49 results about "Classification scheme" patented technology

The invention discloses a method for improving the intelligent classification precision of distillate oil, and the method comprises the steps: employing a method based on a threshold value during spectrum cleaning, and adding S-G to smooth and sharpen spectral features during data preprocessing; during model supervised training, the high-dimensional feature center of distillate oil types is increased, and the identification capability of the model on inter-class differences is enhanced. The method can effectively improve the fraction oil spectrum classification precision, improve the model generalization ability, and provide a more accurate and efficient intelligent classification scheme for refinery enterprises.

The embodiment of the invention provides a wafer defect classification method, a model training method, a system, equipment and a medium. According to the wafer defect classification scheme provided by the invention, the multi-modal test information of the wafer can be acquired, so that a plurality of test maps generated based on the multi-modal test information of the wafer are used as the basis of wafer defect classification, and the test information of different modals (namely, different dimensions) is considered during wafer defect classification; therefore, the accuracy of the classification result can be improved, and an actual manual wafer defect analysis mode can be met. Wherein the plurality of test maps comprise at least two types of maps, and one type of map is generated based on one type of modal test information.

The invention relates to the technical field of satellite remote sensing application, and discloses a crop classification method based on a multi-source satellite image, and the method comprises the steps: firstly obtaining multi-temporal satellite image data, extracting spectral reflectivity characteristics, generating a matrix, and constructing a classification model set; setting a feature parameter category set, and establishing a feature fusion correlation model based on the obtained texture, vegetation index parameters and spatial resolution data of the historical image; extracting spectrum and texture feature parameters of a crop area in the current image, and generating an optimized feature set in combination with model optimization; updating classification logic based on the optimized feature set and the classification model, generating a target classification scheme and calibrating a spatial relationship; and finally, acquiring crop growth cycle data, and establishing a time sequence feature association rule to optimize a crop type spatial distribution map. According to the method, through multi-source feature fusion and dynamic optimization, the crop classification precision and reliability are improved, and the method is suitable for a precision agricultural management scene.

The invention discloses a shale oil geological engineering dessert evaluation method and device based on geological modeling, and the method comprises the steps: determining a shale oil facies classification scheme and shale oil dessert evaluation key parameter values according to the shale oil geological engineering logging interpretation data, determining the corresponding scores of different shale rocks, and obtaining the shale oil dessert evaluation key parameter values of the shale oil facies classification scheme and the shale oil dessert evaluation key parameter values of the shale oil facies classification scheme; and determining a target sweet spot evaluation parameter weight based on sweet spot evaluation attributes of the lithofacies three-dimensional model and actual well drilling productivity data, establishing a shale oil geological engineering integrated comprehensive sweet spot factor, and determining a shale oil geological engineering comprehensive sweet spot evaluation result based on the sweet spot factor and the target sweet spot evaluation parameter value. Through the technical scheme of the embodiment of the invention, comprehensive evaluation of shale oil geological engineering desserts is realized, complexity of shale oil geological features can be adapted, correlation between geological and engineering dessert evaluation parameters is improved, and fine evaluation of shale oil dessert space distribution is ensured.

This application relates to an automated data management system and a corresponding method. The system comprises: a data collection module for gathering raw job position data from public resources; a data preprocessing module for preprocessing the collected raw job position data to remove irrelevant information and / or symbols; a data identification module for identifying text related to job skill requirements from the pre-processed data and identifying keywords related to the job skills; a semantic analysis module for semantically analysing the identified keywords related to the job skills and forming a skill classification scheme; a data storage module for establishing a skill database based on the skill classification scheme and storing the skill classification scheme. The system automates the analysis of job postings to identify the most in-demand skills in the current market. Through big data analysis, this invention accurately assesses the demand for various skills, providing valuable data support for job seekers and companies.

