Patents
Literature
16results about How to "Comprehensive representation" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Method and apparatus for predicting fracture network complexity in deep coal and rock gas formations
This application provides a method and apparatus for predicting the fracture network complexity of deep coal and shale gas formations. The method includes: obtaining multiple fracturing parameters based on fracturing operation curve data of the target well; constructing a three-dimensional mesh data model based on seismic data, well logging data, and core analysis data of the target well's location; obtaining multiple geological parameters based on the three-dimensional mesh data model; standardizing the multiple fracturing parameters to obtain standardized multiple fracturing parameters; standardizing the multiple geological parameters to obtain standardized multiple geological parameters; and inputting the standardized multiple fracturing parameters and standardized multiple geological parameters into a trained fracture network complexity prediction model, causing the trained fracture network complexity prediction model to output the fracture network complexity. This method improves the accuracy of predicting the fracture network complexity of deep coal and shale gas formations.
Owner:PETROCHINA CO LTD +2
Welding quality inspection method and device based on machine vision
ActiveCN120908185Bimprove accuracyImprove efficiencyImage enhancementImage analysisMachine visionWelding defect
This application provides a machine vision-based welding quality inspection method and apparatus, belonging to the field of machine vision and intelligent inspection technology. The method includes: acquiring a target image to be inspected, wherein the target image is an image containing a printed circuit board; inputting the target image to be inspected into a defect detection model for defect detection, and obtaining a defect detection result, which is used to characterize the defect type of the printed circuit board. The machine vision-based welding quality inspection method and apparatus provided in this application can improve the accuracy of welding defect detection.
Owner:YANSHAN UNIV
A tool state real-time monitoring and wear compensation integrated intelligent tool bit
ActiveCN117840816Bavoid damagereduce volumeAutomatic control devicesMeasurement/indication equipmentsWireless transmissionControl system
The application provides a tool state real-time monitoring and wear compensation integrated intelligent turning tool. The integrated intelligent turning tool utilizes a vibration sensor and a force sensor to measure vibration and force in real time during turning, and based on a flexible hinge group, a certain artificial intelligence model is used to predict the wear state and remaining life of the turning tool, and a compensation value is fed back to a control system to control a piezoelectric driver to realize wear compensation. The integrated intelligent turning tool can realize real-time measurement and wireless transmission of vibration and force in turning to an upper computer, and can realize tool state monitoring, tool wear prediction and remaining life and other functions.
Owner:CHONGQING UNIV
A gait recognition method, system, device and medium based on point cloud
ActiveCN120748035Bwell representedComprehensive representationCharacter and pattern recognitionBiological modelsPoint cloudCloud data
The application discloses a gait recognition method, system, device and medium based on point cloud, which comprises the following steps: performing point cloud projection on gait point cloud data to obtain a depth image sequence; encoding the depth image sequence to obtain initial features, inputting the initial features into a large-scale spatial attention module and a small-scale spatial attention module to extract multi-scale enhanced features, and performing feature fusion on the initial features and the multi-scale enhanced features to obtain first depth features; inputting the first depth features into a multi-scale space-time convolution network module to perform space dimension and time dimension feature extraction and fusion through a pseudo 3D convolution chain of several levels to obtain second depth features, and performing aggregation on the second depth features to obtain target depth features; and inputting real-time acquired gait data into a preset gait recognition model to determine a recognition object. The application can improve the accuracy and efficiency of gait recognition.
Owner:GUANGDONG ZHIYUN URBAN CONSTR TECH CO LTD +1
Method for adjusting process parameters in an atom transfer radical polymerization process
ActiveCN120708732BEasy to adjustComprehensive representationBiological modelsChemical processes analysis/designAlgorithmAtom-transfer radical-polymerization
The application discloses a method for adjusting process parameters in an atom transfer radical polymerization process. The method is based on an orthogonal configuration method, divides an infinite chain length into finite elements and orthogonal configuration points, reconstructs a micro quality index of the process, directly solves the micro quality, and then adjusts parameters based on a micro quality model to provide effective guidance for experiments and production. The method includes a chain length discretization method, a micro quality reconstruction algorithm, an adaptive initialization algorithm and a parameter adjustment algorithm. Compared with a traditional parameter adjustment method, the method can directly solve the micro quality index, thereby guiding the parameter adjustment, and is beneficial to simulation, optimization and operation design of polymer production.
