28 results about "Background distribution" patented technology

Provided are an anomaly detection method and system for multi-source heterogeneous data, an electronic device, a vehicle, a computer-readable storage medium, a computer program product, and a computer program. The method comprises: performing statistical modeling on multi-source heterogeneous data, and obtaining background distribution features of multi-source heterogeneous data distribution through a data splitting method; preprocessing the background distribution features by using a preset sliding window to obtain a background image sequence on a specific time series; on the basis of the size of a target in the background distribution features, performing adaptive partitioning on the background image sequence to obtain an adaptive partitioning result, and identifying single source points of each partition in the adaptive partitioning result through a decoupling representation method; and on the basis of the identified single source points, determining the location of anomalous data in the background image sequence, and on the basis of a comparison calculation result of the multi-source heterogeneous data and the background image sequence from which the anomalous data is removed, obtaining an anomalous data location of the multi-source heterogeneous data.

The invention relates to an intelligent short message template generation method and system based on a large language AI model, and the method comprises the steps: extracting cross-cultural communication frequency, sentence pattern preference analysis results and screen size adaptation data from social media interaction data and equipment use logs of target audiences, and generating a cultural background distribution matrix; identifying regional culture features in the culture background distribution matrix to obtain a taboo matching result; generating an expression habit preference matrix according to the updated culture background distribution matrix; generating a preliminary short message template according to the expression habit preference matrix and the symbol semantic mapping table, and outputting an adjusted template set conforming to message length control; analyzing the acceptability of the adjusted template set on the language conciseness requirement and the interactive button layout, and generating a new template set; evaluating a text alignment mode of the new template set; and screening candidate short message templates according to the information definition score. According to the invention, the accuracy and acceptability of cross-culture short message communication can be effectively improved, and the participation degree of audiences is enhanced.

The invention discloses an ultrahigh-sensitivity sample component evaluation and traceability method and device. The method comprises the following steps: acquiring a sample, and carrying out nucleic acid extraction, library construction, capture enrichment and sequencing to generate sequencing data; preprocessing the sequencing data to obtain high-quality sequencing data; identifying SNP loci and genotypes thereof in the high-quality sequencing data, and constructing an SNP combination database; carrying out quantitative statistics on the double allelic genotypes of the SNP sites, and calculating the variation abundance of secondary alleles; constructing an SNP site variation abundance background distribution model according to the genotype information and allele variation abundance of the SNP sites; and performing cross contamination assessment on the sample by using the constructed SNP combination database and the variation abundance background distribution model. According to the method, qualitative evaluation of multi-source components in the sample, quantitative calculation of the cross contamination proportion and traceability analysis of non-self sources are achieved.

Disclosed in the present invention are a few-shot point cloud semantic segmentation method based on difference enhancement, and a related device. The method comprises: obtaining various initial prototypes on the basis of support set features and corresponding support set masks; calculating similarities between the initial prototypes and query set features, so as to obtain probability distributions of the query set features belonging to foreground and background categories; inverting foreground distributions on the basis of background-foreground difference enhancement, combining same with current background distributions to obtain accurate background probability distributions, and performing integration to obtain a reliable probability distribution of the categories as a whole; transforming the query set features by means of a feature aggregation module, so as to obtain aggregated query set features; on the basis of the reliable probability distribution and the aggregated query set features, performing aggregation by means of a prototype rectification module, so as to obtain pseudo prototypes; and on the basis of the pseudo prototypes, expanding support set data by means of the prototype rectification module, so as to obtain corrected prototypes, and obtaining a point cloud segmentation result on the basis of the corrected prototypes. The present invention achieves a better segmentation effect.