The invention provides a pore geometric morphology fine characterization method based on confining pore forming of mineral particles, which comprises the following steps: S1, performing fine characterization of the mineral particles based on geometric morphology characteristics, and accurately identifying the mineral particles in combination with characterization results; s2, performing geometric shape quantitative characterization on different types of pores from the angles of pore diameters, roundness, flatness, shape indexes and corner angle indexes to obtain geometric shape parameters of the pores; s3, on the basis of the recognized mineral particles, the names of confinement pores are determined, clustering analysis is conducted on the confinement pores in combination with the geometric morphology quantitative characterization result obtained in the step S2, and a pore classification scheme is established; and S4, based on a classification scheme and a quantitative characterization result, determining development characteristics of shale reservoir pores, establishing a porosity contribution index model formula, and matching and verifying a reservoir physical property result. According to the method, through comprehensive analysis of the pore morphological characteristics, solid data support and theoretical basis can be provided for scientific evaluation of a high-quality pore development mode.

The invention relates to a method of determining one or more conditions, of a geographical line, GL, or its surroundings. The method comprises: acquiring geo-referenced earth observation data representing one or more spatially overlapping imagery layers covering from an aerial or space perspective a specific region of interest, ROI, of the Earth's surface, the ROI comprising the GL; geometrically transforming the geo-referenced observation data, at least in parts, into a local internal frame of reference of the GL within the ROI to obtain a mapping of the geo-referenced observation data to respective corresponding coordinates within the local internal frame of reference of the GL; and evaluating the mapped earth observation data as represented in the local internal frame of reference of the GL according to a classification scheme to obtain therefrom evaluation data representing a classification of one or more properties of the GL or of its surroundings according to one or more conditions of the GL.

Taxonomy driven multi-system networking and content delivery systems and methods are provided herein. An example systems includes a website authoring platform generating a taxonomy structure for a webpage, the taxonomy structure indicating assets to be included in the webpage a layout for the assets, a technical documentation authoring system for creating technical documents related to the assets, and a metadata binder providing the technical documentation authoring system with access to the taxonomy structure of the website authoring platform so that technical document authors are provided with the taxonomy structure to guide creation and structuring of the technical documents so that the technical documents comprise data that corresponds to the assets.

The invention relates to computer-implemented systems and methods for data risk management that provides traceability across governing artifacts which is key to driving effective data risk management and achieving compliance to policy, standards and controls. An embodiment of the present invention is directed to a standardized data risk taxonomy, harmonized classification schema, policy and standard hierarchy, control catalog and standard of care. These components facilitate an alignment to a full information lifecycle with a common definition of data risk, traceability across governing artifacts (e.g., obligations, policies, standards, risks, controls, etc.) and standardized catalogs with defined treatment across harmonized classification of assets.

The invention discloses an import and export commodity intelligent classification method based on knowledge graph metadata topology, and relates to the technical field of reinforcement learning, and the method comprises the steps: inputting an initial data packet into a dynamic interaction model, carrying out explicit association mining through a semantic enhancement layer, optimizing a rule matching path through a rule evolution layer, and constructing a dynamic commodity knowledge graph; performing topological structure derivation on the dynamic commodity knowledge graph to generate a graph topological analysis report and a metadata list, and performing knowledge reasoning integration on the graph topological analysis report and the metadata list to generate an intelligent navigation engine; calling an intelligent navigation engine to execute multi-path semantic query and rule verification on the dynamic knowledge graph to generate a candidate classification scheme set; and performing multi-target collaborative optimization on the candidate classification scheme set to generate a sorting scheme sequence, performing traceability packaging on the sorting scheme sequence, and outputting an intelligent classification scheme. According to the invention, through the dynamic interaction model and multi-target collaborative optimization, the rule adaptation efficiency in a complex scene is improved.

