101 results about "Trip chain" patented technology

The invention discloses a traveler home-work location identification and trip chain depicting method based on mobile phone signaling data, and belongs to the field of analysis of transportation planning data. The method comprises the steps of: triggering an information database by communication network records provided by a mobile network operator; after cleaning, integrating and calculating by using a position conversion algorithm, converting the data of the operator into a reference dataset; aiming at each user, converting the dataset into a mobile time-space trajectory, identifying stopover points, high frequency points and long time points in the mobile time-space trajectory, and on the basis, identifying home-work locations, activity target locations and insignificant stopover points; and finally depicting a closed trip chain of the user by being combined with the mobile time-space trajectory. The traveler home-work location identification and trip chain depicting method based on mobile phone signaling data has the advantages of being conductive to reducing trip survey costs of residents, obtaining more precision trip characteristics of crowds with different identities, and thereby allowing the traffic demand forecasting to be more accurate; and 2, being conductive to improving scientificity of planning layout construction, such as transport corridors, public transit networks and traffic facilities, in urban traffic planning.

The invention relates to a mobile phone information processing method, in particular to a mobile phone signaling trip chain-based OD matrix acquisition method. The method includes the following steps that: mobile phone signaling trip chain data of a specified date are acquired according to sampling requirements; an origin point (O point) and a destination point (D point) of a trip are determined according to the mobile phone signaling trip chain data; a sample is expanded according to a sampling coefficient; coarse granularity information OD matrix data are obtained; mode divisional OD matrix data are obtained; a multiple-trip OD matrix data are obtained; and a trip occurrence attraction histogram and a corresponding OD expectation graph are outputted. According to the mobile phone signaling trip chain-based OD matrix acquisition method of the invention, the trip chain data which are depicted by mobile phone signaling information and are simple in acquisition mode, low in acquisition cost, large in sample information and flexible in sampling time are utilized to construct a coarse granularity information OD matrix, a trip mode divisional OD matrix and a multi-destination and multi-trip OD matrix. The mobile phone signaling trip chain-based OD matrix acquisition method has the advantages of high real-time performance and high precision.

The invention discloses a bus passenger travel station prediction method, a storage medium and a server. The bus passenger travel station prediction method comprises the steps that bus GPS track data,passenger bus IC card swiping record data and bus station and route vector data of a certain urban area are acquired; based on the bus GPS track data, the passenger bus IC card swiping record data and the bus station and route vector data, historical bus card swiping get-on stations of passengers are matched, and passenger historical get-on station travel links are constructed; spatial clusteringis carried out on the bus stations, and a passenger historical get-on clustering travel link is constructed; bus get-on clustering is predicated based on a variable-order Markov model and the passenger historical get-on clustering travel link, and a specific get-on station is predicated based on a probability model and based on the analysis of the bus and subway mixed travel chain, bus get-off clusters and get-off stations are predicated. According to the method, the bus get-on and get-off stations are well predicted, and the prediction accuracy of the travel stations is obviously improved.

The invention provides a method for judging the getting-off stations of public transportation IC card passengers based on historical trip patterns. Intelligent public transportation system data are acquired; public transportation IC card data are associated with intelligent dispatching system data, so that the getting-on station information of the public transportation passengers is obtained; commuting passengers in the public transportation IC card passengers, as well as the residence places and working sites of the commuting passengers are identified through a commuting OD estimation method; getting-off stations of the commuting trips of the current day are judged through using obtained commuting trip patterns; the getting-off station information of a part of the trips of the public transportation IC card passengers in the previous days is obtained through using a trip chain method; and the trips of the current day are matched with the associated trips of the previous days, so that the getting-off stations of the trips of the current day can be judged. The method provided by the invention is implemented through algorithms; and testing and accuracy analysis are performed on the algorithms through using a large number of practical data. The proportion of judged getting-off stations of the passengers in workdays is increased by 12.13% on the basis of an existing method, and an accuracy rate reaches 87.89%.

