2952 results about "Cluster result" patented technology

A layout optimization method of water quality monitoring points based on a RF-C-SOM clustering algorithm includes: preprocessing collected water quality data to obtain preprocessed water quality data that are used as data, and using water quality categories as labels to train a random forest model to determine feature importance of water quality indicators; selecting important features based on the feature importance and model training accuracy, performing dimensionality reduction on the preprocessed water quality data to obtain dimension-reduced data; performing a fuzzy clustering on the dimension-reduced data to obtain a water quality section classification result, and based on it, determining initial weight values of a self-organizing mapping algorithm; initializing neurons and training a self-organizing mapping network model with the initial weight values; obtaining a point clustering result through the self-organizing mapping network model; and conducting a water quality index evaluation for the point clustering result before and after screening.

The invention discloses an APT attack path reconstruction method based on time sequence diagram comparison clustering and a medium. A security event standardized data set is obtained; mapping each security event into a multi-modal node through a heterogeneous time sequence diagram set construction method, and generating a directed edge to construct and complete a heterogeneous time sequence diagram set; a stage embedding time sequence diagram set is obtained through the joint attack stage set; outputting a time sequence diagram similarity matrix by adopting a multi-scale diagram similarity algorithm of time alignment perception; generating an event semantic sparse matrix based on the threat intelligence knowledge graph; obtaining an image clustering result set; uncertain samples in the graph clustering result set are obtained and processed, and an APT attack path reconstruction result is obtained. The problem that an APT attack path reconstruction method mainly depends on rule matching, single-dimensional feature comparison and manual analysis of security logs or alarm streams is solved, the interpretability of APT traceability is greatly enhanced, and subjective errors of manual research and judgment are reduced.

The present invention relates to a data interaction method, device, equipment and storage medium of a multi-layer stacked memory, comprising the following steps: based on the access frequency clustering result, the target transmission data is mapped to a storage location to obtain a multi-layer storage allocation strategy table; based on the multi-layer storage allocation strategy table, the target transmission data is interactively planned to obtain an optimal interactive path plan; based on the optimal interactive path plan, the target transmission data is hierarchically migrated and scheduled to obtain a data migration execution queue; and the data migration execution queue is transmitted in parallel through an asynchronous pipeline transmission mechanism, which solves the technical problem that the existing data transmission strategies often lack in-depth analysis of the historical access characteristics of the storage hierarchy, resulting in unreasonable data distribution, and frequent cross-level data migration increases system delay and energy consumption.

The invention provides a cold and hot data object life cycle feature extraction method based on deep learning, and the method comprises the steps: carrying out the clustering of feature vectors through employing a clustering algorithm, dividing the data into different viscosity level data clusters according to a clustering result, and enabling the data in each viscosity level data cluster to have similar access modes and life cycle features; for each viscosity level data cluster, analyzing the access time distribution and life cycle stage of the data cluster, and judging the heat type to which the data cluster belongs, including continuous heat, periodic heat, temporary heat and cold; according to the current popularity type and the historical access mode of the viscosity level data cluster, predicting the popularity change trend of the viscosity level data cluster in a future period of time, and obtaining a popularity change curve of each cluster; by monitoring the access condition and the heat change of the data in real time, the migration and replication modes of the data between different storage layers are dynamically adjusted, and when the actual access mode of the data is deviated from the predicted mode, data re-clustering and storage optimization are triggered.

The invention relates to a shipping risk assessment method, which comprises the following steps of: S1, establishing a semantic network of entities related to shipping and relationships among the entities, and determining a shipping basic information knowledge graph; s2, acquiring multi-source data related to shipping risks, and extracting risk entities and risk information from the multi-source data; s3, expanding a shipping basic information knowledge graph according to the risk entity and the risk information, constructing a risk association knowledge graph, and obtaining relationships between different risk factors and ship risks; s4, the risk factors are clustered, a risk identification model is constructed according to a clustering result to carry out quantitative evaluation on risks, a shipping risk level is obtained according to a shipping risk inference rule, if the shipping risk level is a low risk or a high risk, direct output is carried out, and otherwise, S5 is carried out; and S5, based on a quantitative evaluation result, carrying out weighted average calculation on the multi-factor risk to obtain a risk index, and determining a shipping risk level of the ship according to the risk index. Compared with the prior art, the method has the advantages of being high in precision and reliability.

Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for constructing training data. The method includes determining multiple clusters by clustering prompts in a training dataset; and determining, based on multiple cohesion levels of the multiple clusters, multiple sampling probabilities corresponding to the multiple clusters, where the cohesion levels indicate intra-cluster distances in the clusters. The method further includes determining, according to the multiple sampling probabilities, a target cluster for sampling. The method further includes constructing target training data by sampling target prompts from the target cluster. According to embodiments of the present disclosure, when fine-tuning a language model, prompts can be screened according to a clustering result of the prompts, so as to make the determined prompts more valuable for annotation, thereby ensuring output results of the language model obtained by training to be comprehensive and diverse.

The invention discloses an abnormal behavior detection method and system based on a multi-source log and electronic equipment, and the method comprises the steps: collecting log data, carrying out alignment processing and data preprocessing, and generating normalized log data; carrying out attribute screening on the standardized log data set, and packaging the screened logs into a JSON format; extracting features of the log data, converting the features into data points, clustering the data points, and retaining a log cluster according to a clustering result; mining a hidden association mode between log attribute items in the log cluster by using an improved Apriori algorithm, generating an association rule, and constructing a knowledge graph based on the association rule; and constructing a time sequence of the log data by using a self-adaptive time window, and inputting the time sequence and the tag sequence of the log data into the LSTM neural network by combining context information in the knowledge graph and a tag sequence generated by an association rule to obtain an abnormal behavior detection result. According to the method, the log data format is unified, correlation analysis is enhanced, and the accuracy of an anomaly detection result is obviously improved.

The invention is suitable for the technical field of agricultural intellectualization, and provides an intelligent blueberry disease detection method and system based on multi-modal unsupervised learning, and the method comprises the following steps: carrying out the feature extraction and clustering of preprocessed multi-modal data based on an adaptive contrast deep clustering framework, and obtaining a feature extraction result; obtaining a multi-modal preliminary feature and a preliminary clustering result; based on a multi-modal complementary feature fusion mechanism, according to the multi-modal preliminary features and the preliminary clustering result, carrying out adaptive weighted fusion on the multi-modal preliminary features to obtain multi-modal fusion features; performing unsupervised clustering optimization and disease type identification on the multi-modal fusion features to obtain an unsupervised learning model; and performing deployment and incremental learning on the unsupervised learning model, and detecting the blueberry diseases. According to the method, early-stage accurate detection of blueberry diseases is realized through an unsupervised learning algorithm, a new normal form is provided for intelligent accurate management of blueberries, and the disease prevention and control efficiency and industrial economic benefits are effectively improved.

The invention provides a low-orbit satellite resource allocation method and device based on beam and frequency domain collaborative optimization, and the method comprises the steps: dividing the overall bandwidth of a user region into a central sub-band and an edge sub-band through employing a dynamic soft frequency reuse scheme; all ground users are subjected to spatial clustering according to geographic positions and traffic demands, coverage cells are dynamically divided according to clustering results, and balanced service is achieved; on the basis of dynamic cell division, user clusters with high service volume are selected according to priorities, a beam activation set is generated, and a hopping beam matrix is updated; establishing a channel model between a user and a beam and a switching matrix between satellites; constructing a system utility target, and constructing a multi-target optimization problem model by taking the system utility target as a main part and integrating interference, switching overhead and delay penalty; and the multi-dimensional resource collaborative optimization framework based on deep reinforcement learning reconstructs a multi-objective optimization problem model, and outputs a solution of the multi-objective optimization problem model, including an optimal bandwidth and a power allocation result. According to the invention, resource allocation can be carried out on low-orbit satellites.