The invention discloses a multi-dimensional text data classification processing method and system, and relates to the field of text data classification processing. Collecting structured, unstructured and semi-structured texts, and carrying out denoising, word segmentation, standardization, missing value processing and abnormal text processing; extracting features from semantics, grammar, emotion and domain exclusive dimensions; optimizing features through standardization, correlation analysis, PCA dimension reduction and feature importance ranking; a'pre-training language model + traditional machine learning model 'fusion framework is constructed and trained; real-time and batch reasoning is supported; evaluating a classification result and feeding back a to-be-optimized sample; when the to-be-optimized sample reaches the standard or the performance is reduced, model iteration is started, and the model is updated after test verification. According to the method, the multi-source text preprocessing suitability and the data quality are improved, the classification accuracy and the field suitability are enhanced through multi-dimensional feature fusion, the performance and efficiency are optimized through the fusion model and incremental training, data changes are continuously adapted, and an efficient and reliable classification scheme is provided.

The invention relates to the technical field of ocean sample management, and discloses an ocean sample full-life-cycle digital management method, which comprises the following steps of: firstly, collecting characteristic data such as sample types, source positions and chemical component information of ocean samples, and calculating a classification scheme and storage parameters according to the characteristic data; evaluating a management demand and generating a target management strategy by combining the real-time management data of the sample library; making and optimizing a preliminary management plan by using algorithms such as k-means clustering and a decision tree in combination with historical management data and sample use frequency data, and generating a personalized management scheme; and finally, implementing the scheme, monitoring a sample preservation rate index through a sensor, dynamically adjusting a temperature threshold value and a storage position of classified storage equipment, introducing a real-time feedback mechanism to iteratively correct and adjust parameters, and generating a full-life-cycle management scheme. According to the method, full-process digital management of the ocean samples is realized, and the management efficiency and the sample storage quality are improved.

The application discloses an import and export commodity intelligent classification method based on knowledge graph metadata topology, relates to the technical field of reinforcement learning, and comprises the following steps: inputting initial data packets into a dynamic interaction model, performing explicit association mining in a semantic enhancement layer, optimizing rule matching paths in a rule evolution layer, and constructing a dynamic commodity knowledge graph; performing topology structure derivation on the dynamic commodity knowledge graph, generating a graph topology analysis report and a metadata list, integrating knowledge reasoning on the graph topology analysis report and the metadata list, and generating an intelligent navigation engine; calling the intelligent navigation engine to perform multi-path semantic query and rule verification on the dynamic knowledge graph, generating a candidate classification scheme set; performing multi-objective collaborative optimization on the candidate classification scheme set, generating a sorting scheme sequence, performing traceability packaging on the sorting scheme sequence, and outputting an intelligent classification scheme. The application improves the rule adaptation efficiency in complex scenarios through the dynamic interaction model and multi-objective collaborative optimization.

A classification apparatus includes: a feature quantity output unit that outputs a feature quantity of input data; and a classification unit that retains, as a classification weight, a feature quantity obtained by averaging, per each class, the feature quantity output by the feature quantity output unit in response to a base class dataset and a novel class dataset with a smaller number of data items than the base class dataset and that outputs a result of classification of the input data by using the feature quantity of the input data and the classification weight.

The invention relates to a content recommendation method and device, computer equipment and a storage medium. The method comprises the following steps: clustering user browsing data of different user accounts in an acquisition period, thereby dynamically dividing interest grading thresholds corresponding to different content types, and further pushing interested contents of different content types to each user account according to the dynamically determined interest grading thresholds. Compared with the prior art, the method does not depend on fixed statistical quantiles or normal distribution hypotheses, interference of hot content or extreme users on grading results can be reduced, objectivity of interest grading threshold values is improved, and the problem that certain interest grading schemes are insufficient in interest grading generalization is solved.

