Product
Patsnap Eureka
For R&D, Patsnap Eureka makes reading and utilizing patents & technical documents easy.
Patsnap Eureka AIR
Designed for self-driven R&D workflows. Generate viable solutions, solve complex R&D challenges, empower your innovation with AI.
Patsnap Eureka Materials
Designed for material experts only. Revolutionize your material R&D, from search, analyze, to developing new materials.
Feature
TechResearch
Generate reliable direction feasibility study reports for your R&D in just a few steps.
TechSeek
Discover and master advanced knowledge NOW. Basics, ideas, possibilities, all at once.
TechMind
As an expert in R&D Theories, TechMind can generates customized viable solutions instantly.
TechRisk
Analyze your overall solution with one click, know your potential R&D risks in advance.
TechMonitor
Get weekly tech updates, stay abreast of the latest tech innovations and key insights.
Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
429results about How to "Implement automatic classification" 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
Device and method for automatically detecting and sorting light emitting diodes (LEDs)
The invention discloses a device and a method for automatically detecting and sorting light emitting diodes (LEDs). The system comprises a first conveying device which is used for loading materials onto LED material strips and conveying the LED material strips and is capable of dotting unqualified LED material strips, a detecting device which is used for detecting the surface appearance, the size, the color and defects of each LED bracket in the LED material strips, a second conveying device which is used for sending out the detected LED material strips, a sorting device which is used for storing out the unqualified LED material strips, a display device which is used for displaying detection data, and a control device which is used for comparing the detection data with standard data to determine whether the LED brackets are qualified or not, and controlling the whole process of material loading, detection, dotting, conveying and sorting of each device. The method comprises multiple steps of standard setting, control device startup, sampling, comparison and output. Products can be automatically classified, the automation degree is high and the labor force is effectively reduced.
Owner:DONGGUAN KECHENDA ELECTRONICS TECH
Electrocardiogram classification method and system
ActiveCN104970789AImplement automatic classificationImprove accuracyDiagnostic recording/measuringSensorsClassification methodsConvolution
The invention relates to an electrocardiogram classification method. The electrocardiogram classification method comprises the following steps that filtering and downsampling are conducted on an original electrocardiogram waveform; horizontal start point moving operation is conducted on electrocardiogram data obtained after filtering and downsampling are conducted; a convolution neural network is led to recognize and classify the electrocardiogram data. The invention further relates to an electrocardiogram classification system. According to the electrocardiogram classification method and system, the classification accuracy rate can be increased, and the effect of the middle link on the final classification performance can be reduced.
Owner:SUZHOU INST OF NANO TECH & NANO BIONICS CHINESE ACEDEMY OF SCI
Intelligent speech recognition and automatic classification garbage can
PendingCN110255014AImprove classification accuracyImplement automatic classificationRefuse receptaclesProximity sensorEngineering
The invention relates to an intelligent speech recognition and automatic classification garbage can. An upright column is arranged on the axis of an outer cylinder body; a plurality of garbage inner barrels uniformly distributed along the circumference are arranged around the upright column; a rotatable garbage transfer table is arranged at the top end of the upright column; a garbage recovery bin is arranged on the garbage transfer table; an opening and closing mechanism is arranged at the bottom end of the garbage recovery bin; a top cover is arranged above the outer cylinder body; a display screen, a proximity sensor, a speech collector and a throwing port are arranged on the top cover; an intelligent camera is arranged in the throwing port; and the intelligent camera, an infrared sensing device, the display screen, the speech collector, a throwing door, a garbage throwing mechanism and a driving device of the garbage transfer table are all connected with a controller arranged in the top cover or the outer cylinder body. The intelligent speech recognition and automatic classification garbage can has the advantages that the corresponding garbage recycling bin can be automatically started according to garbage names directly described by multilingual speeches, so that the automatic classification of domestic garbage is realized, the difficulty of household garbage classification and throwing is greatly reduced, the classification time consumption is greatly reduced, and the garbage classification accuracy is improved.
