505 results about "Statistical model" patented technology

The invention relates to the field of energy consumption analysis, and discloses an AI-based energy consumption data analysis and prediction system, which comprises the steps of collecting environmental parameters and running states of equipment, dynamically identifying the current system working condition by using a working condition identification algorithm combining incremental clustering and historical mode matching, and predicting the energy consumption data. Collected data is divided according to time, space and working condition dimensions, multi-scale features are extracted, normalization parameters can be dynamically adjusted along with changes of working conditions, a drift index is calculated through comparison of a drift threshold value and historical distribution, an optimal normalization updating strategy is selected according to the drift index, the normalization parameters are dynamically updated, and energy consumption trend prediction is conducted through a statistical model. A prediction result is combined with a working condition label to carry out weighted correction, error analysis and deviation detection are carried out in combination with a drift index, working condition prediction and historical error data, and an analysis result is fed back to a working condition sensing module, a feature adaptive module and a normalization control module. The method has the advantage of improving the stability and reliability in a dynamic environment.

The invention discloses a slope deformation trend prediction method based on three-dimensional point cloud and deep learning, and relates to the technical field of geological disasters, and the method comprises the following steps: S1, obtaining multi-time sequence three-dimensional point cloud data of a target slope, S2, carrying out the preprocessing, obtaining a standardized time sequence point cloud data set, and carrying out the prediction of the deformation trend of the target slope. S3, extracting slope deformation characteristic parameters from the standardized time sequence point cloud data set, S4, constructing a prediction model, S5, integrating the data into a model training sample, and training and optimizing the deep learning prediction model, and S6, inputting the data into the trained deep learning prediction model, and outputting a deformation trend prediction result of a target slope. And S7, carrying out reliability evaluation on the deformation trend prediction result, and generating a final prediction report. According to the method, through the deep learning model fusing the CNN and the attention mechanism LSTM, the spatial relevance and the time dynamics of slope deformation can be mined at the same time, compared with a traditional statistical model, the prediction precision is improved, and the method is especially suitable for long-term deformation trend prediction.

The invention relates to the technical field of artificial intelligence and data analysis, in particular to an unsupervised anomaly detection method and system based on comparative potential fusion. The method aims at solving the problems that in the prior art, an unsupervised anomaly detection method is limited in feature expression ability, sensitive in noise, insufficient in potential feature discrimination and lack of statistical interpretability in detection results. According to the method, the global potential features generated by comparison learning and the self-encoder reconstruction residual error are fused, the statistical model is combined for self-adaptive threshold judgment, the problems of insufficient feature expression and high noise sensitivity in multi-source heterogeneous time series data anomaly detection are effectively solved, and the method has the advantages that the detection precision and robustness are improved, and the dependence on labeled data is reduced.

The invention relates to the technical field of power system scheduling, and discloses an intra-day look-ahead scheduling rapid solving method considering large-scale new energy cluster power generation volatility. Comprising the following steps of S1, new energy cluster space-time fluctuation scene generation based on a neuron cellular automaton, S2, power grid dynamic security domain definition and simplification based on a physical information neural network, S3, scheduling rapid optimization solution based on model prediction path integration, and S4, scheduling scheme dynamic elasticity and stability evaluation based on a Kupman operator theory. The new energy cluster space-time fluctuation scene generation method based on the neuron cell automaton can effectively generate a space-time scene reflecting large-scale new energy cluster power generation volatility, supports uncertainty analysis, has the advantages of being high in calculation efficiency and scene authenticity, and is suitable for large-scale new energy cluster power generation. The problem that scene generation is inaccurate due to the fact that a traditional statistical model ignores space-time coupling is solved.

An adaptive random access system and method with learned query optimization for compacted data files that enhances random access performance through machine learning and pattern recognition. The system incorporates a query pattern learning module that analyzes historical access patterns and user behavior to build statistical models of data usage. An adaptive estimator module improves location estimation accuracy by incorporating learned patterns rather than relying solely on mathematical calculations. A predictive boundary detector uses learned codeword patterns to more accurately identify boundaries in compacted data, reducing misalignment errors. An intelligent search engine coordinates optimization strategies including context-aware search string parsing and encoding strategy selection based on learned performance data. A dynamic codebook optimizer reorganizes sourceblock layout based on access frequencies and co-occurrence patterns to improve retrieval speed. An enhanced search cache implements predictive caching algorithms that anticipate user queries and proactively load relevant data.