The invention relates to the technical field of fault monitoring, in particular to a power transmission line fault monitoring and positioning method, system and device and a medium. The method comprises the following steps: firstly, performing digital conversion on an original current signal to obtain time sequence data, and then identifying and classifying fault events through threshold detection and a feature extraction algorithm to obtain classification labels of fault types; then, based on the classification label, establishing a traveling wave propagation model and carrying out time difference calculation, carrying out clustering analysis on a plurality of wave head data in a preset time window, and judging whether the fault is a single-point fault or a multi-point fault through a clustering result; and finally, a positioning result is transmitted to the central server for comprehensive verification and alarm management, and a final fault response is formed. By introducing a time series data analysis and clustering judgment mechanism, the fault type can be accurately identified, single-point and multi-point fault conditions can be effectively distinguished, and meanwhile, the reliability of a positioning result is improved through comprehensive verification of the central server.

An air conditioner load monitoring and anomaly detection method and system. The method comprises: acquiring user power consumption data and meteorological data, the user power consumption data and the meteorological data comprising the total power of an electricity meter, the power of an air conditioner, and the outdoor temperature, preprocessing the data, and computing electrical characteristics of the user power consumption data; on the basis of the electrical characteristics, learning by using a two-tower neural network so as to obtain operating rules of the air conditioner, and extracting an air conditioner operation curve; on the basis of the air conditioner operation curve, computing electrical characteristics and energy consumption characteristics of the air conditioner, and performing cluster analysis by using a K-means clustering algorithm; and, on the basis of clustering results, comparing the clustering results with clustering results of collected electrical data of the air conditioner under normal and abnormal operating conditions to determine whether the air conditioner is in an abnormal state, so as to implement detection of anomalies in the operation of the air conditioner, thereby improving the precision of load decomposition of the air conditioner, reducing application costs, providing a decision-making reference for equipment maintenance personnel, and prolonging the service life of the equipment.

The invention discloses a thermal power plant immersive equipment state monitoring method and system based on AI, and relates to the technical field of equipment monitoring, and the method comprises the steps: building a digital twinborn model of a thermal power plant after a monitoring sensor is deployed on equipment of the thermal power plant; executing attraction clustering according to an equipment topological relation in the digital twin model, and establishing a multi-level clustering result; reading a monitoring data set of the monitoring sensor; activating an independent anomaly recognition network, and establishing an independent anomaly recognition result; establishing equipment criticality according to the independent anomaly recognition result; establishing equipment abnormity joint early warning; and carrying out immersive visual presentation. The technical problems that in the prior art, the operation state of the thermal power plant equipment is not comprehensively and accurately monitored, the equipment management efficiency is low, and the reliability is difficult to guarantee are solved, and the technical effects that the operation state of the thermal power plant equipment is comprehensively and accurately monitored, and the efficiency and the reliability of equipment management are effectively improved are achieved.

The invention discloses a smart city planning design method, and relates to the field of city planning, and the method comprises the steps: collecting monitoring data; determining two targets of land utilization rate maximization and traffic jam minimization according to the preprocessed monitoring data; an epsilon-constraint method is adopted to convert two targets of land utilization rate maximization and traffic jam minimization into a single-target optimization problem; solving a single-target optimization problem by adopting a swarm intelligence algorithm MOEAD to obtain a Pareto non-inferior solution set; performing clustering analysis on the Pareto non-inferior solution set by adopting a K-means clustering algorithm, and dividing the Pareto non-inferior solution set into K clusters according to a clustering result; and according to the preprocessed monitoring data, constructing a three-dimensional city information model by using a smart city CIM technology, mapping each solution in the representative solution set to a corresponding planning parameter in the three-dimensional city information model, and generating a corresponding city planning design scheme. The contradiction between the land utilization rate and the traffic efficiency in urban planning is balanced.

