-time data and predictive models. For instance, a main road is prone to congestion on rainy days, which will be visually represented on the map by different colors or symbols. Based on these two maps, passenger flow demand at bus stops can be further established. Taking bus stops as an example, combined with the spatiotemporal heat map, if an area experiences high heat during a specific time period, it indicates a large potential passenger flow demand for bus stops in the surrounding area. For instance, if the heat of an area where a large shopping mall is located increases significantly on weekends, it can be inferred that the passenger flow entering nearby bus stops will increase accordingly. Meanwhile, by referring to the regional road congestion map, if the roads leading to the area are severely congested, some passengers who originally planned to take the bus may change their travel methods, which will also affect the passenger flow demand at the station. By taking into account these factors, a more accurate passenger flow demand model for the station can be established.

[0032] Meanwhile, for establishing route travel time, spatiotemporal heat maps can provide trends in pedestrian and vehicle traffic in different areas at different times, while regional road congestion maps can clearly show the actual traffic conditions of each road. For example, if a bus route passes through multiple areas, and one of those areas is busy during the morning rush hour with congested surrounding roads, the bus's stop time at that area may be extended due to increased passenger boarding and alighting. At the same time, the bus's speed on ground sections or at junctions with other modes of transportation will also decrease due to road congestion. By combining this information, an accurate travel time model for the route can be established.

[0033] Regarding the establishment of congestion status, regional road congestion maps themselves directly reflect the road congestion situation. However, combining them with spatiotemporal heat map prediction can further uncover the underlying causes and patterns of congestion. For example, if a region experiences a sharp increase in popularity during a specific event, and surrounding roads become congested, analysis can clearly identify that the large influx of people and vehicles brought by the event caused the congestion. This allows for the establishment of a more comprehensive congestion status assessment system, providing a strong basis for subsequent traffic management and congestion control.

[0034] S50: Configure a multi-objective scheduling channel, take the passenger flow demand of the station, the route travel time and the congestion status as input data, and optimize the bus route scheduling through passenger waiting time objective, scheduling cost objective, vehicle utilization objective and congestion impact objective, and establish the optimization result.

[0035] S60: Perform bus dispatch management based on the optimization results.

[0036] Specifically, public transportation operation management requires the configuration of multi-objective dispatch channels. These channels can be understood as information processing hubs that integrate key input data such as station passenger flow demand, route travel time, and congestion status. Station passenger flow demand reflects the boarding and alighting needs of passengers at various bus stops during different time periods. For example, during weekday morning rush hours, passenger flow demand at stops near schools and office buildings increases significantly. Route travel time encompasses the entire journey of a bus from its starting station to its terminal station, including stop times at each stop and travel time along the route. Congestion status reflects the current traffic conditions on the road, such as severe congestion on a main road due to a traffic accident.

[0037] After importing these input data into the multi-objective scheduling channel, the bus route scheduling is optimized based on passenger waiting time objectives, scheduling cost objectives, vehicle utilization objectives, and congestion impact objectives. The passenger waiting time objective aims to minimize passenger waiting time at stops and improve the travel experience, for example, by scheduling bus departure intervals more rationally to reduce passenger waiting time. The scheduling cost objective focuses on reducing bus operating costs while ensuring service quality, such as by rationally allocating the number of vehicles and routes to reduce unnecessary fuel consumption and vehicle wear and tear. The vehicle utilization objective aims to ensure that every bus is fully utilized and avoids vehicle idleness, such as by flexibly allocating vehicles according to passenger flow demand to increase vehicle occupancy rates. The congestion impact objective, as a reverse externality indicator, is used to assess the impact of buses on road traffic congestion. For example, if a large number of buses enter congested sections during peak hours, it may further exacerbate road congestion; therefore, the scheduling plan needs to be optimized to reduce this negative impact.

[0038] For example, a bus route in a city passes through a commercial area, a residential area, and a school. During the morning rush hour, passenger demand is high near the school. If conventional scheduling is followed, a large number of buses entering the area at once could exacerbate traffic congestion in the surrounding area. In this case, optimizing the multi-objective scheduling channel will comprehensively consider the above four objectives and adjust the departure time and routes of the buses. For example, the departure time of some buses may be advanced, or some buses may be rerouted to other less congested sections of the road, in order to balance passenger waiting time, scheduling costs, vehicle utilization, and the impact on congestion.

[0039] After optimization, an optimized result is established, which includes information such as the improved bus departure schedule and routes. Based on this result, bus dispatching and management can be carried out, bus operations can be rationally arranged, the overall operational efficiency and service quality of the public transportation system can be improved, and a more convenient and comfortable travel environment can be provided for passengers.