The present invention belongs to the field of urban functional area classification, and in particular relates to a functional area classification method, system, medium and equipment based on multi-source data fusion. Combining the two- and three-dimensional morphological features of the city and POI data, supplemented by road network data, a functional area classification study based on multi-source data fusion is carried out. Based on the differences in spatial landscape structure and socio-economic activities reflected by different functional areas, the two- and three-dimensional morphological features of each functional area are extracted to describe its spatial landscape structure, and POI data is used to describe basic human activities; the two- and three-dimensional morphological features of the city and POI features are fused, different functional area classification schemes are designed, and the impact of different features on the accuracy of functional area classification is compared and analyzed, which significantly improves the urban functional area classification results.

The landslide analysis method based on the sensitivity of risk factors solves the problem of the existing difficulty in landslide prevention analysis and belongs to the field of disaster prevention technology. The present invention includes: collecting data of landslide disaster points and various landslide risk factors; dividing classification feature intervals for the raster data of each landslide risk factor to obtain a variety of different classification schemes, and each classification scheme includes multiple classification feature intervals; constructing a classification model for each landslide risk factor by using the deviation sum index and the fitting deviation sum index, and selecting the classification scheme when the classification model value is closest to 1; optimizing the classification feature intervals of the selected classification scheme; calculating the sensitivity DC of the landslide risk factor in the optimized classification feature interval; if DC>0, it means that the landslide is likely to occur in the corresponding classification feature interval; if DC<0, it means that the landslide is not likely to occur in the corresponding classification feature interval; if DC≈0, it means that it cannot be determined whether the landslide is likely to occur in the corresponding classification feature interval.

The application discloses a kind of based on deep learning's round billet end face billet number direction classification scheme, belong to intelligent metallurgical technology field, the method includes: establishing round billet end face billet number data set;Round billet end face billet number data set is divided into training data set and test data set;Each image in training data set is preprocessed;Based on the image after pre-processing, improved AlexNet network is trained, and classification model is obtained;Classification model is tested based on test data set, in the case where test result is classification model meets preset condition, it is determined that the classification model training is completed;Based on the classification model of training completion and text recognition unit, to be tested image is handled, to determine the class that round billet end face billet number direction in to-be-tested image belongs to.The based on deep learning's round billet end face billet number direction classification scheme provided in application can efficiently and accurately identify round billet end face billet number direction.

The application provides a webpage information extraction and classification method and device, and belongs to the technical field of artificial intelligence. The webpage information extraction and classification method comprises the following steps: converting the source code of a target webpage into a dom tree; processing each node of the dom tree to obtain four feature matrices, i.e., a text feature matrix, an Xpath feature matrix, a layout feature matrix and a visual feature matrix; inputting the four feature matrices into an encoding network respectively to obtain four representation vectors; performing feature fusion on the four representation vectors to obtain fused features; inputting the fused features into a classification network to obtain and store the classification result of an information unit of the target webpage, wherein the classification result comprises at least one of the following: a table, a form to be filled, a text unit that needs to be linked to a next webpage for display, a navigation bar or a display bar, pure text, an advertisement and useless information. The technical scheme of the application can improve the universality of the webpage information extraction and classification scheme.

This invention proposes a structurally enhanced discriminative width learning system for image classification. First, it introduces graph regularization based on class relationships to ensure that similar samples remain closely distributed in the projection space. Second, it adds intra-class divergence regularization to further enhance the aggregation of samples within the same class. Furthermore, it introduces inter-class divergence regularization to ensure that the centers of different classes are far apart in the feature space. Finally, in the output layer regression stage, it replaces the Frobenius norm regularization in ridge regression with sparse norm regularization to effectively suppress noise and redundant information. This image classification scheme, while maintaining the simplicity and efficiency of the optimization process, organically integrates three different types of structured information—intra-class structure, inter-class structure, and local manifold information—into a unified model, enabling the learned feature representations to possess stronger structure preservation and discriminative capabilities.

The application provides a data mining-based storage period prediction method and system, relates to the technical field of archive management, and comprises the following steps: analyzing a classification scheme and a storage period table to construct a labeled sample set, and training a period prediction mapping relationship by combining the text and metadata features of historical archiving data. For the data to be predicted, the modified period result is calculated by determining the rule matching degree, and the source system identifier is bound and returned. The application can improve the accuracy and automation level of the storage period prediction.

