364 results about "Unsupervised learning" patented technology

Methods, systems, and computer storage media for providing a data analysis pipeline using a data analysis pipeline engine in a data intelligence system are described. A data analysis pipeline refers to a structured sequence of data processing steps that support transforming raw data into meaningful insights or actionable outcomes. The data analysis pipeline engine is an unsupervised learning pipeline based on clustering, topic modeling, and Large Language Models (LLMs). For example, the data analysis pipeline can use advanced machine learning techniques to automatically categorize emails into semantically similar clusters, enabling the data intelligence system to quickly identify and prioritize potentially high-risk emails for further investigation. The data analysis pipeline employs AI agents for context-aware graph induction relevance assessment. The AI agents employ induction and deduction loops to build and refine a data feature hypergraph (e.g., vulnerability hypergraph) that encompasses identified relevant data providing a holistic view of a contextual landscape.

The invention provides a fly ash composite material goaf filling body interface quality intelligent evaluation method, and belongs to the technical field of mining engineering and artificial intelligence detection crossing. The method comprises the steps that firstly, filling body interface quality characteristic data are collected and comprise interface sound wave signals, stress strain, coal ash composite material physical parameters and environment working condition data; secondly, constructing a multi-physical field data completion model, performing unsupervised learning on the acquired sound wave, stress, temperature and moisture content data, and generating completion data of global spatial distribution; secondly, constructing a multi-field fusion interface quality index prediction model, and inputting multi-source data into the model to obtain an interface quality index; and finally, combining the quality index to realize interface defect mode classification and grade evaluation, and generating a targeted maintenance strategy. The invention provides an intelligent evaluation method which fuses multi-source data and gives consideration to real-time performance and comprehensiveness, so as to solve the industrial pain points of interface quality evaluation lag, low precision, large destructiveness and the like.

A dynamic adaptive learning method for mineral prediction includes: collecting a dataset including geological data and labels of the geological data; extracting features from the geological data, initializing parameters of a training model and optimizing the parameters to obtain training parameters; performing an associative training on the training model based on the training parameters and the labels in a dynamic adaptive learning framework to obtain a mineral prediction model, algorithms of the associative training including a variational expectation algorithm and a variational maximization algorithm, and the variational expectation algorithm including an unsupervised learning mode, a semi-supervised learning mode, and a fully supervised learning mode; and predicting, by using the mineral prediction model, a mineral to obtain a mineral prediction result. The method can break through limitations of the traditional machine learning technology, offering a more efficient, universal, and stable strategy for geophysical data analysis and mineral resource assessment.

The invention relates to the technical field of intelligent diagnosis, and discloses a micro-grid fault diagnosis method and system based on data driving and unsupervised learning. The method comprises the following steps: collecting current, voltage, temperature and power data of a micro-grid and constructing a time sequence matrix; inputting a time sequence prediction network and a time sequence reconstruction network, and performing parallel processing to obtain a prediction error and a reconstruction error; carrying out weighted fusion on the two errors and constructing a two-dimensional error space to judge normal fluctuation and fault abnormity; and extracting a state variable to generate a dynamic threshold to judge a fault. The false alarm rate and the missing report rate of fault diagnosis are reduced.

The invention relates to the technical field of power utilization monitoring, and discloses a photovoltaic user power utilization abnormity monitoring method and system based on artificial intelligence. The photovoltaic user electricity consumption abnormity monitoring system based on artificial intelligence comprises a data acquisition module which is used for acquiring photovoltaic power generation data, electricity consumption data and environment data of a user; the data preprocessing and feature engineering module is used for cleaning, aligning and normalizing the original data acquired by the data acquisition module and constructing a feature data set for model training and reasoning; and the artificial intelligence analysis engine module comprises an unsupervised learning unit, a supervised learning unit and a deep learning unit. According to the invention, the false alarm rate and the missing report rate can be effectively reduced, the accurate diagnosis of the abnormal type can be realized, and the intelligent and accurate operation and maintenance requirements of power grid enterprises on the power utilization monitoring of photovoltaic users are met.

