421 results about "Bus transit" patented technology

The invention discloses a public transport passenger flow monitoring method and system based on human body detection, and the method comprises the steps: synchronously collecting skeleton key points, heat distribution and contour features of passengers through a vehicle-mounted multi-view camera and an infrared sensor, and generating a passenger space-time feature matrix; outputting a passenger movement track set based on the passenger space-time characteristic matrix; generating a dynamic congestion degree index according to the staying duration and the spatial distribution density of the passengers in the passenger movement track set; calculating an abnormal behavior probability based on the dynamic congestion degree index, and outputting an abnormal event early warning signal; and fusing the dynamic congestion degree index, the abnormal event early warning signal and the real-time passenger flow data, and generating a bus passenger flow monitoring result through space-time correlation analysis. According to the embodiment of the invention, high-precision, low-delay and intelligent passenger flow state monitoring and abnormity early warning can be realized.

The invention discloses a public traffic composite traffic network key node identification method based on an improved K-shell algorithm, and the method comprises the steps: firstly extracting the line, geographic position, vehicle arrival interval and rated passenger capacity information of a subway and a bus station from multi-source data, and constructing a weighted composite traffic network considering the intra-layer transportation capacity and inter-layer transfer relation; node stripping is carried out based on a K-shell algorithm, and a shell fine position KP value is calculated in combination with a node removal sequence; further introducing a neighborhood structure overlap ratio, and constructing a node local propagation influence index; meanwhile, a comprehensive correction coefficient is constructed by considering the difference between intra-layer node strength and transfer attributes and the transportation capacity difference between subway and bus layers; and finally, a node comprehensive importance index IKA is formed and is used for sorting and identifying network key nodes. Finally, the recognition effect is verified through network efficiency, connectivity and SIR (susceptibility-infection-recovery) propagation simulation, and the result shows that the method is superior to a traditional centrality algorithm in the aspects of recognition precision and propagation influence measurement.

The invention discloses a bus intelligent travel service dynamic recommendation transfer method, and relates to the technical field of bus services, and the method comprises the steps: S1, building a bus route set; s2, matching the overlapped stations with adjacent stations; s3, acquiring a starting point and an ending point of a user and generating candidate paths; s4, calculating transfer efficiency density, and performing path pruning; s5, calculating a departure time rhythm staggering coefficient between the transfer nodes; s6, calculating a transfer chain type risk accumulation function; s7, estimating total consumed time and waiting time; and S8, constructing a path comprehensive score and a recommendation sequence. According to the bus smart travel service dynamic recommendation transfer method provided by the invention, based on the public traffic operation path and station information, in combination with adjacent station distance calculation and departure rhythm feature construction, the structural association between transfer nodes can be identified more accurately, and path screening is realized through the rhythm interleaving factor, so that the transfer efficiency is improved. The recommendation frequency of the high-risk transfer path is effectively reduced, and the stability of the transfer process is improved.

A sensor bar or other array of sensors are mounted to the bus beneath or adjacent to a doorway of the bus. Ultrasonic sensors are located within the sensor bar and detect the presence of foreign objects such as an entrapped passenger close to the doorway. A safety output is generated by the system when an unsafe condition is detected. Examples of safety outputs can include warning sounds, warning lights, automatic door opening, using the brake transmission shift interlock (BTSI) to prevent transmission shifting for vehicle movement, and other safety outputs.

The invention relates to the field of urban public transport deployment, and provides a public transport network matching method and system based on an urban space structure, which divides urban areas by constructing a traffic model, identifies areas with dense demands on the basis of power consumption density, and provides a public transport network matching method and system based on the urban space structure. And the coverage condition of the existing public transport network on the areas with dense demands is evaluated, and uncovered areas are identified. For the uncovered areas, the information of stores and companies in the map data is used to subdivide the uncovered areas into a plurality of types of areas. A bus rapid transit system is additionally arranged in a commercial district to improve transportation efficiency, a peak period special line is additionally arranged in an office building area to meet commuting requirements, a customized bus special line is provided in an industrial district to meet requirements of specific periods and routes, and a conventional bus route is additionally arranged in a residential district to improve daily travel. Accurate matching between the urban space structure and the public transport demand is realized, and the coverage rate and efficiency of public transport service are improved.