Owner:ZHEJIANG UNIV
Patent text processing method, storage medium and computer device
The application discloses a patent text processing method, a storage medium and computer equipment. The method comprises the following steps: obtaining a semantic feature vector corresponding to multi-dimensional semantic information of a patent text and a structure feature vector corresponding to a knowledge graph structure of the patent text; distributing fusion weights of the semantic feature vector and the structure feature vector based on a field scene attribute; fusing the semantic feature vector and the structure feature vector according to the distributed first fusion weight and the second fusion weight to generate a genetic feature vector representing the patent text; and associatively storing a globally unique identifier, the genetic feature vector, multi-dimensional semantic information, a patent knowledge graph and metadata of the patent text corresponding to the patent text. The application realizes feature fusion vectorization and associative storage of the patent text, can comprehensively and accurately represent patent text semantics and patent structure information, guarantees the efficiency, interpretability and traceability of patent retrieval and analysis, and is beneficial to improving the management and application efficiency of the patent text.
Owner:SHENZHEN TECHVISUM TECH LTD
Vulnerability management method and device, storage medium and product
PendingCN122087824AImprove repair efficiencyavoid wastingPlatform integrity maintainanceVulnerability managementDynamic data
The invention discloses a vulnerability management method and device, a storage medium and a product, and relates to the technical field of security vulnerability management, and the method comprises the steps: carrying out the multi-dimensional risk assessment of a to-be-managed vulnerability, and obtaining an initial risk score of the to-be-managed vulnerability; collecting dynamic data of to-be-managed vulnerabilities, and updating the initial risk score in real time through the dynamic data to obtain a standard risk score; and sorting the to-be-managed vulnerabilities based on the standard risk scores to obtain a repair priority sequence of the to-be-managed vulnerabilities. According to the method, comprehensive and accurate assessment of the vulnerability risk is realized, the obtained standard risk score fits the threat situation of the vulnerability in real time, the repair resource distribution can be effectively optimized according to the repair priority sequence, the vulnerability management repair efficiency is improved, and the system security risk is remarkably reduced.
Owner:VIPSHOP (GUANGZHOU) SOFTWARE CO LTD
Donor motion flora feature classification method and system based on cluster analysis
The present application relates to the technical field of flora classification, in particular to a donor exercise flora feature classification method and system based on cluster analysis, the method comprising: performing metagenome sequencing on the fecal samples of donors after exercise intervention and performing biological information purification to obtain pure flora sequence data; comparing the pure flora sequence data with a pre-stored reference genome database, and performing species annotation and abundance spectrum construction on the comparison results to obtain a species composition spectrum; performing feature cascading on the metabolic pathway abundance resolved in the species composition spectrum and the functional gene abundance spectrum identified in the pure flora sequence data to construct an exercise-associated flora feature vector; determining a flora ecological distance based on the exercise-associated flora feature vector, and delimiting a cluster division threshold value according to the distribution characteristics of the flora ecological distance to obtain a flora type after cluster analysis; the present application can improve the efficiency of donor exercise flora feature classification based on cluster analysis.