[0040] In a preferred embodiment, the step of establishing a spatiotemporal heat prediction map based on the matching analysis results and the feature set of the card-swiping station includes: establishing station function labels, station co-occurrence probability labels, and station passenger density gradient labels; using the station function labels, station co-occurrence probability labels, and station passenger density gradient labels to predict the destination station of passengers boarding at the station, and establishing a destination prediction result; using the destination prediction result to establish a passenger station path, and updating the destination prediction result and the passenger station path to the spatiotemporal heat prediction map.

[0041] In a specific implementation, a series of labels need to be established during the construction of the spatiotemporal heat map. Among these, the station function label identifies the main attributes of the station, such as classifying stations into types like office areas, residential areas, commercial districts, and schools. These areas are typically locations with a high probability of passengers boarding and alighting. For example, a station located in an area with a high concentration of office buildings would be labeled "office area," as these stations experience high passenger flow during morning and evening rush hours. The station co-occurrence probability label reflects passenger travel habits, i.e., a passenger frequently boards at station A and then stops near station B. By collecting and analyzing a large amount of passenger travel data, co-occurrence relationships between these stations can be identified. For example, many office workers may board at station A near their residence and alight at station B near their workplace every day; this regular travel behavior will be captured by the station co-occurrence probability label. The station passenger density gradient label is defined based on the difference in the number of passengers boarding and alighting at a station within a specific time period. If the number of passengers alighting at a station significantly exceeds the number of passengers boarding within a certain period, then this station is likely a drop-off point. For example, on a weekend afternoon, a large number of passengers may get off at a station near a large shopping mall to enter the mall for shopping, while the number of passengers getting on is relatively small. At this time, the station will show obvious characteristics of a drop-off point.

[0042] After establishing these labels, the destination stations of passengers boarding at each station are predicted using station function labels, station co-occurrence probability labels, and station passenger density gradient labels. Taking a passenger boarding at an office area station as an example, the station function label indicates that the area is predominantly populated by office workers. The station co-occurrence probability label reveals that many office workers with similar travel habits frequently stop near a certain commercial area station. Considering the station passenger density gradient label, a large number of passengers disembark at this commercial area station during the corresponding time period. Combining this information, it can be predicted that the passenger's destination station is likely within this commercial area. By performing destination station prediction on a large number of boarding passengers in this way, a destination prediction result is established.

[0043] Next, passenger station routes are established using the destination prediction results. For example, if a passenger boards at an office area station and their predicted destination is a shopping district station, then the passenger's station route can be determined to be from the office area station to the shopping district station. Finally, the destination prediction results and passenger station routes are updated in the spatiotemporal heat map. As new destination prediction results and passenger station routes are continuously added, the spatiotemporal heat map can more accurately reflect the travel intensity and flow of passengers in different areas and time periods. For example, the updated spatiotemporal heat map clearly shows that during weekday morning rush hours, the route from residential area stations to office area stations has higher intensity, while on weekends, the route from residential area stations to shopping district stations shows a significant increase in intensity. This provides strong data support for traffic planning and resource allocation.

[0044] In a preferred embodiment, the optimization of bus route scheduling based on passenger waiting time targets, scheduling cost targets, vehicle utilization targets, and congestion impact targets includes: identifying buses sharing stops on the current bus route and establishing a collaboratively scheduled bus set; calling the passenger stop paths and using them to perform shared scheduling matching of the collaboratively scheduled bus set, generating shared scheduling matching results, and configuring shared starting stops; establishing an extended objective function, which is a shared collaborative evaluation function, with evaluation features including shared waiting time and shared congestion comfort; obtaining the predicted time nodes from the collaboratively scheduled bus set to the shared starting stops and the predicted in-vehicle passenger status; performing combined scheduling impact compensation based on the predicted time nodes and the predicted in-vehicle passenger status using the extended objective function, and using the combined scheduling impact compensation to complete the optimization of bus route scheduling.

[0045] Optionally, in the process of optimizing bus route scheduling, it is first necessary to identify buses sharing stops on the current route. This means analyzing buses on different routes to find those buses that share stops at certain stations, and then establishing a collaboratively scheduled bus set. For example, in an urban bus network, there are two routes, Route 1 and Route 3, both of which stop at stops A and B. Buses on these two routes can then be included in the collaboratively scheduled bus set.

[0046] Next, the system calls the passenger station paths and uses these paths to perform shared scheduling matching for the coordinated bus set. Taking a passenger's travel demand from station C to station D as an example, if there are buses in the coordinated bus set that can pass through both stations C and D, the system will perform matching, generate shared scheduling matching results, and configure shared starting stations. For example, if it finds that bus routes 1 and 3 can both meet the travel demand from C to D, and station A can be used as the shared starting station, then the corresponding matching results will be generated.

