1014 results about "Traffic prediction" patented technology

A system and method for traffic prediction based on space-time relation are disclosed. The system comprises a section spatial influence determining section for determining, for each of a plurality of sections to be predicted, spatial influences on the section by its neighboring sections; a traffic prediction model establishment section for establishing, for each of the plurality of sections to be predicted, a traffic prediction model by using the determined spatial influences and historical traffic data of the plurality of sections; and a traffic prediction section for predicting traffic of each of the plurality of sections to be predicted for a future time period by using real-time traffic data and the traffic prediction model. An apparatus and method for determining spatial influences among sections, as well as an apparatus and method for traffic prediction, are also disclosed. With the present invention, a spatial influence of a section can be used as a spatial operator and a time sequence model can be incorporated, such that the influences on a current section by its neighboring section for a plurality of spatial orders can be taken into account. In this way, the traffic condition in a spatial scope can be measured more practically, so as to improve accuracy of prediction.

A dynamic upstream bandwidth allocation scheme is disclosed, i.e., limited sharing with traffic prediction (LSTP), to improve the bandwidth efficiency of upstream transmission over PONs. LSTP adopts the PON MAC control messages, and dynamically allocates bandwidth according to the on-line traffic load. The ONU bandwidth requirement includes the already buffered data and a prediction of the incoming data, thus reducing the frame delay and alleviating the data loss. ONUs are served by the OLT in a fixed order in LSTP to facilitate the traffic prediction. Each optical network unit (ONU) classifies its local traffic into three classes with descending priorities: expedited forwarding (EF), assured forwarding (AF), and best effort (BE). Data with higher priority replace data with lower priority when the buffer is full. In order to alleviate uncontrolled delay and unfair drop of the lower priority data, the priority-based scheduling is employed to deliver the buffered data in a particular transmission timeslot. The bandwidth allocation incorporates the service level agreements (SLAs) and the on-line traffic dynamics. The basic limited sharing with traffic prediction (LSTP) scheme is extended to serve the classified network traffic.

The invention belongs to the field of intelligent transportation, and discloses a traffic prediction method based on an attention temporal graph convolutional network. The method includes the following steps that: firstly, an urban road network is modeled as a graph structure, nodes of the graph represent road sections, edges are connection relationships between the road sections, and the time series of each road section is described as attribute characteristics of the nodes; secondly, the temporal and spatial characteristics of the traffic flow are captured by using an attention temporal graph convolutional network model, the temporal variation trend of the traffic flow on urban roads is learned by using gated cycle units to capture the time dependence, and the global temporal variation trend of the traffic flow is learned by using an attention mechanism; and then, the traffic flow state at different times on each road section is obtained by using a fully connected layer; and finally,different evaluation indexes are used to estimate the difference between the real value and the predicted value of the traffic flow on the urban roads and further estimate the prediction ability of the model. Experiments prove that the method provided by the invention can effectively realize tasks of predicting the traffic flow on the urban roads.

In the present invention a traffic information providing apparatus makes a vehicle location and a running date a starting point, and predicts arrival time to each link included in a designated area, based on current traffic information provided by a traffic information center; meteorological forecast information provided by a meteorological information center; and statistical traffic information acquired from a traffic information data base where past traffic information is stored, thereby produces meteorological consideration traffic prediction information of the link, and sends the produced meteorological consideration traffic prediction information to a car navigation device. Then the car navigation device is configured to receive the produced meteorological consideration traffic prediction information and to search a guidance route, based on the produced meteorological consideration traffic prediction information.

Real-time high-fidelity spatiotemporal data on transportation networks can be used to learn about traffic behavior at different times and locations, potentially resulting in major savings in time and fuel. Real-world data collected from transportation networks can be used to incorporate the data's intrinsic behavior into a time-series mining technique to enhance its accuracy for traffic prediction. For example, the spatiotemporal behaviors of rush hours and events can be used to perform a more accurate prediction of both short-term and long-term average speed on road-segments, even in the presence of infrequent events (e.g., accidents). Taking historical rush-hour behavior into account can improve the accuracy of traditional predictors by up to 67% and 78% in short-term and long-term predictions, respectively. Moreover, the impact of an accident can be incorporated to improve the prediction accuracy by up to 91%.