Owner:中竞科技有限公司
Track center line automatic detection method based on vehicle-mounted mobile laser point cloud
ActiveCN110647798AImprove computing efficiencyQuick splitImage enhancementImage analysisIn vehicleTrackway
The invention discloses a track center line automatic detection method based on vehicle-mounted mobile laser point cloud. The method comprises the following steps: S1, point cloud segmentation of a roadbed and a track; s2, track point cloud classification; s3, automatic track center line detection: according to a cross section design drawing of a standard steel rail, automatically reconstructing astandard three-dimensional geometric model of the steel rail in a segmented manner, carrying out iterative registration on the standard steel rail model and the segmented steel rail point cloud in the S2, and carrying out automatic reconstruction on a segmented three-dimensional model of the steel rail; calculating track geometric parameters by utilizing the reconstructed track three-dimensionalgeometric model, calculating track center line point locations in a segmented manner on the basis of the reference track, and sequentially connecting the track center line point locations extracted inthe segmented manner to form a line center line. According to the method, roadbed and rail point clouds can be rapidly segmented, the area of rail point cloud classification search is reduced, automatic classification of laser point clouds on the surfaces of left and right steel rails is realized, and the precision requirement of existing rail transit midline detection can be met.
Owner:CHINA RAILWAY DESIGN GRP CO LTD
Method and system for achieving automatic voice classification
ActiveCN105427858AReduce manual workloadImprove accuracySpeech recognitionSpeech classificationVoice data
The invention discloses a method and system for achieving automatic voice classification. The method includes the steps of receiving to-be-classified voice data, carrying out voice recognition on the to-be-classified voice data to obtain recognition texts, carrying out acoustic analysis on the to-be-classified voice data to obtain classification characteristics in acoustics, carrying out content analysis on the recognition texts to obtain classification characteristics in content, classifying the to-be-classified voice data by means of the classification characteristics in acoustics, the classification characteristics in content and a pre-built voice classification model to obtain the type of the to-be-classified voice data. By means of the method and system, workloads of workers can be reduced, and classification accuracy of the voice data is improved.
Owner:IFLYTEK CO LTD
Medical image classification method for combining deep characteristic extraction and shallow characteristic extraction
InactiveCN106156793AImprove accuracyImplement automatic classificationCharacter and pattern recognitionFeature extractionBag-of-words model
The invention relates to a medical image classification method for combining deep characteristic extraction and shallow characteristic extraction. The medical image classification method comprises the following steps: training a deep convolutional neural network model, a bag-of-word model and a BP neural network at first, then dividing a medical image to be classified into image sub blocks, inputting the image sub blocks into the deep convolutional neural network model, the bag-of-word model and the BP neural network, which are trained, in sequence to obtain the type of each image sub block, and classifying the medical image to be classified based on the majority voting principle.
Owner:NORTHWESTERN POLYTECHNICAL UNIV
Method for against refuse E-mail
ActiveCN1707492ASimple filterImplement automatic classificationOffice automationPlatform integrity maintainanceEmail addressSpamming
The present invention relates to technology of resisting spamming and provides one reliable method of resisting spamming capable of rejecting most of the spamming. The method includes the following steps: comparing the e-mail sending address with the addresses in the white list and receiving e-mail with sending address in the white list; comparing the e-mail sending address with the addresses in the black list and reject e-mail with sending address in the black list; verifying the sender's defined verification information provided in the request of the acceptor for the e-mail with sending address not in the white list nor the black list; and receiving the e-mail with correct verification information or rejecting e-mail with incorrect verification information.
Owner:TENCENT TECH (SHENZHEN) CO LTD
Intelligent classification garbage can
InactiveCN109368092AImplement automatic classificationRealize automatic fire extinguishingAcutation objectsWaste collection and transferMicrocomputerMicrocontroller
The invention discloses an intelligent classification garbage can. The intelligent classification garbage can comprises a can body, an infrared detector, a micro camera, a single-chip microcomputer and a cloud server; the can body is provided with a garbage feeding port; a garbage allocating device and sub can boxes are arranged in the can body; the garbage allocating device comprises a main motor, a first baffle plate, a second motor and an extension baffle plate; the infrared detector is arranged in the garbage feeding port, and is used for scanning the garbage feeding port in real time; themicro camera shoots garbage fed in the can body; the cloud server identifies the garbage according to image files, and returns the identifying result to the single-chip microcomputer; and an allocating control module controls cooperative work of the main motor and the second motor according to the feedback result. The intelligent classification garbage can achieves multiple functions of automaticclassification of the garbage, prevention of the overflowing phenomenon of the garbage can, prevention of the influence on the work of a system due to power failure, automatic fire extinguishing in the can body, fault self-inspection, environmental-protection checking, green self-service and data acquisition.