The invention discloses a high-quality full employment distribution prediction system and method, and relates to the technical field of employment prediction. The system comprises a data integration platform module, a prediction model construction module, a group identification and occupational planning module, a labor flow prediction module, an occupational development trend prediction module and an employment difficulty group monitoring and early warning module. An advanced big data analysis and machine learning technology is applied to construct an innovative prediction model, and the model can process and analyze large-scale multi-dimensional data including industry classification, occupational transition, educational background distribution and skill requirements, can comprehensively reflect the dynamic change of an employment market in real time, and has a good application prospect. Unstructured employment data is deeply processed by means of a machine learning technology, employment types are divided into four types of high-quality full employment, full but non-high-quality employment, insufficient employment and unemployment, and unemployment risk groups are identified, so that more accurate employment prediction and personalized occupational planning suggestions are provided, and the employment prediction efficiency is improved. Scientific decision-making basis is provided for the government and enterprises, and timely strategy adjustment is made.

The invention provides a deep space background-oriented space target sequence image generation method and device, electronic equipment and a medium, and relates to the field of space target optical image simulation. The method comprises the steps of obtaining pose data of a space target in an observation time period through simulation based on pre-defined initial parameters; screening imageable fixed stars from the reference star library according to the field angle and the detectability of the on-orbit optical camera; based on the position data of the imageable fixed star, generating a deep space background image matched with the observation view field of the space target through brightness simulation and coordinate system transformation; generating a time sequence rendering image through a rendering engine by using the three-dimensional model and the pose data of the space target; and superposing the deep space background image and the time sequence rendering image according to foreground and background distribution, and adding noise to obtain a simulation sequence image.

The invention discloses a background analysis method and system based on atmospheric greenhouse gas monitoring data. The method comprises the following steps: collecting greenhouse gas monitoring data through monitoring equipment; generating an intelligent agent about the monitoring space according to the distribution condition of the monitoring data; constructing the monitoring data of the intelligent agent into a composite state formed by superposing background data and interference data; and carrying out complex state evolution analysis among different intelligent agents, and carrying out background data reconstruction on the monitoring space to obtain a background analysis result of the atmospheric greenhouse gas monitoring data. The background distribution of the atmospheric greenhouse gas can be reconstructed more accurately and stably under the scenes of complex interference, multi-source isomerism and remarkable boundary effect, and the scientificity and precision of background judgment are improved.

The application discloses a small sample point cloud semantic segmentation method based on difference enhancement and related equipment, and the method comprises the following steps: obtaining initial prototypes of various categories according to support set features and corresponding support set masks; calculating the similarity between the initial prototypes and query set features to obtain the probability distribution of the query set features belonging to foreground and background categories; taking the inverse of the foreground distribution according to foreground and background difference enhancement, combining the current background distribution to obtain accurate background probability distribution, and integrating to obtain reliable probability distribution of the entire category; the query set features are subjected to transformation processing through a feature aggregation module to obtain aggregated query set features; the reliable probability distribution and the aggregated query set features are subjected to aggregation processing through a prototype correction module to obtain pseudo prototypes; the support set data is expanded according to the pseudo prototypes through the prototype correction module to obtain corrected prototypes, and the segmentation result of the point cloud is obtained according to the corrected prototypes. The application obtains better segmentation effect.

This invention relates to the field of defect detection technology, specifically to a PCB defect detection method for industrial incremental scenarios. It includes a feature fusion method based on a lightweight segmentation strategy that combines random pruning with separate processing of strong and weak features. This strategy simplifies redundant computation by using a feature selector, and differentiates and recombines defect features of varying saliency during the feature fusion stage. This significantly improves inference speed while maintaining the precision of segmentation, solving the problems of high computational cost and difficulty in capturing minute defects in existing methods. The method also includes an incremental learning approach employing a background classifier adaptation mechanism and local semantic distillation. Class-specific regularization and spatially weighted logical alignment distillation work synergistically. By dynamically calibrating the background prediction logic and constructing a pixel-level semantic relevance matrix, it achieves deep alignment between new and old knowledge and background distribution. This effectively solves the catastrophic forgetting problem caused by the evolution of PCB background texture in existing incremental learning methods, significantly enhancing detection stability and the adaptability of the enhanced model.

