140 results about "Trajectory clustering" patented technology

The invention relates to the technical field of traffic mode recognition, in particular to an urban traffic mode recognition system based on trajectory clustering, which comprises a trajectory credibility rejection module, a trajectory semantic clustering module, a trajectory evolution stage recognition module, a dynamic parking judgment module and an urban traffic mode generation module. According to the method, boundary dispersion rate difference analysis is carried out on traffic trajectory data, continuous cross-grid anomalies are identified, unstable sections in the trajectory are effectively eliminated, the spatial direction distribution concentration degree is taken as a basis, the trajectory coverage rate difference of the clustering center in adjacent time periods is calculated, and the spatial evolution trend of the trajectory is quantified; according to the method, dynamic description of a traffic mode in the time dimension is achieved, the misjudgment risk caused by a single time or space index is avoided in combination with double indexes of the space overlapping degree and the parking persistence between track fragments, and efficient identification of urban area travel function types is achieved through similarity matching between track features and travel features.

The invention relates to a chronic heart failure dynamic course evolution prediction model construction method. Comprising the following steps: uniformly mapping continuous variables including LVEF and heart rate and event variables into a time trajectory frame through an event alignment and time domain nesting strategy; using a local change rate algorithm to identify inflection points including states before acute deterioration and intervention reactions in the course of disease of each patient; constructing a state fragment set for supporting hierarchical modeling in an evolution stage; a bidirectional fusion method of trajectory clustering and medical knowledge embedding is used to construct a state space with clinical interpretability including a compensation period, edge decompensation and an acute deterioration period; taking the trajectory vector as a main input, taking a state space as a prediction target, and introducing a dual-channel structure; predicting a future path based on the current state; the disease course track change of early medication / non-hospitalization / treatment scheme change is simulated; a doctor is supported to deduce a result; the change of the output state is analyzed through perturbation of the current trajectory, and key variables are found out.

The invention discloses an auxiliary piloting method based on a double-layer trajectory clustering algorithm. The auxiliary piloting method comprises the steps of obtaining a historical trajectory set of a target ship based on a constructed ship space-time matching and speed / course difference judgment mechanism; performing main-level trajectory clustering on the historical trajectory set of the target ship according to the trajectory similarity measurement in combination with an HDBSCAN algorithm to obtain a trajectory main cluster; extracting and standardizing low-dimensional features of each target ship historical trajectory in each trajectory main cluster, and obtaining a standardized feature set for secondary trajectory clustering; according to the standardized feature set, a K-Means algorithm is combined to carry out secondary clustering on the track main clustering cluster to obtain a track sub-clustering cluster so as to obtain a ship piloting representative track, and then auxiliary piloting is carried out on different types of ships; and constructing a route recommendation and warning mechanism to realize route recommendation and warning. The problem that it is difficult to give consideration to fine analysis of multiple types of ships and timely provide effective route suggestions due to huge scale and large difference of obtained data with continuous expansion of marine transportation scale and popularization of AIS equipment at present is solved.

The invention provides a ship traffic flow prediction method and device, electronic equipment and a storage medium, and belongs to the field of marine traffic management. The method comprises the following steps: acquiring ship trajectory data of a to-be-detected port, and performing bidirectional trajectory prediction restoration on the ship trajectory data to obtain restored trajectory data; performing direction identification trajectory clustering on the repaired trajectory data to obtain trajectory clustering data, and performing density adaptive parameter node clustering on the trajectory clustering data to obtain node clustering data; and performing spatial-temporal feature extraction and prediction output on the node clustering data to obtain a ship traffic flow prediction result. According to the method, the integrity of ship trajectory data is ensured through bidirectional trajectory prediction and restoration, trajectory direction information is mined while clustering is performed through direction recognition trajectory clustering, and node comprehensive information is mined while clustering is performed through density adaptive parameter node clustering; dynamic transformation information and a deep relationship can be reserved, data can be effectively integrated, and the accuracy of ship traffic flow prediction is improved.