The invention provides a remote sensing image target statistical method and system fusing a large language model and visual prompt driving. The method comprises the following steps: acquiring a remote sensing instance segmentation image to be processed and a visual prompt thereof; inputting a to-be-processed remote sensing instance segmentation image and a visual prompt thereof into the trained remote sensing image target statistical model, and outputting a remote sensing image target statistical result; the training comprises the following steps: introducing a large language model and visual cue into an encoder architecture of a GrondingDINO model to obtain a remote sensing image target statistical model; inputting a remote sensing instance segmented image and the visual cue thereof into an encoder, and outputting an image feature, a visual cue feature and a text feature; the feature intensifier carries out fusion processing on the output of the encoder; a language-guided query selection module calculates cross-modal query according to the fusion processing result, and a cross-modal decoder obtains a target statistical result of the image based on the fusion processing result and the cross-modal query; and training by using the training data and outputting the trained model.

The invention discloses a crested ibis habitat ecological quality trend analysis method and system, and relates to ecological quality monitoring. The method comprises the following steps: S1, constructing an intelligent sensing network, synchronously obtaining multi-source data of a habitat, identifying activity events of crested ibis, and generating a multi-dimensional habitat parameter table; s2, collecting environmental samples, and generating a microbial functional gene abundance matrix through metagenome sequencing and bioinformatics analysis; s3, taking the activity events of the crested ibis as behavior tags, and generating habitat function health indexes by coupling the parameter table and the matrix training machine learning prediction model; s4, performing spatial interpolation and trend analysis based on the habitat function health index to generate an ecological quality space-time evolution graph; and S5, based on the ecological quality space-time evolution graph, performing quantitative analysis by using a spatial differentiation statistical model, and generating a trend analysis report. By fusing multi-source data, real-time dynamic evaluation of habitat ecological quality and quantitative analysis of driving factors are realized, and a direct decision basis is provided for accurate protection.

The invention relates to the technical field of risk assessment optimization, and discloses a risk assessment method based on statistical model optimization. The method comprises the following steps: acquiring a running state data set of a target object containing multi-dimensional monitoring index time sequence data; and inputting the operation state data set into a pre-trained reference risk assessment model, and generating an initial risk score and risk distribution characteristics. And iteratively adjusting parameters of the reference risk assessment model through a dynamic correction algorithm according to the generated risk distribution characteristics, and generating an optimized risk assessment model. And adopting the optimized risk assessment model to re-assess the same operation state data set, and outputting a corrected risk score and a key risk area identifier. According to the method, the risk distribution characteristics of the specific data of the target object under the reference model are analyzed, and the model parameters are dynamically adjusted, so that the risk assessment standard better fits the actual risk mode, the accuracy and pertinence of risk identification are improved, and a more reliable basis is provided for a risk management and control decision.

The invention discloses a few-sample inductance core surface defect detection method based on model interaction, and belongs to the technical field of machine vision and industrial defect detection. The method comprises the following steps: S1, data acquisition and image preprocessing are carried out, and normal samples, labeled samples and unlabeled samples are constructed; s2, constructing an unsupervised statistical model based on statistical learning; s3, constructing a supervised semantic segmentation model; s4, inputting an inductance core image to be detected into the unsupervised statistical model and the supervised semantic segmentation model at the same time for processing, and generating a segmentation result; s5, detecting result differences are quantified; s6, performing parameter updating on the unsupervised statistical model; s7, generating a pseudo label based on an unsupervised statistical model; s8, carrying out weight updating on the supervised semantic segmentation model; and S9, inputting the processed to-be-detected images into the updated unsupervised statistical model and supervised semantic segmentation model in batches for detection to obtain a detection result, and analyzing and calculating system performance indexes.