The application discloses a polarimetric SAR ship detection method based on fusion of statistics of Wasserstein distance, and relates to the field of polarimetric synthetic aperture radar ship target detection and identification. The method comprises the following steps: S1, acquiring polarimetric synthetic aperture radar data of an original ship and performing filtering processing; S2, performing feature extraction on the polarimetric synthetic aperture radar data after filtering processing to obtain three polarization features; S3, calculating a statistics map of Wasserstein distance of each pixel of a to-be-detected image by using the three polarization features; S4, screening a sea surface background on the statistics map by using a feature prior method, estimating a sea surface background distribution by using a kernel density method combined with a constant false alarm rate detection method, obtaining a threshold according to a preset false alarm rate, and completing pixel-by-pixel judgment on the sea surface background. The application significantly enhances the target / background contrast, and can still achieve high recall, low missed detection and good robustness in complex scenes such as strong sidelobes, strip artifacts and dense targets.

The application discloses a kind of intelligent behavior detection method and system based on motion feature enhancement, construct based on adaptive mixture Gaussian model, the Mahalanobis distance of pixel point and background distribution is calculated and model weight is dynamically updated, realize the accurate decoupling and separation of foreground motion region in video frame;Then, the foreground mask obtained initially is based on the connected domain analysis of area threshold to filter out discrete noise, and the morphological closing operation of structure element adaptation is used to fill target internal cavity and repair edge fracture, to generate the high signal-to-noise ratio of motion region binary graph;Again, the purified binary graph is mapped as high visual saliency color heat map, it is weighted linearly fused with original RGB video frame, the fusion feature map is used to guide deep learning model to pay attention to motion region, and through double threshold detection strategy, the perception and identification ability of system to small target and hidden uncivilized behavior under complex dynamic scene is greatly improved.

The present invention relates to a method and system for generating intelligent SMS templates based on a large language AI model. The method comprises: extracting cross-cultural communication frequency, sentence preference analysis results, and screen size adaptation data from the target audience's social media interaction data and device usage logs to generate a cultural background distribution matrix; identifying regional cultural characteristics in the cultural background distribution matrix to obtain taboo matching results; generating an expression habit preference matrix based on the updated cultural background distribution matrix; generating preliminary SMS templates based on the expression habit preference matrix and a symbol semantic mapping table, and outputting an adjusted template set that meets message length control; analyzing the acceptance of the adjusted template set in terms of language conciseness requirements and interactive button layout to generate a new template set; evaluating the text alignment of the new template set; and screening candidate SMS templates based on information clarity scores. The present invention can effectively improve the accuracy and acceptance of cross-cultural SMS communication and enhance audience engagement.

The invention discloses a DETR-based multispectral methane gas leakage detection method, the method can effectively detect and position methane gas leakage, a DETR framework is adopted, an end-to-end method for detecting methane leakage gas by using a hyperspectral image is designed, a spectral feature generation and query optimization module in the method improves the performance of the traditional Transform, and the performance of the hyperspectral image is improved. A spectrum sensing linear filter is used for positioning potential methane hot spots of a hyperspectral image, improved query representation enables coding to be more effective, and by strategically selecting related pixels in a spectral domain, background distribution is whitened better, and a methane gas area is amplified better. The method provided by the invention has certain significance for accurately detecting methane gas leakage.

A method for identifying a defect within a cement layer of a multistring wellbore includes deploying a gamma scanner into the multistring wellbore, the gamma scanner including at least one source and at least one detector, the at least one source emitting radiation into the multistring wellbore and the at least one detector receiving backscatter radiation. The method also includes obtaining, from the gamma scanner, a count rate associated with at least one region of interest of the multistring wellbore. The method further includes identifying, based at least in part on data acquired from the gamma scanner, a background profile for the multistring wellbore. The method includes removing the background profile from the count rate. The method further includes identifying, within the at least one region of interest, a defect within the cement layer.

The application provides a space target sequence image generation method and device for a deep space background, electronic equipment and a medium, and relates to the field of space target optical image simulation. The method comprises the following steps: obtaining pose data of a space target in an observation period through simulation based on predefined initial parameters; selecting imageable stars from a reference star library according to the field of view and detection capability of an on-orbit optical camera; generating a deep space background image matched with the observation field of view of the space target through brightness simulation and coordinate system transformation based on the position data of the imageable stars; generating a time sequence rendering image through a rendering engine by using a three-dimensional model and pose data of the space target; and superimposing the deep space background image and the time sequence rendering image according to the foreground and background distribution, and adding noise to obtain a simulation sequence image.

