56 results about "Trajectory clustering" patented technology

The invention provides a trajectory clustering method based on space-time weighting and a density peak value, and relates to the technical field of trajectory clustering. The method provided by the invention comprises the following steps: based on a minimum description length criterion, fusing an adaptive space-time weight and a space-time geometric distance to segment trajectory data to obtain sub-trajectory segments; calculating a space-time local density, a relative distance and a decision value of each sub-track segment based on a density peak clustering algorithm; performing noise identification on the sub-track segments based on the average space-time geometric distance and the average local space-time density, iteratively selecting a class cluster center based on the decision values of the non-noise sub-track segments and the time-space factor decision values, and generating a class cluster set; and determining a candidate representative trajectory set from the class cluster set based on the spatio-temporal local density and the maximum density, extracting continuous sub-trajectory segments from the candidate representative trajectory set based on spatio-temporal continuity constraints, and sequentially connecting end points of the continuous sub-trajectory segments to generate a representative trajectory. According to the method, the trajectory clustering effect is improved through space-time weighted segmentation and density peak trajectory clustering.

The invention discloses a data knowledge dual-driven unsupervised ship navigation mode identification method, and belongs to the technical field of ship traffic management. Comprising the following steps: acquiring AIS historical data sets of all ships; performing trajectory clustering based on a DBSCAN clustering algorithm of particle swarm optimization to obtain similar ship matching pairs; constructing a ship macroscopic navigation mode encoder based on a frequency domain multilayer sensor and a comparative learning method; constructing a ship microcosmic navigation mode decoder based on the hypergraph neural network; and acquiring real-time AIS data of a ship, and inputting the real-time AIS data into the trained ship macroscopic navigation mode encoder and the trained ship microcosmic navigation mode decoder to obtain intermediate features of a ship encountering scene. According to the method, the navigation mode of the ship in a habitual airway and the collision avoidance behavior mode in a multi-ship encounter scene are effectively extracted, and the limitation that the ship navigation mode recognition precision is insufficient in a single scale in the past is improved.

The invention discloses an atmospheric pollutant traceability method and system based on trajectory clustering. The method comprises the following steps: collecting hourly pollutant concentration data and synchronous meteorological data of a target monitoring station during a pollution event; based on the meteorological data, calculating an air mass backward track arriving at the target monitoring station; carrying out preprocessing and clustering analysis on the backward trajectory of the air mass to obtain a plurality of trajectory clusters; aiming at each track cluster, potential pollution source contribution analysis related to the cluster is respectively carried out, and potential source area space distribution information corresponding to the cluster is identified and generated based on an analysis result; extracting a central track of each track cluster as a typical transmission path, and analyzing vertical transmission characteristics of pollutants of different air mass types; and generating a traceability map for assisting in formulating a differentiated regional joint defense and joint control scheme for different transmission paths and source regions. The mixed pollution source can be effectively deconstructed, and the source area and the conveying channel can be accurately associated.

The invention discloses an intelligent robot integrated debugging system based on digital twinning, and the system comprises a model building module which is used for building a digital twinning model, collecting data, and generating a virtual mapping body; the structure analysis module is used for carrying out structure analysis on the virtual mapping body and constructing a simulation data set; the virtual debugging module is used for performing virtual debugging according to the simulation data set, generating action track data and constructing a debugging instruction set; the feature extraction module is used for extracting an image feature set of an instruction execution process; the difference analysis module is used for comparing the image feature set with the action track data and constructing a difference feedback matrix; and the circular updating module is used for updating the digital twin model and starting a new round of virtual debugging and instruction generation process. According to the invention, digital twinning, AI vision and trajectory clustering technologies are fused, and an intelligent robot debugging closed-loop system with high intelligence, high efficiency and high-precision feedback capability is constructed.

This invention relates to the field of business signaling technology, specifically a cloud-based voice call data analysis system. The system includes: a signaling acquisition module, a stability assessment module, a dynamic compression module, an abnormal trajectory clustering module, and a cloud feature library module. In this invention, distributed nodes collect multi-dimensional parameters of the link and store them in time slices. Sliding difference calculations are used to calculate the rate difference of three consecutive hops, accurately identifying stable path segments. Mean compression filters the latency within segments to generate feature vectors and reduce redundancy. Cloud K-means integrates state duration, timeout rate, and retransmission counts to detect trajectory deviations and construct abnormal clustering labels. Time-series correlation storage and elastic architecture dynamically filter path segments to reduce invalid data processing. Mean compression reduces computational complexity, multi-dimensional clustering improves detection accuracy, time windows optimize the storage structure, sliding difference enhances fluctuation capture capabilities, and elastic storage improves the efficiency of massive data access, forming an end-to-end quality analysis closed loop.

