52 results about "Correlation method" patented technology

The invention discloses a vegetation gross primary productivity monitoring method based on downscaling and multi-source remote sensing data, and belongs to the field of remote sensing image processing. In order to accurately monitor the GPP change of an engineering scale, the vegetation total primary productivity monitoring method comprises the following steps: acquiring first resolution multisource remote sensing data, downscaling by using CNN, inputting data containing DEM and LUCC in a layer, and dynamically adjusting background weight in a loss function through an LUCC binarization mask (a vegetation region is 1, and a non-vegetation region is 0); a CASA method is used for simulating GPP, a multi-year target area GPP data set is generated, and the maximum light energy utilization rate is determined by the vegetation type; analyzing GPP spatial and temporal change characteristics of the data set by using a Theil-Sen slope estimation method and the like, and extracting spatial distribution and a time change mode; extracting principal components of similar factors by using a principal component analysis method, calculating local correlation coefficients of the principal components and the GPP by using a partial correlation method, identifying dominant influence factors by using a contribution degree decomposition model, and extracting an environmental factor driven map. The method is applied to the field of ecological remote sensing monitoring.

The invention discloses an optical measurement segmental arc correlation method based on probability expression, and the method comprises the steps: obtaining an initial orbit feasible region of a segmental arc through an admissible domain, carrying out the uniform distribution discrete sampling of the admissible domain, and describing the uncertainty distribution of the initial orbit of the segmental arc through a Gaussian mixture model. The uncertainty distribution and propagation of the orbit are described in a corrected spring equinox orbital element space, and the state transition tensor of a gravity potential model of any order is applied, so that the precision and speed of orbit uncertainty propagation are improved. In combination with a Gaussian mixture model and a state transition tensor, sparse sampling points are used as component mean propagation dense sampling points of the Gaussian mixture model, and uncertainty distribution of the initial orbit of the arc section is propagated to a common moment. And giving a definition of association probability measurement, calculating the association probability measurement by utilizing a probability density function of track distribution of the segmental arc at the public moment, and carrying out association judgment on the optical measurement segmental arc based on probability expression.

The invention discloses an industrial product quality risk association method based on a graph neural network, and relates to the field of industrial manufacturing, and the method comprises the steps: collecting multi-source industrial data, carrying out the preprocessing of the multi-source industrial data, obtaining a standardized data table, and constructing an industrial element heterogeneous graph based on the standardized data table; inputting the industrial element heterogeneous graph into a graph attention network basic model for node representation learning, and setting a supervised learning task taking a product batch node in the industrial element heterogeneous graph as a prediction target and taking a historical quality detection result as a supervised label; and introducing a meta-path self-learning layer in a message passing process of the graph attention network basic model. According to the method, deterministic prediction is upgraded into probabilistic inference, internal confidence degree measurement is provided for each risk prediction value, and automatic, accurate and interpretable correlation analysis and traceability positioning of the industrial quality risk are realized.

The embodiment of the invention relates to the technical field of multi-radar target association, in particular to an intelligent track association method driven by a state space model, which comprises the following steps of: performing spatial registration on track data captured by a radar sensor, so that the position information of the track data is converted from a radar self-coordinate system to a geocentric geodetic coordinate system; performing time registration on a pair of to-be-associated track data subjected to space registration, and performing time alignment on the two pieces of track data by using a cubic spline interpolation algorithm; inputting two pieces of track data subjected to spatial registration into a feature extractor formed by a state space model, and performing sequence modeling on each piece of track data; inputting the track characteristics of the two pieces of track data into a dual-state space aggregation module, comparing the track characteristics of the two pieces of track data, and generating a decision vector; and inputting the decision vector into a classifier to obtain an association result of the two tracks. According to the method, the accuracy of the association result can be well improved.

