Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

15results about How to "Solve extraction difficulties" patented technology

Method for improving satellite data inversion soil salinity by using unmanned aerial vehicle data

The invention relates to a method for improving satellite data inversion soil salinity by using hyperspectral data of an unmanned aerial vehicle. The method comprises the following steps: collecting a soil sample in a test area, and calculating soil salt content; acquiring and preprocessing satellite remote sensing image data of a test area; storing data, outputting a single-band satellite image, and calculating a spectral index; obtaining and preprocessing hyperspectral image data of the unmanned aerial vehicle in the test area; reconstructing and upscaling unmanned aerial vehicle image data pixels to a spatial resolution of 10m; reconstructing the narrow-band spectral data of the unmanned aerial vehicle into broadband spectral data consistent with a satellite image, storing and outputting a single band, and calculating a spectral index; screening a soil salt content characteristic variable, and constructing a soil salt content inversion model by taking the screened characteristic variable as an independent variable and the actually measured soil salt content as a dependent variable; and fitting a function relationship between the upscaling unmanned aerial vehicle soil salt content inversion model and the satellite inversion model by adopting a numerical regression function method to realize correction of the satellite inversion model.
Owner:NINGXIA UNIVERSITY

Digital employee assisting method and system and electronic equipment

The invention provides a digital employee assisting method and system and electronic equipment. The method comprises the steps of obtaining query vector data of a user; performing vector similarity calculation on the query vector data and document data stored in a vector library to obtain a plurality of similar text blocks and the similarity of each similar text block; and displaying the similar text blocks of which the similarity is greater than a preset threshold value through the trained large language model according to a preset prompt word. Through application of model tools such as a large language model, a digital employee auxiliary system which is familiar with related working programs and can perform solution and guidance for specific application scene problems of the employees is provided for the employees, and proper solution and guidance contents are extracted from numerous documents with different formats; a proper model is adopted for adaptive equipment conditions; due to local deployment, the leakage risk of data in the transmission process is avoided, and the information security is guaranteed; relevance and accuracy of answers are ensured, and convenience is improved.
Owner:STATE NUCLEAR POWER AUTOMATION SYST ENGCO

Highway pavement crack detection method based on improved RT-DETR

The invention discloses a highway pavement crack detection method based on improved RT-DETR, and relates to the field of pavement disease detection. The method comprises the following steps: constructing a pavement crack sample set based on pavement crack images; the RT-DETR model is improved based on a high and low frequency attention mechanism; training an improved RT-DETR model based on the pavement crack sample set to obtain a crack detection model; and detecting the acquired pavement image based on the crack detection model, and determining the target crack in the pavement image, thereby effectively solving the problem of difficult crack feature extraction under the condition of a complex pavement, and meanwhile, needing to process interference factors such as noise, shadow and texture in the image, and improving the accuracy of the detection result. The technical problems of poor universality and accuracy of pavement crack identification are solved, and the technical effects of improving the pavement crack feature extraction precision and unifying the pavement disease detection standard are achieved.
Owner:SOUTHWEST FORESTRY UNIVERSITY

Portable meat doping identification chip and detection method

The invention discloses a portable meat doping identification chip and a detection method, and the method comprises the following steps: placing a meat sample slice on a sample bearing layer of the chip, starting the chip to collect a terahertz time-domain spectral signal, and calculating optical parameters of a meat sample in a frequency band of 0.2-2.0 THz; performing principal component analysis on the high-dimensional data of the optical parameters in the whole frequency band to obtain feature vectors; and inputting the feature vector into a pre-trained artificial intelligence model, respectively performing qualitative identification of meat species and quantitative prediction of the doping content, and outputting an analysis report containing a species identification result and a doping ratio.
Owner:吉林警察学院

An expert warehousing method and system for petrochemical engineering

PendingCN122616916ASolve extraction difficultiesRealize warehousing
The application discloses an expert warehousing method and system for petrochemical engineering. The experts to be warehoused are composed of application warehousing experts and designated warehousing experts with high-level professional technology. The method comprises the following steps: collecting basic information and work experience information of historical warehousing experts, analyzing the influence of the operation characteristics of the units to which the experts belong on the experience and professional skills of the experts, and determining multiple expert information classification items as expert extraction conditions; determining whether each application warehousing expert has the qualification of bid evaluation according to the sub-information under each classification item in the reported expert information of each application warehousing expert, then warehousing the experts with the qualification of bid evaluation and the sub-information under each classification item as the warehousing objects to form an initial expert warehouse; and updating the current initial expert warehouse by using the sub-information under the specific classification items configured for each designated warehousing expert, so as to complete the warehousing of experts. The application realizes the warehousing and classification of petrochemical engineering experts.
Owner:CHINA PETROLEUM & CHEMICAL CORP +1