The invention relates to the technical field of image analysis, in particular to a metal composite material surface defect intelligent detection method based on machine vision, which comprises the following steps: acquiring an original image and converting the original image into an observation matrix; decomposing the matrix into a low-rank matrix and a sparse matrix through a robust principal component analysis algorithm; utilizing a nuclear norm constraint low-rank matrix to establish a background statistical model, and utilizing a norm constraint sparse matrix; positioning a defect area in the sparse matrix and extracting a gray level co-occurrence matrix feature vector; performing connected domain analysis on the sparse matrix, calculating geometrical morphology parameters and evaluating a stress concentration coefficient; and establishing a self-adaptive decision model to carry out fusion judgment so as to judge the physical damage. According to the method, through low-rank sparse matrix decoupling and multi-dimensional statistical geometric feature fusion analysis, accurate stripping of weak defects and quantitative evaluation of physical damage attributes under a complex background are realized.

A facility for estimating a value relating to a occurrence is described. The facility receives a first occurrence that specifies a first value for each of a plurality of independent variables that include a distinguished independent variable designated to be monotonically linked to a dependent variable. The facility subjects the first independent variable values specified by the received occurrence to a statistical model to obtain a first value of the dependent variable. The facility receives a second occurrence that specifies a second value for each of the plurality of independent variables, the second value of the distinguished independent variable varying from the first value of the distinguished independent variable in a first direction. The facility subjects the second independent variable values specified by the received occurrence to the statistical model to obtain a second value of the dependent variable, the second value of the dependent variable being guaranteed not to vary from the first value of the dependent variable in a second direction that is opposite the first direction.

The invention relates to the technical field of vehicle damage detection and identification based on computer vision, and discloses a vehicle damage detection and identification method based on computer vision. The method comprises the steps of image acquisition, polarization image acquisition, Stokes parameter calculation, polarization feature extraction, anomaly evaluation, connected region analysis and the like. A polarization statistical model is established by setting an image coordinate system, collecting a multi-angle polarization diagram and calculating the polarization degree and the polarization angle of each pixel and taking an artificially selected nondestructive area as a reference, so that anomaly measurement and adaptive threshold segmentation are performed on the pixels, and a structured vehicle damage detection result is output in combination with corrosion, expansion and connected domain analysis. Physical interpretability and detection precision are enhanced by using polarization characteristics, recesses or scratches can be accurately identified even in a vehicle body area with a smooth surface or complex reflection, a standardized report containing position information and abnormality is provided, and automation and accuracy of vehicle damage assessment are effectively improved.

A bot detection service associated with an overlay network operates to score traffic as a probability of being a bot, as opposed to returning a binary classification (i.e., bot or human). According to the approach herein, scoring is determined through probability estimates, wherein a score (the probability) is based on considering a set of detections concurrently. In one embodiment, all (or substantially all) triggered (current) threat detections contribute to the score. The preferred approach penalizes requests that fail all (or substantially all) combinations of detection algorithms. According to a further feature, an automated tuning (autotuning) is also applied, e.g., using real-time empirical statistical models, to adapt the measurement of false positive probability for one or more threat detection algorithms to suit customer traffic trends. The approach herein is also extensible to include any number of future threat detection algorithms.

The invention provides a laser stripe center extraction method based on gray coefficient binarization, and aims to solve the problems of non-uniform brightness distribution of laser stripes, difficulty in extraction of weak stripes, breakage of center lines and the like. The method comprises the following steps: enhancing an image; realizing self-adaptive threshold segmentation through a local gray scale statistical model and a peak variable coefficient by using a gray scale coefficient binarization method; extracting a sub-pixel-level center point by combining a secondary positioning method of skeleton constraint; and carrying out fitting smoothing by adopting bicubic interpolation and a smooth spline method. According to the method, the problem of extraction of strong and weak stripes under complex working conditions is effectively solved, and the precision, connectivity and robustness of stripe center positioning are remarkably improved while background noise is suppressed.