The invention discloses a power plant 5G private network elastic security data analysis method and device based on data mining, and relates to the technical field of power grid security data analysis. The method comprises the steps of defining a power grid security data analysis target and an analysis range; establishing a data acquisition and transmission link, and acquiring operation parameters, operation logs and fault record data of key equipment of the power grid in real time; the acquisition server transmits the acquired data to the security access area; the collection server preprocesses the received data to obtain a time sequence data set of the security data; performing preliminary correlation analysis on the time series data set by adopting a Spearman rank-based correlation method to obtain correlation among a plurality of security data state indexes; based on the correlation between the indexes, obtaining a time series data set corresponding to the strong association security data indexes; and based on the time sequence data set, mining the association rule of the security data by adopting a time sequence FP-Growth algorithm to obtain a strong time sequence association rule. According to the invention, the utilization efficiency of the security data can be improved.

The embodiment of the invention provides an investment product data association method and system and electronic equipment, and relates to the technical field of computer application. The investment product data association method comprises the following steps: acquiring a plurality of investment product data records in a plurality of data sources; for each investment product data record, extracting a key field of the investment product data record, the key field being used for identifying an investment product corresponding to the investment product data record; calculating the similarity of key fields of different investment product data records; under the condition that the similarity of the key fields of the different investment product data records reaches a preset similarity condition, establishing an association relationship of the different investment product data records; and merging the investment product data records with the association relationship to obtain a merged data record. Through the investment product data association method and system and the electronic equipment provided by the embodiment of the invention, the accuracy of data association of the same investment product can be improved.

The invention discloses an optical observation correlation method based on mixed multi-hour ephemeris, and belongs to the technical field of space target monitoring. Aiming at the problem that the correlation performance is reduced when the ephemeris quality is unstable due to dependence on a single ephemeris in the prior art, the method comprises the following steps of: firstly, constructing a mixed set containing multi-source ephemeris; secondly, intelligently selecting a leading ephemeris and a lagging ephemeris which are closest in time for each observation arc section and each target; then, the two ephemeris are used for association respectively, and union sets of results are obtained, so that an initial association set is expanded; and for the generated fuzzy correlation, performing primary disambiguation based on the comprehensive confidence, and performing secondary accurate disambiguation on the residual fuzzy condition by comparing the weighted angular distance residual error root-mean-square value of the whole arc section. According to the method, the dependence on single-term and single-source ephemeris precision is effectively reduced, available information is fully utilized, and the correlation robustness and accuracy of optical observation data under the complex ephemeris condition are remarkably improved.

The present invention discloses an intelligent arc segment correlation method based on the minimum optical tolerance domain, belonging to the field of intelligent computing optimization for space target surveillance, which solves the problem of large computational volume of arc segment correlation, and includes: constructing a minimum optical tolerance domain from the first observation arc segment; uniformly sampling in the minimum optical tolerance domain, and propagating the orbit of each sampling point under the J2 perturbation model to obtain the theoretical optical observation data of the second observation arc segment and calculating the root mean square error of the angle of the second observation arc segment to obtain an angle loss function; using the DBSCAN clustering algorithm to identify the wave valleys; selecting the initial value of the simplex method in each wave valley to obtain the optimal angle solution; calculating the probability loss function by the Bayesian theorem; substituting the optimal angle solution into the probability loss function and using the LM algorithm to obtain the optimal probability solution; setting a threshold according to the chi-square distribution of the probability loss function, and when the optimal probability solution is less than the threshold, the two arc segments are successfully correlated; the present invention saves computational costs and improves the accuracy of space target observation.

The invention provides a product full life cycle data model construction and association method, system and device and a medium, and relates to the field of weapon equipment digitization. According to the method, a data model architecture is determined by analyzing light weapon full life cycle data, and a unified modeling language is used for carrying out model building on a meta-model layer, an abstract model layer and an object instance layer. On the basis of a constructed light weapon development and production process data model, a light weapon product data association rule is constructed from the perspective of application. Based on the constructed association rule and the light weapon product data model, combining the data with the association rule, constructing a light weapon product data association relationship, and associating the light weapon product data through unique identifiers such as a product code, a batch number, a system code and the like. The method provides a basis for application of quality problem tracing, rapid fault diagnosis and positioning, product digital resumes, knowledge maps and the like in the whole life cycle, and the light weapon whole life cycle data acquisition efficiency can be effectively improved.