The present disclosure relates to systems, methods, and non-transitory computer readable media that provide a trajectory-based explainability framework for reinforcement learning models. For example, the disclosed systems generate trajectory clusters from trajectories utilized to train a reinforcement learning agent. In some embodiments, the disclosed system generates a complementary target data set by removing a target trajectory cluster from the trajectory clusters. In some cases, the disclosed system trains a test reinforcement learning agent utilizing the complementary target data set and generates a cluster attribution by comparing the result of the test reinforcement learning agent with the result of the reinforcement learning agent.

The invention discloses a multi-sensor track fusion method, device and equipment, a storage medium and a computer product, and relates to the technical field of data processing, and the method comprises the steps: carrying out the time clustering processing and the space clustering processing of a plurality of tracks collected by a plurality of sensors in sequence based on the time information and the space distribution information of the tracks, and obtaining a multi-sensor trajectory cluster, and fusing all trajectories in the multi-sensor trajectory cluster to obtain a fused trajectory of the corresponding target object. According to the method, first clustering processing is carried out on a plurality of tracks collected by each sensor according to time information to form a preliminary track cluster, so that independent analysis processing of each cluster is realized, the complexity of subsequent calculation is reduced, and then the spatial distribution condition of each track is determined according to spatial distribution information, so that the accuracy of track distribution is improved. Therefore, the calculation data volume of sensor track fusion is further reduced, and the technical effect of improving the multi-sensor track fusion efficiency is achieved.

The invention discloses an agricultural machinery field and road track classification method fusing spatial-temporal clustering and semantic segmentation. The requirements for farmland track and road track classification precision and operation efficiency in an actual agricultural machinery operation scene are met at the same time. The method mainly comprises three stages: firstly, track preprocessing; and removing abnormal track points by using four preprocessing operations of null value filling, attribute filtering, speed cleaning and linear interpolation, and complementing missing tracks. And 2, track clustering. A space-time neighbor track segment clustering method based on track position, time sequence and direction information is adopted to form a track group on the basis of removing a long-distance road driving track. And 3, track segmentation. And combining a channel and space mixed attention mechanism and a focus loss function to construct a trajectory diagram segmentation model based on U-Net so as to realize segmentation of a road driving trajectory, a drifting trajectory and a farmland trajectory close to a farmland plot in each trajectory group. Experiments show that the method provided by the invention has the highest classification precision in a real agricultural machine operation scene data set, and the average reasoning time is superior to that of a method with the highest precision in latest classification methods.

The invention provides an aircraft trajectory prediction method based on trajectory clustering and a spatial-temporal characteristic network, and the method comprises the following steps: data set preparation: a data set mainly comprises the spatial information and time information of an aircraft trajectory, and the data is preprocessed; track clustering: similar tracks are grouped through track clustering; spatio-temporal feature extraction: extracting spatio-temporal features of the trajectory data by combining a convolutional neural network and a bidirectional long-short-term memory network; and constructing a trajectory prediction model based on trajectory clustering and a spatio-temporal feature network, training and storing a model with optimal performance in a verification set, and realizing targeted prediction of different time sequence data trajectories in a complex path and variable environment. According to the method, the accuracy and efficiency of aircraft trajectory prediction can be improved.

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 vehicle trajectory anomaly detection method and device based on trajectory clustering and electronic equipment, and the method comprises the steps: obtaining a target feature vector generated after each intelligent beacon carries out the data collection of a passing target vehicle, and obtaining historical feature vectors corresponding to a plurality of historical vehicles; the elements contained in each feature vector comprise the track horizontal and vertical coordinates, the speed, the time and the magnetic field intensity when the vehicle passes through the smart beacon; for each smart beacon, clustering the same class of elements in all historical feature vectors of the smart beacon to obtain a clustering center for each class of elements of the smart beacon; connecting the clustering centers of each class of elements according to the sequence of the intelligent beacons to obtain a reference trajectory; all types of elements of the target vehicle are connected according to the sequence of the intelligent beacons to obtain a to-be-detected track; and performing similarity calculation on the reference trajectory of each type of element and the trajectory to be detected to determine whether the trajectory of the target vehicle is abnormal or not. Whether the track of the vehicle is abnormal or not can be judged according to the vehicle motion information returned by the beacon.