The application discloses a kind of based on deep learning's drag chain cable life prediction method and system, including the following steps: obtaining drag chain cable operation data and motion state data, division drag chain motion cycle and carry out phase normalization, form cycle latent state sequence by deep learning coding;Establish historical state return relationship and cycle historical state matrix;Perform Cadzow structured low rank reconstruction, combine spectral background distribution and historical state return relationship to form cycle benchmark low rank structure and candidate fatigue evolution component;Perform structure back projection and form cycle return residual state;Cross-cycle consistency correction is carried out to candidate fatigue evolution component, and fatigue evolution state is formed;Construct fatigue evolution trajectory, and obtain residual life prediction value by deep learning prediction, output drag chain cable life prediction result.The application can distinguish recoverable cycle response and continuous fatigue evolution, improve the accuracy and stability of residual life prediction of drag chain cable.

The invention discloses a foreground object recognition and correction method based on background distribution self-adaption, which realizes accurate quantification of background prejudice and self-adaption data construction, and improves the pertinence and effectiveness of correction from the source. By analyzing a small number of real scene samples, the method can accurately describe the intensity and diversity of background prejudice features in a specific scene. The correlation and effectiveness of the training data are ensured, subsequent model training can respond to indications, and a solid foundation is laid for fundamentally correcting background prejudice and improving model robustness. An original feature destruction and double-model cooperative training mechanism significantly enhances the recognition and stripping capability of background prejudice features. According to the method, the performance and reliability of a foreground object recognition model in a real deployment scene are remarkably improved, and powerful technical support is provided for robustness application of artificial intelligence in key fields such as safety, automatic driving and medical image analysis.

The application discloses a foreground object recognition and rectification method based on background distribution self-adaption, realizes accurate quantification and self-adaptive data construction of background bias, and improves the pertinence and effectiveness of rectification from the root. Through analysis of a small amount of real scene samples, the method can accurately depict the intensity and diversity of the background bias characteristics in a specific scene. This not only ensures the relevance and effectiveness of the training data, but also enables the subsequent model training to be targeted, laying a solid foundation for fundamentally correcting the background bias and improving the robustness of the model. The unique feature destruction and double-model collaborative training mechanism significantly enhances the recognition and stripping ability of the background bias characteristics. It significantly improves the performance and reliability of the foreground object recognition model in real deployment scenarios, and provides strong technical support for the robust application of artificial intelligence in key fields such as safety, autonomous driving and medical image analysis.

The invention discloses a vehicle-mounted underway high-precision greenhouse gas two-dimensional distribution monitoring system and method, and relates to the technical field of environment monitoring. According to the vehicle-mounted underway high-precision greenhouse gas two-dimensional distribution monitoring method, gas is alternately collected through double-path sampling probes arranged at different heights of a vehicle roof, and instantaneous interference of exhaust emission of motor vehicles on a road is removed by combining an underway position and real-time meteorological data which are synchronously obtained and based on concentration difference and meteorological information by utilizing a specific algorithm, so that the real-time distribution of the greenhouse gas is realized. Therefore, the real environment background greenhouse gas concentration is extracted. According to the method, the high-precision two-dimensional greenhouse gas concentration distribution diagram of the underway area is inverted through spatial interpolation processing according to the purified background concentration data, credible quantification of regional scale greenhouse gas spatial distribution is realized, a key technical means is provided for accurate measurement and traceability of carbon emission, and the method is suitable for popularization and application. The core problem that the existing mobile monitoring technology is difficult to accurately reflect regional background distribution due to self-path pollution is effectively solved.