The invention provides a video content enhancement method for a low-illumination environment, and the method comprises the steps: achieving the data preprocessing based on an original low-illumination video frame sequence through frame synchronization, color space conversion and local brightness analysis, generating a noise sensitivity thermodynamic diagram through multi-feature unsupervised learning, and constructing a noise perception gating mechanism through the combination of affine transformation. Dynamic modulation of the characteristic channel is realized; in the multi-scale network structure, a channel attention module is used for carrying out layer-by-layer self-adaptive adjustment on a noise sensitive area; a basic illumination image and an edge enhancement image are generated through double-branch decoding, and then weighted fusion is carried out in combination with a noise thermodynamic diagram, so that brightness balance and detail enhancement are realized; a noise smoothing regular term is introduced during end-to-end training, so that the network achieves dynamic balance between an enhancement effect and noise control.

A power transformation equipment temperature anomaly identification and diagnosis method comprises the following steps: collecting state variables, performing cleaning, interpolation complementation and abnormal point elimination on multi-source data through a time synchronization mechanism, and constructing a unified data matrix; extracting statistical features and time sequence dynamic features in the time sequence based on the data matrix, and performing dimensionality reduction on redundant information in combination with a principal component analysis method to form a multi-dimensional fusion feature vector; an unsupervised learning model based on LSTM-AE is constructed, a normal working condition data learning feature reconstruction mode is utilized, and a reconstruction error is taken as a criterion to identify potential temperature anomaly; and calling a preset expert rule base and a knowledge graph, automatically analyzing dominant factors causing anomalies, and identifying typical anomaly types. According to the invention, automatic identification and classification diagnosis of the temperature abnormity of the power transformation equipment under an unsupervised condition are realized, the accuracy and response speed of fault identification are obviously improved, and the intelligence and practicability of equipment operation state monitoring are enhanced.

The invention discloses a transformer insulation state evaluation method based on artificial intelligence multi-parameter fusion perception, and relates to the technical field of electrical equipment detection, and the method comprises the steps: 1, obtaining the multi-modal monitoring data of a transformer, and constructing a dynamic graph structure; wherein the multi-modal monitoring data comprises oil chromatography data, partial discharge data and thermal image data; 2, encoding the dynamic graph structure through an encoder extraction embedding technology, carrying out space-time dimension feature aggregation and evolution modeling based on the encoded dynamic graph structure by utilizing graph convolution and time convolution technologies, inputting preset transformer insulation positive and negative sample pairs into a constructed model, carrying out InfoNCE loss unsupervised learning, and carrying out infoNCE loss unsupervised learning; obtaining a state manifold of a normal transformer, and carrying out multi-modal data space-time alignment and anomaly distinguishing on the state manifold; and step 3, introducing a Bayesian weight after multi-modal data space-time alignment and anomaly distinguishing, and outputting probability distribution of insulation state embedding.

The invention relates to the technical field of industrial automation control, and discloses a desulfurization system pH value intelligent pre-control feedback control method based on big data learning, and the method comprises the following steps: S1, collecting full-chain process data related to pH control; s2, preprocessing the original data and constructing feature vectors; s3, dividing working conditions by adopting unsupervised learning, and independently training an LSTM prediction sub-model for each working condition; s4, solving a comprehensive cost function, and outputting a dynamic optimal pH set value; s5, performing dynamic weight fusion on prediction results of the sub-models to obtain an intelligent feed-forward regulation quantity; s6, fusing the feedforward adjusting quantity and the feedback correcting quantity to form a final control instruction; and S7, periodically retraining all the models to realize self-learning and iterative updating of the system. According to the method, through multi-working-condition model fusion prediction, multi-target online optimization and self-learning iteration, the control precision is improved, the operation cost is reduced, and long-term self-adaption of the control system is realized.

A system is adapted to automatically identify suspected fraudulent transactions. The system includes a fraud management server configured to perform these operations: receiving unlabeled transactions, each having a number of features, and storing them in a transaction repository; with the features, determining a risk score for each transaction; based on the risk scores, dividing the unlabeled transactions into bins in order of their risk scores; labeling transactions of the first bin legitimate and those of last bin as fraudulent; with the labeled transactions, training a first machine learning model; with the trained first machine learning model, labeling transactions of a second bin and a second-to-last bin as either fraudulent or legitimate; storing the labeled transactions of the first bin, second bin, second-to-last bin, and last-bin in the transaction repository; and with the labeled transactions of the first bin, second bin, second-to-last bin, and last-bin, training a second machine learning model.

