Patents
Literature
10results about How to "Real-time identification" 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
A Text Printing Method and System Based on Speech Recognition
ActiveCN116339655BImprove user experiencereal-time identificationSpeech recognitionNeural architecturesComputer printingTimed text
This invention belongs to the field of text printing technology and discloses a text printing method and system based on speech recognition. The method includes the following steps: constructing a text printing template database; constructing a mixed-language speech recognition model; acquiring speech audio data in real time and performing speech recognition; matching several corresponding text printing templates; selecting a text printing template; fusing the real-time speech text data with the selected text printing template; and printing the real-time text printing data. The system includes a database construction unit, a model construction unit, a storage unit, a speech audio acquisition unit, a speech recognition application unit, a template matching unit, a template selection unit, a data fusion unit, and a printer. This invention solves the problems of low intelligence, poor speech recognition effect, low recognition efficiency, and lack of organic integration in existing technologies.
Owner:魏鹏飞
Park weed accurate identification method and system based on improved YOLOv11 deep convolutional network
PendingCN121999203ASpeed up the extraction processImprove the ability to distinguishCharacter and pattern recognitionBiological modelsData setAlgorithm
The invention discloses a park weed accurate identification method and system based on an improved YOLOv11 deep convolutional network, and the method comprises the steps: 1, constructing a multi-scene park weed image data set, 2, carrying out the data enhancement and preprocessing, 3, constructing an improved YOLOv11 lightweight network model, 4, designing a self-adaptive loss function, and 5, carrying out the recognition of a multi-scene park weed image data set. Multi-stage model training and optimization are executed; and step 6, weed real-time identification and result output are realized. According to the method, a lightweight attention mechanism and an improved multi-scale feature fusion structure are introduced, the extraction and distinguishing capability of the network on small-scale weed features under a complex background is remarkably enhanced, the false detection and omission ratio is effectively reduced, and the dynamic label distribution strategy and a loss function fusing global context information are adopted, so that the robustness of the network is improved. And the detection robustness and the positioning precision of the model in dense, shielded and form-variable weed scenes are improved.
Owner:BEIJING GUOKELIN TECHNOLOGY CO LTD
A recognition method, apparatus, device and medium
The application discloses a recognition method, device, equipment and medium, the method comprises: obtaining an image to be recognized containing at least a target object; target detection is performed on the image to be recognized to obtain a first image; wherein the first image comprises an image containing the target object segmented from the image to be recognized; direction detection is performed on the first image to obtain direction information of the first image; the first image is corrected based on the direction information to obtain a second image; the second image is recognized to obtain a recognition result of the target object.
Owner:CHINA MOBILE COMM LTD RES INST +1
A power grid dispatching support system fault diagnosis method and device
ActiveCN115441456Breal-time identificationquick identificationEnsemble learningForecastingPrediction algorithmsTechnology fusion
The application discloses a kind of power grid dispatching support system fault diagnosis method and device, method includes: obtaining the operation and maintenance index acquisition data of server, process;At preset fixed time, based on index time series prediction algorithm, the index future prediction data of preset time range is obtained;In combination with operation and maintenance index anomaly detection algorithm, identify system operation failure, generate operation failure information;All operation failure information is summarized, complete operation failure detection, and send operation failure alarm.The application realizes the operation and maintenance index time series prediction technology under the condition of mass model, establishes adaptive and self-learning model construction and optimization architecture, based on index prediction automatically sets dynamic threshold, through the multi-technology fusion analysis based on mass operation and maintenance data, real-time, fast, accurately identify system failure, realize experience type to intelligent analysis type management change, realize system failure accurate perception, guarantee control system safe, reliable and stable operation.
Owner:NARI TECH CO LTD +1
A method and system for rapid identification of risk areas on rock slopes
ActiveCN120869065Breal-time identificationquick identificationClimate change adaptationForecastingRisk levelPoint cloud
This invention discloses a method and system for rapid identification of risk areas on rock slopes, belonging to the field of rock slope engineering monitoring and geological disaster early warning technology. The method includes: a model construction stage, constructing a three-dimensional point cloud model of the original rock surface of a steep rock slope based on UAV oblique photography and three-dimensional laser scanning; a preliminary risk zone delineation stage, delineating preliminary risk zones on the original rock surface based on the three-dimensional point cloud model; a system deployment stage, deploying a slope microseismic monitoring system according to the preliminary risk zones before slope excavation; a risk level evaluation stage, using joint spacing and the moment magnitude of microseismic events as preliminary evaluation indicators to delineate slope excavation risk areas and evaluate risk levels; and a risk verification stage, issuing early warnings based on risk levels, verifying risk levels using in-depth evaluation indicators, and dynamically delineating the final risk area range through multi-source parameters. This invention can dynamically and rapidly identify risk areas on rock slopes in real time as excavation progresses.