The present application relates to the field of agricultural data analysis, and more particularly to a farmland water-salt evolution law mining system based on time series trajectory clustering, which comprises the following steps: collecting and preprocessing original farmland water and salt data to obtain a two-dimensional time series trajectory set; analyzing the water-salt lag accumulation effect of the two-dimensional time series trajectory set to obtain a first optimization factor; analyzing the local water-salt trajectory fluctuation degree of the two-dimensional time series trajectory set to obtain a second optimization factor; jointly modifying the original single-step distance based on the first optimization factor and the second optimization factor to obtain a final time series similarity distance; and clustering and dividing the final time series similarity distance to extract the farmland water-salt evolution law, thereby solving the problem that the existing dynamic time warping algorithm cannot represent the asynchronous lag difference of farmland water and salt, resulting in the wrong clustering of different water-salt evolution mechanism plots.

The invention provides a low-intervention efficient regulation and control method and system for a large language model in a digital twin hydraulic system, and the method comprises the steps: (1) constructing a non-instructive test set in a task-free and clear-target-free environment, carrying out the multi-round generation sampling of the model, and recording the discourse structure, theme progression and semantic coherence in the output; (2) performing semantic embedding and style embedding extraction and trajectory clustering analysis on the original output data to obtain a naturally generated behavior path diagram and a high-influence expression change point; (3) perturbation template injection and language structure adjustment are carried out on the high-influence expression change points, and an optimized expression path of the tone and the structure trend is obtained; and (4) carrying out semantic topic change comparative analysis on the optimized expression path and original output data in the step (3), and evaluating the intervention effect of perturbation insertion on the overall expression behavior. According to the method, the model generation path can be accurately guided by minimizing the intervention cost, and the controllability and stability of large model output in the digital twin water conservancy scene are improved.

The application discloses a medical path accurate classification model generation method and system based on case feature labels, first extracts medical logs into structured logs, and collects treatment event sequences of each case; then, similar cases are aggregated through trajectory clustering, process mining is carried out on each clustering cluster, a process tree model is generated and a cycle node is optimized, and a medical path is extracted from the process tree model; a trained neural network model cluster is used to determine the case feature labels of the extracted medical path; finally, the case feature label determination and the corresponding medical path are integrated to form a usable medical path accurate classification model. The application combines trajectory clustering, process discovery, neural network and other technologies, fully gives play to the advantages of each technology, and the performance of the obtained model is much higher than that of a model generated by a single technology, so that the purpose of accurately recommending a medical path according to case features can be achieved.

The application provides a backward trajectory analysis method and device for atmospheric pollutant transport path identification, and belongs to the field of pollution source tracking. The method comprises the following steps: setting trajectory simulation parameters, generating a plurality of backward trajectories through a trajectory simulation model; constructing a trajectory dataset comprising each coded backward trajectory; automatically or manually selecting a clustering strategy from a plurality of preset trajectory clustering algorithms based on the dimension, time sequence characteristics, community structure complexity and nonlinear path characteristics of each coded backward trajectory in the trajectory dataset; applying the selected clustering strategy to the trajectory dataset for classification, thereby generating a plurality of trajectory categories; and performing classification processing on each trajectory category, and outputting the processing result after the classification processing. The application realizes flexible classification of trajectory data with different structures, supports abnormal trajectory identification, trajectory dimension reduction mapping and unified format output.

The application discloses a kind of based on tourist dynamic line heat forecast service facility dynamic scheduling method, fusion history passenger flow, real-time positioning, video analysis and weather and other multi-source data, construct unified space-time grid;Through trajectory clustering mining typical tour path, and combined with LSTM etc. Time series model rolling prediction future tourist density heat map;Further introduce crowd portrait label identification old people, special groups of parents and children, and differentially calculate facility demand in demand mapping, and set vulnerable area minimum service guarantee constraint;Then adopt multi-agent reinforcement learning (MARL) collaborative optimization dynamic scheduling of facilities such as feeder car, mobile toilet, give consideration to tourist waiting time, scheduling cost and fairness;Through model predictive control (MPC) framework rolling execution scheduling instruction, and combined with A / B test continuously correct prediction and strategy.The application realizes facility "pre-judgment-dispatch-feedback-evolution" closed loop, significantly improves service response efficiency, resource utilization and tourist satisfaction.