The invention provides a dry bulk cargo port energy consumption key node identification method and system, and the method comprises the steps: collecting the energy consumption data of dry bulk cargo port loading and unloading equipment, and carrying out the multi-dimensional statistics and analysis, and obtaining the multi-dimensional energy consumption data; based on an unsupervised learning method, capturing high-energy-consumption nodes and low-energy-consumption nodes from the multi-dimensional energy consumption data; in combination with an equipment operation track and time information, a space-time law of energy consumption key nodes of the dry bulk port is excavated, the energy consumption key nodes are identified, and space-time evolution speculation is realized; an interactive digital twinborn platform is constructed based on a WebGL technology, and energy consumption distribution is presented in combination with a thermodynamic diagram; according to energy consumption key node information and port operation requirements, a loading and unloading operation strategy is made, an equipment scheduling scheme is optimized, energy conservation and operation efficiency are both considered, and intelligent scheduling decision making is achieved. Through multi-dimensional energy consumption data collection and analysis, unsupervised learning and space-time law mining are combined, the loading and unloading operation process is optimized, and the port operation efficiency and the energy-saving effect are improved.

The invention relates to the technical field of steelmaking, in particular to a method for quickly detecting the non-uniformity of a flow field of a continuous casting crystallizer on line, which comprises the following steps of: acquiring a signal in a hydraulic vibration device of the crystallizer, converting the signal into a digital signal, and preprocessing the digital signal as time sequence synchronization data; the method comprises the following steps: slicing time sequence synchronization data according to a fixed time window, extracting multi-dimensional features from data in each time window, and constructing feature vectors; performing flow field evaluation by adopting a mixed model combining supervised learning and unsupervised learning; and outputting an alarm level prediction and diagnosis mode by using the multi-task learning model. An original signal capable of directly or indirectly reflecting a flow field state is acquired at high frequency through a multi-source sensor array arranged on a crystallizer; extracting characteristic values strongly related to the characteristics of the flow field by using a signal processing technology; inputting the characteristic value into a pre-trained deep learning neural network model; the model outputs a comprehensive evaluation index about the uniformity of the flow field in real time, and automatically identifies a non-uniform mode and grade.

The invention provides a power distribution communication network optical cable fault prediction method and system based on machine learning. The method comprises the following steps: collecting Rayleigh scattering signals of a plurality of monitoring points along an optical cable; performing unsupervised learning on the optical cable adaptive reconstruction model, and calculating a reconstruction error matrix and an abnormal cumulative metric; constructing an optical cable network diagram, calculating a fault propagation probability matrix, predicting a future optical cable health index, and obtaining a future health index matrix; establishing an environment influence matrix, and adopting an optical cable environment adaptive filtering model; and based on the health index and the fault confidence coefficient matrix after filtering optimization, optical cable maintenance priority scores are calculated and sorted, and a self-adaptive inspection and maintenance strategy is formulated. According to the invention, high-precision monitoring, fault propagation prediction and environmental adaptability optimization of the health state of the optical cable are realized, and the intelligent level of operation and maintenance of the optical cable is improved.

The invention discloses a behavior baseline-based ammeter state monitoring method, system, equipment and medium, and relates to the technical field of equipment behavior anomaly detection, and the method comprises the steps: collecting operation parameter time sequence data of an intelligent ammeter in a preset monitoring region during operation, carrying out the combined processing of the operation parameter time sequence data, extracting the multi-dimensional features of the region, and carrying out the detection of the behavior baseline; based on regional multi-dimensional features in a historical normal state, a regional behavior baseline is established through unsupervised learning, regional multi-dimensional features at a current monitoring moment are acquired, a regional consistency index is generated through matching degree calculation with the regional behavior baseline, and an abnormal ammeter is identified according to an individual deviation degree. And based on the region consistency index and a preset period, triggering update maintenance of the region behavior baseline. According to the method, visual visualization and a model self-evolution mechanism are combined, and the state of the industrial electric meter is changed from passive warning to active, accurate and large-scale predictive intelligent operation and maintenance.