A highway pavement crack detection method based on improved RT-DETR

The present application discloses a method for detecting cracks in a highway pavement based on an improved RT-DETR, and relates to the field of pavement disease detection. The method includes constructing a pavement crack sample set based on a pavement crack image; improving the RT-DETR model based on a high- and low-frequency attention mechanism; training the improved RT-DETR model based on the pavement crack sample set to obtain a crack detection model; detecting the collected pavement image based on the crack detection model to determine the target crack in the pavement image. The present invention effectively solves the problem of difficulty in extracting crack features under complex pavement conditions, and at the same time, it is necessary to process interference factors such as noise, shadows, and textures in the image, which leads to poor versatility and accuracy in pavement crack recognition, and achieves the technical effect of improving the accuracy of pavement crack feature extraction and unifying pavement disease detection standards.
Owner:SOUTHWEST FORESTRY UNIVERSITY

Elastic tensioning sleeve extracting tool

ActiveCN119282963Aextraction reachedSolve extraction difficultiesMetal-working hand toolsClassical mechanicsStructural engineering
The invention discloses an elastic tensioning sleeve extracting tool, and belongs to the field of mechanical tool equipment. The clamping assembly is connected to the end of the supporting component, the clamping assembly has an opening state and a closing state, and when the clamping assembly is in the closing state, the clamping assembly can stretch into an inner hole of the elastic tensioning sleeve; when the clamping assembly extends into the inner hole of the elastic tensioning sleeve and is switched from the folded state to the unfolded state, the clamping assembly and the elastic tensioning sleeve are clamped and fixed. The control assembly is located on the supporting component and used for controlling the clamping assembly to be switched from the folded state to the unfolded state. The tool has the advantages that the scrapping risk of the height control valve caused by the problem that an inner hole is scratched when a pair of nipper pliers or an L-shaped extraction tool is used for extraction is reduced, the extraction efficiency of the elastic tensioning sleeve is improved, and meanwhile the tool can be suitable for disassembly and assembly operation of the elastic tensioning sleeve.
Owner:CRRC QINGDAO SIFANG CO LTD

A container stopper structure

ActiveCN224428482USolve extraction difficultiesImprove sealing
This utility model discloses a stopper structure for a container, including a container body with an opening at the top. A stopper is detachably mounted on the opening. The stopper includes a stopper body and a insert. The stopper body can be inserted into the opening to seal it. The stopper body has an insertion hole into which the insert can be inserted. Fixed rods are mounted on both sides of the insert, and rotating rods are hinged to the fixed rods. The rotating rod includes a rod body that extends from the inner wall of the insert through the outer wall of the insert. A spring abuts between the two rod bodies. A baffle is fixedly mounted at the bottom of the rotating rod, with the baffle and rod body located on opposite sides of the rotating rod. The baffle can extend under the stopper body and move radially along the stopper body so that it moves upward to abut against the bottom surface of the stopper body. This utility model provides a stopper structure for a container that improves sealing performance while facilitating stopper removal.
Owner:SHAOXING ECOM BIOMEDICAL TECH CO LTD

Rolling bearing fault targeted migration diagnosis method and system across working conditions

ActiveCN116026593BSolve extraction difficultiesReduce differences between domainsMachine part testingBiological modelsRolling-element bearingEngineering
The application provides a kind of cross-condition rolling bearing fault targeting migration diagnosis method and system, solve the problem that traditional rolling bearing fault diagnosis algorithm is difficult to extract network deep feature information in source domain and target domain, cannot realize effective cross-domain fault diagnosis.This application uses feature encoder to accurately extract high-dimensional mapping features of the signal from the input rolling bearing vibration signal;Further input the feature to the graph construction layer, mine the deep features of the data, and model the instance graph using the multi-channel kernel graph convolution network;Use the training based on difference and confrontation to minimize the distance between the source domain and target domain distribution, and the classifier uses the extracted domain invariant feature to complete cross-domain fault recognition.Compared with other methods, under the cross-condition of rolling bearing, the deep features can be better extracted for cross-domain transmission, greatly improving the diagnosis accuracy.
Owner:SHANDONG UNIV

Worker helmet two-dimensional code small target detection method and system in factory environment

The invention discloses a worker helmet two-dimensional code small target detection method and system in a factory environment, and relates to the technical field of artificial intelligence and image digital processing, and the method comprises the steps: obtaining a scene image of a worker wearing a helmet with a two-dimensional code in the factory environment in real time; the scene image after standardization processing is input into a target detection model based on a Fast-RCNN network, the Fast-RCNN network comprises a backbone network based on pre-training ResNet18, a region proposal network RPN and a prediction network, depth features of the input scene image are extracted through the backbone network, the depth features are extracted through the region proposal network RPN, a two-dimensional code candidate region is extracted through the prediction network RPN, and the two-dimensional code candidate region is extracted through the prediction network RPN; after the two-dimensional code candidate region is classified and regressed through a prediction network, identifying and outputting a low-resolution two-dimensional code image in the scene image; and inputting the low-resolution two-dimensional code image into a GAN generator, and outputting a high-resolution two-dimensional code image with a corrected geometrical shape.
Owner:SHANGHAI NUCLEAR ENGINEERING RESEARCH & DESIGN INSTITUTE CO LTD