The application discloses a weakly supervised semantic segmentation method and device based on commonality-specificity supervision mechanism, establishes a contrast convolution module, utilizes the convolution cognitive difference of different receptive fields in an image to identify the boundary area with ambiguity in the image, and overcomes the problem of fuzzy segmentation boundary in the weakly supervised semantic segmentation task; a commonality-specificity supervision module is established, a commonality supervision mechanism is utilized to find the similar structural background distribution between different category images, a specificity supervision mechanism is utilized to identify the prominent area in the image distribution, semantic segmentation of a target object is realized, the positioning area is improved to be sparse, and the segmentation boundary is optimized; a knowledge gap module constructs a structure distribution enhanced contrast generated image, and the knowledge gap between the contrast generated image and the category image effectively overcomes the incomplete activation corresponding relationship in mainstream methods, and improves the image level weakly supervised semantic segmentation performance.

The invention discloses a ship detection method based on Warsestein distance fusion statistics, and relates to the field of polarized synthetic aperture radar ship target detection and identification. The method comprises the following steps: S1, acquiring polarized synthetic aperture radar data of an original ship and carrying out filtering processing; s2, performing feature extraction on the filtered polarized synthetic aperture radar data to obtain three polarized features; s3, using the three polarization features to calculate a statistical diagram of the Warisstein distance of each pixel of the image to be detected; and S4, screening a sea surface background on the statistical magnitude map by using a feature prior mode, estimating the distribution of the sea surface background by using a kernel density method in combination with a constant false alarm rate detection method, solving a threshold value according to a preset false alarm rate, and completing pixel-by-pixel judgment on the sea surface background. According to the method, the target / background contrast is remarkably enhanced, and high recall, low leak detection and good robustness can still be realized in complex scenes such as strong side lobes, stripe artifacts and dense targets.

The invention discloses a three-dimensional space-time kernel density estimation method based on adaptive bandwidth, and the method comprises the steps: determining the boundary contour of a research region in a geographic space, determining the lower bound and upper bound of the occurrence time of a target event, constructing an effective space-time cube, and collecting a target event sample in the interior, thereby obtaining a target event data set. And inputting the data set to calculate and fit the real background distribution of the target event, namely a joint probability density model. And carrying out time-by-time slicing processing on the joint probability density model to obtain a space condition probability density model. And respectively carrying out qualitative analysis and quantitative analysis on the two models according to requirements, and analyzing a spatial distribution rule and a time evolution characteristic of a high-incidence area (hot area) of a target event. The adaptive bandwidth change is introduced into the traditional algorithm, so that the algorithm provided by the invention has better fitting result, more accurate prediction performance, more concentrated hot area identification capability and more robust extreme event impact absorption capability.

The invention discloses a daytime star point detection method based on spatio-temporal feature context enhancement, which comprises the following steps: designing a frame difference-optical flow guided spatio-temporal feature context enhancement module, extracting spatial features, frame difference features and optical flow motion features of continuous frame star point targets through a sliding observation window, and supplementing the spatial features, the frame difference features and the optical flow motion features to a data-driven network through multi-flow feature fusion; constructing a synthetic star map data set covering various noise and background distributions, and adopting U-Net as a backbone network to realize a coding and decoding architecture to carry out star point segmentation training; the performance of the method is verified through a simulation experiment and an external field star observation experiment. According to the method, the receptive field of the star points in the time dimension is expanded, the dark and weak star point features are enhanced, non-stationary background interference is restrained, the detection precision and robustness of the dark and weak star points under the complex background in the daytime are remarkably improved, and the method is suitable for daytime dark and weak star point detection of an all-day star sensor.

The application provides a spatial domain division-based variational autoencoder and spatial clustering anomaly identification method, and belongs to the field of marine mineral resources exploration and geochemical anomaly identification. Multivariate features and spatial adjacency relationship are adopted to divide local background domains, a variational autoencoder is used to learn local background distribution in each spatial domain, a Mahalanobis distance is used to comprehensively form multi-dimensional reconstruction errors to form an anomaly score, and finally, discrete anomaly points are converted into continuous anomaly areas through density clustering and boundary processing, so as to significantly improve the anomaly identification precision under complex sea area background conditions, and to realize the purposes of reducing the influence of artificial interpretation and improving the accuracy of regionalization results of ore-prospecting target area delineation.

