32 results about "Trajectory clustering" patented technology

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.

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 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 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 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 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.

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.

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 invention relates to the technical field of GIS (Geographic Information System), in particular to an atmospheric pollutant transmission trajectory clustering analysis method and system, which comprises the following steps of: extracting sampling longitude and latitude time and toluene concentration, calculating a ratio to construct trajectory points, selecting core points to screen spatial neighborhoods, calculating a ratio difference and performing threshold filtering to form semantic neighborhoods; according to the method, the chemical fingerprints are constructed by extracting the concentration of methylbenzene and the concentration of benzene and calculating the ratio, concentration fluctuation interference caused by atmospheric dilution is avoided, double constraints are implemented by combining the spherical distance and the ratio difference value, interference points which are physically adjacent but have different components are removed, and the pollution source is determined. The method comprises the following steps: constructing a semantic connected set according to a difference sequence to generate a track cluster, reconstructing a homologous transmission path, calculating an in-cluster mean value, matching a source spectrum by using cosine similarity, quantifying component similarity to lock a pollution source, solving the problem of multi-source mixing by using an internal component rule, getting rid of meteorological parameter dependence, and improving traceability accuracy.

This application provides a method, device, vehicle, and medium for diagnosing vehicle energy consumption causes. The method includes: acquiring M driving route trajectories, where M is a positive integer; performing trajectory clustering processing based on the M driving route trajectories to obtain at least one category of route clusters, each category including at least one driving route trajectory belonging to the same category; and diagnosing the causes of vehicle energy consumption based on the driving route trajectories in the at least one category to obtain the corresponding causes of vehicle energy consumption. The vehicle energy consumption and the causes of vehicle energy consumption are in one-to-one correspondence, and the vehicle energy consumption includes at least one of the following: energy consumption per 100 kilometers, motor energy consumption, drive energy consumption, idling energy consumption, energy recovery energy consumption, and accessory energy consumption. This addresses the limitations of existing energy management solutions, the lack of automatic discovery and clustering capabilities for common routes, and the inability to diagnose the root causes of vehicle energy consumption.

The application discloses a ship trajectory prediction method based on trajectory clustering and Conv-LSTM, and comprises the following steps: step 1, obtaining historical ship trajectories of different navigation modes in a region; step 2, clustering the ship trajectories of different navigation modes in the region in space form and time sequence characteristics to obtain trajectory clusters; step 3, inputting the center trajectories of the trajectory clusters and the current trajectory of a target ship into a preprocessing module to obtain normalized center trajectories of the trajectory clusters and the current trajectory of the target ship; step 4, inputting the center trajectories of the trajectory clusters and the current trajectory of the target ship into a Conv-LSTM model for training, verification and testing; and step 5, inputting the preprocessed ship trajectory data into the trained network model to realize prediction of the trajectory of the target ship. The application realizes accurate division of different navigation modes, reduces clustering complexity, guarantees time sequence continuity of the predicted trajectory, and improves the accuracy and reliability of ship trajectory prediction.

The application provides a low-intervention and efficient regulation method and system for a large language model in a digital twin water conservancy system, comprising the following steps: (1) constructing a non-guided test set in a task-free and explicit target-free environment, performing multiple rounds of generation sampling on 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 natural generation behavior path graph and a high-impact expression change point; (3) injecting a perturbation template into the high-impact expression change point and adjusting the language structure to obtain an optimized expression path of tone and structure trend; (4) comparing and analyzing the semantic theme changes of the optimized expression path and the original output data to evaluate the intervention effect of the perturbation insertion on the overall expression behavior. The application can minimize the intervention cost and accurately guide the model generation path, thereby improving the controllability and stability of the large model output in the digital twin water conservancy scenario.

The application discloses a kind of automobile mould manufacturing management systems of fusion situation awareness mechanism, specifically related to the technical field of situation awareness mechanism's automobile mould manufacturing management, including trajectory modeling module for collecting automobile mould historical manufacturing behavior data, generate normalized trajectory and execute trajectory clustering, construct reference trajectory set and behavior change rate set for subsequent comparison;Offset identification module is used to perform time normalization and derivative calculation on current manufacturing behavior data, difference comparison obtains continuous deviation section, and whether it constitutes offset state is judged based on trajectory direction;By constructing the normalized trajectory model and change rate model of manufacturing behavior variable, and based on the behavior difference identification result of current manufacturing state and historical reference trajectory, dynamic compensation control path and update plan trigger condition are generated, so as to solve the core problem that existing manufacturing system cannot identify processing condition offset within the planning time.