An architecture for capture and generation, and a set of methods for characterization, prediction, and classification of traffic in packet networks are disclosed. The architecture consists of a device that stores packet timing information and processes the data so that characterization, prediction, and classification algorithms can perform operations in real-time. A methodology is disclosed for real-time traffic analysis, characterization, prediction, and classification in packet networks. The methodology is based on the simultaneous aggregation of packet arrival times at different times scales. The traffic is represented at the synchronous carrier level by the arrival or non-arrival of a packet. The invention does not require knowledge about the information source, nor needs to decode the information contents of the packets. Only the arrival timing information is required. The invention provides a characterization of the traffic on packet networks suitable for a real-time implementation. The methodology can be applied in real-time traffic classification by training a neural network from calculated second order statistics of the traffic of several known sources. Performance descriptors for the network can also be obtained by calculating the deviation of the traffic distribution from calculated models. Traffic prediction can also be done by training a neural network from a vector of the results of a given processing against a vector of results of the subsequent processing unit; noticing that the latter vector contains information at a larger time scale than the previous. The invention also provides a method of estimating an effective bandwidth measure in real time which can be used for connection admission control and dynamic routing in packet networks. The invention provides appropriate traffic descriptors that can be applied in more efficient traffic control on packet networks.

A system or computer usable program product for tracking and routing traffic to avoid congestion via a plurality of user devices including providing a traffic reservation user interface for receiving a plurality of path selections from the plurality of user devices; responsive to predicting a traffic congestion from the plurality of user devices taking into account real-time and predicted conditions, presenting a first set of users with a first set of route selection recommendations via the user interface; and responsive to receiving a plurality of actual routing selections from the first set of users from the user interface, adjusting the traffic prediction, and presenting a second set of users with a second set of route selection recommendations via the user interface to reduce expected traffic congestion.

A method and apparatus for predicting traffic on a transportation network where real time data points are missing. In one embodiment, the missing data is estimated using a calibration model comprised of historical data that can be periodically updated, from select links constituting a relationship vector. The missing data can be estimated off-line whereafter it can be used to predict traffic for at least a part of the network, the traffic prediction being calculated by using a deviation from a historical traffic on the network. The invention further discloses a method for in-vehicle navigation; and a method for traffic prediction for a single lane.

The invention relates to an intelligent traffic system, in particular to short-time prediction method and system of traffic flow data, which are used for improving the prediction accuracy of the traffic flow data and are suitable for real-time traffic prediction. The short-time prediction method of traffic flow data, which is provided by the invention, improves the accuracy of short-time traffic flow prediction and acquires optimal K and l values and corresponding predicted traffic flow data by further adding a state pattern vector to a traditional K adjacent nonparametric regression prediction method and adopting search methods of variable adjacent numbers K and match numbers l.

The invention discloses an abnormal flow detection method and device, computer equipment and a storage medium. The method comprises the following steps of: screening the historical flow data of the monitoring object; obtaining target traffic data, carrying out regression analysis on the target traffic data; establishing a flow prediction model, predicting the flow data of the monitored object by using the flow prediction model; obtaining a prediction result of the flow data of the monitoring object in a preset time period, carrying out statistical analysis is on a prediction result according to a preset statistical mode; obtaining a traffic alarm threshold value of the monitored object, further obtaining a real-time access log of the monitored object when the real-time traffic data of themonitored object is greater than the traffic alarm threshold value, and performing abnormal traffic alarm if the response time of the real-time access log is greater than the response time threshold value. According to the embodiment of the invention, the accuracy of the alarm threshold can be improved, judgment is carried out by combining the response time of the service, and thus the accuracy ofabnormal flow detection is improved.

The invention relates to a vehicle flow predicting method based on an integrated LSTM neural network. On the basis of historical data obtained by vehicle flow detection, an integrated LSTM neural network vehicle flow prediction model is established to carry out vehicle flow prediction, so that the generalization error of the prediction model is reduced and the accuracy is improved. The method comprises the following steps that: data preprocessing is carried out; according to a preprocessed vehicle flow time sequence value, a vehicle flow matrix data set is constructed and the vehicle flow of an (n+1)th period of time is predicted by using first n periods of time, wherein each period of time is delta t expressing the time length and the unit is min; a plurality of different LSTM neural network models are constructed by using different initial weights; on the basis of a bagging integrated learning method, a training set and a verification set are constructed; a plurality of LSTM neural networks are trained to obtain an optimized module; a weighting coefficient of the single LSTM model is calculated by using the verification set; and inverse transformation and reverse normalization are carried out on a predicted vehicle flow value to obtain a predicted vehicle flow and integrated weighting is carried out to obtain a vehicle flow value predicted finally by the model.