The application discloses a track correlation method based on improved topology, which comprises the following steps: S1, converting two radar target tracks into a common coordinate system; S2, constructing a topology sequence of the radar target tracks; S3, combining historical topology information to calculate the topology average distance of the target at the current moment; S4, using the OSPA distance to measure the correlation degree of the target topology set to obtain a correlation matrix; and S5, using the Hungarian algorithm to perform optimal distribution on the correlation matrix to obtain a correlation result. The track correlation method based on the improved topology can effectively reduce the influence of random errors on the track correlation algorithm and improve the correlation performance.

The application discloses a kind of equipment fault diagnosis methods based on time series data analysis in industrial production in industrial scene, steps include: the data in time series database generated when industrial production system runs is preprocessed;Effective sample is extracted from the data after pre-processing, and multiple measuring point sample time is synchronized;Effective sample data is analyzed according to the characteristics of occurrence frequency, occurrence time, duration, and the correlation of the measuring points is obtained, so as to extract relevant measuring points;According to the data of relevant measuring points, the fault attribution factor graph is inferred.The application uses the data mining method related to big data to mine the correlation of equipment failure from massive sensor data, uses the related method in the field of artificial intelligence, carries out single-source, multi-source time series analysis on historical sensor data, locates one or more fault positions corresponding to abnormal data in combination with the correlation relationship mined.

The application provides a satellite in-orbit anomaly and space environment correlation method based on density distribution drift, comprising the following steps: S1: determining a typical repetitive anomaly of an in-orbit spacecraft, on the basis of which, it can be considered that the event has consistent environmental correlation characteristics, so that it can be statistically analyzed together and further analyzed; S2: using the occurrence of the abnormal event as a condition, the space environment data is divided into two parts, and the probability density distribution of the two parts is counted; S3: according to the difference between the probability density distribution of the two parts in S2, the influence of the space environment is formed to form an explainable correlation characteristic, and the correlation analysis is completed. The method is suitable for analyzing the in-orbit repetitive anomaly phenomenon, and the possible correlation characteristics between the change characteristics of the space environment and a kind of repetitive in-orbit anomaly phenomenon are analyzed by using the distribution characteristic construction method in statistics.

The present invention relates to an interrupted track association method based on situation diagram classification, and belongs to the field of radar target tracking technology. The present invention first performs an initial association on the new and old track pairs based on the time threshold and the speed threshold to reduce the total association time; then the track pairs that have passed the initial association are combined and converted into a situation diagram, and the position characteristics, speed characteristics and time characteristics of the track are pre-extracted; then a neural network model is constructed based on a residual network, and the track situation diagram is judged using the constructed network model; then the ambiguity problem of track association is solved based on 2D optimal allocation; finally, a simulation comparison experiment is used to verify that the proposed method has a significantly improved accuracy compared to several typical TSA algorithms currently available.

The application discloses an industrial product quality risk correlation method based on a graph neural network, relates to the field of industrial manufacturing, and comprises the following steps: collecting multi-source industrial data, preprocessing the multi-source industrial data, obtaining a standardized data table, constructing an industrial element heterogeneous graph based on the standardized data table, inputting the industrial element heterogeneous graph into a graph attention network base model for node representation learning, setting a product batch node in the industrial element heterogeneous graph as a prediction target, and setting a historical quality detection result as a supervised label of a supervised learning task, and introducing a meta-path self-learning layer in a message passing process of the graph attention network base model. The application upgrades deterministic prediction to probabilistic inference, provides an inherent confidence measure for each risk prediction value, and realizes automatic, accurate and interpretable correlation analysis and traceability positioning of industrial quality risks.