[0047] Then, an extended objective function is established, which is a shared collaborative evaluation function. Its evaluation characteristics include shared waiting time and shared crowding comfort. Shared waiting time refers to the time passengers spend waiting for the bus at the shared starting point, while shared crowding comfort reflects the impact of the degree of crowding inside the bus on passenger experience. For example, if the shared waiting time is too long, or the bus is too crowded, the value of the shared collaborative evaluation function will be affected.

[0048] Next, the predicted arrival time of the coordinated dispatch buses at the shared starting point and the predicted passenger status inside the buses are obtained. The predicted arrival time is based on factors such as bus speed and road conditions to estimate the time it will take for the buses to arrive at the shared starting point; the predicted passenger status is based on historical data and real-time information to predict the number and distribution of passengers when the buses arrive at the shared starting point. For example, an intelligent algorithm might predict that bus route 1 will arrive at station A in 10 minutes, and that the bus will be crowded with many passengers.

[0049] Finally, a combined scheduling impact compensation is applied to the extended objective function based on the predicted time points and predicted passenger conditions inside the bus. This compensation mechanism can be understood as a reward or penalty term in multi-objective optimization, or it can be used independently for local fine-tuning. For example, if it is predicted that a bus will be very crowded when it arrives at the shared starting point, then during scheduling optimization, the route selecting that bus will be penalized, reducing its probability of being selected; conversely, if it is predicted that the bus will be relatively spacious and the waiting time will be short when it arrives, then it will be rewarded, increasing its probability of being selected. By continuously updating the above data in this way, the optimal bus scheduling for the route is ultimately achieved, resulting in more rational and efficient bus scheduling management and improving the passenger travel experience.

[0050] In a preferred embodiment, the step of optimizing bus route scheduling based on passenger waiting time targets, scheduling cost targets, vehicle utilization targets, and congestion impact targets, and establishing optimization results, includes: predicting the passenger arrival time distribution at each station based on passenger flow demand, and establishing a station passenger aggregation curve; predicting bus arrival times based on scheduling data in the solution pool, and performing overlapping calculations based on the arrival time prediction results and the station passenger aggregation curves to establish an average waiting time; predicting the scheduling costs of fuel consumption, driving time, and off-peak empty runs based on route travel time and congestion status, and generating a scheduling cost prediction result; and optimizing bus scheduling under the passenger waiting time target and scheduling cost target based on the average waiting time and scheduling cost prediction results.

[0051] For example, in the process of optimizing bus route scheduling to establish optimization results, it is further necessary to predict the passenger arrival time distribution at each station based on passenger flow demand, thereby establishing a station passenger aggregation curve. Station passenger flow demand reflects the travel needs of passengers at the station during different time periods. For example, during the morning rush hour on weekdays, passenger flow demand at stations near schools and office buildings will increase significantly. By analyzing multi-source information such as historical passenger flow data and real-time location data, the number of passengers arriving at the station at different times can be predicted, thus drawing a station passenger aggregation curve. For example, near a certain subway station, the number of passengers arriving will rise rapidly between 7:00 and 8:00 in the morning, reaching a peak at 8:00, and then gradually declining. This curve intuitively shows the passenger aggregation situation at the station during this period. Next, bus arrival time is predicted based on the scheduling data in the solution pool. The solution pool contains data on various possible bus scheduling schemes. Using prediction models and algorithms, combined with factors such as road conditions and traffic flow, the arrival time of buses at each station under different scheduling schemes can be predicted. For example, based on the historical travel data of a certain route and the current real-time road information, it can be predicted that a certain bus will arrive at a certain station at 9:00 under a specific scheduling scheme. Then, the average waiting time is established by overlaying the arrival time prediction results with the passenger gathering curve at the station. This involves comparing the bus arrival time prediction results with the passenger gathering curve to calculate the average waiting time for passengers at the station. For example, if the bus is predicted to arrive at the station at 9:00 AM, but the passenger gathering curve shows a large number of passengers arriving between 8:50 AM and 9:00 AM, the average waiting time for these passengers can be calculated.

[0052] Simultaneously, based on route travel time and congestion status, the system predicts fuel consumption, driving time, and off-peak empty-running scheduling costs from the data in the unset pool, generating scheduling cost prediction results. Route travel time is affected by factors such as road congestion and stop times, while congestion status directly reflects road traffic conditions. By analyzing these factors, fuel consumption, driving time, and off-peak empty-running mileage costs under different scheduling schemes can be predicted. For example, when traveling on congested roads, bus fuel consumption increases, and driving time also lengthens. During off-peak hours, some buses may run empty, all of which increase scheduling costs.