The invention relates to a medical waste supervision process risk early warning system based on artificial intelligence. The system comprises a whole process data acquisition module, a data preliminary processing module, a preliminary early warning model construction module, a risk grading model construction module and a supervision process risk early warning module. According to the invention, original data is obtained through data acquisition; a data preliminary processing method of multi-source data cleaning, graph sequence construction, time sequence attribute graph construction, data standardization and data set segmentation is adopted; a clustering model is adopted as a preliminary early warning model, potential risk process nodes are quickly identified through an unsupervised learning mode, high-quality input is provided for subsequent grading, and meanwhile, a graph structure is introduced to facilitate fusion of data attributes, structural relationships and time sequence behaviors; a deep learning model is adopted as a risk grading model, dynamic risk quantification is realized by integrating sub-graph features, time sequence context and environmental factors, and meanwhile, the fine grading precision is improved by utilizing data to drive threshold adjustment.

The invention relates to a convolutional neural network hologram generation method based on unsupervised learning, and belongs to the field of artificial intelligence technology and computer-generated holography. Comprising the following steps: incorporating a physical diffraction model into an unsupervised learning convolutional neural network, firstly inputting a target image into the SCLSK-Net network, outputting a predicted phase by a coding part, introducing space and channel reconstruction convolution into the coding part of the network, reducing redundancy calculation, promoting learning of representative features, and then transmitting to a decoding part; a large-selectivity nuclear network is introduced in a decoding part, a space acceptance field is dynamically adjusted, ranging environments of various objects in different scenes are simulated, then transmission of a physical diffraction model is realized, and learning parameters can be automatically updated by reversely transmitting loss to an initial coding part; and through an attention mechanism and space channel reconstruction convolution, generation of a high-quality rapid computer-generated hologram is realized.

The invention provides an encrypted traffic anomaly detection method based on unsupervised learning, and relates to the field of artificial intelligence network security. In order to solve the problems of dependence on a large number of labeled abnormal samples, poor model generalization ability and poor dynamic adaptability of the existing encrypted traffic anomaly detection method, the invention provides an encrypted traffic anomaly detection method based on unsupervised learning, which comprises the following steps: extracting effective features of an encrypted traffic data packet, generating a state sequence by using a KMeans clustering algorithm, and carrying out unsupervised learning on the state sequence; calculating the occurrence probability of the state sequence in combination with an n-order homogeneous Markov chain model; a dynamic adaptive threshold is constructed based on exponential weighted moving average (EWMA) and a sliding window mechanism, and abnormality judgment is realized by comparing the occurrence probability of a state sequence with the dynamic threshold. According to the method, only normal encrypted traffic is utilized for training, and effective detection of all encrypted traffic including abnormal traffic can be realized.

The invention discloses a method and system for monitoring the abnormal state of a belt conveyor based on deep learning, and the method comprises the steps: laying sensing optical fibers along the line of a rack of the belt conveyor, and collecting the operation sound signals of a plurality of spatial point locations along the line through the sensing optical fibers by a distributed acoustic sensing DAS device; the method comprises the following steps: in a normal operation state of a belt conveyor, collecting normal sound signals of each point location, preprocessing the signals, and constructing a normal sample data set; for a normal sample of each spatial point location, training a corresponding unsupervised learning model; in real-time monitoring, sound signals collected at each point location are input into a corresponding unsupervised learning model, a reconstruction error is calculated, and the reconstruction error is compared with a dynamic threshold value based on normal sample statistical characteristics to obtain an abnormal result; and performing comprehensive judgment on an abnormal result based on statistical logic of the time window, and triggering an alarm if an abnormal proportion in the window exceeds a set value. High-accuracy abnormity early warning is realized, and system deployment is convenient.

A method and system for automated support sub-topic classification using large language models (LLMs). The method includes collecting user transcripts and LLM-generated summaries, performing unsupervised learning to identify common themes, generating sub-topics, and creating labeled datasets. A supervised learning model is trained to categorize user transcripts into the identified sub-topics. The system performs categorization of new user queries and generates appropriate action responses.