The invention discloses a forest multi-type disturbance remote sensing classification scheme under an unbalanced small sample condition, and the scheme comprises the steps: carrying out the classifier training of a limit gradient lifting classifier and a lightweight gradient lifting classifier through employing the manually labeled forest disturbance type sample data; generating a first classifier and a second classifier, and performing classification prediction on the unlabeled forest disturbance detection result based on the two classifiers to obtain amplified forest disturbance classification prediction result data, and performing pseudo sample generation on the amplified forest disturbance classification prediction result data by using a potential diffusion model to obtain first forest disturbance type data; and based on the first forest disturbance type data, iteratively performing forest disturbance type sample data amplification and classifier training by adopting a mode of mutual guidance of a first classifier and a second classifier to obtain a target limit gradient lifting classifier and a target lightweight gradient lifting classifier, and performing classification prediction on the unlabeled forest disturbance data. The forest multi-type disturbance classification result is obtained, and the forest multi-type disturbance classification precision can be improved.

The process is for use with: a plurality of data sets including a data set for each of a plurality of variants of a product, each set including data about the variant for which the set is provided, the data about the variant for which the set is provided including details of at least portions of a spectra created by NMR analysis of the variant; and a predetermined arrangement of a predetermined number of cells. The process comprises defining a classification scheme. The scheme divides that part of an NMR spectrum which is present in the plurality of sets into a plurality of parts equal in number to the predetermined number of cells and assigns each of said parts to a unique cell of the predetermined arrangement; and defines a relationship between the range of NMR intensities found in the sets and a predetermined portion of the visible spectrum.

The invention discloses an electric power Internet of Things communication protocol data cleaning and feature extraction method, which relates to the technical field of electric power Internet of Things, and comprises the following steps: generating exchange data based on a communication protocol of edge side equipment and intelligent electric power Internet of Things terminal equipment, carrying out structured processing on the exchange data, generating a feature field, and carrying out feature extraction on the feature field; generating an original data set based on the feature field; extracting feature data in the original data set based on a communication protocol, generating a key feature field based on the feature data, and performing normalization processing on the key feature data set to generate a normalized data set; establishing a feature similarity model based on a communication protocol, extracting effective features in the normalized data set by using the feature similarity model, and generating a training data set based on the effective features; a data basis is provided for side deployment of a power Internet of Things terminal protocol identification and classification scheme based on a data driving method, and conditions are provided for power Internet of Things terminal protocol identification and classification feature extraction.

The invention discloses a physical constraint-fused time sequence intelligent correction method, which comprises the following steps of: carrying out double clustering based on a meteorological station geographic position and a meteorological element time sequence curve shape by adopting a self-adaptive evolutionary optimization geographic space clustering model; an optimal classification scheme is selected through a weighted evaluation index of the contour coefficient and the intra-cluster distance quadratic sum; on the basis of the classification result, noise identification and marking are carried out on each type of meteorological element data by jointly using a local abnormal factor algorithm and dynamic physical constraint conditions based on cut-in wind speed, cut-out wind speed and a theoretical power curve; constructing a mixed feature refining model, and forming a feature set with high expression ability; carrying out 15-minute single-step prediction by using a self-adaptive dynamic correction prediction model driven by mixed features; comprehensively evaluating the prediction result; the prediction precision is obviously improved.