This invention provides a method, device, and storage device for ship trajectory clustering based on AIS data, comprising: extracting historical trajectory data; preprocessing outliers and redundant values; resampling missing data using a linear interpolation algorithm; and segmenting the processed trajectories; extracting the start and end points of each trajectory segment; clustering the start and end points using an improved DBSCAN algorithm, and grouping trajectories with the same start and end point cluster into one class; for trajectories in the same class, calculating the similarity between trajectories using an improved DTW algorithm to further classify the trajectory categories; extracting feature trajectories for each class of trajectories; calculating the similarity of the trajectories using the improved DTW algorithm to obtain the final clustering result. Compared with traditional DBSCAN or DTW algorithms, this invention improves the efficiency and accuracy of trajectory clustering, can handle dense datasets well, and, through trajectory similarity calculation, can better adapt to clustering results for routes of arbitrary shapes.

The invention belongs to the technical field of electric digital data processing, and particularly relates to an unsupervised agricultural machine track classification method and device based on comparative learning. According to the method, through mechanisms such as multi-view enhancement, global and local time sequence modeling, dynamic negative sample optimization and the like, the model can automatically learn track feature representation with discrimination from unlabeled data, so that unsupervised track clustering and classification are realized, and the stability, interpretability and generalization ability of model learning are remarkably improved. According to the method, an end-to-end unsupervised learning framework is constructed, potential operation modes and structural differences can be directly and automatically found from continuously collected mass agricultural machine trajectory data, no prior category information or artificial experience rules are needed, the problems that manual labeling is high in subjectivity, high in cost and difficult to scale are solved, and the method is suitable for popularization and application. The method is especially suitable for continuous analysis scenes of multi-region and multi-model long-term operation data.

The invention discloses a fine-tuning-free diffusion model acceleration method and system based on residual cache, and the method comprises the steps: dividing the calculation time step of a diffusion model into a dense calculation stage and a sparse calculation stage for the diffusion model in diffusion reverse denoising; in the dense calculation stage, complete forward calculation is carried out on all primitives of input images or video data, features of the primitives are cached, and meanwhile the primitives are divided into a plurality of clusters through a trajectory clustering method based on time sequence enhancement; in the sparse calculation stage, one proxy primitive is selected from each cluster for real denoising, and updating of other proxy primitives in the same cluster is deduced by utilizing a denoising simulation method based on proxy guidance, so that diffusion model acceleration is realized. According to the system, the calculation amount and the reasoning time of diffusion model reasoning can be remarkably reduced on the premise that the generation quality and the semantic alignment performance are not lost basically.

The invention relates to the field of agricultural data analysis, in particular to a farmland water and salt evolution rule mining system based on time sequence trajectory clustering, and the method comprises the steps: obtaining a two-dimensional time sequence trajectory set through the collection and preprocessing of the original data of farmland water and salt; performing water-salt lag cumulative effect analysis on the two-dimensional time sequence track set to obtain a first optimization factor; performing local water-salt trajectory fluctuation analysis on the two-dimensional time sequence trajectory set to obtain a second optimization factor; performing joint correction based on the first optimization factor and the second optimization factor on the original single-step distance to obtain a final time sequence similarity distance; and performing clustering division and rule extraction on the final time sequence similarity distance to obtain a farmland water-salt evolution rule, thereby solving the problem that the land parcels with different water-salt evolution mechanisms are wrongly clustered due to the fact that an existing dynamic time warping algorithm cannot represent farmland water-salt asynchronous hysteresis difference.