[0053] Finally, based on the predicted average waiting time and scheduling cost, the bus scheduling is optimized under the objectives of passenger waiting time and scheduling cost. The scheduling schemes in the solution pool are evaluated and screened with the goal of minimizing the average waiting time and scheduling cost. For example, one scheduling scheme may result in a shorter average passenger waiting time, but with excessively high scheduling costs; while another scheme has lower scheduling costs, but longer average passenger waiting times. By comprehensively considering these two objectives, the scheduling scheme is continuously adjusted and optimized using optimization algorithms, ultimately finding the optimal bus scheduling scheme under both passenger waiting time and scheduling cost objectives. The optimization results are established, providing a more scientific and reasonable basis for bus operation scheduling decisions.

[0054] In a preferred embodiment, the step of optimizing bus scheduling under passenger waiting time and scheduling cost targets based on the average waiting time and scheduling cost prediction results includes: obtaining the maximum capacity of buses; predicting vehicle passenger density from scheduling data in the solution pool to establish passenger density prediction results; calculating the effective occupancy rate based on the maximum capacity and passenger density prediction results to generate an effective occupancy rate calculation result; obtaining the arrival time of congested road segments from scheduling data in the solution pool, using the arrival time to predict the congestion state to establish a basic congestion state; performing intervention increment fitting under the basic congestion state based on bus length characteristics and stopping characteristics to generate a fitted congestion state; and optimizing bus scheduling under passenger waiting time targets, scheduling cost targets, vehicle utilization targets, and congestion impact targets using the average waiting time, scheduling cost prediction results, effective occupancy rate calculation results, and fitted congestion states.

[0055] Preferably, in the process of optimizing bus scheduling under the objectives of passenger waiting time and scheduling cost, the maximum capacity of the bus is obtained, for example, a certain type of bus can carry a maximum of 80 passengers. Next, the scheduling data in the solution pool is used to predict vehicle passenger density. The solution pool contains data on various possible bus scheduling schemes. By analyzing historical passenger flow data and boarding / alighting patterns at stops, the passenger density of buses at various stops and road sections under different scheduling schemes is predicted, thus establishing passenger density prediction results. For example, it is predicted that during peak hours on a certain route, the passenger density on a bus will increase significantly after passing a stop near a school. Based on the maximum capacity of the bus and the passenger density prediction results, the effective occupancy rate is calculated. The effective occupancy rate reflects the ratio of the actual number of passengers carried by the bus to its maximum capacity, generating the effective occupancy rate calculation result. For example, if a bus has a maximum capacity of 80 people and actually carries 60 people during a certain period, then the effective occupancy rate is 75%.

[0056] Simultaneously, arrival times of congested road segments are obtained based on scheduling data in the solution pool. These arrival times are then used to predict congestion levels and establish a baseline congestion profile. Specifically, by analyzing bus arrival times at congested road segments and historical congestion data for those segments, the degree of congestion at the time of bus arrival is predicted, including indicators such as traffic speed and queue length. For example, it is predicted that when a bus arrives at a congested road segment at 5 PM, the traffic speed on that segment will drop to 10 kilometers per hour.

[0057] Furthermore, incremental intervention data is fitted based on bus length and stopping characteristics under the basic congestion state. Bus length affects its occupied space on the road, while stopping characteristics such as stopping time and location affect surrounding traffic flow. By considering these factors, the degree of negative disturbance to the average capacity (flow rate, density, load, etc.) of a road segment after a bus joins it is measured, generating a fitted congestion state. For example, when a long bus with a long stopping time joins a congested road segment, it will further reduce the traffic flow speed and decrease the capacity of that segment.

[0058] Finally, using average waiting time, predicted scheduling costs, calculated effective passenger utilization, and fitted congestion conditions, the optimal bus scheduling is sought under the objectives of passenger waiting time, scheduling cost, vehicle utilization, and congestion impact. The scheduling schemes in the solution pool are comprehensively evaluated and screened with the goals of minimizing average waiting time, lowest scheduling cost, highest vehicle utilization, and least congestion impact. For example, while one scheduling scheme may result in a shorter average passenger waiting time, its scheduling cost is too high and its impact on congested sections is significant; another scheme achieves a better balance in all aspects. Through continuous optimization and adjustment of the scheduling scheme, the optimal bus scheduling scheme that satisfies multiple objectives is ultimately found, achieving efficient, orderly, and sustainable development of public transportation operations.

[0059] In a preferred embodiment, the step of managing bus dispatch based on the optimization results includes: continuously adding matching records triggered by navigation stations to establish incremental station data; and using the incremental station data to fine-tune the dispatch based on the optimization results to complete the bus dispatch management.