The invention discloses a model classification method and device, equipment, a storage medium and a computer program product, which are used for solving the problems that an existing model classification scheme cannot deeply analyze an internal structure of a model only according to a name, creation time or a few surface parameters of the model, so that a classification result is rough, the precision is insufficient, and the efficiency is high. And refined model management and scenarized calling requirements are difficult to support. The method comprises the steps of obtaining model structure parameters of a to-be-classified model; determining a to-be-classified parameter coefficient corresponding to the to-be-classified model according to the model structure parameter; a predetermined parameter domain reference coefficient corresponding to each classification parameter domain is obtained, and each parameter domain reference coefficient is determined based on a structure parameter coefficient of a preset experiment model of the corresponding classification parameter domain; determining a deviation value between the to-be-classified parameter coefficient and each parameter domain reference coefficient; and determining a target classification parameter domain corresponding to the to-be-classified model according to the deviation value.

The invention relates to a training system and a training method for training an artificial neural network, in particular for medical applications. The training system comprises an image-processing device, which is configured to receive a set of acquired images, an artificial intelligence module, configured to implement an artificial neural network, and a controller device, configured to train the artificial neural network implemented by the artificial intelligence module, wherein the image-processing device is further configured to generate modified images based on a modification of the acquired images, wherein each of the modified images generated by the image-processing device contains less texture information than the respective acquired image from which they stem, and wherein the controller device is configured to receive a set of training images comprising at least part of the modified images and at least part of the acquired images and train an artificial neural network which, based on a classification scheme, is configured to output a probability distribution for each training image according to the classification scheme.

The invention discloses a multi-level classification method and system based on multi-modal data fusion, and belongs to the field of big data analysis and intelligent information processing. The method comprises the following steps: cleaning image, text and table data based on a multi-modal data preprocessing module; feature extraction and structured vector representation are carried out on images, texts and tables based on a multi-modal feature extraction and vectorization module; the image features, the text features and the table features are fused by a multi-modal feature fusion module based on a self-attention mechanism; a multi-level classification framework is constructed based on a multi-level classification framework construction and training module, and hierarchical classification training is carried out; and testing, evaluating, outputting and displaying the multi-level classification result based on the model testing and evaluating module. According to the method, on the basis of fully mining and fusing data information of each modal, an accurate and refined classification scheme is provided for a multi-level complex classification scene, a classification result is refined on the basis of coarse-grained classification, and fine classification in practical application is met.

The present invention discloses a two-stage encrypted traffic classification method for programmable switches, which relates to the field of computer network technology and comprises the following steps: extracting semantic features and statistical feature sequences of input traffic on the switch data plane and performing preprocessing; inputting the semantic features into a matching-action pipeline and matching them with a convolutional neural network model classification table issued by a server, and obtaining a traffic category based on the semantic features if there is a match; if there is no match, inputting the statistical feature sequence into the matching-action pipeline and matching it with a long-short-term memory model classification table, obtaining a matching result for each statistical feature respectively, and performing a bitwise AND operation on them to obtain a traffic category based on the statistical features; executing a traffic decision action based on the traffic category; the encrypted traffic classification method aims to design and implement a network model for encrypted traffic classification and deploy it to a switch, thereby realizing a low-latency, low-load, high-precision and high-availability encrypted traffic classification scheme running on the switch.

The invention relates to the technical field of oil and gas field development geology and geophysics, in particular to an ultra-deep clastic rock fractured phase characterization method based on multi-scale data fusion, which comprises the following steps: fusing field outcrop, logging and seismic data, and adopting a'trend constraint-variation function quantization-collaborative simulation 'three-step geostatistical model to characterize fractured phases of ultra-deep clastic rocks. The method comprises the following steps: firstly, establishing a clastic rock fracture facies classification scheme including a fault control sandstone type, a fault control sand-mud interbed type, a pleat control sandstone type and a pleat control sand-mud interbed type on the basis of a lithology combination, and finally, determining a control mechanism of different fracture facies spatial combinations (such as a seepage-shielding body) on a water invasion path and residual gas distribution. According to the ultra-deep clastic rock fracture phase characterization method based on multi-scale data fusion, the span of the fracture from static description to dynamic prediction is realized, and a precise geological basis is provided for efficient development and residual gas potential tapping of an ultra-deep fractured gas reservoir.