Owner:JUNYIZHI BIOTECHNOLOGY (HANGZHOU) CO LTD
Device control method, device control apparatus, electronic device, and storage medium
PendingCN122284370AComprehensive representationRefined automatic trigger functionComputer hardwareControl objective
Owner:BEIJING XIAOMI MOBILE SOFTWARE CO LTD
A method and system for identifying typical fault defects of a large oil filling device
PendingCN122658347AEliminate multiple reflectionsEliminate reverberation componentsEvaluation resultFeature vector
The present application relates to oil filling equipment technical field, provide a kind of large oil filling equipment typical fault defect identification method and system, it includes the following steps: step 1, acquisition large oil filling equipment in the ultrasonic signal of running process, and the ultrasonic signal is preprocessed, obtain the voiceprint data to be analyzed;Step 2, extract the multi-dimensional acoustic feature in the voiceprint data to be analyzed;Step 3, construct multi-dimensional feature fusion coding mechanism, the multi-dimensional acoustic feature is weighted and fused, obtain fusion feature vector;Step 4, the fusion feature vector is input into the deep learning model that is pre-constructed and trained, and the fault type and confidence corresponding to the current running state of equipment are output;Step 5, based on the fault type and confidence, calculate fault risk index, and combine preset multi-level early warning threshold, generate equipment state evaluation result and operation and maintenance suggestion.The present application can preferably identify fault defect.
Owner:ELECTRIC POWER RES INST OF EAST INNER MONGOLIA ELECTRIC POWER +1
Traditional Chinese medicine abnormal state recognition method, system, device and storage medium
ActiveCN119622603Bcancel noiseeliminate distractionsCharacter and pattern recognitionBiological modelsFeature vectorMedicine
This application provides a method, system, device, and storage medium for identifying abnormal states of traditional Chinese medicine (TCM), relating to the field of anomaly identification. The method includes: acquiring product information of the TCM to be detected, and determining data acquisition standards for the TCM based on the product information and preset detection rules; inputting image data into a preset image anomaly detection model based on the data acquisition standards to obtain preliminary image anomaly regions; fusing visual feature data and spectral feature data to obtain anomaly feature vectors; inputting the anomaly feature vectors into a preset anomaly state discrimination model to output anomaly state data, and determining the anomaly state based on the anomaly state data and a preset anomaly state judgment threshold to obtain the anomaly state detection result of the TCM to be detected. This method enables timely and accurate identification of abnormal states in TCM.
Owner:CONITECH (BEIJING) MANAGEMENT SOFTWARE CO LTD
A safety evaluation method for energy storage power stations based on real-time monitoring data
This invention belongs to the field of data processing technology, specifically disclosing a safety assessment method for energy storage power stations based on real-time monitoring data. The method includes: performing multimodal feature analysis on voltage and environmental data sequences of the energy storage power station to obtain static voltage feature tensors and static environmental feature tensors; conducting collaborative analysis of the static voltage and environmental feature tensors to obtain an environmental voltage feature correlation group; performing entropy weight dynamic analysis on the environmental voltage feature correlation group to construct a multidimensional state vector; performing time-series deduction on the multidimensional state vector to obtain a safety situation evolution matrix; and performing residual analysis between the safety situation evolution matrix and real-time monitoring time-series data to obtain a comprehensive deviation index; and performing root cause assessment on the comprehensive deviation index to obtain comprehensive risk information. This invention enables more accurate, dynamic, and efficient safety assessment of energy storage power stations, allowing for comprehensive situation perception and rapid identification of risk root causes.
Owner:STATE GRID ENERGY CONSERVATION SERVICE
Construction method and detection method of cigar leaf fingerprint and application thereof
PendingCN122591839AComprehensive representationobjective representation
The application discloses a method for constructing a fingerprint of cigar tobacco leaves, a method for detecting the fingerprint and application of the fingerprint. The method for constructing the fingerprint of the cigar tobacco leaves comprises the following steps: mixing a cigar tobacco leaf powder with a solvent, performing ultrasonic extraction, performing solid-liquid separation, collecting a liquid, and preparing a sample solution; performing ultra-high performance liquid chromatography tandem mass spectrometry on the sample solution to construct the fingerprint of the cigar tobacco leaves; wherein the chromatographic conditions of the ultra-high performance liquid chromatography tandem mass spectrometry comprise that a mobile phase comprises mobile phase A and mobile phase B, the mobile phase A is a 0.1% formic acid aqueous solution, the mobile phase B is a 0.1% formic acid acetonitrile solution, and an elution mode is gradient elution. The fingerprint of the cigar tobacco leaves is constructed by using the ultra-high performance liquid chromatography tandem mass spectrometry, and the overall chemical composition of the cigar tobacco leaves can be comprehensively, objectively and stably characterized, thereby providing a scientific basis for research on comprehensive evaluation of the origin, variety and quality of the cigar tobacco leaves.