A road background generation method and device, electronic equipment and storage medium

This invention relates to a method, apparatus, electronic device, and storage medium for generating road backgrounds. The method includes: acquiring a keyframe image sequence by extracting frames from a source video of an intersection; performing interactive prompt segmentation on the first frame image in the keyframe image sequence to obtain a segmentation mask of the road region in the first frame image and corresponding prompt information; based on the prompt information, segmenting each frame image in the keyframe image sequence except for the first frame image to obtain a segmentation mask of the road region in each frame image; and determining a target image containing only the road region and free of dynamic occlusions based on the segmentation masks corresponding to all frame images. This solution effectively solves the problem of road background extraction in complex scenes by using interactive prompt segmentation and temporal fusion technology, improving the accuracy and stability of background extraction, and providing high-quality background images for applications in fields such as intelligent transportation.
Owner:BEIJING UNIV OF POSTS & TELECOMM

A method for detecting object edge position based on convolutional neural network

The present invention provides an object edge position detection method based on a convolutional neural network. It relates to the field of edge detection technology, and the method includes: obtaining an object image according to a pre-deployed laser sensor and performing image preprocessing; constructing a training set, training the convolutional neural network once, and extracting features from the pre-processed object image to determine the edge position of the object; pre-deploying an angle sensor, obtaining the training angle between each training data in the training set and the deployed angle sensor, and performing secondary training on the convolutional neural network; inputting the edge position of the object and the angle into the convolutional neural network after secondary training to obtain the edge position of the object; both improving the detection accuracy of the edge position of the object and accelerating the detection speed of the edge position of the object.
Owner:TIMACO (JIANGSU) IND TECHNOLOGY CO LTD

Motion information detection method, device, computer program product and storage medium

This invention discloses a method, device, computer program product, and storage medium for detecting motion information. The method includes: receiving a first reflected signal corresponding to a first radar signal emitted by the detection device; determining the position information and point cloud velocity information of a human body based on the first reflected signal; inputting the position information and the point cloud velocity information into a pre-trained human motion model to obtain motion information, wherein the motion information includes first motion data of a target body part and second motion data of other body parts besides the target body part; filtering out the second motion data based on a preset filtering frequency, and obtaining target respiratory features and target heart rate features based on the first motion data. This technical solution solves the problem of difficulty in extracting heart rate and respiratory information during exercise and improves the measurement accuracy of heart rate and respiratory information.
Owner:SHENZHEN HUAYI MEDICAL TECH CO LTD

Image recognition method for steel bars

PendingCN122135374ASolve extraction difficultiesGuaranteed relevanceInstrumentsPattern recognitionPixel density
This invention discloses an image recognition method for reinforcing bars, belonging to the field of image recognition technology. The method involves acquiring an image of reinforcing bars with parameter annotations, identifying the parameter annotations within the image, and expanding the range of the parameter annotations based on the pixel density surrounding them. Next, by identifying the contour of the reinforcing bars in the image, and based on the overlap between the contour and the expanded parameter annotations, a main contour containing both the reinforcing bar contour and the parameter annotations is obtained. The main contour is then expanded to retrieve other parameter annotations, resulting in candidate influence regions. Based on the overlap between the main contour and the candidate influence regions, other parameter annotations falling within the candidate response regions are matched with the reinforcing bar contour. This invention establishes a mapping between geometric topology analysis and semantic text extraction, enabling image analysis to possess geometric cognitive capabilities, thereby automatically recognizing the shape and parameter information of reinforcing bars and outputting structured data.
Owner:NINGBO HIGHWAY CONSTR MANAGEMENT CENT +1

A method for inferring occluded line vectors based on aircraft images

The present invention provides an obstruction line vector reasoning method based on aircraft images, which belongs to the field of conventional target range optical attitude feature extraction, and is used to solve the problem of difficulty in extracting line vectors caused by perspective conversion vector obstruction and image blur caused by light, motion, etc. in single-station images or multi-station images. The present invention uses 3D-2D projection and multi-vector joint object-image mapping to reason and analyze the obstruction vector in the intersection mode and single-station measurement mode, respectively, to restore the state of the obstruction vector in the sub-station image, and provide intuitive data support for the next step of attitude processing optimization and fault diagnosis.
Owner:CHINESE PEOPLES LIBERATION ARMY UNIT 63875