The application discloses a kind of based on frequency domain enhancement and domain self-adapting migration's kite line detection method, it is related to transmission line intelligent inspection technical field.The method takes YOLO26 as baseline detection network, integrates wavelet transform convolution module in backbone network shallow layer, carries out two-dimensional discrete wavelet decomposition to feature map and reconstructs after depth separable convolution is applied on high-frequency subband, to enhance the horizontal and vertical high-frequency edge response of kite line;Cross-layer frequency domain attention fusion module is inserted in neck network P3 and P4 scale output node, and multi-scale convolution aggregation, wavelet domain high-frequency channel attention weighting and residual fusion are sequentially executed;Two-stage domain self-adapting migration strategy is used, the first stage freezes backbone shallow layer and fine-tunes deep layer and neck to adapt low-frequency background distribution, and the second stage unfreezes all networks and enables wavelet transform convolution to reduce learning rate and adapt kite line high-frequency feature;NWD-SIoU hybrid loss is used as boundary box regression loss;And the image containing kite line in training set is improved sampling weight, and kite line area replication pasting enhancement is implemented.The application effectively solves the problem of missed detection and inaccurate positioning caused by extreme aspect ratio, minimum size and cross-domain semantic gap of kite line, and is suitable for unmanned aerial vehicle transmission line intelligent inspection in kite line automatic identification.

The present application relates to the technical field of carbon footprint uncertainty analysis, and particularly relates to a carbon footprint uncertainty calculation method and electronic equipment, the method comprising: automatically generating a plurality of rules from unstructured text comprising carbon footprint historical data; fuzzy weighted synthesis of the plurality of rules in a scenario to generate a credibility distribution; extracting a global range and a scenario range according to a credibility threshold, and truncating the probability density function of the obtained truncated normal distribution on the global range to obtain a background distribution; equally dividing the scenario range into three scenario sub-intervals, and calculating the scenario weights using the background distribution; conditionally truncating sampling for each scenario sub-interval, and independently running Monte Carlo simulation to output the corresponding mean and variance; and weighting and synthesizing the Monte Carlo simulation results of each scenario through the corresponding scenario weights to obtain the uncertainty of the carbon footprint. Compared with the prior art, the present application has the advantages of efficient and accurate analysis of carbon footprint uncertainty, etc.

The application discloses a kind of ultra-high sensitivity sample component evaluation and traceability method and device, the method comprises: obtaining sample, carries out nucleic acid extraction, library construction, capture enrichment and sequencing, generates sequencing data;Sequencing data is preprocessed, and high-quality sequencing data is obtained;Identify the SNP site and its genotype that exist in high-quality sequencing data, construct SNP combination database;Quantitative statistics is carried out to the double allele genotype of SNP site, and the variation abundance of suballele is calculated;According to the genotype information and allele variation abundance of SNP site, construct SNP site variation abundance background distribution model;Using the SNP combination database and variation abundance background distribution model constructed, cross contamination evaluation is carried out to sample.The method of the application realizes the qualitative evaluation of multiple source components in sample, the quantitative calculation of cross contamination proportion and the traceability analysis of non-self source.

The invention relates to the technical field of carbon footprint uncertainty analysis, in particular to a carbon footprint uncertainty calculation method and electronic equipment, and the method comprises the steps: automatically generating a plurality of rules from an unstructured text comprising carbon footprint historical data; performing fuzzy weighted synthesis on the plurality of rules in one scene to generate credibility distribution; extracting a global range and a scene range according to a credibility threshold, and truncating the probability density function of the sampled truncation normal distribution in the global range to obtain background distribution; equally dividing the scene range into three scene subintervals, and calculating to obtain the weight of each scene by using background distribution; performing conditional truncation sampling on each scene subinterval, independently running Monte Carlo simulation, and outputting a corresponding mean value and variance; and performing weighted integration on Monte Carlo simulation results of the scenes through corresponding scene weights to obtain the uncertainty of the carbon footprint. Compared with the prior art, the method has the advantages of efficiently and accurately analyzing the carbon footprint uncertainty and the like.