A method for tracking and routing traffic to avoid congestion via a plurality of user devices including providing a traffic reservation user interface for receiving a plurality of path selections from the plurality of user devices; responsive to predicting a traffic congestion from the plurality of user devices taking into account real-time and predicted conditions, presenting a first set of users with a first set of route selection recommendations via the user interface; and responsive to receiving a plurality of actual routing selections from the first set of users from the user interface, adjusting the traffic prediction, and presenting a second set of users with a second set of route selection recommendations via the user interface to reduce expected traffic congestion.

The method is suitable for the technical field of traffic prediction, and provides a traffic flow prediction method and system, and a terminal device. The method comprises the following steps of: acquiring traffic data in a specified time period of a target area, performing graph convolution network training on the traffic data, capturing a topological structure of an urban road network to obtainspatial features, inputting the time sequence of the spatial features into a gating cycle unit model, and obtaining dynamic changes through information transmission between units to capture time features; and establishing a prediction model according to the spatial features and the time features so as to predict the traffic flow of the target area according to the prediction model. According to the invention, a graph convolutional neural network based on an attention mechanism is applied to the prediction problem in the traffic field, high-dimensional features in the road traffic network can be better mined in a complex road structure, the accuracy of traffic flow prediction is improved in cooperation with the improved recurrent neural network, and the improvement effect is obvious especially in medium-term and long-term prediction.

The invention discloses a graph neural network traffic flow prediction method and system based on an attention mechanism. The method comprises the steps of obtaining to-be-predicted urban traffic flowdata; constructing a road network map according to the road connection relationship; preprocessing the urban traffic flow data to be predicted; and inputting the road network map and the preprocessedresult into a pre-trained neural network based on an attention mechanism, and finally outputting a prediction result of the urban traffic flow. Roads and checkpoints are encoded according to the roadnetwork information, a road network graph structure is established according to the upstream and downstream relationship of the roads, vehicle passing data of the checkpoints is counted under different time dimensions nd summarized to form a road network traffic flow data table; a graph neural network formed by stacking multiple layers of attention modules is constructed, a time sequence attention mechanism and the graph attention network are used for modeling the traffic flow in the whole road network, and the future traffic flow condition of a specified checkpoint is predicted.

The invention discloses a method and a device for predicting traffic, which predicting the traffic based on a mass measurement report and comprises: determining the grid in which a measurement report MR is positioned during reporting according to the report position of the measurement report received, wherein the grid is obtained by dividing the geographic area of the traffic to be tested in advanced; counting the MRs in all time periods of each grid according to the report time and the grid of the MR; acquiring the number of MRs in the M adjacent time periods of a current time period in each grid and calculating a predicted value of the traffic in the current time period in each grid by using a time sequence prediction algorithm. The method and device realize real-time, fine-granularity and high-precision traffic prediction.

A system, method and computer program product for forecasting a vehicle traffic condition in a near future. The system comprises a traffic prediction tool, a turning percentage prediction module and a simulation tool. The traffic prediction tool estimates a traffic speed and volume in a traffic link. A traffic link refers to a portion of a traffic road where the traffic prediction tool is installed. The turning percentage prediction module estimates a turning percentage in the traffic link based on the estimated traffic speed and traffic volume. The simulation tool computes, based on the estimated turning percentage, the estimated traffic speed and the estimated traffic volume, an expected traffic volume in the traffic link.

This invention provide a network flow performance prediction and abnormal alarming technology and a method based on the genetic algorithms, which utilizes genetic algorithms to predict the flow state of the next time from the horizontal time degree then to utilize the statistics method to judge the abnormal situation of said flow based on the flow sample in a related time period of each day in the historical flow information from the longitudinal time degree. The method is realized by four steps of network flow data collection, process and storage, prediction and abnormal alarming.

