18 results about "Supervised clustering" patented technology

The method for automatic identification, classification and development trend analysis of net red villages based on multi-source data fusion and natural language processing comprises the following steps: UGC data is crawled from Xiaohongshu and Douyin through a distributed master-slave architecture, de-duplicated based on SimHash, and normalized in time and coding format; a text semantic fingerprint is generated, and multi-level semantic cache fingerprint matching is performed; for unassigned text, its complexity is calculated, and a large language model API is adaptively called to automatically complete and extract five-level administrative divisions; weights are determined based on the analytic hierarchy process, interaction indicators such as likes, comments, collections and forwards are integrated, and a comprehensive network heat index of the village is obtained; an external text mining tool is connected, and batch word frequency analysis, semantic network analysis and sentiment tendency evaluation are performed; a document-term matrix is constructed, TF-IDF weighting is performed, and unsupervised clustering algorithm is used for clustering analysis of village characteristics; cross-dimension analysis is performed on the clustering results, and a development portrait, advantage mining and operation suggestion warning are automatically generated in combination with the SWOT model.

The application provides a charging facility fault early warning model construction method based on multi-source data perception, and belongs to the technical field of charging facility fault early warning.The application forms a multi-source time series data set by collecting charging pile operation state data and environmental data and performing time series alignment, expands fault samples by using an adversarial generative network and a semi-supervised clustering algorithm to form a balanced sample data set, constructs a fault early warning model containing a time series memory pool encoding layer and a frequency domain convolution feature extraction layer, cooperatively optimizes early warning accuracy and response time delay by using a double-layer game optimization framework to obtain an optimal parameter combination, deploys the optimized model to an edge computing module to realize real-time fault early warning, establishes an online incremental learning mechanism based on sliding time window detection data distribution offset, and uses an elastic weight consolidation technology to update model parameters and retain historical knowledge, thereby solving the problem of early warning performance degradation of charging facility fault early warning in a data distribution evolution environment.

The application relates to a medical term normalization method, and belongs to the technical field of data processing. The method solves the problems that coverage cannot be guaranteed and new variations cannot be dynamically adapted in the prior art. The method comprises the following steps: acquiring historical unmatched original words to construct an original word set; acquiring terms labeled for part of the original words in the original word set; adopting a supervised clustering algorithm to cluster the original word set to obtain original word clusters; for each original word cluster, an improved genetic algorithm is adopted to obtain a regular expression for mapping the original word cluster to a term corresponding to the original word cluster. The method realizes the improvement of coverage, can automatically discover new variations, and dynamically adapts new variations.

This invention discloses a data annotation method and system based on user behavior and attention tracking. It synchronously and in real-time collects multi-source behavioral signals from doctors, including mouse, keyboard, and eye movements. Combined with identity and interface metadata, the data undergoes standardization, anomaly removal, and short-term behavioral unit segmentation. Unsupervised clustering is used to extract individual behavioral micro-patterns, and a behavioral profile library is constructed. Through multimodal temporal modeling and an adaptive spatiotemporal attention mechanism, behavioral features, interface regions, and report text are deeply integrated to output multi-level correlation probabilities, achieving high-precision automatic labeling of content and image regions.

This invention discloses an array ACFM detection method and system for detecting wide weld seams. The method includes: S1, establishing an AC electromagnetic field by attaching the array detection probe to the surface of the wide weld seam to be tested, and scanning along the weld seam direction; S2, synchronously acquiring multi-channel magnetic field disturbance signals using a magnetic field sensor array; S3, preprocessing and demodulating the multi-channel magnetic field disturbance signals to extract in-phase and quadrature components; S4, calculating the amplitude and phase to construct a joint feature vector; S5, constructing a similarity matrix and a degree matrix to obtain a Laplace matrix, and using an unsupervised clustering algorithm for defect classification; S6, calculating the confidence index of the classification result and comparing it with a preset threshold to determine whether crack defects exist. This invention achieves accurate determination of crack defects in wide weld seams by extracting the joint feature vector and spatial correlation features of multi-channel magnetic field signals and performing unsupervised clustering using the Laplace matrix, and then calculating the confidence index based on the classification results.

This invention discloses an unsupervised clustering and attribution method and system for dynamic deception-enhanced network attacks. The invention identifies suspicious behavioral clusters by real-time collection of raw network logs and unsupervised incremental clustering. When the suspiciousness exceeds a threshold, deception resources matching the behavioral pattern are automatically and dynamically deployed to capture deep interaction sequences of the attacker, generating enhanced data. The features of the raw logs and the enhanced data are spatiotemporally aligned and fused to generate an intent feature vector representing the attacker's tactics, techniques, and processes. Based on this vector, refined clustering and attacker attribution are performed. This invention solves the problems of inaccurate clustering intent identification and low attribution accuracy caused by the lack of deep interaction data in existing technologies, significantly improving the ability to discover unknown threats and the accuracy of attack attribution.