The invention discloses a bus passenger getting-on station estimation method based on multi-source data fusion, and relates to the field of public traffic operation planning and management, and the method comprises the steps: obtaining multi-source sample data, and carrying out the integration processing, and obtaining database storage information; processing and extracting by using the public transport data preprocessing terminal to obtain a public transport operation time parameter; segmenting and constructing a fixed threshold time window; matching the intelligent card data to obtain an intelligent card data set of the candidate site; performing first data screening, constructing a candidate site group, and calculating by using a maximum likelihood estimation model to obtain a first data set of a determined site; performing second data screening and division to obtain a time sequence subset, and performing prediction by using a prediction neighbor information algorithm to obtain site information of the second data; and carrying out unified site numbering to obtain a site matching data set, and carrying out verification by using a multi-dimensional data terminal to obtain an evaluation result of the multi-dimensional data. According to the method, key field dependence is broken through, and data adaptability is improved.

The invention provides a conventional bus resource optimal configuration method and system considering subway toughness improvement, and belongs to the technical field of urban rail transit emergency connection. According to the method, actual factors such as a rail transit and bus network structure, conventional bus transportation requirements, metro emergency connection requirements, limited bus transportation capacity and bus system extension cost are comprehensively considered, and conventional bus service planning and metro interruption emergency response are collaboratively optimized; according to the method, stable operation of conventional buses can be guaranteed, meanwhile, passengers detained in the metro can be evacuated to the maximum extent, the service quality of a rail transit and bus connection mode can be improved, and the public transport network toughness can also be enhanced to the great extent. Meanwhile, in the collaborative optimization process of the conventional bus service and the bus connection service, a Pareto optimal method is introduced in view of the complexity of a dual-objective planning problem, so that efficient solving of an actual scale case is realized, and the method is closer to an actual problem.

The invention discloses an intelligent public transportation transfer recommendation system based on multi-source data fusion, and relates to the technical field of intelligent transportation systems, and the system comprises a transfer recommendation management center which is in communication connection with the following modules: a data acquisition module which is used for collecting and preprocessing traffic data from a plurality of traffic data sources, and transmitting the traffic data to a data processing module; various traffic modes of metros and buses are covered; and the multi-source data fusion analysis module is used for carrying out fusion processing on the collected multi-source heterogeneous data. By fusing multi-source traffic data and combining simulation analysis and real-time traffic states, the transfer path is dynamically optimized, the transfer waiting time and total consumed time of the user are remarkably shortened, the user can obtain optimal path recommendation based on real-time traffic information, long-time waiting caused by sudden delay is avoided, the travel efficiency and experience are improved, and meanwhile, the user experience is improved. Double constraints of walking distance and transfer waiting time are supported, it is ensured that path planning meets actual requirements of users, and travel experience is further optimized.

The invention discloses an urban circle traffic demand prediction method and system, and belongs to the technical field of traffic data processing, and the method comprises the steps: taking a four-stage theory as a basis, efficiently obtaining a travel demand OD matrix of urban circle global traffic middle area granularity in the future, and mastering the overall traffic demand pattern of an urban circle from a macroscopic level; on the basis of a trip chain theory, a city traffic cell granularity trip demand OD matrix with higher time-space precision in the future year is accurately obtained, and the method can adapt to more application scenes and reflect traffic prediction and evaluation analysis of traffic demand details; through a traffic distribution algorithm of motor vehicles and public traffic, traffic flow indexes borne by urban circle traffic supply facilities are obtained, and continuity and consistency of spatial and temporal distribution of the current situation and indexes such as traffic supply facilities, travel demands, road flow and bus passenger volume in the future are achieved. And therefore, the traffic demand prediction and evaluation index result of the urban circle in the future year can scientifically meet the needs of users.

The invention provides a bus automatic driving method and system, and relates to the technical field of intelligent public transportation, passenger flow prediction is carried out on a target area, route planning is carried out according to a passenger flow prediction result, and a bus operation baseline is constructed; collecting travel reservation requests of users, performing spatial-temporal clustering analysis, and constructing a travel demand cluster; and performing scheduling decision analysis on the travel demand cluster and the candidate vehicle information, establishing a bus scheduling strategy, issuing and executing the strategy, receiving a real-time travel request of a user, performing matching analysis on the real-time travel request and the initial running path, and performing dynamic insertion updating on the initial running path according to an analysis result. The technical problems of low scheduling efficiency and resource waste caused by the fact that personalized and decentralized travel requirements cannot be responded in time due to fixed lines and scheduling response lag in the prior art are solved, and the technical effects of improving the bus travel service matching rate and enhancing the operation flexibility and the resource configuration efficiency are achieved.