[0060] Furthermore, after obtaining the optimization results for bus route scheduling, the system enters the bus dispatch management phase. First, it continuously adds matching records triggered by navigation stations. This process leverages the mechanism triggered by passengers using specific navigation software based on their location and destination selection. For example, when a large number of passengers use navigation software to travel to or from a popular commercial area during morning and evening rush hours, the system accurately captures the correlation information between different stations and the commercial area based on these navigation records, such as which stations have the most passengers traveling to the commercial area, and which stations they mainly travel to from the commercial area. These newly generated matching records constitute incremental station data. This incremental station data is characterized by real-time and dynamic features, reflecting the latest changes in passenger travel demand. For instance, during a large-scale event, navigation trigger records at stations surrounding the event will increase dramatically. By continuously collecting these records to form incremental station data, the system can promptly capture the impact of the event on surrounding public transportation demand.

[0061] Next, the optimization results are fine-tuned using incremental station data. Since the optimization results are derived based on a certain timeframe and data, while actual public transport demand is constantly changing, the results need to be adjusted in a timely manner based on incremental station data. For example, if incremental station data shows a significant recent increase in the number of passengers boarding at a particular station, and these passengers' destinations are relatively concentrated, then the bus departure intervals and vehicle allocation related to that station in the optimization results can be fine-tuned to increase the number of buses heading towards those destinations, thus better meeting passenger travel needs.

[0062] By continuously fine-tuning the optimization results based on real-time incremental station data in this way, it is possible to ensure that bus dispatch management always matches actual travel demand, improve the efficiency and service quality of bus operations, achieve scientific and reasonable bus dispatch management, and provide passengers with a more convenient and comfortable bus travel experience.

[0063] In a preferred embodiment, establishing the spatiotemporal heat map includes: identifying passenger subjects and establishing specific passenger groups; setting scheduling preferences for specific passenger groups and adding the scheduling preferences to the spatiotemporal heat map.

[0064] Specifically, identifying passenger groups is also necessary in the process of constructing spatiotemporal heat map. This identification aims to distinguish different groups from the large number of passengers, such as commuters, students, seniors, and tourists. By analyzing multi-dimensional data such as passengers' travel time, travel location, and consumption habits, data mining and machine learning algorithms can accurately identify specific passenger groups. For example, by analyzing whether passengers frequently board at residential stops and disembark at stops near commercial areas or office buildings during weekday morning rush hours, these passengers can be identified as commuters.

[0065] Next, dispatch preferences for specific passenger groups are established. Different passenger groups have different preferences for bus dispatching due to differences in travel purpose, time sensitivity, and other factors. Commuters typically prioritize punctuality and comfort, hoping to reach their destination quickly and conveniently during peak hours; therefore, they may prefer buses with short intervals and a comfortable interior environment. Students may be more price-sensitive and also desire bus coverage of areas surrounding their schools. The elderly may prioritize bus safety and ease of boarding and alighting. Based on these characteristics, corresponding dispatch preferences are established for specific passenger groups.

[0066] Finally, dispatch preferences are added to the spatiotemporal heat map. The spatiotemporal heat map itself is a tool that comprehensively reflects traffic volume in different areas at different times. By incorporating the dispatch preferences of specific passenger groups, the map can more accurately reflect the travel needs and preferences of different passenger groups. For example, on the spatiotemporal heat map, for areas and time periods with high concentrations of commuters, information indicating a higher demand for punctuality and comfort of buses can be highlighted; for areas with high concentrations of students, information related to fares and coverage can be emphasized. In this way, when formulating dispatch plans, public transport operators can refer to the spatiotemporal heat map and rationally arrange bus routes, departure intervals, and vehicle types according to the dispatch preferences of different passenger groups, thereby improving the quality and efficiency of public transport services and better meeting passenger travel needs.

[0067] The intelligent public transport combined scheduling method provided in this embodiment of the invention has at least the following technical effects:

[0068] 1. By accessing bus card swipe records, a feature set of card-swiping stations is established. Combined with matching analysis triggered by navigation stations, a spatiotemporal heat map is created. Simultaneously, a multi-source traffic flow dataset is constructed to predict road congestion status and a regional-level road congestion map is built. The fusion of multi-source data makes the prediction of station passenger demand, route travel time, and congestion status more accurate, providing a reliable data foundation for subsequent scheduling optimization and helping to improve the scientific and rational nature of bus scheduling. For example, bus card swipe records can reveal passenger boarding and alighting patterns, navigation records can reflect real-time travel demand, and traffic flow data can accurately grasp road congestion conditions. Integrating this information allows for a more comprehensive understanding of the bus operating environment.

