27 results about "Association mapping" patented technology

The invention discloses a cerebral hemorrhage postoperative gastrointestinal hemorrhage prediction method based on an LGBM model. The method comprises the steps of obtaining a multi-dimensional clinical feature sequence of a target patient, screening out a stable feature subset by adopting a Boruta feature selection algorithm, performing nonlinear relation fitting and integrated decision by utilizing a pre-trained LightGBM machine learning model, and generating an individualized ATH risk probability value; and when the risk probability value exceeds a dynamic risk threshold value, triggering a high-risk early warning signal, and based on a Kaplan-Meier survival analysis model, carrying out association mapping on a prognosis track of poor long-term neural function recovery, and finally generating a comprehensive prediction report. According to the invention, accurate quantitative evaluation of ATH risk is realized, clinical intervention timeliness is improved through a dynamic threshold early warning mechanism, short-term complication risk and long-term function prognosis are organically combined, and a comprehensive and reliable prognosis basis is provided for individualized treatment decision.

The invention discloses a crop disease and pest identification method and system based on an unmanned aerial vehicle, and belongs to the technical field of image identification, and the method comprises the steps: building an association mapping table based on geographic coordinates, obtaining disease and pest labels obtained through rough identification of each planting collection image, and obtaining a label matrix, performing feature extraction on each planting acquisition image to construct a pest and disease damage matrix; and on the basis of the label matrix and the pest and disease damage matrix, determining a refined sub-region and the recognition precision of the refined sub-region, and according to the coarse recognition result of the non-refined sub-region and the fine recognition result of the refined sub-region, obtaining a pest and disease damage distribution map, and outputting and displaying the pest and disease damage distribution map. And an accurate spatial position and severity basis is provided for agricultural prevention and control.

The invention discloses a laying hen genetic disease molecular marker screening system based on data fusion and AI prediction, the system comprises six modules, a multi-omics data acquisition module obtains laying hen genome and transcriptome data, and a FineDataLink data fusion module carries out feature alignment and association mapping to generate a fusion feature matrix; the dynamic time sequence diagram neural network processing module constructs a time sequence association diagram and outputs a time sequence feature vector, and the attention enhancement deep forest analysis module evaluates feature importance and outputs a screening result; the federal variation auto-encoder modeling module constructs a federal training framework to generate a molecular marker probability distribution model, and finally the molecular marker screening output module extracts key molecular markers. The system realizes deep fusion of multi-omics data and efficient application of an AI algorithm through multi-module cooperation, improves the molecular marker screening efficiency and accuracy, and provides technical support for disease-resistant breeding of laying hens.

The invention discloses an unmanned aerial vehicle inspection bridge disease positioning method based on ray collision detection, and belongs to the technical field of bridge disease intelligent inspection and informatization management. According to the method, firstly, a mapping table of waypoints and BIM component visibility is generated through pre-flight planning, and the collision detection range is greatly reduced; during unmanned aerial vehicle inspection, acquiring centimeter-level pose data by using RTK / IMU, and identifying diseases and extracting centroid coordinates through an improved deep learning model; the method comprises the core steps that disease pixel points are mapped into rays in a world coordinate system through a camera model, and specific BIM components colliding with the disease pixel points are quickly positioned by utilizing a pre-association mapping table and R tree spatial indexes, so that component-level accurate affiliation is realized; and for a cross-component disease, segmentation and independent positioning are carried out in combination with the instance segmentation model. According to the method, the problems of large positioning error, low calculation efficiency and incapability of processing cross-member diseases in the prior art are effectively solved, and high-efficiency, high-precision and real-time bridge disease informatization positioning and marking are realized.