The invention relates to the technical field of data analysis, in particular to a diabetes clinical test data intelligent clustering analysis system and method based on federal learning. Comprising a data acquisition and preprocessing unit; a federal privacy protection unit; the dynamic clustering modeling unit is used for constructing a clustering model of self-adaptive diabetes data features, and realizing joint clustering analysis of multi-source heterogeneous data by adopting a hierarchical federal architecture and a dynamic parameter aggregation algorithm and combining a diabetes course time decay factor and a clinical feature weight adjustment strategy; a double-track verification optimization unit; and an intelligent decision support unit. According to the method, the incidence matrix of the diabetes disease course time decay factor and the clinical characteristics is introduced, the dynamic weight vector is constructed and applied to clustering distance calculation, so that the model can adapt to dynamic changes of the clinical characteristics in different disease course stages, the adaptability to multi-center heterogeneous data is improved, and the stability of a clustering result is enhanced.

The invention discloses a ternary internet-of-things battery management system, particularly relates to the technical field of lithium battery management, realizes lithium battery thermal safety closed-loop management through multi-sensor fusion, and comprises the following steps: deploying a digital sensor array to obtain time-space associated data; constructing a spatio-temporal feature vector including fusion of a local temperature gradient, a neighborhood temperature gradient and a stress coupling ratio; a density clustering algorithm is adopted to dynamically divide spontaneous heating, radiant heat and stress coupling clusters, and cluster boundaries are updated in real time; calculating a dual thermal coupling coefficient based on a clustering result, and eliminating the interference of temperature reading through a dual temperature compensation formula; a three-level alarm mechanism of a radiant heat proportion, a stress coupling degree and a compensation error is established, a side gateway is linked to realize parameter adaptive optimization, and the thermal runaway early warning precision and the structural failure detection rate are improved; strain monitoring resource optimization is realized through physically-driven key point screening and dynamic graph neural network prediction.

The invention provides a keyword-based file information identification method and system, and the method comprises the steps: obtaining existing files, building a file database based on the existing files, carrying out the clustering of the existing files in the file database according to the obtained preset industry term data, and obtaining a first clustering result of keywords; the method comprises the following steps: acquiring a correlation score of an existing file and a query keyword based on a BM25 model, performing optimization clustering on a first clustering result of the keyword based on the correlation score, acquiring a second clustering result of the keyword, constructing a keyword semantic association magnetic field according to the second clustering result of the keyword in combination with an electromagnetic field simulation mode, and acquiring historical query data of a user. A personalized dynamic weight is established based on historical query data of the user, a third clustering result of the keywords is obtained according to the personalized dynamic weight and the keyword semantic association magnetic field, and a corresponding existing file is recognized and matched in the file database for the user based on the third clustering result of the keywords. Through the method, the accuracy of querying the matched document file by the user can be improved.

The invention discloses a power transmission line abnormity early warning and fault positioning system, which belongs to the technical field of line detection, and specifically comprises the following steps: dividing early warning equipment in a line into sub-regions according to distribution through a region delimiting module; when a fault occurs, the region positioning module quickly marks the related sub-regions and equipment as undetermined states; the data acquisition module is used for collecting data of the to-be-determined equipment in a set time window before a fault, and preprocessing the data to judge whether the fault is caused by an electrical problem or not; if yes, collecting historical power consumption data of the to-be-determined area; the fault positioning module normalizes historical data, constructs a time sequence model, extracts a current value change sequence, divides the current value change sequence into a plurality of subsequences and then performs clustering analysis; judging the fault reason according to the offset condition of the category cluster where the undetermined current value change sequence is located in the clustering result; if the offset exceeds a preset threshold value, considering that the electric equipment is abnormal; otherwise, the aging of the line insulating material is caused.