The invention discloses a detection and processing method for two-segment trajectory cheating, which identifies and repairs jumping, rollback and overlapping phenomena through a vector included angle cosine value and an ellipse method, thereby improving the integrity of trajectory data and ensuring the accurate calculation of mileage. In combination with trajectory clustering and a Markov chain model, the system can realize more accurate short-term and long-term trajectory prediction, and platform scheduling is optimized; by means of similarity analysis and unsupervised learning, the system can efficiently detect abnormal track behaviors, and automatic recognition can be achieved even under the condition that no annotated data exists; besides, through a transfer learning framework and in combination with track data of taxis and buses, the system can effectively detect illegal online taxi-hailing behaviors, and the problem of insufficient annotation data is solved; finally, the system accurately calculates the driving mileage of the vehicle through the repaired track, and the fairness and accuracy of cost calculation are ensured.

The present disclosure provides an automatic driving control method and a trajectory retrieval and index construction method and device, relates to the technical field of data processing, and particularly relates to the technical field of automatic driving and intelligent traffic. The specific implementation scheme is as follows: scene encodings representing different driving scenes are acquired; the scene encodings are obtained by encoding scene data contained in historical driving data of different driving scenes, and the historical driving data further includes trajectory data; the historical driving data is subjected to scene clustering according to the scene encodings, and at least one scene cluster is obtained; for each scene cluster, the trajectory data in the scene cluster is subjected to trajectory clustering, and at least one trajectory cluster is obtained; and an index is constructed based on the scene encodings and the trajectory clusters, and the index is used for trajectory retrieval.

This invention discloses a method and system for identifying pilot EBT training target competencies driven by the fusion of eye-tracking data and flight data. The method includes: S0: acquiring eye-tracking data from the pilot's EBT training process, constructing a GDETC network to achieve spatiotemporal trajectory clustering of the eye-tracking data, and extracting the pilot's gaze spatiotemporal trajectory; S1: extracting competency assessment scores and error spatiotemporal point data from the EBT competency assessment worksheet and flight data; S2: constructing a VAE-STRF network, fusing the data extracted in S0 and S1, extracting the pilot's key competency assessment score matrix, establishing a pilot key competency assessment model, and outputting the target competencies for EBT training. This invention identifies the target competencies that pilots need to further improve through eye-tracking data during EBT training, replacing existing manual evaluation systems and providing effective decision support for improving the targeting of pilot training.

The invention relates to a target rolling clustering task planning method based on a sub-satellite point trajectory. The invention relates to the technical field of multi-target observation. Point targets which are close to each other and associated with the same sub-satellite point trajectory are integrated into a clustering observation target; distributing observation satellites according to the association degree of the clustering target and satellites corresponding to different sub-satellite point trajectories, and realizing pre-distribution of observation tasks; and task planning is carried out on all processed clustering targets and single targets, and conflicts between adjacent tasks are solved through a sliding window. As the sub-satellite point trajectory moves along with the rotation of the earth, the target clustered for each trajectory is updated in a rolling manner. Simulation examples show that by means of the clustering method, the number of tasks can be reasonably and effectively reduced, target observation conflicts can be relieved, calculation time consumption can be reduced, and the effect is better when the number of the targets is larger.

The invention relates to the technical field of platform management, in particular to an internet shopping mall management platform system. The system comprises the following modules: a track acquisition module, a track clustering module, a cognitive optimization module and a conflict processing module, specifically, periodically acquiring user mouse coordinates, when the distance between a starting point and an ending point of a mouse track in a preset range is detected to be smaller than a first threshold value and the total length of a path is detected to be larger than a second threshold value, judging that the mouse track is a convolution track, outputting convolution trajectory data; the convolution trajectories of the multiple users in a preset time period are overlapped according to page positions, when the trajectory overlapping degree exceeds a preset overlapping threshold value, a trajectory cluster is formed, and the geometric center of the trajectory cluster is calculated based on convolution trajectory data to serve as a cognitive hotspot; and judging a group cognitive impairment point according to the number of the user sources of the cognitive hotspot. According to the method, the cognitive confusion moment of the user can be captured in real time through dynamic sampling frequency adjustment, and group cognitive impairment and individual preference are accurately distinguished through multi-user trajectory overlay analysis.