The invention belongs to the technical field of urban traffic management, and particularly relates to an electric bus cooperative scheduling method in a charging facility time-sharing sharing mode. The objective of the invention is to solve the problem that the existing method faces a single electric bus route, neglects the fluctuation of the charging demand of private cars in each time period, and is easy to cause low utilization rate caused by excessive charging facility distribution number in individual time periods, or long charging queuing time of private cars caused by insufficient charging facility distribution number. The method comprises the following steps: constructing a collaborative optimization model of a bus scheduling scheme and a charging facility sharing scheme based on the daily charging cost of an electric bus line and an expression of an estimated value of earnings obtained by sharing a charging pile to an electric car every day by a bus enterprise; solving the collaborative optimization model to obtain an optimal feasible solution and a corresponding objective function value; the optimal feasible solution comprises an electric bus scheduling scheme and a charging facility sharing scheme.

The invention discloses a public transportation auxiliary unmanned aerial vehicle cooperative distribution method considering client point dynamic demands, introduces a public transportation auxiliary unmanned aerial vehicle with large service range coverage to carry out express distribution, and aims to reduce the terminal logistics distribution cost and improve the distribution timeliness. The method comprises the following steps: constructing a generation model which simulates a dynamic customer demand and considers a time window in combination with an actual scene, and establishing a bus auxiliary unmanned aerial vehicle cooperative distribution optimization model which considers the customer point dynamic demand based on a customer point generation mechanism and a bus unmanned aerial vehicle cooperative operation mechanism in the generation model; and aiming at the established model, designing a dynamic information processing strategy based on bus departure time, and fusing the dynamic information processing strategy into an adaptive large neighborhood search framework for solving, thereby obtaining a heuristic algorithm suitable for solving a bus-assisted unmanned aerial vehicle cooperative distribution problem considering the dynamic demand of a client point. The distribution path can be dynamically planned according to the demand points generated at any time, the logistics delivery efficiency is improved, and the distribution cost is reduced.

The invention discloses an intelligent bus scheduling system and method based on an AI large model, and the system comprises a data collection unit which is used for collecting multi-source urban traffic data; the data preprocessing unit is used for performing cleaning, standardization and feature extraction on the acquired multi-source urban traffic data; the knowledge graph construction unit is used for constructing the processed data into a knowledge graph containing entities, relationships and attributes; the AI reasoning unit is used for generating a natural language scheduling suggestion based on the knowledge graph state; the strategy optimization unit is used for optimizing a scheduling strategy based on a reinforcement learning algorithm; and the execution feedback unit is used for executing the scheduling instruction and collecting execution effect feedback. The problems that an existing bus dispatching system is insufficient in data utilization and lacks deep understanding and reasoning ability for a complex traffic environment are solved.

The invention provides a parallel main cabinet type direct current charging pile system, which comprises a main control unit, at least one power distribution matrix unit, at least one main cabinet and a plurality of charging terminals, and is characterized in that each main cabinet is internally provided with a plurality of pluggable power supply modules, and each charging terminal is provided with at least one charging gun; the switching control logic of the power distribution matrix unit supports any power scheduling across a main cabinet, across a charging terminal and across a charging gun; each power distribution matrix unit is constructed as an M * N full-connection switch matrix, and the power distribution matrix unit dynamically switches the output power of any one power supply module to any one charging gun. The main control unit dynamically dispatches the output ports of the SCU to be connected in parallel according to the number of the charging gun, automatic superposition of power of multiple main cabinets is achieved, the megawatt charging requirements of electric heavy trucks, buses and the like are met, any power module is supported to be correspondingly connected with the charging gun of any number, and the physical boundary among the main cabinets, the charging terminals and the charging gun is broken.