The invention proposes a traffic signal control method and device, relating to the technical field of control. The method comprises a step of obtaining a traffic flow prediction model established according to a historical traffic flow, wherein the historical traffic flow is the historical traffic flow in each direction of a first intersection in each first period in a past first time interval, a step of obtaining the predicted traffic flow in each direction of the first intersection in each first period in a future second time interval according to the traffic flow prediction model, and a step of determining the time of the traffic signal lamp in each direction of the first intersection in each first period in the second time interval according to the predicted traffic flow. According to the method, the traffic flow of a future time period can be predicted based on the historical traffic flow, the time of the traffic signal lamp is set based on the predicted traffic flow, thus the time setting of the traffic signal lamp is more in accordance with the rule of the future traffic flow, and the cost of manual adjustment can be saved.

The invention discloses an automatic scheduling method for a call center based on telephone traffic prediction, and the method comprises the steps: overlapping a deep learning model and a conventionalmachine model, obtaining an integrated model, obtaining a high-precision telephone traffic prediction result through the integrated model, and correcting a telephone traffic prediction model with theconsideration to the remarkable features of the increase of the telephone traffic and a marketing factor, thereby improving the precision of the model; employing an optimized genetic algorithm to meet the complex scheduling constraints, and enabling the obtained scheduling result to be more humanized. Based on the transfer of the manpower distribution mode, the method enables a manager to be liberated from the tedious and hard scheduling work, and a fairer scheduling result enables the work enthusiasm of the employees to be further improved. The method enables an intelligent power distribution system to improve the service perception and satisfaction degree of customers.

A dynamic upstream bandwidth allocation scheme is disclosed, i.e., limited sharing with traffic prediction (LSTP), to improve the bandwidth efficiency of upstream transmission over PONs. LSTP adopts the PON MAC control messages, and dynamically allocates bandwidth according to the on-line traffic load. The ONU bandwidth requirement includes the already buffered data and a prediction of the incoming data, thus reducing the frame delay and alleviating the data loss. ONUs are served by the OLT in a fixed order in LSTP to facilitate the traffic prediction. Each optical network unit (ONU) classifies its local traffic into three classes with descending priorities: expedited forwarding (EF), assured forwarding (AF), and best effort (BE). Data with higher priority replace data with lower priority when the buffer is full. In order to alleviate uncontrolled delay and unfair drop of the lower priority data, the priority-based scheduling is employed to deliver the buffered data in a particular transmission timeslot. The bandwidth allocation incorporates the service level agreements (SLAs) and the on-line traffic dynamics. The basic limited sharing with traffic prediction (LSTP) scheme is extended to serve the classified network traffic.

The invention provides a method for predicting data based on a support vector machine and an equipment thereof. The method comprises the following steps of: reading a plurality of first data (historical data) related to a first period (historical periods); and predicting a second data which corresponds to a second sub-period contained in a second period (predicting period). At least one subset of the read plurality of first data is taken as an input variable of the support vector machine. The time of the second period is later than that of the first period. The embodiment of the invention has effective traffic prediction, thus bringing considerable economic benefits for operators directly or indirectly.

A three-dimensional urban traffic road network global state prediction method under a large data environment is disclosed. Aiming at a coupling multi-layer large-scale urban traffic road network, a global traffic mode containing coupling information is defined, a method of extracting a main road network characteristic is provided, a high dimension state time sequence is converted into a discrete state type sequence, and difficulties of high dimension data in processing and prediction aspects are simplified. From aspects of traffic periodicity, delay performance and other characteristics, a historical state transfer information database containing a multielement traffic characteristic is constructed, mass data information and a data driving idea are fully used and a Markov transition probability theory is applied so as to realize multi-step global traffic state prediction. Through the global traffic prediction, a traffic state of each area can be acquired one time. Compared to an existing traffic prediction method, by using the method of the invention, a long-term prediction result is acquired rapidly and a good prediction output effect is possessed.

The present invention discloses a method for predicting a tourist flow volume of a tourist attraction based on multi-source data analysis. The method comprises: S1, determining a starting point and a time period; S2, predicting a tourist flow volume; S3, correcting a first tourist flow volume; S4, correcting a second tourist flow volume; S5, correcting a current tourist flow volume; S6, regulating prediction on the tourist flow volume; S7, generating prediction on the tourist flow volume; and S8, correcting system parameters. Technical effects on promotion on timeliness, rapidness and convenience, effectiveness and accuracy of prediction on the tourist flow volume of the tourist attraction are achieved.