This invention relates to an online partial discharge detection device and monitoring system. The discharge detection device includes a sensor module for acquiring partial discharge signals; a data acquisition system connected to the sensor module, which includes a multiplexer for multi-channel signal selection and switching, a signal conditioning circuit including a low-noise amplifier and bypass control circuit, an analog-to-digital converter, and an FPGA data acquisition module for receiving digital sampled data and power frequency synchronization signals; a data processing system, which includes an FPGA data processing module with data buffering, trigger control, phase detection, waveform management, and digital filtering functions, and an embedded processor communicating with the FPGA for feature extraction, unsupervised clustering, and supervised classification; and a communication system for transmitting the identification results to a remote monitoring platform. This invention can meet the application requirements of large-scale online monitoring of power equipment.

This invention provides a method and system for cancer subtype identification based on multi-omics data, belonging to the field of bioinformatics processing technology. The method includes: constructing a DILCORE model that integrates a multi-branch variational autoencoder, contrastive learning, and cross-view attention mechanisms. The multi-branch variational autoencoder decomposes omics observation data into common components for subtype classification and view-specific noise components, achieving noise suppression; the InfoNCE contrastive loss is introduced to bring common representations of the same sample closer across different views, enhancing cross-omics consistency; the cross-view residual self-attention mechanism is used to adaptively weight and fuse common vectors; finally, a self-supervised clustering fine-tuning optimization strategy is introduced to jointly improve representation quality and clustering performance in the latent space. This achieves deep and effective integration of multi-omics data, significantly improving the accuracy of cancer subtype identification and providing a powerful tool for personalized cancer treatment and prognostic assessment.

This invention belongs to the field of Earth observation and data processing technology, and relates to a method for estimating the magnitude of strong earthquakes based on unsupervised learning clustering weighting, addressing the problem of insufficient accuracy in magnitude estimation in existing technologies. The method first collects peak surface deformation (PGD) and peak surface deformation (PGV) data and epicentral distance from seismic monitoring stations; constructs a magnitude regression equation, and performs cluster analysis on the observed features using the FCM unsupervised learning clustering algorithm, adaptively determining the observation weight factors based on the degree of difference between the cluster centers and the benchmark cluster centers; then, the cluster weights are introduced into a robust estimation model, and sequential weighted least squares calculation is performed using the IGG3 equivalent weight function to obtain the fused magnitude. This invention combines unsupervised clustering adaptive weighting with robust estimation to rapidly estimate the magnitude of strong earthquakes with complex fault structures, significantly improving the accuracy, stability, and reliability of strong earthquake magnitude estimation.

The application provides a photovoltaic module defect recognition method and device, the method obtains a plurality of infrared image sample sets of photovoltaic modules, determines a labeled sample set and an unlabeled sample set therefrom, constructs a defect recognition model, performs semi-supervised training based on the labeled sample set and the unlabeled sample set, the training generates generated samples through a generation module, a discrimination module performs true or false discrimination and defect category discrimination on real samples and generated samples, and model parameters are updated in combination with unsupervised clustering and loss optimization, and the trained defect recognition model is called to output recognition results containing defect categories for a to-be-recognized infrared image. The technical scheme of the application realizes semi-supervised recognition of photovoltaic module defects using a small amount of labeled data and a large amount of unlabeled data, and improves the accuracy and applicability of defect recognition.

This invention discloses a signal processing method applicable to various signal characteristics, relating to the fields of communication and radar signal processing technology. By combining the construction of a multi-dimensional signal feature library with real-time spectrum sensing, this invention achieves rapid analysis and accurate characterization of deep-space radar signal characteristics. The feature library is generated based on unsupervised clustering of historical data, covering various signal templates such as transient impulses, periodic coherence, and steady-state noise. It not only provides rich prior knowledge references but also supports online sliding window incremental updates, ensuring that feature representation always conforms to actual environmental changes. The real-time spectrum sensing employs adaptive window time-frequency analysis, with the window length dynamically adjusted according to the signal's instantaneous bandwidth and local stationarity, effectively balancing the contradiction between frequency resolution and time resolution and overcoming the limitations of traditional fixed-window analysis in non-stationary scenarios.

The application discloses a tobacco slitting method based on multi-view weight learning and a storage medium, obtains a hyperspectral image of target batch tobacco and performs division; an effective area of the tobacco is obtained by using a threshold segmentation method, the tobacco is divided into a set number of subareas with the same longitudinal length, characteristic spectra of the subareas corresponding to the tobacco are calculated, and a tobacco spectrum database is constructed; spectrum data in the tobacco spectrum database is subjected to band division, different band combinations are obtained, and a multi-view tobacco spectrum database is constructed; a semi-supervised clustering algorithm model is constructed based on multi-view weight and similarity learning, the semi-supervised clustering algorithm model is trained through the multi-view tobacco spectrum database, and a semi-supervised clustering algorithm model with an optimized target function is obtained; and a tobacco segmentation result is obtained through the semi-supervised clustering algorithm model. Through construction of the multi-view of the tobacco, weights are allocated to each view, differences between different tobaccos are accurately quantified, and the tobacco slitting effect is ensured.