The invention relates to the technical field of intelligent detection, and discloses a T-SVAE feature extraction strategy and a method for improving near infrared spectrum soil rapidly available potassium measurement precision by using the T-SVAE feature extraction strategy, and the method comprises the following steps: step 1, collecting soil surface samples of different plots, obtaining near infrared spectrum data of the soil samples by using a Fourier transform near infrared spectrometer, and calculating the near infrared spectrum data of the soil samples; determining the actual content of quick-acting potassium in the soil sample by adopting a national standard method; the method comprises the following steps: 1, acquiring near infrared spectrum data, 2, preprocessing the acquired near infrared spectrum data, and removing impurity signals caused by instrument fluctuation, environmental interference and sample physical form difference, and 3, constructing a Transform and supervision constraint fused variational self-encoding model (T-SVAE). By constructing a variational self-encoding model fusing Transform and supervision constraint, the problem of feature blindness caused by high-dimensional data difficulty, nonlinear modeling limitation and unsupervised learning in near infrared spectrum data processing of a traditional feature extraction method is effectively solved.

The invention belongs to the technical field of distributed control and intelligent operation and maintenance, particularly relates to a synchronous timing system fault diagnosis method based on unsupervised learning, and aims to solve the technical problems that fault early warning is lagged, hidden coupling faults are difficult to recognize and fault samples are scarce in the prior art. Constructing a time sequence of the multi-dimensional state space; s2, calculating a dynamic control entropy feature representing the disorder degree of the control loop; s3, obtaining a reconstruction sequence of the input sequence, and calculating a reconstruction error vector; and S4, calculating a real-time abnormal score of the synchronous timing system, and judging whether the synchronous timing system enters a metastable fault state or not according to the real-time abnormal score. According to the invention, the early warning of the fault is realized, and the early warning can be given out when the SoftPLL enters the metastable state and does not lose the lock yet.

The invention discloses a high polymer material performance prediction method and system based on deep learning, and the method comprises the steps: constructing an automatic encoder, and carrying out the dimension reduction of various data of a high polymer material through unsupervised learning; optimizing a multi-mode encoder structure by adopting an automatic design mechanism; extracting a fusion characteristic value of the high polymer material by using a multi-modal data encoder; dynamic attention fusion: introducing a dynamic gating weight to adaptively distribute modal weights to input data; introducing physical constraint, and embedding molecular dynamics into back propagation; performing quantum circuit acceleration graph convolution; and predicting and outputting, mapping the fusion characteristic value to the tensile strength and elastic modulus performance indexes of the high polymer material, and realizing nonlinear regression through a multi-layer perceptron. According to the method, a material molecular dynamics equation is converted into a forward propagation kernel from a posterior constraint, the dynamic behaviors of molecules can be simulated and predicted more accurately, and the calculation efficiency is improved while the precision is ensured.

The invention relates to the field of data security, in particular to a network security intelligent detection method based on big data, and the method comprises the steps: collecting network flow data, a terminal system call sequence and a user operation behavior log, and carrying out the data fusion processing to generate a unified behavior event flow; selecting a key behavior event based on an information entropy threshold value, performing time alignment through a dynamic time warping algorithm, and constructing a behavior gene map containing a communication association gene, an operation sequence gene and a behavior time sequence gene; a dynamic behavior baseline model is established by using unsupervised learning, and gene mutation detection and alarm are realized by calculating the deviation degree of each gene dimension; the detection performance is evaluated based on the false alarm rate, model parameters are optimized through a negative feedback mechanism, and acknowledged attack features are stored in a sharable threat gene feature library through a positive feedback mechanism. According to the method, the detection accuracy is continuously improved through a closed-loop learning mechanism, and a self-adaptive safety protection system with self-optimization capability is constructed.

The invention provides an intelligent abnormal value detection and processing method based on deep learning product quality data. The method comprises the following steps: collecting multi-dimensional product quality data from a production line; an encoder module is constructed, and an encoder adopts a multi-layer neural network structure and is used for compressing and mapping input high-dimensional quality data into low-dimensional hidden layer feature representation; constructing a decoder module, receiving low-dimensional representation features output by an encoder, and reconstructing original data through a reverse neural network structure; training the automatic encoder by adopting an unsupervised learning mode, and learning a distribution mode and feature representation of normal data; and based on the trained automatic encoder, performing reconstruction error calculation on the quality data input in real time, judging an abnormal value through a preset threshold value, and triggering an alarm. Through the steps, the problem that high-precision detection of product quality data in production cannot be achieved in the prior art is solved, the alarm function is achieved, and therefore the quality problem of products in the future is avoided.