[0069] 2. Configure a multi-objective scheduling channel to optimize bus route scheduling based on objectives such as passenger waiting time, scheduling costs, vehicle utilization, and congestion impact. During the optimization process, not only are buses on the current route considered, but buses sharing stops are also identified, a collaborative scheduling bus set is established, shared scheduling is matched based on passenger stop paths, and a combined scheduling impact compensation is performed using an extended objective function. This multi-objective optimization and collaborative scheduling approach fully considers multiple aspects of bus operation, achieving efficient resource utilization and maximizing overall benefits, thereby improving the quality and efficiency of bus services. For example, collaborative scheduling can reduce empty vehicle runs, lower scheduling costs, and shorten passenger waiting times.

[0070] 3. When managing bus dispatch based on the optimization results, continuously add matching records triggered by navigation stations to establish incremental station data. This data is then used to fine-tune the dispatch based on the optimization results, enabling dynamic adjustments to bus dispatch to adapt to constantly changing travel demands. Furthermore, when building the spatiotemporal heat map, passenger groups are identified, specific passenger groups are defined, and their dispatch preferences are set. These preferences are added to the prediction map to provide personalized bus services for different passenger groups. This dynamic adjustment and personalized service better meets the diverse needs of passengers, improves passenger satisfaction, and enhances the attractiveness and competitiveness of public transportation. For example, bus dispatch schemes tailored to the travel characteristics of different groups such as commuters and students can be provided.

[0071] Example 2:

[0072] like Figure 2 As shown, based on the same inventive concept as the intelligent bus combined dispatching method provided in Embodiment 1, this embodiment of the invention also provides an intelligent bus combined dispatching device, the device comprising:

[0073] Information retrieval module 11 is used to retrieve bus card swiping records and establish a feature set of card swiping stations.

[0074] The matching analysis module 12 is used to establish a navigation site trigger, perform navigation record matching analysis using the navigation site trigger, and establish a spatiotemporal heat prediction map based on the matching analysis results and the card swiping site feature set.

[0075] The state prediction module 13 is used to construct a multi-source traffic flow dataset, use the multi-source traffic flow dataset to predict road congestion status, and construct a regional road congestion status map.

[0076] The information flow module 14 is used to establish station passenger flow demand, route travel time and congestion status based on the spatiotemporal heat prediction map and the regional road congestion status map.

[0077] The channel configuration module 15 is used to configure multi-objective scheduling channels. It takes the passenger flow demand of the station, the route travel time and the congestion status as input data, and optimizes the bus scheduling of the route through passenger waiting time target, scheduling cost target, vehicle utilization rate target and congestion impact target, and establishes the optimization result.

[0078] The scheduling management module 16 is used to perform bus scheduling management based on the optimization results.

[0079] Furthermore, the matching analysis module 12 is also used to perform the following steps:

[0080] Establish station function labels, station co-occurrence probability labels, and station passenger density gradient labels; use the station function labels, station co-occurrence probability labels, and station passenger density gradient labels to predict the destination station of passengers boarding at the station, and establish the destination prediction result; use the destination prediction result to establish the passenger station path, and update the destination prediction result and the passenger station path to the spatiotemporal heat map.

[0081] Furthermore, the channel configuration module 15 is also used to perform the following steps:

[0082] The system identifies buses sharing stops on the current bus route and establishes a collaboratively scheduled bus set. It then calls upon the passenger stop paths to perform shared scheduling matching on the collaboratively scheduled bus set, generating a shared scheduling matching result and configuring a shared starting station. An extended objective function is established, which is a shared collaborative evaluation function. Evaluation features include shared waiting time and shared congestion comfort. The system obtains the predicted time points from the collaboratively scheduled bus set to the shared starting station and the predicted passenger status inside the bus. Based on the predicted time points and the predicted passenger status inside the bus, the system performs combined scheduling impact compensation using the extended objective function, and uses this combined scheduling impact compensation to complete the route bus scheduling optimization.

[0083] Furthermore, the channel configuration module 15 is also used to perform the following steps:

[0084] Based on the passenger flow demand at the stations, predict the passenger arrival time distribution and establish a passenger aggregation curve. Predict bus arrival times based on scheduling data in the solution pool, and calculate the average waiting time by overlapping the arrival time prediction results and the passenger aggregation curve. Based on route travel time and congestion status, predict fuel consumption, driving time, and off-peak empty-running scheduling costs from the scheduling data in the solution pool, generating a scheduling cost prediction result. Optimize bus scheduling under the passenger waiting time target and scheduling cost target based on the average waiting time and scheduling cost prediction results.