The present invention relates to the technical field of tray line layout optimization, and provides a tray line layout optimization method and system based on Internet of Things. The method comprises: receiving from a user terminal a circuit topological structure diagram of a preset area to perform cable relationship assignment; constructing a cable layout tree diagram; extracting an i-th level cable set for multi-level clustering analysis; generating a cable set clustering result; setting wiring constraint directions and wiring constraint areas; setting tray distance constraint parameters; generating a three-dimensional model of the preset area; on the basis of the clustering result and under the described constraints, performing cable layout optimization in the three-dimensional model; generating a tray line layout optimization scheme; and sending the tray line layout optimization scheme to the user terminal. The present invention solves the technical problems in conventional tray line layout methods of an unsatisfactory layout result caused by relatively vague layout constraints and layout requirements, and low layout efficiency caused by excessive manual intervention and lack of automation and intelligence in the layout process.

The invention belongs to the field of rehabilitation medical treatment and intelligent computing, and particularly discloses a cerebral apoplexy rehabilitation personalized treatment recommendation system based on artificial intelligence. Comprising a multi-modal data acquisition module, a feature extraction and clustering modeling module, a personalized path making module and a recommended path generation and feedback optimization module, and can realize dynamic monitoring and intelligent analysis of rehabilitation data of a stroke patient; a multi-modal aggregation neural network model is constructed by fusing multi-dimensional data such as images, biomarkers, clinical behaviors and cognitive emotions, a rehabilitation path is formulated according to a medical data clustering result, and a recommended path is dynamically adjusted and optimized in combination with treatment feedback of a patient; compared with a traditional method, the method has the advantages that scientificity and adaptability of personalized treatment are improved, the method has the advantages of real-time updating of rehabilitation paths, closed-loop management of a system, high model robustness and the like, rehabilitation intervention efficiency and accuracy can be remarkably improved, and technical support is provided for intelligent development of rehabilitation medicine.

The invention discloses a marketing channel clustering modeling and optimizing method driven by heterogeneous data. The method comprises the steps of obtaining a multi-dimensional data set of a marketing channel, and performing preprocessing; the data set comprises structured data and unstructured data; and extracting a text word segmentation result and an emotion feature from the unstructured data, and extracting an image feature to generate a structured feature set, an unstructured feature set and the like. According to the method, structured and unstructured data can be integrated, and potential information of marketing channels can be comprehensively mined. Through a deep learning model (an auto-encoder, a variational auto-encoder and a generative adversarial network), features are extracted and optimized layer by layer, and the quality of the features and the performance of the model are improved. And in combination with a clustering algorithm and an evaluation index, the accuracy and reliability of a clustering result are ensured, and powerful support is provided for optimization of a marketing channel.

The invention discloses a voiceprint clustering method guided by a speaker recognition pre-training model based on short voices, and the method comprises the following steps: obtaining an original voice signal, and randomly combining a plurality of enhancement strategies to achieve data enhancement; performing voice segmentation on the voice signal after data enhancement based on a uniform segmentation mode; extracting voiceprint features of the segmented voice based on an attention mechanism of global time-frequency domain context modeling; and obtaining a clustering result based on K-means clustering and spectral clustering, matching the clustering result with a real speaker tag, performing reverse transmission based on angle-dependent AAM-Softmax loss, and outputting a voiceprint clustering result. According to the method, the influence of environmental interference on feature extraction can be overcome, feature dimensions which are more effective for identity identification can be screened, a clustering output effect which is superior to that of a mainstream algorithm can be obtained with a relatively low parameter quantity, and the robustness under a noise interference condition is improved.

The invention discloses a moving target trajectory prediction method and system based on a trajectory library, and the method comprises the steps: calculating multi-dimensional features between trajectories according to historical target trajectory data, and then calculating the overall similarity between the trajectories; clustering all historical target trajectories based on the overall similarity between the trajectories to obtain a plurality of trajectory clusters; constructing a trajectory sample data set according to each trajectory cluster, training a deep learning model by using the trajectory sample data set, and generating a corresponding trajectory prediction model; extracting a central trajectory from each trajectory cluster, and constructing a trajectory library according to all the central trajectories; matching the new target trajectory data with a trajectory library, and determining the attribution of the new target trajectory; and determining a trajectory prediction model according to the affiliation of the new target trajectory, and predicting the new target trajectory by using the determined trajectory prediction model. According to the invention, the accuracy of the clustering result and target trajectory prediction is improved, and the target trajectory prediction efficiency is improved.