The application provides a kind of abnormal monomer detection method in lithium battery pack based on probability distribution, by the charging voltage data of monomer unified statistical feature extraction is carried out, and subsequent cluster analysis is carried out to corresponding statistical value, avoid the existing processing mode of monomer voltage frame by frame acquisition, significantly reduce the cost of calculation.The Gaussian mixture model used in the method belongs to unsupervised clustering, compared with the K-means clustering method used in the prior art, it can more smoothly fit different distribution forms and has higher accuracy.The method of the application is more suitable for the scale of hundreds of monomers in the current vehicle battery pack, the obtained statistical value distribution is relatively concentrated, easier to process, so as to simplify the fitting classification and provide faster processing speed and higher calculation efficiency.

The application provides an API access behavior threat hunting method, system, device, medium and program product. The method comprises: obtaining API access data of an access subject and constructing an access behavior sequence; performing vectorization processing on the access behavior sequence to obtain a uniform-dimension behavior representation vector, and performing similarity measurement processing to form a comparable behavior representation; performing unsupervised clustering analysis on the comparable behavior representation to obtain a clustering result including at least one behavior mode cluster and abnormal behavior data; performing behavior analysis processing on the behavior mode cluster and the abnormal behavior data based on the clustering result to generate a behavior analysis result; storing and updating the behavior analysis result, and triggering a corresponding security disposal operation based on the behavior analysis result. The application forms a closed-loop threat hunting mechanism from data collection, behavior representation, mode discovery to knowledge sedimentation and strategy execution, and improves the accuracy, self-adaptability and real-time security response capability of API access behavior identification.

Systems, methods, and other embodiments associated with quasi-supervised clustering for activity pattern characterization and anomalous activity detection are described. In one embodiment, a method accesses a plurality of data points. An individual data point of the plurality characterizes a pattern of activity associated with an account. The method splits the plurality of data points into clusters of similar data points. The method evaluates the clusters to detect that the individual data point has changed clusters in a manner indicative of an anomalous change to the pattern of activity. And, the method generates an electronic alert that the pattern of activity has changed anomalously.

The application discloses a radar pulse repetition interval (PRI) estimation method based on dynamic threshold and deep physical fitting. First, the dynamic threshold is calculated based on the coefficient of variation and sensitivity parameters of the time difference of arrival (DTOA) sequence to determine the validity of the subsequence. Second, according to the modulation type, the noise points are removed by the median absolute deviation for the fixed frequency, the jump points are detected and clustered for the group variable frequency, and the independent subsequences are extracted according to the dynamic threshold by using the mean shift unsupervised clustering algorithm for the uneven frequency. Then, the time offset of each pulse in the sequence relative to the first pulse is calculated, divided by the median of the sequence, and rounded to generate a virtual pulse sequence number. Finally, the physics-informed neural networks (PINNs) are introduced, the virtual sequence is iteratively fitted by gradient descent, and the slope of the fitted straight line is taken as the final PRI estimation value. The application solves the defect that the traditional method is susceptible to noise interference, and improves the PRI estimation precision and robustness in a complex electromagnetic environment.

This invention discloses an AI-driven IVF personalized treatment plan generation system, relating to the fields of medical and artificial intelligence technologies. Through the deep coupling of unsupervised clustering and long-term reinforcement learning planning, this invention achieves a leap from static classification to dynamic strategy generation, constructing a globally optimal personalized treatment path for complex patient groups. It utilizes unsupervised clustering algorithms to perform deep pattern mining on patient baseline data, automatically identifying fine subtypes with similar physiological characteristics. The reinforcement learning agent module models the patient's treatment process as a sequential decision-making process. The agent's state space integrates the patient's subtype attributes and dynamically changing cyclical treatment outcomes. By iteratively building a simulation environment with historical data, a higher success probability is achieved at the global level, transforming clinical decisions based on subjective experience into an automated decision-making process based on historical evidence and global optimization.

This invention discloses a semi-supervised clustering modeling method and system for reservoir prediction. Addressing the challenges of large seismic attribute data volume, high redundancy, scarce labels, and low signal-to-noise ratio, this invention embeds a modified K-means framework simultaneously with pairwise constraint guidance and sparse feature weighting. It iteratively optimizes cluster assignment and attribute weights, achieving a balance between maximizing inter-class differences and minimizing intra-class differences. Differential privacy noise is introduced to ensure data security without significantly reducing accuracy. It supports downsampling acceleration and multi-layer 3D label alignment, enabling efficient processing of millions of data points. Compared to conventional K-means and waveform clustering, this invention significantly improves the accuracy of blind well testing, clearly characterizing micro-structures such as channels and riverbeds, providing a high-resolution, highly interpretable integrated solution for reservoir distribution, thickness, hydrocarbon content, and sedimentary facies analysis.