[0085] Furthermore, the channel configuration module 15 is also used to perform the following steps:

[0086] The system obtains the maximum capacity of buses; predicts vehicle passenger density based on the scheduling data in the solution pool, and establishes passenger density prediction results; calculates the effective passenger utilization rate based on the maximum capacity and passenger density prediction results, and generates effective passenger utilization rate calculation results; obtains the arrival time of congested road segments based on the scheduling data in the solution pool, and uses the arrival time to predict the congestion state, establishing a basic congestion state; performs incremental intervention fitting based on bus length characteristics and stopping characteristics under the basic congestion state, generating a fitted congestion state; and optimizes bus scheduling under passenger waiting time targets, scheduling cost targets, vehicle utilization rate targets, and congestion impact targets using the average waiting time, scheduling cost prediction results, effective passenger utilization rate calculation results, and fitted congestion state.

[0087] Furthermore, the scheduling management module 16 is also used to perform the following steps:

[0088] Continuously add matching records triggered by navigation stations to establish incremental station data; use the incremental station data to perform optimization results and fine-tune the scheduling to complete bus dispatch management.

[0089] Furthermore, the matching analysis module 12 is also used to perform the following steps:

[0090] Identify passenger subjects and establish specific passenger groups; set scheduling preferences for specific passenger groups and add the scheduling preferences to the spatiotemporal heat prediction map.

[0091] Through the foregoing detailed description of a smart bus combination scheduling method, those skilled in the art can clearly understand the smart bus combination scheduling device in this embodiment. As the device disclosed in the embodiment corresponds to the method disclosed in the embodiment, the description is relatively simple, and relevant parts can be referred to the method section description.

[0092] Example 3:

[0093] This invention provides a computer device, the computer device comprising:

[0094] Memory, used to store executable instructions;

[0095] When the processor runs the executable instructions stored in the memory, it implements a smart bus combination scheduling method as described in Embodiment 1.

[0096] It should be noted that the processor may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. The processor may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The memory may include one or more computer-readable storage media, which may be non-transitory. The memory may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the computer device may also optionally include input interfaces and output interfaces. The processor, memory, and input / output interfaces can be connected via a bus or signal lines. Various peripheral devices can be connected to the input / output interfaces via buses, signal lines, or circuit boards. The input / output interfaces can be used to connect at least one input / output related peripheral device to the processor and memory. In some embodiments, the processor, memory, and input / output interfaces are integrated on the same chip or circuit board; in other embodiments, any one or two of the processor, memory, and input / output interfaces can be implemented on separate chips or circuit boards, and the embodiments of the present invention do not limit this.

[0097] Example 4:

[0098] Please see Figure 3 , Figure 3 This is a schematic diagram illustrating an embodiment of a computer-readable storage medium provided by an embodiment of the present invention. For example... Figure 3 As shown, this embodiment provides a computer-readable storage medium 600, on which a second computer program 611 is stored. When the second computer program 611 is executed by a processor, it implements a smart bus combination scheduling method as described in Embodiment 1.

[0099] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0100] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0101] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0102] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0103] Although preferred embodiments of the invention have been described, those skilled in the art, once they have learned the basic inventive concept, can make other changes and modifications to these embodiments.

[0104] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of this invention and its equivalents, this invention also intends to include these modifications and variations.

Claims

1. A smart bus combination scheduling method, characterized in that, The method includes: Access bus card swipe records to establish a feature set of card swipe stations; A navigation site trigger is established, and navigation record matching analysis is performed using the navigation site trigger. A spatiotemporal heat prediction map is established based on the matching analysis results and the feature set of card swiping sites. Construct a multi-source traffic flow dataset, use the multi-source traffic flow dataset to predict road congestion status, and construct a regional road congestion status map. Based on the spatiotemporal heat map and the regional road congestion status map, station passenger flow demand, route travel time and congestion status are established. Configure a multi-objective scheduling channel, take the passenger flow demand of the station, the route travel time and the congestion status as input data, and optimize the bus route scheduling through passenger waiting time target, scheduling cost target, vehicle utilization rate target and congestion impact target, and establish the optimization result; Bus dispatching and management are carried out based on the optimization results.

2. The intelligent bus combination scheduling method as described in claim 1, characterized in that, The step of establishing a spatiotemporal heat map based on the matching analysis results and the feature set of card-swiping stations includes: Establish site function tags, site co-occurrence probability tags, and site passenger density gradient tags; Using the station function labels, station co-occurrence probability labels, and station passenger density gradient labels, the destination station of passengers boarding at the station is predicted, and a destination prediction result is established. The passenger station path is established using the destination prediction result, and the destination prediction result and the passenger station path are updated to the spatiotemporal heat map.