The invention discloses a track association method based on a neural network. The method comprises the following steps: 1, preprocessing track data; 2, constructing a network model based on an attention mechanism; 3, feature processing of the trajectory data; 4, establishing an association probability loss function; 5, training a network model based on the attention mechanism; and 6, utilizing the trained network model based on the attention mechanism to carry out association prediction on a subsequent track. The method is simple in steps and reasonable in design, the feature point descriptors of the flight path serve as initial features, the association degree score matrix is obtained through feature updating and point product operation of the network model based on the attention mechanism, the association degree score matrix is optimized through the Sinkhorn algorithm to obtain the association probability matrix, the model efficiency is improved, and the method is suitable for being popularized and applied. Therefore, output of the association probability matrix is completed according to the input track characteristics, and track association is determined according to the association probability matrix.

The present application relates to the technical field of smart grid, disclose a kind of multi-factor associated return home degree winter power load pre-control method and system, method includes: the historical power consumption data obtained in advance is transformed to obtain power load data, and power load data is identified to obtain power consumption problem;The influencing factor is obtained by analyzing power consumption problem, and the strong correlation factor data matrix is obtained by analyzing influencing factor, and the correlation influence coefficient is obtained by analyzing strong correlation factor data matrix;The trained power load prediction model is obtained by iterative training to power load prediction model, and the current power consumption data obtained in advance is input into trained power load prediction model to obtain load prediction data;The red yellow green classification area is obtained by dividing power grid;Power load pre-control scheme is formulated, so as to carry out power consumption prevention and control management.The present application can solve the problem that power grid overload is difficult to prevent and control during return home degree winter and power consumption prediction is not accurate enough.

The invention relates to the technical field of knowledge base fusion, in particular to a knowledge base data fusion association method and system based on an AI large model, and the method comprises the steps: firstly collecting original data through a connector, then carrying out cleaning and duplicate removal processing, then carrying out vectorization alignment on field names, extracting entities and attributes through the AI large model, and carrying out data fusion association on the entities and attributes; according to the method, entity conflicts are solved through a density clustering algorithm and an entity similarity threshold value, a relation triple is generated, unified identifiers are distributed for entities and attributes for standardization processing, data conflicts are detected through variable coefficients, parameters are dynamically adjusted to optimize a fusion strategy, and finally a graph database is utilized to construct a vector index and provide a graph downloading interface. According to the method, on the basis of realizing data fusion, the problem that reasons are difficult to discriminate and solutions are difficult to give in a targeted manner when data conflicts occur in an existing database fusion method is ingeniously solved, the accuracy and reliability of knowledge base data fusion are remarkably improved, and the method has important innovative significance and practical value.

The application discloses a dynamic information association method, comprising the following steps: 1) receiving a new information record, and determining a similar information entity set according to a static attribute; 2) if there is no similar information entity, a new information entity is created, and the process is ended; if there is a similar information entity, a history information record of a dynamic attribute of the similar information entity is obtained; 3) a prediction model for each dynamic attribute of the information entity is constructed, a reasonable value range of the dynamic attribute is determined, a correlation feature of the prediction model of each dynamic attribute of the information entity is constructed, and a prediction value range of the dynamic attribute of the similar information entity is calculated; and 4) if there is no similar information entity, a new information entity is created; if there is a similar information entity, the new information record is associated to the most matched candidate information entity. According to the application, the change trend of the dynamic attribute and the correlation between the dynamic attributes are utilized to associate information from different data sources and / or different time points, so that the accuracy and recall rate of the association are improved.

The application provides a relaxation and creep performance correlation method, and belongs to the field of new materials and is used for developing new materials by testing related activities. First, a high-temperature relaxation test is carried out to obtain corresponding data of temperature-stress-creep relaxation rate. Second, a high-temperature creep test is carried out to obtain minimum creep rate data. Finally, the third step is data processing, and a correlation model is constructed. The application aims at the shortcomings of long data obtaining time and large sample consumption of existing creep performance data, and proposes to use the characteristics of short stress relaxation test, i.e., more creep information and less sample consumption, to quickly obtain a large amount of stress relaxation performance data, and then combine the correlation method shown in the application to quickly and massively obtain the creep performance, so that the service performance can be evaluated.