The present application relates to a kind of air traffic control instruction recognition and aircraft behavior early warning method for apron control, belong to air traffic management technical field, first using speech recognition model, the air traffic control instruction voice of apron control is transcribed into text, the text identified is then recognized intention and slot extraction, accurately extract the behavior category and key parameters in instruction, form instruction analysis result, ensure the accurate understanding of instruction content;Then, through trajectory clustering and association rule, a standardized intention association path set is constructed, combined with airport map, accurate path generation is realized;Finally, the aircraft position monitored in real time is matched with intention path and verified, abnormal behavior is identified and early warning is triggered, the predictability and safety of air traffic control system are improved.The present application realizes accurate abnormal behavior early warning by efficient instruction recognition and intention understanding, combined with behavior knowledge base and real-time position matching.

The invention discloses a front-end lightweight correlation analysis and calculation method and device, and relates to the technical field of urban management information. Comprising the steps of 1, constructing a front-end lightweight correlation analysis and calculation device, 2, constructing a front-end equipment correlation relation pair according to longitude and latitude in metadata of accessed multi-source front-end sensing equipment through a lightweight correlation calculation engine module, and preprocessing collected sensing data to obtain standardized data; extracting feature vectors from the standardized data by using a lightweight dynamic graph neural network, and performing entity trajectory clustering analysis on the sensing data based on a DBSCAN clustering algorithm to generate various entity trajectories; on the basis of the entity co-occurrence frequency, the time proximity and the space proximity, the association strength between the entities is calculated, and an association analysis result is obtained; 3, converting an association analysis result into a visual decision support interface through a leader cockpit visual adaptation engine module; 4, building a configurable association analysis process by using a fuzzy scene matching mode through a dynamic configurable association rule chain module; and 5, performing real-time data synchronization under a high-load condition through a real-time data synchronization and performance optimization module, and performing calculation performance optimization and resource loading optimization.

The application discloses a lane geometry information extraction method based on a road section track, performs track cluster analysis on a track subset passing through the same road, obtains a track cluster belonging to the same lane, extracts a track geometry center of the track subset in the same cluster in the form of a non-parametric curve, and fits to obtain a candidate lane center line; a lane change lane line identification method based on maximum group search, an intersection relationship graph is established, the lane change lane line is identified and removed through maximum group analysis, a set of lane center lines which do not intersect with each other is obtained as basic lane center lines, the number of lanes at both ends of the road section is reviewed through a Gaussian mixture model, and the candidate lane center line is extracted as a newly-added lane center line based on the newly-added Gaussian component and parameters. The application effectively extracts accurate lane geometry information based on track data, the acquisition method is simple and effective, easy to implement, has important significance for lane-level mapping application, and provides bottom layer data support for automatic driving application.

The application discloses a ship trajectory clustering method, comprising the following steps: cleaning AIS data to obtain the sailing trajectories of a plurality of ships in a set time period; calculating the Hausdorff distance between any two sailing trajectories as the basis for calculation of a DBSCAN algorithm; constructing a core point prediction model and screening high-probability data points in the sailing trajectories as candidate core points; performing neighborhood query on the candidate core points and carrying out clustering expansion through the DBSCAN algorithm; improving a Bayesian optimization algorithm through an adaptive acquisition function, and optimizing the hyperparameters of the DBSCAN algorithm based on the improved Bayesian optimization algorithm. The application has the beneficial effects that: in view of the problem that the operation efficiency of the density clustering algorithm is relatively low in the case of a large amount of data, the DBSCAN algorithm is improved, the operation efficiency of the algorithm is improved while the calculation accuracy is ensured, the Bayesian optimization algorithm is introduced to automatically optimize the hyperparameters of the DBSCAN algorithm, and the effect and stability of the clustering analysis are improved.

This invention relates to the field of big data mining technology, and discloses a spatiotemporal trajectory clustering method based on federated learning, which saves communication bandwidth and improves the privacy of data processing. In this invention, the client first samples trajectory points from the preprocessed trajectory; then, the trajectory is segmented based on these points, and spline functions are used to fit each segment. Finally, the start and end position information, start and end time sequence information, and parameter information of the corresponding spline function for each trajectory segment are encoded and sent to the server according to their respective trajectories and segments. During server processing, the decoded spline functions with the same trajectory number are concatenated according to time sequence and position to obtain the reconstructed trajectory. Then, cluster analysis is performed on the reconstructed trajectories to identify normal and abnormal trajectories.