The application discloses an operation and maintenance data anomaly detection device and method and a storage medium. An acquisition module acquires operation and maintenance data. A detection module is connected with the acquisition module and is used for receiving the operation and maintenance data of the acquisition module. According to the type of the operation and maintenance data, an anomaly detection algorithm is used to perform anomaly detection processing on the operation and maintenance data to obtain an anomaly detection result. According to the type of the operation and maintenance data, the operation and maintenance data is predicted to obtain a prediction result. The operation and maintenance data including indexes, logs and call chains can be uniformly accessed to the detection module. The interface calling and the input mode of the operation and maintenance data are unified. The anomaly detection processing and the prediction processing are uniformly performed through the detection module. The integration is not needed additionally. The output mode of the result is unified. The convenience is improved. In addition, the anomaly detection algorithm uses unsupervised learning and integrated learning voting. The cumbersome work of labeling and the reuse according to different specific businesses are avoided. The applicability is improved.

A system and method of building a well construction knowledge mining system using an artificial intelligence ("AI") model and a plurality of databases, the method comprising: accessing, within the plurality of databases, a set of well construction files; wherein the set of well construction files comprise files in a plurality of formats; and wherein the set of well construction files comprise data relating to well construction operations; preprocessing the set of well construction files to generate a training data set, comprising: reformatting at least a portion of the data to standardized machine-readable data; labeling data in the machine-readable files using the model; and cleaning the data; and training the model, using supervised and unsupervised learning and the training data set, to build the well construction knowledge mining system.

This application relates to the field of computer technology and provides a regression data analysis method, computer device, and medium based on unsupervised learning. The method includes: analyzing regression logs using a natural language processing model to determine the natural language analysis results associated with the regression logs; determining the error type associated with the regression logs based on the natural language analysis results associated with the regression logs using an unsupervised learning model; and determining whether the regression logs contain anomalous regression test cases based on the natural language analysis results associated with the regression logs using an anomaly detection model, and, when the regression logs contain the anomalous regression test cases, determining the error type associated with the anomalous regression test cases. This provides efficient error localization and saves on localization components, thus helping to improve verification efficiency.

The application discloses a photovoltaic image defect classification method based on a transfer learning and unsupervised learning method. The method performs transfer learning through a pre-training model obtained on a general image dataset to establish an initial defect classification model; then a large number of collected unlabeled images are mapped into a feature space through the initial model, clustering is performed according to L2 distance in the feature space, and corresponding labels are obtained, so that the initial model is continuously retrained, and the accuracy index of the photovoltaic image defect classification model is improved. The application takes collected images of a certain photovoltaic power station in Hainan as test data, gives a detailed algorithm description, and designs test examples to evaluate and verify the defect classification performance of the photovoltaic image.

The invention provides a digital economy risk assessment method and system based on artificial intelligence, and the method comprises the steps: collecting risk data related to digital economy from a plurality of preset data sources, and fusing the risk data to form a risk analysis data set of the digital economy; performing risk feature extraction on the risk data set in a plurality of preset dimensions to obtain risk features of the digital economy in each preset dimension; obtaining an operation log of the digital economy, training a preset unsupervised learning model by adopting the operation log, and obtaining an abnormal score of the digital economy according to the unsupervised learning model; and obtaining a preset intelligent risk assessment model, and fusing the risk features and the abnormal score by using the preset intelligent risk assessment model to obtain a risk score of the digital economy. According to the technical scheme, the accuracy and reliability of the risk assessment result can be improved.

This invention discloses a predictive maintenance system for medical X-ray equipment, belonging to the field of medical equipment maintenance technology. It includes a multi-source data acquisition module, a feature construction module, a coupled degradation modeling module, a risk assessment module, and a maintenance strategy generation module. Based on voltage distortion rate, current harmonic components, and temperature field gradient, this invention extracts the standard deviation of voltage distortion rate, the total distortion coefficient of current harmonics, and the rate of change of temperature gradient after denoising using wavelet thresholding, and fuses them into a feature vector. Combining a long short-term memory network and a Bayesian network, it calculates a comprehensive degradation index of multi-parameter coupling; subsequently, it constructs a multi-parameter feature space and outputs a comprehensive risk level through unsupervised learning methods; finally, it generates targeted maintenance strategies based on the risk level and optimization algorithms. This invention achieves accurate prediction and intelligent maintenance of medical X-ray equipment faults, reduces sudden failures, lowers maintenance costs, and improves equipment operational reliability and diagnostic and treatment safety.