The invention provides a vehicle travel trajectory identification method based on bayonet data, which adopts a spectral clustering method to realize automatic separation of travel chain from the time-space characteristic of bayonet data, thereby identifying the starting point, the end point and the passing point of a single travel trajectory. The method particualy includes generating a complete travel chain of the vehicle on the day; establishing a similarity matrix S; calculating an adjacency matrix W and a degree matrix D; constructing a Laplace matrix L and further determining a characteristic matrix F; using the DBSCASN clustering algorithm to perform cluster analysis, and obtaining the clustering results; determining the cluster partition result of trajectory points to generate sub-trajectories. This method takes into account both the time and space attributes of vehicles, and is more comprehensive than the method based on travel time to partition the trajectory. No preset threshold is needed, and the vehicle trajectory recognition is completely driven by the measured data, which improves the accuracy of trajectory recognition. The analysis results can be used in vehicle travel behavior recognition, travel characteristics analysis, traffic flow OD estimation and so on.

A bus IC card passenger get-off station derivation method based on multi-source data has accuracy, effectiveness and operability, can be widely applied to bus OD derivation, and provides theoretical and method bases for analyzing line passenger flow distribution, determining departure shifts and the like. The method comprises the following steps: (1) making basic data preparation: preprocessing original data to obtain effective bus GPS data and IC card swiping data, calculating a bus arrival time table, and counting people getting on a bus at each station; (2) deriving get-off stations based on a commuting travel chain: identifying the commuting travel chain, deriving commuting crowd get-off stations, and counting people getting off at each station; (3) deriving get-off stations based on acommon trip chain: identifying the common trip chain, deriving get-off stations according to the characteristics of the trip chain, and counting people getting off at each station; and (4) deriving get-off stations based on the station attraction weight: defining a station attraction weight calculation method, and calculating the get-off probability of each station from the perspective of gathercounting, thereby obtaining the number of people getting off at each station.

The invention discloses a public electric bicycle leasing point address-selecting method based on a trip chain. The method comprises steps of: 1) acquiring the planning basic information of a public electric bicycle system to be established; 2) establishing the generalized trip cost function; 3) establishing an upper model and a lower model by considering the planner and the users of the public electric bicycle system respectively so as to construct a double-layer planning model to describe the public electric bicycle leasing point address-selecting problem; and 4) solving the double-layer planning model formed by the upper planning model and the lower planning model to obtain a public electric bicycle leasing point address-selecting scheme. The public electric bicycle leasing point address-selecting method may enhance the accuracy and reliability of the public electric bicycle leasing points, gives an impetus to the construction of associated city public electric bicycle system, and has real popularization value.

The invention provides an airport passenger multi-traffic-mode transfer travel chain construction device. The system comprises a travel preference model construction device which is based on passengerportraits and used for predicting airport passenger travel behaviors; a travel full-coverage segmentation time consumption estimation device which is used for estimating travel time inside and outside a port arrival passenger land side traffic transfer room; a passenger flow gathering and dispersing rule and multi-mode traffic capacity coupling module which is used for analyzing the passenger gathering and dispersing rule in the land-side traffic hub and predicting waiting time of different traffic modes; a passenger travel chain multi-target construction method device which takes passenger travel preferences, travel whole-course time, passenger flow gathering and scattering distribution, traffic mode transport capacity and the like are taken as influence factors, and generates a passenger travel chain through comprehensive optimization. The method can predict passenger group travel preferences with different travel purposes, the number of people traveling together, age structures andthe like, accurately estimate the walking time of passengers in the terminal, the travel time outside the terminal and the waiting time, and recommend an efficient and comfortable travel scheme for airport arrival passengers.

The invention discloses an individual behavior analysis method based on mobile phone signaling data and POI (Point of Interest) data, which is used for solving the problem of individual travel behavior identification of special social crowds. The method comprises two parts of personal travel feature extraction and travel behavior prediction: (1) personal travel feature extraction: completing personal travel chain extraction by using mobile phone signaling data; based on the personal travel chain data, designing travel features and calculating the personal travel features in combination with POI interest point data a;nd (2) personal travel behavior prediction: based on personal travel characteristics, predicting personal travel behaviors by adopting a decision tree method.

The invention discloses multi-mode trip chain optimization method and system facing to integration trip. Selectable trip routes, containing multiple trip modes and combinations thereof, are divided until non-dividable units; and with consideration of real-time data, short-time prediction, user preference and the like, the utilization coefficient of each non-dividable unit is calculated; and then on the basis of different targets including convenience, reliability, economy, comfort and the like, generalized costs of the available trip routes are calculated so as to form a whole trip chain alternative route sequence, which satisfies user demands, and a recommended trip route is pushed to the user. The method and the system can integrate information of multiple trip modes and can recommend trip schemes, at trip chain level, including parking, bicycles and the like comprehensive trip modes; and meanwhile, trip modes and user intention are combined, so that a specific trip mode is supplied for the user; the trip route is individually pushed and recommendation of differentiation trip modes is supplied, so that individual trip server level is greatly improved.