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 relates to a bus synchronous movement mode detection method oriented to a large space-time scale, and belongs to the technical field of GPS track synchronous movement mode mining. The method comprises the following steps: firstly, designing a special distance mapping function, and mapping a three-dimensional bus GPS track to a two-dimensional space; secondly, dividing the trajectory in a two-dimensional space by a time window, and designing a mixed index based on an inclination angle and MBR to organize trajectory fragments; and finally, designing a verification-filtering framework to accelerate the mode detection process. The method is implemented on a big data calculation engine Spark, and through testing, the method can efficiently process massive bus GPS track data and can meet the demand of bunching detection in a large-scale bus scene. According to the method, a traditional method based on track clustering is avoided, and the time complexity of the method is remarkably reduced.

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 a data-driven ship abnormal behavior online detection and early warning method and system. The method comprises the following steps: carrying out data cleaning on original ship AIS (Automatic Identification System) trajectory data; compressing the cleaned trajectory data by adopting a trajectory data compression algorithm, calculating trajectory similarity with all ships based on a time sequence similarity algorithm, and constructing a trajectory similarity measurement matrix; performing clustering analysis on the trajectory similarity measurement matrix by using a trajectory clustering algorithm to obtain a clustering result; backtracking the cleaned trajectory data based on a clustering result, and determining a ship navigation area by using a boundary extraction algorithm; utilizing a historical average ship trajectory prediction algorithm to generate a ship prediction trajectory under a time length threshold value; and in combination with the ship navigation area and the ship prediction trajectory, ship abnormal behavior detection is realized through angle difference change analysis and matching of the ship trajectory point and the ship navigation area, and early warning is carried out. According to the invention, real-time, efficient and accurate judgment and early warning of the ship trajectory can be realized.

The present invention relates to a method for detecting synchronous movement patterns of buses at large temporal and spatial scales, and belongs to the technical field of synchronous movement pattern mining of GPS trajectories. First, a special distance mapping function is designed to map the three-dimensional GPS trajectory of a bus to a two-dimensional space. Secondly, the trajectory is divided by time windows in the two-dimensional space, and a hybrid index based on inclination angle and MBR is designed to organize the trajectory fragments. Finally, a verification-filtering framework is designed to accelerate the pattern detection process. The present invention is implemented on the big data computing engine Spark. After testing, the present invention can efficiently process massive bus GPS trajectory data and meet the needs of vehicle-to-vehicle detection in large-scale bus scenarios. The present invention avoids the traditional method based on trajectory clustering and significantly reduces the time complexity of the method.

The invention provides an aviation ADS-B anomaly detection method and system based on semi-supervised joint modeling, and belongs to the technical field of aviation safety monitoring. The method comprises the following steps: receiving and screening ADS-B data, and extracting NACp, position, speed and time features; denoising and screening low-confidence samples through Hampel filtering and a Gaussian mixture model; using trajectory clustering and NACp precision clustering to construct a dual anomaly labeling set; fusing point-level, trajectory-level and space grid features to form a multi-dimensional feature set; generating a high-confidence pseudo label based on multi-model voting, and dynamically training and inferring in combination with a LightGBM semi-supervised model; and outputting an abnormal level and visualizing the abnormal level through a thermodynamic diagram. Through semi-supervised learning and multi-modal clustering, the problems of label scarcity and category imbalance are solved, and the detection precision is improved; in combination with heterogeneous calculation and dynamic iterative optimization, efficient real-time processing is realized, and support is provided for aviation safety monitoring in complex space weather.