The invention discloses a data-driven multi-level ship abnormal behavior intelligent detection method, and belongs to the technical field of traffic and transportation engineering. The method comprises the following steps: preprocessing original AIS data and constructing a multi-granularity feature system; a rule detection module based on domain knowledge outputs a first anomaly score through a dynamic threshold mechanism, a group anomaly recognition module based on trajectory clustering outputs a second anomaly score in a clustering manner, and a time sequence anomaly detection module based on sequence prediction outputs a third anomaly score; and through a multi-source evidence fusion mechanism, performing standardized calibration, dynamic weight fusion and conflict resolution on abnormal scores output by each module, generating a comprehensive abnormal score, and outputting a final abnormal label. According to the invention, through multi-level and multi-view collaborative analysis, omnibearing intelligent detection of abnormal behaviors of the ship is realized, and the accuracy, robustness and interpretability of detection are significantly improved.

This invention discloses an intelligent image processing method and system based on behavioral feature recognition, comprising the following steps: Step 1: Acquire image frame sequences and perform target detection and temporal correlation to generate behavioral target trajectory sequences; Step 2: Perform initial segmentation to generate an initial trajectory segment set; Step 3: Perform a first round of improved TRACKUS clustering; Step 4: Perform segment structure reconstruction based on the clustering results; Step 5: Perform a second round of improved TRACKUS clustering to generate a trajectory clustering structure; Step 6: Generate temporal pixel occupancy tubes; Step 7: Perform joint cluster arbitration to generate an arbitration trajectory segment cluster set; Step 8: Determine the behavioral feature recognition results and perform intelligent image processing, outputting the processed image. This invention improves the recognition accuracy and image processing targeting in complex behavioral scenarios.

The application provides a trajectory clustering method and device based on a spatiotemporal Mahalanobis distance and density peak value, which comprises the following steps: determining an optimal segmentation point of an original trajectory according to spatiotemporal trajectory data, dividing the original trajectory according to the optimal segmentation point to obtain a plurality of sub-trajectory segments and form a sub-trajectory segment set; calculating a spatiotemporal Mahalanobis local density of each sub-trajectory segment, measuring a spatiotemporal Mahalanobis relative distance of each sub-trajectory segment, calculating a decision value by comprehensively considering the spatiotemporal Mahalanobis local density and the spatiotemporal Mahalanobis relative distance of each sub-trajectory segment, and screening a potential class cluster center; calculating the membership of each sub-trajectory segment of all non-potential centers to each potential class cluster center, and distributing the sub-trajectory segments according to the membership to obtain a sub-trajectory segment class cluster division result. By modeling the spatiotemporal covariance structure, the method can generate sub-trajectory segments which are more in line with the data characteristics; by designing a density peak sub-trajectory segment clustering strategy of a spatiotemporal Mahalanobis k inverse neighbor and fuzzy membership, the parameter sensitivity can be reduced and the clustering robustness to density uneven data can be improved.

The application discloses a riding road curve fitting method based on shape perception, first extracts intersection trajectories and road section trajectories according to historical riding trajectory data and intersection positions and their influence ranges, and obtains turning trajectory clusters in intersections and road section trajectory clusters between intersections based on a trajectory clustering algorithm, then models shape features of each trajectory segment in the trajectory cluster based on directions and positions of trajectory points to obtain a shape feature vector of the trajectory segment, then uses an XGBoost classification model to predict a shape category of each trajectory in the trajectory cluster, and counts the number of trajectories belonging to each shape in the trajectory cluster to obtain a shape of the trajectory cluster, and finally selects a corresponding optimal center line fitting method for each type of trajectory cluster to perform fitting to obtain a road curve.

The present application relates to platform management technical field, especially to a kind of internet mall management platform system.The system includes the following modules: trajectory acquisition module, trajectory clustering module, cognitive optimization module and conflict processing module, specifically, periodically collect user mouse coordinates, when the starting point and the end point distance of mouse trajectory in the preset range are detected to be less than the first threshold value and the total length of path is greater than the second threshold value, it is determined as whirlpool trajectory, whirlpool trajectory data is output;The whirlpool trajectories of multiple users in the preset time period are superimposed according to page position, when the trajectory overlap degree exceeds the preset overlap threshold, trajectory cluster is formed, and the geometric center of trajectory cluster is calculated as cognitive hot area based on whirlpool trajectory data;According to the number of user sources of cognitive hot area, group cognitive disorder point is determined.The present application can capture the cognitive confusion moment of user in real time through dynamic sampling frequency adjustment, and accurately distinguish group cognitive disorder and individual preference through multi-user trajectory superposition analysis.