The invention belongs to the technical field of wireless communication, and particularly relates to a dynamic heterogeneous network flow prediction method based on a deep space-time neural network. Aiming at the problems of small coverage area, low prediction precision, short prediction time and the like of the existing mobile data traffic prediction method, the dynamic heterogeneous network traffic prediction method based on the deep space-time neural network is studied. Considering the characteristics of user mobility, flow data space-time correlation and the like, deeply researching a wide-coverage long-term mobile data flow prediction mathematical model description method in the dynamic heterogeneous network; On the basis, a space-time related convolutional long-short time memory network model is studied to predict the long-term trend of the mobile traffic in the dynamic heterogeneous network; A space-time related three-dimensional convolutional neural network model is studied to capture micro-fluctuation of a mobile flow sequence in the dynamic heterogeneous network; And fusing the long-term trend prediction model and the short-term change model of the mobile traffic, therebyrealizing wide-coverage and high-precision long-term mobile traffic prediction in the dynamic heterogeneous network.

The invention discloses network flow-predicting method and device based on wavelet package decomposition and a fuzzy neural network, wherein the method comprises the steps of: collecting historic measured data of network flow; decomposing the original network flow onto wavelets with different time scales by wavelet package conversion; reconstructing flow signals on all time scales so as to lead the data volume of the flow signals to be identical with that of original signals; by the fuzzy neural network, studying and predicting the flow signals decomposed onto all time scales; and summing thepredicted values of the flow signals on all time scales to obtain the predicted value of network flow.

The invention discloses a construction method of a flat shoal flow prediction model based on joint control of upstream-downstream borders over a lower reach. The construction method specifically comprises the steps of adopting a one-dimensional hydrodynamic model to calculate and study a water level-flow relation curve of each fixed section in the reach; determining flat shoal flow in each section according to flat shoal elevation in each fixed section; adopting a method based on the combination of geometric average of logarithmic transformation and weighted average of section spacing to calculate the flat shoal flow of reach dimension; analyzing a response relationship of the flat shoal flow adjustment on an upstream water-sediment condition and downstream water level change, and constructing the prediction model based on joint control of the upstream-downstream borders over the lower reach. According to the construction method of the flat shoal flow prediction model based on joint control of the upstream-downstream borders over the lower reach, the calculated and obtained flat shoal flow of reach dimension is capable of better describing the flow passing capacity of the whole reach, and thus the flat shoal flow is more representative; the constructed flat shoal flow prediction model is capable of well reflecting the variation trend of the flat shoal flow along with the upstream water-sediment condition when the downstream water level changes sharply, and thus the constructed flat shoal flow prediction model has a guidance significance in the flood prevention and riverway management.

The embodiment of the invention discloses a target value area analysis method and device, and apparatus based on big data and a medium. The method comprises the steps of obtaining network operation and maintenance O-domain big data and operation analysis B-domain big data; performing association analysis on the O-domain big data and the B-domain big data, positioning a target value area, and obtaining a target network grid corresponding to the target value area; based on the O-domain big data and the B-domain big data, performing user behavior analysis on the target value area, and constructing a user portrait; constructing a user flow model based on O-domain and B-domain big data; and performing service traffic prediction on the user traffic model based on the target network grid and theuser portrait, rasterizing the predicted service traffic, identifying a target value user from the traffic grid, and performing network planning on the target value area according to the target network grid and the target value user. By utilizing the embodiment of the invention, O-domain and B-domain big data can be integrated, and network planning optimization and marketing can be better supported.

Disclosed is a system and a method for collecting various road traffic information, road image information, and position information of a position information generation device carried by an object, the position of which is to be tracked, by interworking with an information provision means and using the collected information to provide service subscribers with real-time traffic information, traffic prediction, or position information of the object via wireless Internet, satellite broadcasting, DMB, or cable data broadcasting. The system and method can provide detailed traffic information service regarding a specific region or location on a nationwide scale, predict traffic to properly deal with it, and easily provide position information of an object to be tracked.