Disclosed in the present invention is a cross-domain multi-modal data automatic association mapping and fusion recognition method, comprising: initializing two encoder networks and two decoder networks; constructing a cross-domain multi-modal data set, and randomly sampling a batch of samples from the data set; extracting representations of all the samples in a latent space by means of the encoder networks; calculating a loss function of the representations in the latent space by means of a contrastive learning loss function; concatenating the representations in the latent space, and respectively using the two decoder networks for decoding; calculating a reconstructed loss function by means of the decoded samples and input samples; performing summation on the reconstructed loss function and then performing back propagation to update network parameters until a model converges; and inputting cross-domain multi-modal data into a trained model. The present invention retains original information of modalities and improves the accuracy of model recognition.

The invention discloses a model-training-oriented data set construction method and system, and belongs to the technical field of data set analysis. Semantic extraction and tag adaptation effect evaluation and quantification are performed, semantic tag iterative optimization necessity study and judgment are performed based on an evaluation and quantification result, and if the study and judgment result is that semantic tag iterative optimization is adopted, the semantic tag adaptation effect is evaluated and quantified; if the research and judgment result is that semantic label iterative optimization is adopted, semantic matching performance analysis is carried out after optimization is finished, if the research and judgment result is that semantic label iterative optimization is not adopted, semantic matching performance analysis is directly carried out, data semantic association necessity judgment is carried out based on the performance analysis result, and if the judgment result is that a data semantic automatic association mapping and matching mechanism is started; according to the method, the technical problems that in the prior art, when data set searching is carried out under the condition of low efficiency, the model training progress is directly influenced, a data hidden mode and a core connotation are difficult to mine, and finally the navigation and analysis efficiency of the data set is insufficient are solved.

The invention discloses a culture organism growth situation monitoring method and system based on multi-source data fusion, and relates to the technical field of intelligent culture and intelligent monitoring, and the method comprises the following steps: obtaining culture organism environment, behavior track and morphological image data, carrying out cross-source space-time coupling reconstruction, and generating a growth reference data stream; executing cross-modal association mapping and dynamic weight reconstruction on the growth reference data flow to form a real-time growth situation evolution sequence; based on the real-time growth situation evolution sequence, time sequence trend enhancement identification is carried out, and a growth abnormity offset state signal is output; according to the growth abnormity deviation state signal, environment and feeding cooperative adjustment is triggered; according to the method, through a time sequence trend enhanced recognition and environment and feeding collaborative closed-loop regulation technology, the problems that in a traditional breeding growth monitoring method, abnormal recognition lags behind, and regulation and control strategies are lack of collaboration are solved.

The invention discloses an X-RAY material intelligent counting and bar code matching tracing method and system, and relates to the technical field of X-ray nondestructive detection.The method comprises the steps that X-RAY detection equipment is started, collection parameters are set according to the type of a material, and an original image covering the full view of the material is obtained through a multi-angle rotating collection assembly; performing noise reduction enhanced geometric correction preprocessing on the original image, and outputting a high-quality image; generating a material area mask graph based on a deep learning semantic segmentation algorithm; extracting material feature separation overlapping areas, screening impurities, and counting the actual number; positioning a bar code area to remove interference decoding to obtain a unique identifier; and establishing association mapping between the counting result and the bar code, storing data to a tracing database, and generating a tracing code to support full-process query. The multi-type material counting precision and the bar code recognition reliability are improved, the multi-scene detection requirement is met, the completeness of a tracing chain is guaranteed, and the detection efficiency and the production management intelligent level are improved.

This invention provides a method and system for analyzing road asset condition monitoring data using deep learning. By acquiring a road asset data set, cross-modal feature association mapping is performed on the data set to generate a cross-modal association feature matrix. A feature evolution dependency network is constructed based on the cross-modal association feature matrix, and the road asset condition inference result is output through the feature evolution dependency network. This invention can effectively improve the comprehensiveness and accuracy of road asset condition monitoring.