The present invention relates to a software evaluation method, and in particular to a component quality evaluation method for application software. The method organically combines the evaluation of experts and the attribute correlation obtained from defect data, comprehensively considers the weight of component attributes, and then obtains the component quality. The method comprises the following steps: (1) according to the evaluation of the importance of component attributes by experts, the subjective weight of each attribute is obtained by using a fuzzy hierarchical analysis method; (2) according to each attribute value and defect data obtained by the test, the defect data is analyzed by using a grey correlation method to construct a reference quality, and the attribute importance weight is obtained from an objective perspective based on the comparative analysis between the obtained attribute value and the reference quality; (3) using a control parameter, the ratio of subjective weight to objective weight is adjusted, and finally the comprehensive weight of each attribute is obtained. (4) according to the attribute value and comprehensive weight of each attribute, the quality of the component is calculated.

The application discloses an AI auxiliary-based natural resource factor cross-layer index correlation method and system, which comprises the following steps: firstly, a set containing multiple remote sensing images is acquired, and the set and to-be-matched natural resource factor information are loaded into a pre-trained multi-modal ground feature correlation model to respectively obtain remote sensing image features and description features; and a target remote sensing image is determined by calculating a matching degree. Different layer data is obtained by separating a target image layer, layer features are extracted, and correlation with factor index features is established, thereby constructing a cross-layer index correlation model, and effective correlation of natural resource factor cross-layer indexes is realized.

The present invention discloses a sample selection method based on atomic norm minimization to reconstruct clutter similarity, which belongs to the field of space-time adaptive processing technology, and includes the following steps: acquiring airborne radar echo data, and using the generalized inner product method to eliminate abnormal data contaminated by strong reflectors; using atomic norm minimization to reconstruct the clutter covariance matrix of training samples; without the need to accurately extract the clutter subspace, using a weighted volume cross-correlation function to evaluate the similarity between the training samples and the samples of the unit to be detected; selecting the training samples in which the clutter distribution is similar to the unit to be detected, and applying them to space-time adaptive processing for clutter suppression. The present invention eliminates the need for the volume cross-correlation method to accurately extract the clutter subspace, and has strong robustness when it is difficult to accurately extract the clutter subspace, thereby improving the clutter suppression performance of the airborne radar in a non-uniform environment.

The present invention provides a track association method based on multi-factor multi-model selection, comprising the following steps: S10, selecting a fuzzy factor set and an evaluation set. S20, calculating a weight fuzzy set based on the fuzzy factor set and the evaluation set. S30, calculating a correlation degree fuzzy set based on the fuzzy factor set, the evaluation set and the weight fuzzy set. S40, making an association decision for the track based on the correlation degree fuzzy set. The present invention overcomes the defect of the existing method that the same factor and synthetic operation model cannot be applied to all evaluation levels, and improves the association performance.

The application discloses a stratum correlation method and device. The method comprises the following steps: performing continuous wavelet transform on selected well logging curves of a target well to obtain a modulus distribution diagram of the continuous wavelet transform coefficients at each depth point under each set scale; obtaining a modulus maximum line from the modulus distribution diagram; taking the position of the selected well logging curve when the modulus maximum line takes the minimum value of the scale variable as a singular value position; determining a to-be-correlated depth interval of the target well according to the singular value position and a correlation depth interval of a standard well determined in advance; obtaining a first data point sequence of the selected well logging curves in the to-be-correlated depth interval and a second data point sequence of standard well logging curves of the standard well in the correlation depth interval; determining a path between the first data point sequence and the second data point sequence according to a set rule; determining the distance of each path; and obtaining a stratum correlation result of the target well and the standard well according to the path with the shortest distance. The method can realize automatic fine stratum correlation.