The invention provides a comprehensive traffic service evaluation method and device based on individual travel chains. The comprehensive traffic service evaluation method based on individual travel chains mainly comprises the steps: acquiring travel data of the individual travel chains of a plurality of tested objects; grading each individual trip chain according to the trip data through a presetevaluation index; and calculating a traffic service index of the preset area according to the levels and the number of the individual travel chains in the preset area. By implementing the comprehensive traffic service evaluation method, the traffic service is evaluated based on the individual travel chain; starting from the perspective of travelers, the travel experience of the traveler is fully considered, and the travel chain of the traveler is composed of a plurality of travel modes; and by taking the individual travel chain as a research object, the cooperative operation and service capability of urban comprehensive passenger transport can be reflected, and the evaluation result of evaluating the traffic service quality in such a way can more truly reflect the travel condition of travelers and better meet the actual requirements of travelers.

The invention discloses a space load prediction method considering electric vehicle charging demands, and the method comprises the following steps: 1, dividing electric vehicles into three types according to operation characteristics and charging modes; 2, fitting the probability distribution of the travel information according to the survey data to obtain a probability density function of the travel information; 3, constructing a travel chain model according to the type of the travel destination of the electric vehicle, and counting the probability proportion of the travel chain model; 4, according to the probability density function of the travel information and the probability proportion of the travel chain model, based on a Monte Carlo algorithm, simulating and calculating charging load variance coefficients of the three types of electric vehicles, carrying out the superposition, and completing the space load prediction. According to the method, the influence of large-scale electric vehicle access to the power grid on the uncertainty of the space load prediction result is solved, the space-time distribution of the electric vehicle charging demand is simulated by comprehensivelyconsidering multiple factors, and reference is provided for planning of a future urban power distribution network.

The invention discloses a trip chain-oriented demand response bus service mode and optimization method. The method comprises the following steps: formulating a trip chain-oriented demand response bus'one ticket 'service mode; generating a constraint set and an objective function of a trip chain-oriented demand response bus 'one-ticket' service operation cost according to the pick-up and drop-off station network topology, the passenger trip chain information and the bus information; according to the constraint set and the target function, establishing a mixed integer linear programming model for travel chain-oriented demand response bus one-ticket service operation vehicle path optimization; and solving the mixed integer linear programming model, and obtaining an optimized service vehicle running path scheme through an effective inequality and a genetic algorithm based on an optimal time difference insertion method. According to the invention, the high-level customized public transportservice is provided, and the complexity that passengers need to select a travel chain combination scheme from a plurality of conventional fixed public transport modes is also reduced.

The invention discloses a traffic demand prediction method and device, and electronic equipment. The method comprises the steps of obtaining a trip chain of each target trip crowd in a target area; generating a model based on the trip chain and the trip data, and generating predicted trip data of each target trip crowd; determining a traffic distribution result of the target area based on the predicted travel data of each target travel crowd; if the traffic distribution result does not meet a preset convergence condition, calculating traffic comprehensive impedance according to the traffic distribution result, obtaining updated predicted travel data of each target travel crowd by combining the traffic comprehensive impedance, and obtaining an updated traffic distribution result based on the updated predicted travel data of each target travel crowd; and if the traffic distribution result or the updated traffic distribution result satisfies a convergence condition, outputting a traffic demand prediction result in the target area, the traffic demand prediction result including predicted travel data and the traffic distribution result. The accuracy of the travel demand prediction result can be improved.

The invention provides a low-carbon travel carbon emission reduction verification method and system based on travel chain big data. The method comprises the steps of 1) obtaining sample data of traveldata; 2) when the sample data is walking data, turning to the step 3); when the sample data is bicycle data, turning to the step 4); when the sample data is electric bicycle data, turning to the step5); 3) adopting a walking travel distance verification method to perform verification and deduplication on the sample data to obtain a final effective travel distance; calculating the carbon emissionof walking according to the final effective travel distance; 4) adopting a bicycle travel distance verification method to perform verification and deduplication on the sample data to obtain a final effective travel distance; calculating the carbon emission of the bicycle according to the final effective travel distance; 5) verifying and de-weighting the sample data by adopting a verification method of the travel distance of the electric bicycle to obtain a final effective travel distance; and calculating the carbon emission of the electric bicycle.