The invention relates to the field of the Internet of Things, and particularly discloses an intelligent operation and maintenance system and a data analysis method for environmental protection facilities based on the Internet of Things, which realize accurate reconstruction of theoretical health readings of a target sensor by introducing equipment operation state data and associated sensor time sequence data and introducing a deep association mapping model. And furthermore, the steady-state residual error between the reconstruction value and the actual measurement value is continuously calculated, and the time sequence mode analysis is performed on the steady-state residual error, so that the precise identification and diagnosis of the sensor performance gradual change soft fault are realized. Thus, the limitation of a traditional method based on a fixed threshold value can be effectively overcome, isolated data judgment is replaced with multivariable correlation verification, and the early warning capacity of an intelligent operation and maintenance system of the environmental protection facility for early-stage and hidden faults is remarkably improved.

The invention provides an intelligent aquatic disease diagnosis method and system applied to smart fishery. The method comprises the following steps: firstly, acquiring body surface image sequences of aquatic organisms in different observation periods, and breeding environment associated data such as environmental influence factors of aquatic organism survival water areas; then carrying out association mapping processing on the obtained aquatic organism image sequence and cultivation environment association data to generate an association feature set of aquatic organism body surface features and environmental influence factors; calling a pre-trained aquatic product disease intelligent diagnosis model, carrying out disease correlation analysis on the correlation feature set, and generating a preliminary disease diagnosis result; analyzing a time sequence change rule of aquatic organism body surface features according to the preliminary disease diagnosis result, and determining disease development trend features; and finally, based on the preliminary disease diagnosis result and the disease development trend characteristics, generating a disease diagnosis report containing a disease type identifier and development stage judgment, and sending the disease diagnosis report to a fishery management terminal to provide a scientific basis for fishery management.

The invention relates to the technical field of intelligent agriculture and image processing, in particular to a three-dimensional planting growth state intelligent evaluation system based on image recognition, which is characterized in that an image with spatial information is acquired by scanning a three-dimensional planting frame in a surrounding manner, the structure and spectral characteristics of a plant are decoupled and separated, and a spatial index map is constructed for association mapping. Plant individuals are positioned based on the atlas, historical features of the plant individuals are backtracked and extracted to form a time sequence growth feature chain, growth abnormal stages are recognized by analyzing feature chain changes, and illumination and nutrient records in the same period are automatically called for cross validation. Finally, the plant growth state deviation degree is calculated by fusing multi-source data, and a hierarchical evaluation report is output. According to the system, accurate positioning, dynamic process tracking and auxiliary diagnosis of abnormal roots of individual plants in a three-dimensional planting environment are realized.

The invention discloses a data observation system based on artificial intelligence, and belongs to the field of data observation systems, and the system comprises a data collection module which is used for obtaining the identity information, application behavior data, credit data and biological characteristic data of a personal loan subject, the business information, the financial data, the tax data, the associated enterprise data and the fund flow data of the enterprise loan main body are acquired; the correlation analysis module is used for constructing a relation graph based on a graph calculation technology and carrying out cross-dimension correlation mapping on the collected data; the abnormity identification module carries a pre-trained AI classification model and identifies personal malicious loan behaviors, enterprise malicious debt evasion behaviors and career debt dormitory features; and the early warning response module is used for generating a graded early warning signal according to the abnormal recognition result and triggering a corresponding disposal instruction. According to the invention, omnibearing and dynamic observation of personal and enterprise loan subjects is realized, various financial risk behaviors are accurately identified, and graded early warning and intelligent response are carried out.

This invention discloses a method and system for identifying waste materials based on multimodal fusion, belonging to the field of intelligent waste material identification technology. The method involves acquiring visible light image data, depth structure data, and near-infrared spectral response data of the waste materials to be identified; obtaining candidate regions from the visible light image data and extracting a set of morphological features based on the depth structure data; extracting material reflection curves from the near-infrared spectral response data; extracting texture distribution features and color stability features from the visible light image data and generating a set of structural consistency features based on the morphological features; constructing a fusion feature vector by performing cross-modal association mapping on multiple features and inputting it into a waste material identification model to obtain candidate identification results; identifying key feature subsets through local sensitivity analysis and reconstructing the weights of the fusion features; and performing classification again to output the final identification result. This invention can effectively improve the accuracy and stability of waste material identification in complex recycling scenarios.