The invention discloses a subway interval interruption scene-oriented planned operation bus route fine adjustment method, which mainly comprises the following steps of: constructing a candidate bus route set and a rail station set capable of being conveniently transferred, and generating a multi-point connection path; on the premise of restraining the total demand of the detained passengers, the number of passengers getting on and off each bus station, the dynamic passenger capacity in the bus, the bus route arrival and departure time and the detour connection time are calculated, and the conventional operation service level is guaranteed; and constructing an optimization model aiming at minimizing the total delay of all system passengers, and solving the optimization model. By scientifically deploying existing operation bus resources, a multi-station dispersed transportation strategy is implemented, and travel requirements of passengers are accurately matched. The method effectively avoids the problem of congestion caused by centralized transportation of a single destination, and the constructed optimization model gives consideration to the operation efficiency of the public transportation system and the evacuation demands of detained passengers in a subway, remarkably reduces the overall delay cost, greatly improves the emergency response speed and the toughness of the public transportation system, and powerfully supports the safe and stable operation of an urban traffic system.

The embodiment of the invention discloses a bus scheduling method and device based on the battery health state, and the method comprises the steps: obtaining the battery health state parameter, the battery remaining capacity, the real-time position information and the line information of each bus in real time, carrying out the loss coefficient evaluation of each bus line based on the line information, and obtaining the loss coefficient of each bus line; matching each loss coefficient obtained by evaluation with the battery health state parameter of each bus, and determining a plurality of dispatchable vehicles on each bus route; classifying the plurality of dispatchable vehicles according to the battery remaining capacity and the battery health state parameter of each dispatchable vehicle and the route information of the corresponding bus route, determining running vehicles and alternative vehicles on each bus route, and when the battery remaining capacity of the running vehicles is smaller than a preset capacity threshold value, sending the alternative vehicles to the dispatchable vehicles; and scheduling the alternative vehicles based on the real-time position information of the running vehicles. The matching precision of each bus route and the schedulable vehicle is improved, and the rationality and timeliness of vehicle scheduling are fully guaranteed.

The invention provides an unmanned aerial vehicle terminal distribution method and system based on a public transport network, and belongs to the technical field of logistics distribution, and the method comprises the steps: obtaining customer information, public transport network information and unmanned aerial vehicle information; establishing a multi-target optimization model for cooperative distribution of the bus and the unmanned aerial vehicle by using the customer information, the public transportation network information and the unmanned aerial vehicle information; the target optimization module takes the minimum cost as a target function and considers time difference constraint, route constraint, load constraint and energy constraint; adopting a non-dominated transformer neighborhood search algorithm of a simulated annealing algorithm acceptance criterion to solve the multi-objective optimization model to obtain an approximate Pareto optimal solution set; the optimal solution set is an unmanned aerial vehicle tail end distribution scheme considering cost, time and risk. Based on the method, the invention further provides an unmanned aerial vehicle tail end distribution system based on the public transport network. According to the invention, through combination of unmanned aerial vehicle electric driving and public transportation network cooperation, multi-objective optimized logistics distribution is realized.

The invention provides an artificial intelligence-driven bus real-time scheduling and path optimization method. The artificial intelligence-driven bus real-time scheduling and path optimization method comprises the following steps: S1, multi-source data acquisition; s2, data preprocessing; s3, constructing an artificial intelligence scheduling optimization model; s4, generating a real-time scheduling decision; s5, vehicle execution and data feedback; and S6, path dynamic optimization. Through deep fusion of an artificial intelligence technology and public transportation services, the precision, dynamic and intelligent scheduling decision is realized, and finally the operation efficiency and service quality of a public transportation system are improved.

The invention relates to the technical field of intelligent transportation, in particular to a public transportation passenger and freight co-transportation scheduling system based on big data and the Internet of Things. Comprising data collection and processing, scheduling system architecture, path optimization and dynamic adjustment, and user interface and system management. Wherein the data collection and processing is used for the process of collecting and processing bus operation data by the system and is the basis of the system; the data collection and processing comprises passenger flow data, cargo flow data, vehicle state data and environment data; the scheduling system architecture is used for realizing comprehensive monitoring, real-time scheduling and resource optimization of bus passenger and freight co-transportation; according to the invention, by integrating real-time passenger flow data, cargo flow data and vehicle state information and utilizing big data analysis, an Internet of Things technology and an artificial intelligence algorithm, co-scheduling of buses and freight, path optimization and maximum utilization of resources are realized.

A bench type seat frame for use in vehicles, such as busses and / or other passenger vehicles has been developed. In one example, the seat frame includes a reinforced pedestal mount. For example, the pedestal includes one or more self-reinforced feet mounted to a floor of the vehicle. In another example, the self-reinforced feet are made from folded steel in a double thickness configuration. The pedestal further includes one or more crumple zones configured to dissipate energy during a collision. In another example, the seat frame includes a cross member extending between the pedestal and a wall mount. In one example, the cross member is able to support both belted and unbelted seat configurations. For example, the cross member includes one or more belt anchors configured to receive and secure one or more seat belts.