Owner:上海良韶智能科技有限公司
Method and system for fine routing inspection of power transmission line through unmanned plane
ActiveCN108365557AImplement automatic classificationReduce workloadImage enhancementChecking time patrolsPattern recognitionComputer vision
The invention relates to a method and system for the fine routing inspection of a power transmission line through an unmanned plane, and the method comprises the following steps: obtaining the type ofa pole to be inspected; obtaining the information of all to-be-inspected parts according to the type of the pole to be inspected; obtaining the image data of all parts according to the information ofall to-be-inspected parts, and enabling the information of all parts and the corresponding obtained image data to be correlated and stored; carrying out the analysis of the defects of all corresponding parts according to the image data of all parts, and obtaining a defect analysis report. compared with the prior art, the method achieves the automatic obtaining of the image data of all to-be-inspected parts of the pole according to the type of the pole, effectively solves a problem of the disordered collection of image data or there is the shortage of data, achieves the automatic classification of the collected image data through the correlation of the collected image data with the information of all parts, greatly reduces the workload, improves the work efficiency, and improves the data classification accuracy.
Owner:GUANGDONG POWER GRID CORP ZHAOQING POWER SUPPLY BUREAU
Novel garbage disposal manipulator system and intelligent control method thereof
InactiveCN106607925AAccurate clampingEfficient and accurate sortingProgramme-controlled manipulatorGripping headsEngineeringBottle
The invention discloses a novel garbage disposal manipulator system and an intelligent control method thereof. The overall structure mainly comprises a support, two manipulators, a conveying belt, eight classifying boxes and eight classifying plates. The two four-freedom-degree manipulators of the same structure are arranged; and three clamping claws arranged in a staggered manner is adopted for a tail end executor of each manipulator. The manipulator system is simple in structure, fast in response and convenient to control, and improves the clamping effectiveness. By adopting the above intelligent control system, the manipulators can accurately reach target bottles and cans, and achieves automatic classification. The sorting and classification problem of bottles and cans in travel rubbish is solved, and technical supporting is provided for healthy development of the travel industry.
Owner:于平
Garbage classification method and device based on image recognition technology and electronic equipment
ActiveCN109684979AImplement automatic classificationImprove classification and recognition efficiencyCharacter and pattern recognitionRefuse receptaclesClassification methodsImage identification
The invention relates to the technical field of image recognition, and discloses a garbage classification method and device based on an image recognition technology and electronic equipment, which areused for recognizing thrown to-be-classified garbage in a garbage can, and the method comprises the following steps: judging whether the to-be-classified garbage exists in a garbage recognition areaor not in a standby state; If the to-be-classified garbage exists in the garbage recognition area, image information of the to-be-classified garbage in the garbage recognition area is collected through a camera; Performing matching recognition on the image information and a preset garbage classification model, and judging the proportion of the recognized garbage to the to-be-classified garbage; And if the proportion reaches a preset proportion threshold value, control information for opening the turnover cover is sent to the garbage can turnover cover control device. According to the method, the garbage types can be quickly and accurately recognized, and the recognition efficiency of garbage classification is improved.
Owner:SHENZHEN INTELLIFUSION TECHNOLOGIES CO LTD
Deep learning and OCR-based bill classification and bill field extraction method
ActiveCN107633239AImplement automatic classificationRealize intelligent extractionCharacter and pattern recognitionPattern recognitionExtraction methods
A deep learning and OCR-based bill classification and bill field extraction method disclosed by the present invention comprises the following steps of selecting a plurality of standard bill images, intercepting the external rectangular contours of the office seal images of the standard bill images as the training samples of the deep learning, and obtaining a deep learning model; classifying the external rectangular contours of the office seals of the to-be-identified bill images via the deep learning model, if the classification is successful, outputting the bill types of the to-be-identifiedbill images and determining the to-be-identified bill images as the standard bill images, if the classification is unsuccessful, determining the to-be-identified bill images as the non-standard bill images. The method of the present invention can classify the bills automatically and extract the bill content intelligently, provides the services of retrieving rapidly and obtaining the bill information rapidly to the financial staff, and enables the working efficiency to be improved.