This invention relates to a real-time simulation and optimization control platform for integrated power generation, grid, load, and storage systems based on digital twins, belonging to the field of power system automation technology. The method includes: a twin model construction and self-calibration unit integrating multi-physics parameters, equipment, and grid characteristics to construct a model; a dual-algorithm collaborative optimization control unit constructing a bidirectional optimization framework through model predictive control and multi-agent reinforcement learning, coupled with a multi-dimensional adaptive reward mechanism to output control commands; a multi-source data fusion and planning linkage unit completing semantic annotation and association mapping of multiple types of data, adjusting production plans and decomposing loads based on simulation results; and a green electricity trading and scheduling coordination unit incorporating core elements of green electricity trading into the optimization objective to generate a trading and scheduling coordination scheme. This method achieves accurate fusion of multi-source data from the power generation, grid, load, and storage system, effectively solving the defects of unscientific planning adjustments and insufficient coordination in existing technologies, and improving the safety and economy of power grid operation.

The invention discloses a hot spot area intelligent identification method based on geographic information and user power consumption data, comprising the following steps: collecting power consumption data and geographic position information of users in a target area, and establishing association mapping to obtain a comprehensive data set; performing data cleaning and standardization processing on the comprehensive data set, and constructing a standardized feature vector containing a power consumption intensity index and a geographic concentration index; performing clustering processing based on an adaptive spatial clustering algorithm, quantifying complexity and geographic distance weight through an information entropy theory to determine a neighborhood radius, and identifying user groups with similar electricity demands and similar geographic positions; calculating a comprehensive power consumption intensity score through a power consumption capacity evaluation model and a growth trend prediction model, and optimizing a region boundary in combination with geographical constraint conditions; and according to a preset threshold standard, screening out a power demand hot spot region meeting the condition. According to the invention, accurate identification of the power demand hot spot area can be realized, and a scientific basis is provided for power system planning and resource configuration.

This invention relates to the field of hole coaxiality measurement technology, specifically to a method and system for measuring the coaxiality of machined holes based on a laser beam. It includes identifying defect points and associated defect points during the re-inspection process, and then re-locating the defect points based on a defect-association mapping set. A precise re-inspection adjustment path is constructed based on the secondary location distribution of the defect points, and a fixed-point re-inspection is performed according to this path. This solution obtains the positional relationship between defect points and associated defect points, constructs a defect-association mapping set, and re-locates the defect points based on the re-inspection process, the associated defect points, and the defect-association mapping set. A precise re-inspection adjustment path is constructed based on the secondary location distribution of the defect points, and a fixed-point re-inspection is performed according to this path. This allows for targeted measurement path planning for the coaxiality testing equipment and location detection of each defect point after re-inspection, improving the efficiency of the re-inspection process.

The invention discloses a river ecological abnormal change identification method based on machine learning, and relates to the technical field of machine learning, and the method comprises the steps: collecting multi-section ecological monitoring data, carrying out the preprocessing, and constructing a time-space sequence data set; constructing a riverway directed topological structure, generating a topological adjacency matrix, and completing association mapping of spatio-temporal data and nodes; inputting spatial-temporal characteristics and an adjacent matrix, improving a DCRNN learning diffusion rule, and outputting a dynamic ecological baseline sequence; a stable ecological sample set is constructed, a stable subspace is generated through mapping, a baseline is corrected, and a structure deviation amount is calculated; constructing an ecological energy transfer interval matrix, and carrying out bidirectional propagation consistency discrimination to obtain a propagation consistency index; and calculating a baseline residual error and combining the structure deviation amount, and outputting an anomaly identification result. According to the method, the topological constraint dynamic ecological base line is constructed, and the stable ecological structure and propagation consistency discrimination are fused, so that accurate identification and early warning of the gradual change type ecological abnormal change of the river channel are realized.