Owner:CHINA TOBACCO SICHUAN IND CO LTD
Low-altitude unmanned aerial vehicle target identification and early warning method based on multi-source perception
This invention discloses a method for low-altitude UAV target identification and early warning based on multi-source perception, relating to the field of low-altitude security and control technology. The method includes: acquiring low-altitude perception data from radar, photoelectric, and passive radio frequency sensors, and preprocessing it to form standardized multi-source observation data; establishing a source quality assessment model to calculate source quality factors and performing spatiotemporal alignment of the data; outputting the target fusion trajectory state quantity and confidence level through gated probabilistic correlation and adaptive weighted fusion, and extracting multi-dimensional features such as radar micro-Doppler, photoelectric shape, and radio frequency fingerprint to construct a fusion feature vector input classifier to identify target categories; establishing a threat scoring function by combining trajectory prediction and behavioral pattern analysis, outputting threat level and confidence level, and executing graded early warning based on dynamic thresholds. This invention solves the problems of unstable detection by a single sensor, low identification accuracy, and delayed early warning in low-altitude environments, improving the robustness and predictability of low-altitude UAV target control.
Owner:YULIN INTELLIGENT UNMANNED EQUIPMENT INNOVATION CENTER CO LTD
Data analysis method and system for visually analyzing quality condition of equipment
PendingCN121787966AComprehensive representationaccurate representationNatural language data processingManufacturing computing systemsGraphicsData set
The invention relates to the technical field of equipment quality data analysis, and discloses a data analysis method and system for visually analyzing equipment quality conditions. The method comprises the steps of obtaining an equipment quality index system, and determining data acquisition items according to the system; establishing a multi-source data acquisition platform, and integrating equipment use data, organization quality data and personnel data; performing cleaning and standardization processing on the data; fusing the data by taking the equipment unique identifier as an association key to form a standardized data set; according to different role requirements of an equipment user, a group quality management layer, each enterprise quality management layer and the like, an equipment overall-level analysis model, a system-level analysis model and a product-level analysis model are adaptively called to carry out multi-level mining analysis; results are displayed through a visual chart, and data screening, graph linkage and report export interaction functions are supported. The system is deployed by adopting a B / S architecture. According to the method, multi-source data fusion and multi-dimensional visual analysis are realized, and the efficiency of equipment quality condition analysis and the decision support capability are improved.
Owner:CHINA AERO POLYTECH ESTAB
Multi-element emotion recognition method and device based on electroencephalogram spatiotemporal dynamic characterization
ActiveCN121265045BDecoding refinementDecoding personalization
The application provides a multi-emotion recognition method and device based on electroencephalogram spatiotemporal dynamic representation, and relates to the technical field of biomedical engineering and artificial intelligence. The multi-emotion recognition method comprises the following steps: acquiring electroencephalogram signals generated by a user when watching a target video; performing frequency decomposition on the electroencephalogram signals to obtain a time-domain feature map representing the time sequence dynamic characteristics of the electroencephalogram signals on multiple frequency scales; acquiring an electroencephalogram spatiotemporal dynamic representation representing the dynamic evolution mode of the electroencephalogram signals in the whole brain space according to the time-domain feature map; determining a target emotion sub-group type to which the user belongs among multiple emotion sub-group types, and acquiring a target decoding strategy corresponding to the target emotion sub-group type; and decoding the electroencephalogram spatiotemporal dynamic representation through the target decoding strategy to obtain the multi-emotion of the user. The method of the application can effectively solve the defects existing in the traditional emotion recognition method, and realize accurate recognition of the multi-emotion of the user.
Owner:TSINGHUA UNIVERSITY