The invention relates to the technical field of image processing, in particular to a composite board production process monitoring method and system. The method comprises the following steps: acquiring a side image of a to-be-detected metal composite plate, and dividing the side image into a first region and a second region; constructing a first texture statistical model for the first region, constructing a second texture statistical model for the second region, and constructing an interpolation texture statistical model according to the first texture statistical model and the second texture statistical model; traversing the image blocks of the side image, and determining a spectrum anomaly score graph of the current image block according to the observation power spectrum of the current image block, an interpolation average power spectrum model corresponding to the central ordinate of the current image block and an interpolation power spectrum standard deviation model, so as to obtain a residual image of the to-be-detected metal composite plate, and monitoring the production process of the metal composite plate by using the residual image. According to the technical scheme, the production process of the metal composite plate can be monitored.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a data processing and decision-making method, device, equipment and medium, and the method comprises the steps: obtaining multi-dimensional source data, carrying out the standardization processing, screening the standardization data based on a decision-making scene, and obtaining a core index set, the method comprises the following steps: establishing and optimizing indexes, mining association characteristics among the indexes, constructing and optimizing a dynamic statistical model, carrying out standardization processing on newly added multi-dimensional source data, obtaining a key decision index value by utilizing the dynamic statistical model, and carrying out comparison judgment on the key decision index value and a preset decision threshold value, and generating a decision scheme by combining the comparison judgment result with a preset scheme generation mechanism. According to the method, multi-scene adaptive support and real-time decision optimization are realized through unified multi-dimensional data standardization, dynamic scene-driven core index screening and association characteristic mining, real-time model updating and closed-loop decision scheme generation.

The invention discloses a slope instability early warning method, and relates to the field of slope monitoring, and the slope instability early warning method based on a multivariate regression statistical model and a quality control chart comprises the steps: building the multivariate regression statistical model between slope physical quantity monitoring data and environmental factors, introducing a risk rate index, and carrying out the quantitative evaluation of a slope state, meanwhile, the change trend of the physical quantity of the side slope is visually reflected by using a quality control chart, and grading early warning indexes are set. Aiming at the problem of low early warning precision of slope instability in the prior art, the invention provides the early warning method for slope instability, and the method comprises the steps: building a multiple regression statistical model between slope physical quantity monitoring data and environmental factors, and introducing a risk rate index to carry out the quantitative evaluation of the slope state, thereby achieving the early warning of slope instability. Meanwhile, the change trend of the physical quantity of the side slope is visually reflected through the quality control chart, graded early warning indexes are set, and the early warning precision is improved.

The invention relates to the technical field of industrial information processing of production logistics scheduling, in particular to an intelligent material scheduling decision-making method and system based on a large language model, and the method comprises the steps: obtaining historical scheduling data, a production plan text, real-time material state information, production rhythm information and production main data; constructing a time statistical model and analyzing the plan text to obtain a scheduling constraint set; generating a candidate transfer time window after consistency verification, and determining a target time window; and generating a timestamp sequence, aligning and correcting according to rhythms, and outputting a scheduling instruction sequence. Constraint conflicts and non-executable instructions can be reduced, and delivery and beat stability is improved.

The invention relates to the technical field of logistics supervision, and discloses a logistics cloud platform information transmission supervision method and device based on big data, and the method comprises the following steps: receiving a sensor data flow of a target carrier vehicle; dividing a plurality of dynamic driving scene segments according to the sensor data; determining a target dynamic driving scene fragment at the current moment, and constructing a multi-dimensional base line feature statistical model; inputting the data points at the current moment into a multi-dimensional base line feature statistical model, and calculating abnormal scores of the data points; when the abnormal score is greater than a preset risk alarm score, generating a risk event record; and generating an early warning instruction based on the risk event record, and sending the early warning instruction to a logistics monitoring center and a vehicle-mounted terminal of the target carriage carrying vehicle. According to the embodiment of the invention, a normal and abnormal boundary is automatically adjusted according to a specific driving scene, false alarm and missing alarm caused by a fixed threshold value are remarkably eliminated, accurate monitoring of dynamic driving behaviors is truly realized, and an original monitoring blind area is eliminated.

The invention relates to the technical field of computer vision and pattern recognition, in particular to an online classroom concentration degree monitoring method for style disturbance privacy protection, which comprises the following steps: acquiring a video data set, introducing style disturbance through a style migration technology, and establishing an online classroom data set; obtaining a corresponding visual privacy protection score through the online classroom data set; positioning a face area in the online classroom data set to obtain a face detection rate; face key point detection is carried out according to the face area, and behavior indexes and face advanced semantic features are determined; inputting the facial key points, the behavior indexes and the facial advanced semantic features into a concentration degree prediction model, and outputting a concentration degree recognition rate; and establishing a correlation statistical model, and balancing visual privacy protection and concentration recognition in combination with a face detection rate and a concentration recognition rate. Namely, a proper visual privacy protection coding range is selected, and the problem that the online classroom concentration degree monitoring application performance is seriously reduced due to excessive privacy protection is avoided.