The invention discloses a ship trajectory clustering method, which comprises the following steps of: cleaning AIS data to obtain a plurality of navigation trajectories of a ship in a set time period; the Hausdorff distance between any two navigation tracks is calculated to serve as the calculation basis of a DBSCAN algorithm; a core point prediction model is constructed, high-probability data points in the navigation trajectory are screened out to serve as candidate core points, and neighborhood query and clustering expansion are performed on the candidate core points through a DBSCAN algorithm; a Bayesian optimization algorithm is improved through an adaptive acquisition function, and hyper-parameters of a DBSCAN algorithm are optimized based on the improved Bayesian optimization algorithm. The DBSCAN algorithm has the beneficial effects that the DBSCAN algorithm is improved aiming at the problem of relatively low operation efficiency of the density clustering algorithm under the condition of large data volume, and the operation efficiency of the algorithm is improved while the calculation precision is ensured. The Bayesian optimization algorithm is introduced to automatically optimize hyper-parameters of the DBSCAN algorithm, and the effect and stability of clustering analysis are improved.

The invention discloses an urban traffic sub-region division method based on overall trajectory clustering, and belongs to the technical field of intelligent traffic management. The method comprises the following steps: carrying out adaptive cutting and matching on a GPS track through a time dimension, and constructing a segmented track data set; based on an improved DTW algorithm, fusing vertical, parallel and angular distances to define trajectory similarity measurement, and retaining overall shape features of the trajectory; carrying out initial clustering by adopting an improved DBSCAN algorithm, and avoiding an over-aggregation problem through a dynamic core trajectory judgment mechanism; and designing a two-stage fine-grained division strategy, and performing secondary classification on unclassified trajectories in combination with polygonal boundaries and trajectory matching information to generate traffic sub-regions with clear boundaries. The method overcomes the defects that a traditional method neglects track space-time characteristics and boundaries are fuzzy, urban traffic zoning with high dynamic performance and high consistency is achieved, an accurate space division basis is provided for real-time traffic control, and the urban road network management efficiency is remarkably improved.

The invention discloses a ship abnormal trajectory real-time discrimination method based on stream-oriented computation, which is applied to identification of ship navigation abnormal trajectories in a specific area of an inland river basin based on ship AIS data. Comprising the following steps: a ship AIS data preprocessing module receives AIS data and performs operations such as de-duplication, analysis and filtering, and the processed data is sent to a track acquisition module and an abnormal track identification module; the ship track acquisition module realizes acquisition and storage of ship navigation tracks in different electronic fence areas by judging ship navigation states; the ship track clustering module is used for clustering tracks of different ships on the basis of an improved DBSCAN (Density Based Spatial Clustering of Applications with Noise), and counting the navigation course and speed of the ships according to a clustering result and grids; and the abnormal trajectory recognition module recognizes the abnormal trajectory of the ship in real time based on the clustering and grid statistical results. Monitoring of the ship navigation trajectory and identification of the abnormal trajectory are realized, and improvement of the management efficiency of water traffic and reduction of the occurrence rate of water traffic accidents are facilitated.

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 invention relates to an atrial fibrillation radiofrequency ablation postoperative recurrence prediction method based on multi-modal analysis. Comprising the following steps: dynamically capturing the form and spatial distribution of a low-voltage region by using a three-dimensional electroanatomical map; introducing a regional complexity quantitative index, and analyzing the non-linear degree of the boundary of the low-voltage region; grading the voltage intensity gradient in the low-voltage region, and quantifying the sensitivity to postoperative recurrence; establishing a composite index model of the area ratio of the low-voltage region and the fragmentation potential intensity; based on spatial distribution and voltage features, performing high, medium and low recurrence risk classification on the low-voltage region, and outputting a classification heat map; analyzing the migration path of the fragmentation potential in the three-dimensional space in the operation, and extracting the migration speed, direction and frequency change; discovering a fragmentation potential concentration trend of the high recurrence sensitive area by using a trajectory clustering algorithm; and extracting spectrum characteristics of the fragmentation potential signal based on wavelet transform, and identifying abnormal distribution of the high-frequency fragmentation potential.