The invention discloses a pseudo code signaling data preprocessing and trip chain identification method. The pseudo code signaling data preprocessing and trip chain identification method includes thefollowing steps: (1) merging redundant signaling records and culling abnormal records; (2) according to parameter characteristics of ping-pong effect records, identifying the ping-pong records and deleting the ping-pong records; (3) calculating the user residence centroid, setting the time and space thresholds when the trip occurs, and identifying the start record point; and (4) setting the user residence time and space threshold, and identifying the record point for ending of the trip, thus completing the trip chain identification. The pseudo code signaling data preprocessing and trip chain identification method effectively cleans and filters the data, improves the data precision, extracts the complicated data as valuable trip OD information, and improves the availability of data in various fields such as transportation. The pseudo code signaling data preprocessing and trip chain identification method is wide in the application range, and is simple and practicable.

The invention provides a bus passenger getting-off station speculating method based on AFC data. A bus taking behavior of a passenger is analyzed according to two adjacent bus card swiping records ina day, and thus on the premise that getting-off station information lacks, the getting-off station corresponding to a getting-on card swiping record each time is speculated; according to the bus passenger getting-off station speculating method based on AFC data, by temporal thresholds which comprise average bus taking time, the longest waiting time and the longest transfer duration, transferring behaviors of bus passengers are recognized, and thus a whole bus trip chain is analyzed. By a space analyzing method, based on walking time, the most possible getting-off station is recognized in a radiating area of a station, and reliability of a getting-off station speculating result is ensured.

The invention relates to the technical field of intelligent traffic control, in particular to a vehicle real-time travel track acquisition method based on vehicle passing video data. The problems thatthe vehicle cannot obtain the travel track, the dynamic update of the vehicle travel chain cannot be realized and the consumption of system resources for calculating the travel chain is too large dueto the lack of GPS equipment can be solved to a certain extent. The method comprises the following steps: constructing an optimal adjacency matrix of a road network according to road network topologyinformation of a city; analyzing the vehicle passing video data from the detection point location to obtain vehicle driving information, wherein the vehicle driving information comprises a snapshot moment, a snapshot point location and a license plate number; and based on the optimal adjacency matrix, comparing and judging the vehicle driving information and a historical travel chain of the vehicle, and constructing a real-time travel track of the vehicle.

The invention provides an inter-provincial travel flow estimation method based on highway toll collection data. The method comprises the following steps of extracting data field data related to trans-provincial travel in highway toll collection data, carrying out data preprocessing on the extracted highway toll collection data, and extracting an inter-provincial travel chain set according to the highway toll collection data after data preprocessing, and calculating highway inter-provincial travel O-D and O-D traffic based on the extracted inter-provincial travel chain set. According to the method, based on national highway toll collection data, in combination with national highway network topology data, national toll station basic information data and the like, an extraction algorithm of a highway inter-provincial trip chain is given, highway inter-provincial trip flow is calculated and is compared with actual section flow obtained through statistics, and the practicability of inter-provincial section flow calculation is effectively improved.

The invention discloses a passenger flow collection and distribution mode discovery and prediction method, and the method comprises the following steps: (1) collecting the information of the number of persons participating in a competition activity, grading and marking the competition activity, collecting passenger flow data, and carrying out trip chain extraction on the passenger flow data; (2) on the basis of a trip chain extraction result and competition activity grading and marking results, calculating a polygonal region net passenger flow volume to obtain a hot spot region and a site; (3) extracting passenger flow collecting and distributing characteristics of the hot bus stations; (4) carrying out clustering training on the constructed passenger flow collection and distribution characteristics based on a Gaussian mixture model to obtain a clustering result, and analyzing the clustering result; (5) passenger flow prediction features are extracted from the hot bus stations; (6) carrying out one-hot coding and standardization on discrete features in the passenger flow prediction features; (7) training and storing the prediction model based on an LSTM method; (8) inputting the prediction set into the stored model to obtain a hot bus station passenger flow prediction result during the competition activity, thereby realizing hot bus station passenger flow prediction during the competition activity.