The invention discloses an interactive multi-model aircraft filtering algorithm and system driven by reinforcement learning, and the algorithm comprises the steps: firstly constructing a multi-model state prediction set composed of a Singer model, a current statistical model and a Jerk model, and presetting a state transition probability matrix according to the state evolution correlation between the models, so as to define the interaction relation between the models; in the filtering stage, state estimation preliminary fusion of the three maneuvering models is achieved according to a traditional interactive multi-model algorithm, the fusion proportion of each model is adjusted in real time in combination with a weight correction vector output by a reinforcement learning strategy function, and strategy iteration optimization is conducted through a reward function containing an error improvement item, a matching item and a balance item. The method can significantly improve the filtering precision and fusion stability of the aircraft maneuvering target.

The embodiment of the invention discloses a specific scene sales volume prediction method and device, equipment and a medium, and relates to the technical field of data analysis, and the method comprises the steps: obtaining customer historical sales data, scene reference data and prediction parameters, and the prediction parameters comprise the number of point locations and a to-be-predicted date; determining a historical data weight coefficient and a historical data sufficiency compensation factor of the historical sales data of the customer; according to the historical sales data of the customer and the date to be predicted, seasonal and time adjustment factors are determined; determining a customer deviation factor according to the customer historical sales data and the scene reference data; and determining a predicted sales amount corresponding to the to-be-predicted date by the advanced statistical model based on the customer historical sales data, the scene reference data, the prediction parameters, the number of point locations, the historical data weight coefficient, the historical data sufficiency compensation factor, the seasonal and time adjustment factor and the customer deviation factor. Therefore, multi-dimensional related data can be comprehensively considered, and the prediction accuracy is effectively improved.

Embodiments of the technology described programmatically decrease the number of spam Uniform Resource locators (URLs) that are accessed from untrusted domains when the subdomain prefix is above a threshold probability of having been randomly generated. In this regard, prior to adding a discovered set of URLs to a crawl queue of a web crawler, the URLs are filtered into URLs from trusted domains and untrusted domains determined by a statistical model. The trusted domain URLs are added to the crawl queue, and the remaining URLs are sandboxed to filter out spam URLs. The subdomain prefixes of the sandboxed URLs are applied to a neural network to determine the probability that the subdomain prefixes are randomly generated. When a subdomain prefix is above a threshold probability of having been randomly generated, the subdomain is determined to be a spam subdomain and can be blocked.

The invention relates to the technical field of computer-aided engineering, and discloses an intelligent water conservancy design simulation system based on digital twinning, which comprises a parameterized geometric feature extraction module, a reduced-order model database, a tangent space linear deduction module and a flow field reconstruction module. According to the method, nonlinear flow field solution is dimensionally reduced into deterministic matrix vector multiplication, traditional statistical regression and iterative solution are replaced, it is ensured that a reconstruction result evolves in the tangential direction of a physical gradient, non-physical guess of a statistical model in a sparse sample area is avoided, and the calculation accuracy is improved. And high-fidelity flow field reconstruction with real-time performance and physical evolution conservation is realized.

The invention provides an SAR target screening method based on binary super-dimensional calculation, and relates to the technical field of real-time target detection. The method comprises the following steps: directly carrying out real and virtual part solution and sign function quantization on I / Q dual-channel complex data of an original echo of a synthetic aperture radar (SAR) to obtain a binary fusion matrix; constructing an abnormal profile based on a preset background statistical model, and adaptively dividing the quantized data into multiple segments according to the abnormal profile; performing super-dimensional mapping on each segment through an independent random binary projection matrix, generating segmented super-vectors, and splicing the segmented super-vectors into a complete sample super-vector; and finally, target discrimination is realized by calculating the Hamming distance between the target and a pre-stored background / target prototype super vector. The quantization logic can be dynamically switched according to the target size, and the problem that a single quantization strategy is poor in adaptability is effectively solved. And through an adaptive segmentation mechanism of energy perception, the weak target characterization capability is effectively enhanced, and the screening accuracy under a strong clutter background is improved.