3. The intelligent bus combination scheduling method as described in claim 2, characterized in that, The optimization of bus route scheduling based on passenger waiting time targets, scheduling cost targets, vehicle utilization rate targets, and congestion impact targets includes: Identify buses sharing stops on the current bus route and establish a collaboratively dispatched bus set. The passenger station path is invoked, and the shared scheduling matching of the bus set is performed using the passenger station path to generate a shared scheduling matching result, and the shared starting station is configured. An extended objective function is established, which is a shared collaborative evaluation function, and the evaluation features include shared waiting time and shared crowding comfort. Obtain the predicted time point for the coordinated dispatch of buses to the shared starting station and the predicted status of passengers inside the buses; Based on the predicted time point and the predicted passenger status inside the vehicle, a combined scheduling impact compensation is performed using an extended objective function. The combined scheduling impact compensation is then used to optimize the bus route scheduling.

4. The intelligent bus combination scheduling method as described in claim 1, characterized in that, The method involves optimizing bus route scheduling based on passenger waiting time targets, scheduling cost targets, vehicle utilization rate targets, and congestion impact targets, and establishing optimization results, including: Based on the predicted passenger flow demand at the stations, the passenger arrival time distribution at the stations is established, and a passenger aggregation curve for the stations is constructed. Bus arrival time is predicted based on scheduling data in the solution pool. The average waiting time is established by overlapping calculations based on the arrival time prediction results and the passenger gathering curve at the station. Based on the route travel time and congestion status, the scheduling cost prediction results are generated by predicting the fuel consumption, driving time, and off-peak empty driving scheduling costs of the scheduling data in the uncollection pool. Based on the average waiting time and scheduling cost prediction results, bus scheduling optimization is performed under the target of passenger waiting time and scheduling cost.

5. The intelligent bus combination scheduling method as described in claim 4, characterized in that, The step of optimizing bus scheduling based on the average waiting time and scheduling cost prediction results, under the target passenger waiting time and scheduling cost, includes: Get the maximum capacity of the bus; Vehicle passenger density is predicted from the scheduling data in the solution pool, and passenger density prediction results are established. The effective occupancy rate is calculated based on the predicted maximum capacity and passenger density, and the effective occupancy rate calculation result is generated. The arrival time of congested road segments is obtained from the scheduling data in the set pool, and the congestion status is predicted using the arrival time to establish a basic congestion status. Based on the characteristics of bus length and stopping, an intervention increment is fitted under the basic congestion state to generate a fitted congestion state. Using the average waiting time, scheduling cost prediction results, effective passenger utilization rate calculation results, and fitted congestion status, bus scheduling optimization is performed under the objectives of passenger waiting time, scheduling cost, vehicle utilization rate, and congestion impact.

6. The intelligent bus combination scheduling method as described in claim 1, characterized in that, The step of managing bus dispatch based on the optimization results includes: Continuously add matching records triggered by navigation sites to build incremental site data; The incremental data from the stations is used to optimize the scheduling and fine-tune the process, thereby completing the bus scheduling and management.

7. The intelligent bus combination scheduling method as described in claim 1, characterized in that, The establishment of the spatiotemporal heat map includes: Identify passenger subjects and establish specific passenger groups; Set scheduling preferences for specific passenger groups and add the scheduling preferences to the spatiotemporal heat map.

8. A smart bus combination dispatching device, characterized in that, The apparatus for implementing the intelligent public transport combined dispatching method according to any one of claims 1-7, the apparatus comprising: The information retrieval module is used to retrieve bus card swiping records and establish a feature set of card swiping stations; The matching analysis module is used to establish navigation site triggers, perform navigation record matching analysis using the navigation site triggers, and establish a spatiotemporal heat prediction map based on the matching analysis results and the feature set of card swiping sites. The state prediction module is used to construct a multi-source traffic flow dataset, use the multi-source traffic flow dataset to predict road congestion status, and construct a regional road congestion status map. The information flow module is used to establish station passenger flow demand, route travel time and congestion status based on the spatiotemporal heat prediction map and the regional road congestion status map; The channel configuration module is used to configure multi-objective scheduling channels. It takes the passenger flow demand of the station, the route travel time and the congestion status as input data, and optimizes the bus route scheduling through passenger waiting time target, scheduling cost target, vehicle utilization rate target and congestion impact target, and establishes the optimization result. The scheduling management module is used to manage bus scheduling based on the optimization results.

9. A computer device, characterized in that, The computer device includes: Memory, used to store executable instructions; The processor, when executing the executable instructions stored in the memory, implements the intelligent bus combination scheduling method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that, The storage medium stores a computer software program, which, when executed by a processor, implements a smart bus combination scheduling method as described in any one of claims 1-7.

Images