The invention discloses a power transformer temperature prediction method and system based on multi-feature extraction and fusion, and the method comprises the steps: carrying out the time-space decoupling standardization and causal emergence clustering of all temperature variables in data, and obtaining a clustering result; extracting a common pattern from each class of the clustering result to obtain an information complemented multivariable time sequence, and performing down-sampling on the information complemented multivariable time sequence to obtain a plurality of subsequences; performing feature extraction on the multivariable time sequence and the sub-sequence after information completion through a dynamic time-frequency domain MLP mechanism to obtain overall features and local features, and fusing the overall features and the local features to obtain time sequence features; acquiring an external environment covariable, inputting the external environment covariable into the self-attention mechanism network to obtain a covariable self-feature, and performing feature fusion on the covariable self-feature and the time sequence feature through a covariable-driven causal convolution fusion mechanism to obtain a fusion feature; and inputting the fusion feature into a dynamic attention feature weighted prediction model for prediction to obtain a prediction result. And the precision and reliability of temperature prediction of the power transformer are obviously improved.

The invention discloses a wind power output clustering method and system based on a DTW-Kmedoids algorithm, and relates to the technical field of wind power output scene generation, and the method comprises the steps: carrying out the interpolation, dimension reduction, per-unit processing and smoothing processing of wind power historical data; carrying out distance measurement by adopting a dynamic time warping (DTW) algorithm, carrying out iteration by adopting a Kmedoids clustering algorithm to obtain a clustering result, and outputting a center curve of each cluster; for clustering results of different cluster numbers, calculating an error sum of squares of each cluster, and determining an optimal cluster number by adopting an elbow rule; and according to the clustering result under the optimal cluster number, generating a typical wind power output scene curve, and establishing a clustering effect evaluation index system. The method introduces the dynamic time bending distance algorithm, can adapt to the nonlinear change of the wind power output curve, improves the accuracy of similarity measurement through the dynamic matching time sequence, and enables the generated typical scene to be more representative. Therefore, the clustering center point is more representative, and the stability of the generated wind power output scene is better.

The invention discloses a data processing method and system for micro-motion detection array station distribution, and relates to the technical field of micro-motion detection, and the method comprises the steps: according to the actually measured starting point coordinates and the azimuth angle of a measuring line, setting the measuring point distance, and the radius and number of nested triangle circumcircles, generating field station coordinates in batches; collecting and preprocessing station waveform data; calculating a spatial autocorrelation coefficient of any center station and a non-center station; dBSCAN clustering is carried out based on the station distance; performing spatial averaging on the spatial autocorrelation coefficient according to a clustering result; fitting the averaged spatial autocorrelation coefficient and a zero-order Bessel function to obtain a frequency dispersion spectrum, picking up a surface wave phase velocity in the frequency dispersion spectrum, and calculating an apparent shear wave velocity; inverting the shear wave velocity of the waveform data by adopting a self-adaptive gradient inversion strategy; and generating a velocity comprehensive profile of a depth domain and a frequency domain according to the surface wave phase velocity, the apparent shear wave velocity and the inverted shear wave velocity. The invention provides a new method for station distribution to data processing for micro-motion detection.