The application discloses a river ecological abnormal change identification method based on machine learning, relates to the technical field of machine learning, and comprises the following steps: collecting multi-section ecological monitoring data, preprocessing, and constructing a time-space sequence dataset; a river directed topological structure is constructed, a topological adjacency matrix is generated, and the association mapping of time-space data and nodes is completed; the time-space characteristics and the adjacency matrix are inputted, the diffusion law is learned by improving DCRNN, and a dynamic ecological baseline sequence is outputted; a stable ecological sample set is constructed, a stable subspace is generated by mapping, the baseline is corrected, and the structural deviation is calculated; an ecological energy transmission interval matrix is constructed, bidirectional propagation consistency discrimination is performed, and a propagation consistency index is obtained; the baseline residual error is calculated, the structural deviation is combined, and an abnormal identification result is outputted. The application realizes accurate identification and early warning of gradual ecological abnormal changes in the river by constructing a topological constraint dynamic ecological baseline and fusing stable ecological structure and propagation consistency discrimination.

In accordance with aspects of the present disclosure, sequencing systems and methodologies described herein may be utilized in various contexts for determining associations between features of a single-cell data set (e.g., perturbations, accessibility, genotype) and gene expression. As discussed herein, various embodiments of the present technique comprise a computational pipeline that accurately maps such associations in a computationally rapid and efficient manner. By way of example, a single-cell data sample comprising hundreds of thousands of cells or more may be processed in less than a day.

This application provides a multi-dimensional flue gas desulfurization status monitoring method and system, relating to the field of intelligent monitoring technology. The method includes acquiring historical process parameters and corresponding fault type labels under historical fault conditions of the desulfurization system; establishing a process fault diagnosis model through multi-parameter joint feature extraction and association training; and continuously collecting status monitoring signals from the desulfurization target equipment. Multi-type diagnostic maps are generated through map analysis and matched with an equipment fault feature knowledge base to identify equipment faults. When a process or equipment fault exists, the method combines a process-equipment fault association mapping table to retrieve corresponding expected abnormal features within the same time window for verification and matching. Finally, the fault level and corresponding adjustment plan are determined based on the matching results. This method can achieve comprehensive identification and predictive control of desulfurization system faults.

The invention relates to the technical field of data processing, and discloses an electric power field operation violation behavior identification method and system fused with multi-modal data. The method comprises the following steps: collecting multi-modal data, distributing violation association sensitivity weights, and constructing a time sequence association database; extracting identifiers to generate a violation behavior evolution feature sequence; adaptively adjusting the weight to output an evolution weight matrix; tracking violation propagation paths to generate an association mapping table; and quantitatively calculating violation correlation degree, and outputting an early warning signal when the correlation degree exceeds a threshold value. According to the method, the problems of unreasonable multi-modal data fusion weight distribution and inaccurate violation behavior relevance identification are solved, and the accuracy of violation behavior identification of power field operation and the real-time performance of violation propagation early warning are improved.

The embodiment of the invention provides a data quality monitoring method, system and device and a medium, and belongs to the technical field of information. The method comprises the following steps: collecting multi-source heterogeneous data; performing multi-dimensional quality index verification on the multi-source heterogeneous data, and performing dynamic threshold adjustment and anomaly prediction on the multi-source heterogeneous data by adopting a pre-trained machine learning model to obtain a multi-dimensional quality index verification result and an anomaly prediction result; and by taking the data object, the time window and the core index as association keys, establishing an association mapping table of a multi-dimensional quality index verification result and an abnormal prediction result, and determining a quality monitoring result of the multi-source heterogeneous data by analyzing the association mapping table. Quality problems can be efficiently found and processed in a multi-source heterogeneous and mass real-time data environment, and the real-time performance, the accuracy and the operation and maintenance efficiency of data governance are remarkably improved.