A process supervision data generation method and system based on adaptive Monte Carlo search, the method comprising generating an initial reasoning trajectory and performing feature extraction; using the standardized features to perform reasoning trajectory clustering; for each cluster, counting the number of successful reasoning trajectories and the total number of trajectories and estimating the success probability, quantifying the cluster uncertainty; performing adaptive iterative sampling, if the termination condition is not met, identifying the active cluster set, selecting the active cluster with the highest uncertainty as the additional sampling target, calculating the additional sampling number, and generating new reasoning trajectories; after sampling termination, calculating the Monte Carlo value of the node to guide the expansion direction of the search tree; for each possible successor node pair of the current node, selecting the successor node with the highest comprehensive expansion score for expansion; recording all intermediate reasoning states and corresponding Monte Carlo values during the search process to generate process supervision data. The present application can dynamically and reasonably allocate computing resources, improving generation efficiency and quality.

This invention belongs to the field of electronic digital data processing technology, specifically relating to an unsupervised agricultural machinery trajectory classification method and apparatus based on contrastive learning. The method utilizes mechanisms such as multi-view enhancement, global and local temporal modeling, and dynamic negative sample optimization to enable the model to automatically learn discriminative trajectory feature representations from unlabeled data. This achieves unsupervised trajectory clustering and classification, significantly improving the model's learning stability, interpretability, and generalization ability. The method constructs an end-to-end unsupervised learning framework that can automatically discover potential operating patterns and structural differences directly from continuously collected massive amounts of agricultural machinery trajectory data, without requiring any prior category information or manual experience rules. This avoids the problems of strong subjectivity, high cost, and difficulty in scaling associated with manual annotation, making it particularly suitable for continuous analysis scenarios involving long-term operational data from multiple regions and multiple machine types.

The invention discloses a ship trajectory clustering method fusing multi-dimensional features. The method comprises the following steps: acquiring a ship trajectory; calculating multi-dimensional similarity features between any two ship trajectories, wherein the multi-dimensional similarity features comprise geographic distance similarity, direction similarity and cumulative common subsequence similarity; based on the multi-dimensional similarity features, different clustering parameter combinations are set to cluster ship trajectories by using a DBSCAN clustering algorithm; determining clustering result evaluation criteria including intra-class standards and the number of noise trajectories; the intra-class standard approximates the standard deviation of the tracks in the cluster based on the comprehensive similarity between the ship tracks, and the comprehensive similarity is comprehensively determined by the geographical distance similarity, the direction similarity and the cumulative common subsequence similarity; based on different clustering parameter combinations and corresponding clustering result evaluation criteria, determining an optimal clustering parameter combination by using a VIKOR multi-criterion optimization method; and completing ship trajectory clustering based on the optimal clustering parameter combination. According to the invention, the ship trajectory clustering accuracy is improved.

The present application belongs to the technical field of space-time trajectory data mining, and specifically relates to a space-time trajectory similarity calculation method based on graph attention and time sequence feature fusion. The present application combines hierarchical partition trees and proposes multiple map migration strategies to reduce the cross-map model training cost and solve the problem of high training cost caused by the need for model retraining in the cross-city map scenario in practical applications. The trajectory representation method of the present application can fuse spatial features and has map generalization capability, thereby improving the accuracy and applicability of trajectory analysis tasks. The present application is suitable for trajectory representation learning methods based on similarity calculation in scenarios such as urban traffic planning, travel recommendation, trajectory clustering and anomaly detection.

The application discloses a kind of vehicle trajectory anomaly detection method, device and electronic equipment based on trajectory clustering, method includes: obtaining the target feature vector generated after each intelligent beacon carries out data collection to target vehicle, and obtains the historical feature vector corresponding to multiple historical vehicles;Each feature vector contains element including trajectory horizontal coordinate, speed, time and magnetic field intensity when vehicle passes through intelligent beacon;To each intelligent beacon, the same element clustering in all historical feature vectors thereof is obtained, and the clustering center thereof for each element is obtained;The clustering center of each element is connected according to the order of intelligent beacon to obtain reference trajectory;Each element of target vehicle is connected according to the order of intelligent beacon to obtain the trajectory to be detected;Whether target vehicle exists trajectory anomaly is determined by similarity calculation to the reference trajectory and the trajectory to be detected of each element.The application can judge whether vehicle exists trajectory anomaly to the beacon returned vehicle motion information.