The invention discloses a semi-supervised radiation source individual identification method based on multi-round clustering and pseudo label updating, which is characterized in that on the basis of a structured slice of a radiation source signal, a deep neural network is adopted to carry out feature extraction and classification prediction on a sample, and network training is carried out through multi-round change trajectory clustering and a pseudo label stability judgment mechanism; the method comprises the following steps: setting a trigger condition of pseudo-label generation as stable convergence of training loss, tracking a historical prediction trend of a sample, screening out a sample set with consistent category evolution trajectory and discrimination as a pseudo-label candidate, expanding a supervised data volume through a pseudo-label iteration updating strategy and a training sample set dynamic reconstruction mechanism, and obtaining a pseudo-label generation result. And finally, based on a joint loss optimization strategy, realizing comprehensive identification of all unknown samples in continuous iteration. According to the method, the adaptive capacity of the identification model to unknown category and weak label data is improved, and the method is suitable for complex wireless environments such as electronic countermeasure, frequency spectrum monitoring and signal traceability needing high-robustness identification capacity.

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 invention discloses a semi-supervised pedestrian re-identification method based on multistage clustering. The method comprises the following steps: acquiring video data; and inputting the video data into a pedestrian re-identification model to obtain a pedestrian identification result. Wherein the pedestrian re-identification model is obtained according to the following steps: training a feature extraction network by using a labeled training set; for unlabeled unsupervised data, extracting corresponding output features by using the trained feature extraction network; performing single-track clustering, single-video clustering and cross-video clustering on the output features to obtain label information, and further constructing an automatic labeling pedestrian training set; carrying out distillation training on a teacher-student mutual learning framework based on the automatic marking pedestrian training set and supervised data, wherein the teacher-student mutual learning framework comprises a teacher model and a student model; and taking the student model subjected to distillation training as the pedestrian re-identification model. According to the invention, the data annotation cost is reduced, and the generalization ability of the pedestrian recognition model is improved.

The present invention relates to the technical field of traffic pattern recognition, and specifically to an urban traffic pattern recognition system based on trajectory clustering. The system includes a trajectory credibility elimination module, a trajectory semantic clustering module, a trajectory evolution stage recognition module, a dynamic stop determination module, and an urban traffic pattern generation module. In the present invention, by performing boundary discretization rate difference analysis on traffic trajectory data and identifying continuous cross-grid anomalies, unstable segments in the trajectories are effectively excluded. Based on the concentration degree of spatial direction distribution, by calculating the difference in trajectory coverage rate of the clustering center in adjacent time periods, the spatial evolution trend of the trajectory is quantified, realizing the dynamic characterization of traffic patterns in the time dimension. Combining the dual indicators of spatial overlap degree and stop duration between trajectory segments, the risk of misjudgment caused by a single time or space indicator is avoided. Through the similarity matching between trajectory features and travel features, the efficient recognition of the travel function types of urban areas is achieved.

The present invention discloses a method and system for mining trajectory adjoint relationships based on a secondary spatiotemporal index. The method comprises: preprocessing trajectory data to obtain subtrajectories meaningful for adjoint query; fuzzifying the subtrajectories meaningful for adjoint query to obtain subtrajectories that improve query accuracy; clustering the fuzzified subtrajectories in time and space to obtain a clustered index structure; and merging the index items of the clustered index structure to obtain a complete adjoint result between trajectories. In the present invention, by clustering the fuzzified subtrajectories in time and space to obtain a clustered index structure, the index structure can directly obtain adjoint trajectory pairs, avoiding similarity calculations between trajectory pairs and significantly improving the efficiency of adjoint trajectory queries.

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 present application relates to a method for detecting game studio users based on trajectory clustering. The method includes: obtaining user event records in a game database and encoding the user event records to obtain preprocessed data; in the user event trajectories composed of the preprocessed data, determining key feature points according to the MDL cost of the feature points, and segmenting the preprocessed data into multiple subsequence segments according to the key feature points; clustering the subsequence segments into multiple clusters according to the similarity between the subsequence segments, and respectively obtaining the key subsequences of the clusters; determining a target range corresponding to the key subsequence in the user event trajectory, and determining studio users in the game database by analyzing the user event records within the target range. Through the present application, the problem of high labor cost in identifying studio users in the early stage of the game in the related art is solved, the verification range can be narrowed, and the labor and time costs for distinguishing studio users are improved.