The invention relates to the technical field of renewable energy infrastructure planning, in particular to a centralized photovoltaic power station site selection optimization method under multiple factors. Comprising the steps of collecting and processing multi-source geographic space data including meteorological conditions and climate disaster risk data; rejecting unsuitable areas through constraint rejection analysis; performing normalization and weighted aggregation on the meteorological conditions and the climate disaster risk data, and constructing a climate suitability index layer; establishing a multi-standard evaluation framework, determining each criterion weight by adopting a multi-standard decision algorithm, and generating a preliminary site power generation potential map through weighted stacking; correcting the power generation potential map by adopting a bivariate local Moran index analysis and geographically weighted regression model; and identifying and dividing an optimal candidate site on the corrected power generation potential map. According to the method, meteorological conditions and climate disaster risks are quantified and integrated, and the evaluation result is corrected by using the spatial statistical model, so that the scientificity and reliability of site selection decision are remarkably improved.

Disclosed is a system and method for controlling and optimizing a fleet of semiconductor process systems using advanced digital twin technology. Each process system has a specific digital twin constructed from various subsystem digital twins and calibrated with real-time sensor data. An AI machine leverages these digital twins to create a fleet-level system digital twin. The AI machine continuously trains a policy neural network to autonomously generate and adjust process recipes. Both individual and fleet digital twins, incorporating statistical models, determine if a specific process system falls within the statistical distributions of the fleet, ensuring consistent and optimal performance.

The invention discloses a marine ranch fish school monitoring method based on acoustic imaging, and belongs to the field of fish school intelligent monitoring, and the method comprises the steps: obtaining a noise interference component from compensated coverage range data, correcting signal fusion through employing Kalman filtering, and obtaining a fusion signal with noise suppression; acquiring a trajectory tracking sequence from the three-dimensional motion vector, and predicting motion complexity by adopting particle filtering to obtain centimeter-level accurate positioning coordinates; extracting a density model and body length estimation parameters from the reliable monitoring data set, and fusing biomass measurement logic to obtain a final fish school biomass value; aiming at the final fish school biomass value analysis distribution mode, correcting deviation by adopting a statistical model, and determining an optimized biomass distribution diagram; and generating an alarm signal according to the optimized biomass distribution diagram, and if the biomass distribution is judged to be abnormal, triggering real-time notification to obtain monitoring response data. According to the invention, the precision and real-time performance of fish school monitoring are obviously improved.

The invention relates to the technical field of optical fiber sensing signal processing, in particular to a DAS signal floor noise elimination method, system and equipment based on statistical analysis, and the method comprises the steps: initializing system parameters, and loading a DAS application field data matrix; performing slicing and frequency domain transformation on the DAS original data; dynamically determining a peak threshold value, and performing adaptive peak searching according to the peak threshold value; sorting the identified and screened local maximum values in a descending order, and selecting frequencies corresponding to the local maximum values as main frequency candidates; performing clustering analysis on the selected dominant frequency candidates; calculating the cumulative proportion of each main frequency in the total statistics, selecting a center frequency, and forming the multi-frequency band elimination of the monitoring unit by using band elimination frequency bands formed by different center frequencies; and adding the multi-frequency band elimination to a statistical filtering frequency band set of all the point locations, storing the statistical filtering frequency band set of all the point locations as a statistical model, and performing background noise elimination on the DAS original signal based on the statistical model.

The invention discloses a machine abnormal sound detection method based on enhanced self-coding reconstruction and probability modeling, and aims to solve the problem that in an existing unsupervised machine abnormal sound detection method based on a generative adversarial network, the time-frequency feature reconstruction result of machine operation sound is too smooth, so that the machine abnormal sound detection capability is insufficient. According to the method, time-frequency feature extraction is carried out on collected machine operation sound signals, modeling is carried out on machine operation sound time-frequency feature distribution under a normal working condition in combination with a probability statistical model, and the time-frequency features of the machine operation sound under the normal working condition are reconstructed and learned by using an auto-encoder of a structure enhancement mechanism. The method realizes unsupervised machine abnormal working condition determination by combining the reconstruction error and the probability determination result, can improve the determination stability and robustness of abnormal sound detection, reduces the model complexity, and is suitable for application scenarios such as industrial equipment operation state monitoring and fault early warning.