This disclosure provides a method and system for predicting gene-phenotype associations in maize based on heterogeneous genetic networks, belonging to the field of bioinformatics. The scheme processes multi-omics data of maize to obtain a heterogeneous genetic network of attributes for multiple sets of biological molecules. Through deep matrix factorization, the network topology and node attributes are collaboratively decomposed to obtain nonlinear feature representations of multiple sets of biological molecules. In this way, network structure information and molecular attribute information are jointly mined, achieving deep fusion of multi-omics data and exploring molecular characterization and the complex interactions between molecules and phenotypes. Based on the nonlinear representation of molecules, the heterogeneous genetic network of attributes is reconstructed, and useful information in the reconstructed network is mined to achieve accurate prediction of gene-phenotype associations and complementary enhancement of association mapping across multi-omics data.

The invention relates to an auxiliary diagnosis method and device based on medical big data, equipment and a medium. The method comprises the steps of obtaining an original medical record text and extracting medical information through a natural language processing technology to generate medical record data; performing clustering analysis on the medical record data to output a personalized feature combination; determining a target disease type and key medical features based on the personalized feature combination, and obtaining clinical quantized values of the key medical features; if the clinical quantized value of the key medical feature accords with a first preset threshold value, generating a trend prediction result by using a preset illness state dynamic time sequence model based on the key medical feature; calling a diagnosis rule base corresponding to the target disease type based on the trend prediction result to generate a diagnosis path; and carrying out association mapping on the key information of the diagnosis path and the path nodes to output a personalized medical service scheme. Through data driving and model analysis, intelligent and personalized generation of a disease diagnosis path is realized, and diagnosis efficiency and scheme pertinence are improved.

The invention discloses a gene localization method (NAM-BSA) based on a multi-parent nested association mapping (NAM) population, and belongs to the technical field of plant genetic breeding. The method comprises the following steps: hybridizing, backcrossing and selfing a common parent and at least three donor parents with different genetic backgrounds to construct a BC4F8 population; based on target character extreme phenotype and functional marker genotype analysis, screening extreme individuals from each subpopulation, and equivalently mixing DNA to construct a high-value and low-value mixing pool; performing whole genome re-sequencing on the mixed pool, and performing strict bioinformatics filtering to obtain a high-quality SNP data set; by calculating delta (SNP-index) and combining with a 99% confidence interval threshold, a genome region significantly associated with the character is determined. The method is successfully applied to positioning the plant height gene PH8 of the 8th chromosome of rice in the 4, 600,000-5,760,000 bp interval, overcomes the defect that the genetic diversity of the traditional BSA technology is limited, remarkably improves the gene positioning efficiency and precision of complex quantitative traits, and has wide application value in crop functional genome research and molecular breeding.

This invention relates to the field of medical electro-digital data processing, and discloses a decision-making system for detecting melting curves of gene polymorphisms in hypertension medication. It collects fluorescence melting curve data of multiple gene targets; maps the melting temperature-fluorescence intensity derivative curve as graph structure nodes, and maps the melting feature associations between different gene loci as edges, constructing a multidimensional melting curve topology graph; extracts the co-fluctuation features of node peak temperature offset and edge weights and inputs them into a graph convolutional network, outputting a polymorphic combination feature vector; maps the polymorphic combination feature vector to a hypertension drug metabolism network graph model, calculates the joint decay coefficient of drug metabolic enzyme activity and receptor binding rate, and determines the type and dosage adjustment parameters for hypertension medication based on the joint decay coefficient. This invention overcomes the deficiency of single-peak independent alignment in separating overlapping peaks, achieves quantitative analysis of co-fluctuation associations of multi-gene polymorphisms, and eliminates medication bias caused by isolated qualitative matching.