Owner:中国水利水电第七工程局有限公司
An intelligent in-machine inspection device and method
PendingCN122077448AEliminate the effects ofGuaranteed accuracyMeasurement/indication equipmentsComputer hardwareNumerical control
This invention provides an intelligent in-machine inspection device and method. The device includes: a probe signal transmitter, mounted on the tool post of a CNC machine tool to move with each axis of the machine tool for in-machine inspection of the machined workpiece; a probe signal receiver, mounted on the CNC machine tool and wirelessly connected to the probe signal transmitter for receiving inspection data collected by the probe signal transmitter; a CNC machine tool control system, communicatively connected to the probe signal receiver for receiving inspection data fed back by the probe signal receiver and generating error detection results; and a host computer system, communicatively connected to the CNC machine tool for receiving error detection results transmitted by the CNC machine tool and generating an inspection report. This invention achieves automatic in-machine inspection, real-time error compensation, and automatic data transmission for wheel hub machining, solving the technical problem that existing inspection methods cannot meet the requirements of fully closed-loop intelligent in-machine inspection.
Owner:SHENYANG INST OF TECH
Lightweight garbage detection method and system based on improved YOLOv11s model
PendingCN121982687Areal-time detectabilityreal-time identificationCharacter and pattern recognitionNeural learning methodsComputer graphics (images)Rgb image
The invention discloses a lightweight garbage detection method and system based on an improved YOLOv11s model, and the method comprises the following steps: S1, only employing a monocular camera, and obtaining the RGB image data of a road through the monocular camera; s2, cutting the acquired image data, cutting off the upper half part of the road image, and keeping key information related to a ground area below the image; and S3, calling an improved YOLOv11s network model, inputting the preprocessed image into the network model, then starting a detection code to carry out image reasoning detection, and drawing a detection result on the image to obtain result image data containing junk bounding box coordinates, junk categories and detection confidence information. According to the method, garbage in complex environments such as urban roads, green belts and community scenes can be efficiently detected and recognized in real time at low cost, and particularly, the detection performance of small-size target garbage is excellent.
Owner:城市之光(深圳)无人驾驶有限公司
An adaptive micro-doppler corner point feature extraction method and device
The application discloses a kind of self-adapting micro-doppler corner point feature extraction method and device, comprising: it is proposed to use micro-doppler corner point feature to realize through-wall radar human behavior recognition, and gives a kind of self-adapting corner point feature extraction method based on Gauss difference convolution filter and deformable convolution network;Micro-doppler corner point feature is defined as the point that gray scale sharply changes in different directions in radar square distance-time image and square doppler-time image, reflects the inflection point of human body limb node's motion trajectory curve, stationary point, curve intersection and boundary;The corner point feature extraction method proposed uses Gauss difference convolution filter to extract micro-doppler corner point supervision label on simulation data, then trains μD-CornerDet model using these labels;Inference stage, only μD-CornerDet model is used to obtain corner point feature map for measured data;The application verifies the effectiveness and robustness of the proposed method through numerical simulation and measurement.
Owner:BEIJING INST OF TECH
Tension anomaly detection method and device for anchoring system on floating photovoltaic platform
PendingCN121990113Aimprove securityImprove operation and maintenance efficiencyOpen water surveyApparatus for force/torque/work measurementMooring systemAnomaly detection
The invention provides a tension anomaly detection method and device for an anchoring system on a floating type photovoltaic platform, and the method comprises the steps: building an initial tension distribution topological graph based on the platform structure of the floating type platform and the arrangement information of each mooring point after collecting the tension data of each mooring point and the real-time wind wave direction data of the floating type platform in real time; mapping the tension data of each mooring point to the initial tension distribution topological graph; inputting the mapped tension distribution topological graph into a pre-trained anomaly recognition model, and recognizing abnormal nodes with abnormal tension distribution; and based on the mooring point position corresponding to the abnormal node and the real-time wind wave direction data, a failed target seabed anchor is positioned. According to the method, the early tension abnormity of the floating type photovoltaic platform anchoring system can be accurately identified and positioned in real time, and the safety and the operation and maintenance efficiency of the platform are remarkably improved.
Owner:HUANENG (FUJIAN ZHANG ZHOU) ENERGY CO LTD +1
Face expression recognition method and device based on multi-teacher network, equipment and medium
ActiveCN117152822Breal-time identificationSimple structureCharacter and pattern recognitionBiological modelsPattern recognitionNetwork structure
Owner:SHENZHEN POLYTECHNIC