The invention provides a fuzzy track association method based on accumulated historical similarity, which comprises the following steps: acquiring state estimation of two radars on a target track, and constructing a fuzzy factor set of position estimation, speed estimation and acceleration estimation in x, y and z directions and a weight set of fuzzy factors; obtaining the similarity of the two tracks according to the membership degree of the fuzzy factors, and constructing a similarity matrix; obtaining the historical cumulative similarity of the moment k, and constructing a historical cumulative matrix based on the historical cumulative similarity; and mapping the historical accumulation matrix to the incidence matrix, constructing an optimal two-dimensional distribution model, carrying out optimal distribution calculation on the optimal two-dimensional distribution model through a Hungary algorithm, and outputting an associated track pair.

The present specification provides a high-precision stratigraphic correlation method, device and electronic equipment, which constructs a filtering factor through well logging data, and then extracts a high-frequency seismic data body and a low-frequency seismic data body from a seismic data body by using the filtering factor. Through time-varying seismic wavelet deconvolution on the high-frequency, medium-frequency and low-frequency seismic data bodies, a target data body with a "virtual resolution" and a much wider frequency band than the seismic data body can be obtained, so that the profile data of the target data body can be used to more accurately distinguish the interwell lateral characteristics, and the stratigraphic correlation is adjusted based on the interwell lateral characteristics to realize high-precision stratigraphic correlation. The high resolution and lateral variation characteristics of the target data profile are used to finely carry out stratigraphic correlation, thereby providing protection for fine exploration and development of oil and gas fields, especially development geology research.

The application relates to the technical field of knowledge base fusion, and particularly relates to a knowledge base data fusion correlation method and system based on an AI large model. First, original data is collected through a connector, then washing and deduplication processing are carried out, then field names are vectorized and aligned, an AI large model is used to extract entities and attributes, entity conflicts are solved through a density clustering algorithm and an entity similarity threshold, relationship triplets are generated, uniform identification is assigned to entities and attributes for standardized processing, data conflicts are detected through a coefficient of variation, and parameters are dynamically adjusted to optimize a fusion strategy, finally, a vector index is constructed through a graph database, and a graph download interface is provided. On the basis of realizing data fusion, the application skillfully solves the problem that in the existing database fusion method, when facing data conflicts, it is difficult to specifically identify the reasons and give solutions, significantly improves the accuracy and reliability of knowledge base data fusion, and has important innovative significance and practical value.

The invention discloses an earthquake-engineering-well testing and dynamic parameter association method and application, and belongs to the technical field of oil and gas development. The association method comprises the following steps: determining dynamic parameters to be associated; collecting the existing dynamic characteristics of the production well similar to the dynamic parameters to be associated and the existing data of the production well; analyzing the dynamic parameter physical property response lower limit of the collected existing dynamic parameters in the corresponding existing data; deleting a physical property response lower limit part in the existing data corresponding to the existing dynamic parameters, and performing statistical analysis to obtain an association result of the to-be-associated dynamic parameters and earthquake-engineering-well testing; compared with the prior art, the method can effectively predict the production dynamics according to the seismic interpretation result of the production well, the drilling and acid fracturing engineering process response parameters and the well testing interpretation result, and provides a theoretical basis for matching engineering parameters and dynamic prediction before drilling of the fractured-vuggy reservoir.

The present application relates to the technical field of data analysis, and particularly relates to a multi-modal data adaptation and feature correlation method for intelligent insight, comprising the following steps: standardizing and arranging structured data fields in data sources of different systems to form a structured field set, identifying field drift patterns, and generating a structure drift label set; guiding semantic flux analysis on content related to the structured field in unstructured modal data, and extracting core semantic candidate units; finally screening out a standardized target semantic unit set; performing graph structure alignment on the standardized target semantic unit set and the structured field set to obtain a field evolution graph, and performing dynamic adaptation based on field inheritance relationships and time sequence evolution paths in the field evolution graph. The present application effectively excludes pseudo-related expressions that are only close in static semantics but have inconsistent contexts, and improves the authenticity and business effectiveness of semantic unit screening.