The invention relates to an intelligent safety management system based on BDS / UWB combined positioning of a bus station and a working method, and belongs to the technical field of intelligent traffic. The combined positioning device is used for carrying out combined positioning through BDS / UWB to realize positioning of different spaces and environments; security personnel receive the patrol plan and the patrol route through the manual patrol device, and report abnormal conditions and position information; the unmanned automatic patrol device is used for automatically receiving the patrol plan and carrying out safety inspection on vehicles in a station or other loose areas according to the plan and a patrol line; and the network service platform is used for regulating and controlling vehicle operation and controlling the combined positioning device, the manual patrol device and the unmanned automatic patrol device. According to the invention, potential safety hazards are reduced, the vehicle safety management level is improved, the intelligent level of public transportation enterprise management is improved, the working intensity of patrol workers is reduced, and the economic benefits of public transportation operation enterprises are improved.

The invention discloses an electric bus station optimization scheduling method and system based on light storage and charging cooperation. The method comprises the following steps: acquiring parameters; according to the obtained parameters, an electric bus charging and discharging behavior model, a photovoltaic output model, an energy storage system operation model and a charging pile operation model considering a one-pile multi-gun sharing mode are established; by taking the minimization of the total operation cost of the station as a target and taking the established unit models as constraints, constructing an optical storage and charging integrated electric bus station optimization scheduling model, and solving to obtain a scheduling plan in the station; and issuing the solved scheduling plan to a station operation control system to generate a scheduling instruction and a charging and discharging instruction of the electric bus so as to realize cooperative scheduling of the station optical storage and charging resources. According to the method, the physical matching relation of the vehicle pile gun is depicted finely, the problem of symmetric solution space explosion caused by neglecting equipment homogenization in a traditional model is solved, and the solving efficiency and feasibility of a large-scale scheduling problem are remarkably improved.

The invention relates to the technical field of intelligent traffic, and provides a public transport priority signal and track cooperative control method and device under dynamic road right distribution, and the method comprises the steps: constructing a historical data set of traffic signal information and vehicle information; according to the phase of the historical data set and the vehicle information of the corresponding lane in the direction from the stop line to the lane entrance, constructing a motorcade according to the constraint that the maximum number of vehicles allowed by phase timing is not exceeded; inputting the vehicle information and the traffic signal information of the motorcade in the historical data set into a signal timing and road right distribution model to obtain signal timing decision information, road right distribution decision information and vehicle decision information of at least a next period; controlling traffic lights according to the signal timing decision information and the right of road distribution decision information; and controlling the vehicle to run according to the right-of-way distribution decision information and the vehicle decision information. According to the invention, the passenger passing efficiency is considered, the lane right is dynamically allocated, and the traffic signal timing is optimized.

The invention provides a bus route planning method and system, and relates to the field of route planning. Establishing a road network model based on station coordinates and inter-station operation time information, establishing Markov decision process models for a plurality of demand response type buses, and designing an improved Q-Learning algorithm; and reasonably distributing travel demands in a road network, importing the travel demands into a designed path planning algorithm, and solving to obtain an optimal running route of each demand response type bus. The problems of path overlapping and local optimization in a traditional single-agent model are solved, an order allocation mechanism is designed, and the problem of vehicle resource competition is avoided.

Methods, systems, and computer program products for determining transit routes through crowd-sourcing, for determining an estimated time of arrival (ETA) of a vehicle of the transit route at a given location, and for providing predictive reminders to a user for catching a vehicle of the transit route. A server receives signal source information about wireless signal sources detected by user devices, including information about a first wireless signal source detected by some devices. The server determines that the first wireless signal source is moving. The server determines that the first wireless signal source is associated with a public transit route upon determining that the signal source information satisfies one or more selection criteria. The server stores information associating the first wireless signal source with the public transit route as transit movement data corresponding to the public transit route.