The invention relates to the field of data processing, and discloses an intelligent data processing system based on an AI large model, which comprises the following steps: when detecting that a plurality of candidate entities exist in a text, judging whether the candidate entities need to be subjected to semantic disambiguation processing or not according to context semantic relevancy and entity historical reference frequency; constructing a cross-domain context representation vector, introducing a pre-training language model to encode the context, generating deep semantic representation of candidate entities, and judging whether a clustering result has ambiguity or not; whether the candidate entities have conflicts or not is judged by fusing language model embedding and structuring knowledge graph information; constructing an entity relationship graph based on a graph neural network, performing causality, temporal and attribute dependence reasoning on the relationship between the existing candidate entities, and judging whether the relationship between the candidate entities should be combined or split; and carrying out label replacement on the candidate entities in the target text in combination with the context and the reasoning result. The method has the advantage of improving the accuracy of data processing.

The invention provides a running log anomaly detection method and system, and the method comprises the steps: obtaining historical running log data of a target system, and converting unstructured data in the historical running log data into structured data; performing feature extraction on the converted structured data by using a variational auto-encoder, and performing clustering analysis on the extracted features; aiming at each clustering result, using a Transform model to carry out time series data analysis so as to capture a long-distance dependency relationship, and carrying out modeling on time series characteristics in the cluster through a self-attention mechanism so as to identify an abnormal event; the method comprises the following steps: training an anomaly detection model consisting of a variational auto-encoder and a Transform model, and carrying out parameter optimization on the model; and processing real-time running log data of the target system by using the trained anomaly detection model to realize an automatic identification result of an abnormal event. According to the method, the potential distribution characteristics of the log data can be automatically captured, and the recognition precision of abnormal events is improved.

The invention provides a pseudo-tag-based intention recognition model training method, an intention recognition method and an intention recognition device. The method comprises the following steps: inputting a sample text into a language model to extract a feature vector; clustering the sample text based on the feature vector, taking a clustering result as a pseudo tag, and calculating normalized mutual information of the real tag and the pseudo tag of the labeled sample text; determining a confidence score corresponding to each sample; the confidence score is used for quantifying noise in the pseudo tag, screening a high-confidence sample and taking the corresponding pseudo tag as a self-supervision signal, and iteratively optimizing the language model until convergence; after iteration, clustering is initialized again, a clustering result is updated, and mutual information and the number of iterations are normalized; when the number of iterations reaches an upper limit or the normalized mutual information amplification is smaller than a threshold value, training is terminated, and the language model is determined as an intention recognition model; the problem that the new intention recognition capability of the model is reduced due to continuous propagation and accumulation of noise pseudo labels can be solved; and the new intention recognition capability of the model is improved.

An embodiment detects by a Clustering Component of a Recommendation System, a candidate content based on a user query, responsive to the detected candidate content, executes a clustering algorithm on the detected candidate content to output a cluster and a cluster result. The embodiment decides, by a Recommendation Clarification Component of the Recommendation System, to recommend a clarification based on the cluster result, comprising computing a distance between a cluster and a response of a large language model to the user query where an option list is updated with the clarification where the clarification is based on the cluster and the distance. The embodiment also detects by the Recommendation System a selection in the option list, responsive to the detected selection, generates a prompt based on the selection where the prompt is inputted into the Recommendation System and the large language model.

The invention relates to the technical field of data processing, in particular to a wind turbine generator running state monitoring method based on machine learning, and the method comprises the steps: carrying out the logarithmic transformation of each piece of data in a data sequence corresponding to a plurality of data indexes in a preset time period during the running of a wind turbine generator, and obtaining a corresponding logarithmic value; constructing a scatter diagram of all logarithm values; obtaining a neighborhood radius and a minimum sample number of a DBSCAN algorithm, and obtaining a clustering result of all data points in the scatter diagram according to the neighborhood radius and the minimum sample number; a plurality of boundary points are obtained according to the clustering result, the isolation degree of each boundary point is obtained according to the distribution characteristics of the data points within the neighborhood radius range of each boundary point, and abnormal points in the scatter diagram are obtained according to the isolation degree of each boundary point; and the operation state of the wind turbine generator is monitored according to the abnormal points in the scatter diagram, so that the accuracy of monitoring the operation state of the wind turbine generator by the DBSCAN algorithm is improved.