Methods and systems of building a knowledge graph based on event-based ontology of a scene and vehicle trajectory in the scene. Image data corresponding to a plurality of scenes captured by one or more cameras is received. Event-based ontology data corresponding to events occurring in the plurality of scenes is received. Via an object-tracking machine-learning model, the system determines (i) a presence of a plurality of vehicles in the image data, and (ii) a plurality of vehicle trajectories, each vehicle trajectory associated with a respective one of the vehicles. Using a clustering model, the vehicle trajectories are clustered. A knowledge graph is augmented based on the clustered vehicle trajectories and the event-based ontology.

The application discloses a vehicle trajectory clustering method and device, a storage medium and an electronic device. The method comprises the following steps: selecting N reference trajectories from a group of vehicle trajectories of a target intersection according to the number N of drivable routes of the target intersection, wherein each vehicle trajectory in the group of vehicle trajectories is a driving trajectory of a vehicle corresponding to each vehicle trajectory from the target intersection to the exit of the target intersection, and N is a positive integer greater than or equal to 2; selecting a group of clustering center points from each reference trajectory in the N reference trajectories respectively to obtain initial N groups of clustering center points; and performing a clustering operation on the group of vehicle trajectories according to the initial N groups of clustering center points to obtain a clustering result of the group of vehicle trajectories, wherein the clustering result of the group of vehicle trajectories is used to indicate N trajectory clusters obtained by clustering the group of vehicle trajectories and vehicle trajectories contained in each trajectory cluster in the N trajectory clusters.

This invention discloses a batch log repair method based on text similarity-constrained trajectory clustering, comprising the following steps: converting activities in the original logs into trajectories, organizing the trajectories, performing constrained trajectory clustering on the organized trajectories to obtain several clusters, and repairing the obtained clusters. This invention applies constraints to each step of trajectory clustering, ensuring that each cluster contains a fitted trajectory as the cluster center and abnormal trajectories similar to the fitted trajectory, with the center trajectory being the repair result of the abnormal trajectory. This method not only directly obtains the repaired fitted trajectory without analyzing abnormal behavior but also achieves batch repair of abnormal trajectories. Experiments show that this method, while deviating from the process model and ensuring high repair accuracy, can effectively and efficiently perform batch repair of event logs after noise filtering.

The invention provides a trajectory clustering method and device based on a space-time mahalanobis distance and a density peak value, and the method comprises the steps: determining an optimal segmentation point of an original trajectory according to space-time trajectory data, dividing the original trajectory according to the optimal segmentation point, and obtaining a plurality of sub-trajectory segments to form a sub-trajectory segment set; calculating the space-time Markov local density of each sub-trajectory segment, measuring the space-time Markov relative distance of each sub-trajectory segment, calculating a decision value by integrating the space-time Markov local density and the space-time Markov relative distance of each sub-trajectory segment, and screening a potential class cluster center; and calculating the membership degree of the sub-track segments of all the non-potential centers to each potential class cluster center, and distributing the sub-track segments according to the membership degree to obtain a sub-track segment class cluster division result. According to the method, by modeling a space-time covariance structure, sub-track segments more conforming to data features are generated; and designing a space-time Markov k inverse neighbor and fuzzy membership degree density peak value sub-trajectory segment clustering strategy, reducing parameter sensitivity and improving clustering robustness of density non-uniform data.

The application discloses a vehicle trajectory clustering method fusing density value and K-means algorithm, and comprises the following steps: step one, collecting original trajectory data to obtain a trajectory set after pretreatment; step two, calculating trajectory distance between trajectories in the trajectory set in turn; step three, determining the density of all trajectories in the trajectory set, and adding the trajectory with the maximum density value as the first center trajectory to a cluster center trajectory set; step four, calculating the weight of the remaining trajectories in the trajectory set in turn, taking the remaining trajectory with the maximum weight value as the next center trajectory, and moving it into the cluster center trajectory set until the capacity of the cluster center trajectory set reaches K, and the center trajectory selection is completed; and step five, removing the trajectory with the minimum density value in the trajectory set, and performing K-means clustering again until the iteration number is reached or the elements in the trajectory cluster no longer change, and the trajectory clustering process is completed. The application has the characteristics of high clustering precision.