The invention discloses a customized bus evaluation method and device and a storage medium, and relates to the technical field of public transportation. The evaluation method of the customized bus comprises the following steps: acquiring first vehicle-road interaction data of the customized bus, wherein the first vehicle-road interaction data is interaction data between a vehicle-mounted communication unit and a road side communication unit of the customized bus; processing the first vehicle-road interaction data to obtain an evaluation value corresponding to an evaluation index under at least one evaluation dimension, the at least one evaluation dimension at least comprising a vehicle-road cooperation service level dimension, and the vehicle-road cooperation service level dimension being used for evaluating the service effect of the customized bus in the vehicle-road cooperation environment; and determining an evaluation score of the customized bus by using the evaluation value corresponding to the evaluation index, the evaluation score being used for indicating the service quality of the customized bus. According to the embodiment of the invention, the reliability of customized bus evaluation can be improved.

This invention provides a method for optimizing the shared use of dedicated bus lanes, relating to the field of transportation technology. The method includes: identifying congested road sections and obtaining vehicle speeds in each lane of the congested sections; comparing the congestion levels of dedicated bus lanes and regular lanes by calculating travel indices, and identifying routes where regular lanes are congested while dedicated bus lanes are unobstructed; establishing a multi-objective integer optimization model with the objectives of maximizing the number of shared vehicles available for reservation and minimizing overall road delays; solving for the maximum number of vehicles that can use the dedicated bus lane during a given time period; conducting simulations to verify the multi-objective integer optimization model and evaluating the impact of the shared reservation scheme on dedicated bus lanes and regular lanes; and, considering user acceptance, constructing a mechanism for regular vehicles to reserve bus lanes using carbon credits. This invention addresses the shortcomings of dynamic schemes and the one-size-fits-all approach to existing dedicated bus lane management models.

The invention relates to an intelligent traffic system, in particular to a bus driver scheduling and shift-by-shift method based on dynamic planning, electronic equipment and a storage medium, and the bus driver scheduling and shift-by-shift method comprises the following steps: in a scheduling stage, according to pre-input parameters, using a dynamic planning algorithm to generate an optimal scheduling fragment for each time period; according to a preset priority, combining the segments to drivers as few as possible for execution; in the shift stage, according to the shift arrangement result, a dynamic planning algorithm is used, the longest path sub-problem is solved continuously, and driver shift schemes as few as possible are generated; and the drivers deviating from the average working hours are automatically subjected to class type replacement, so that the total working hours of the drivers are basically the same. Compared with the prior art, the method has the advantages that the non-aftereffect of the scheduling process is fully utilized, and the optimal solution of the traditional algorithm can be approached in extremely short time; the shift stage gives consideration to labor reduction and equal division of labor and time, and meets the application requirements of enterprises.

The invention discloses a transportation hub transport capacity scheduling system based on big data, and particularly relates to the technical field of traffic scheduling, which comprises a data aggregation and sensing module, an early warning and triggering module, a scheduling scheme simulation and decision module and an instruction distribution and execution monitoring module. The system collects subway, bus, taxi, online car-hailing and passenger flow data in real time through a multi-source interface and a sensor, and a unified transport capacity diagram is generated after cleaning and anomaly detection; carrying out transport capacity gap identification and early warning based on a multi-index coupling risk analysis model; a plurality of scheduling schemes are generated and evaluated through a microscopic simulation model integrated with passenger behavior prediction, and an optimal scheme is recommended; finally, the scheme is converted into a specific instruction to be distributed and executed, and real-time monitoring and feedback are performed to form closed-loop management. According to the invention, the transformation from passive response to active intervention and from experience decision to scientific scheduling is realized, and the transport capacity cooperation efficiency and passenger evacuation capability of the transportation hub are significantly improved.

The invention discloses a public transport passenger flow prediction method based on IC card data, which relates to the technical field of intelligent transportation, and comprises the following steps: respectively carrying out feature inspection on a week time sequence, a day time sequence, a time interval sequence and a holiday effect sequence, selecting an adaptive model, carrying out parameter and noise variance feature analysis on the adaptive model by using an RLS algorithm, and carrying out prediction on the public transport passenger flow. Outputting four groups of prediction result sequences; models corresponding to the four groups of prediction result sequences are converted into a state space form, a noise variance estimation value is estimated online through an RLS algorithm, and four groups of time-varying fusion weights are generated; and constructing an observation noise covariance matrix based on the four groups of time-varying fusion weights, performing recursive optimization through a Kalman filter, and outputting a hybrid prediction result by weighting and fusing observation prediction values of the four groups of sequences. According to the method, accurate fitting of passenger flow periodicity, seasonality and heterovariance is realized, and the single-model prediction precision is improved.