Owner:JIANGSU HONGXIN SYST INTEGRATION
Sample analysis equipment and sample frame transportation device
ActiveCN107300624AImplement automatic classificationImprove transmission efficiencyMaterial analysisEngineeringEquipment use
Owner:SHENZHEN MINDRAY BIO MEDICAL ELECTRONICS CO LTD
Implementation method for data characteristic-oriented synthetic kernel support vector machine
ActiveCN101807254AHigh accuracy of resultsWide range of applicationsCharacter and pattern recognitionClassification resultSample classification
The invention relates to an implementation method for a data characteristic-oriented synthetic kernel support vector machine, which comprises the following steps: pre-processing data and extracting, selecting and grouping characteristics: switching the data from the data space to the characteristic space, wherein the selected characteristic reflects the characteristic of a classification recognition object; training and verifying a sample and selecting the sample to be classified; selecting and implementing a classifier: selecting the data characteristic-oriented synthetic kernel support vector machine classifier so as to obtain the synthetic kernel parameter through calculation; training the classifier: conducting learning training to DOCKSVM classifier by training the sample; verifying the performance of the classifier: checking performance of the samples under verification in classification so as to obtain the DOCKSVM classifier with satisfied verification; classifying the samples to be classified; and outputting the classification result. The method of the invention more objectively integrates the data biochemical characteristic of the application field into the support vector machine obtained by final training according to the data characteristic of the application field so as to improve the accuracy of the result of specific classification and recognition and achieve wide application.
Owner:YANTAI INST OF COASTAL ZONE RES CHINESE ACAD OF SCI
Sleep snoring sound classification detecting method and system based on depth learning
ActiveCN108670200AImplement automatic classificationAvoid affecting the recognition effectAuscultation instrumentsDiagnostic recording/measuringHypopneaDatum reference
The invention discloses a sleep snoring sound classification detecting method based on depth learning. The method mainly comprises the steps of collecting sleep sound signals of a patient to be detected all night long through a sensor, detecting sonic sections in the sleep sound signals, and obtaining a sonic section map in the sleep sound signals; adopting depth learning for performing snoring sound and non-snoring sound classification on the sonic section map, and reserving a pure-snoring sound recognition result; then, adopting the depth learning for classifying four types of snore sounds for the pure-snoring sound recognition result, and completing automatic recognition and detection on snoring sounds of the patient suffering from obstructive sleep apnea-hypopnea syndrome (OSAHS); according to the snoring sound recognizing and detecting result, counting the number of snoring sounds of each type of the patient to be detected all night long, and obtaining an AHI index of the patientto be detected all night long. The invention further discloses a detecting system of the sleep snoring sound classification detecting method based on depth learning. The method and system can effectively and accurately evaluate whether or not a snoring object falls ill and evaluate the illness degree, and data references are provided for the patient suffering from the OSAHS.
Owner:SOUTH CHINA UNIV OF TECH
Cloud photo album classifying and displaying method and device and server
InactiveCN106156347AImplement automatic classificationRealize managementCharacter and pattern recognitionSpecial data processing applicationsComputer graphics (images)The Internet
The invention provides a cloud photo album classifying and displaying method and device and a server. The cloud photo album classifying and displaying method includes following steps: extracting face feature information in each photo file of a cloud photo album; classifying the photo files corresponding to the face feature information with common features into a same group, and classifying to form multiple groups according to multiple common features; constructing an index table which contains group information of each group, wherein the group information includes group name of a group to which the group information belongs and orientation information of the photo files contained in the group. Photos are classified through face recognition of the photos, so that the photo album is neater and easy to find, and user experience is improved. The cloud photo album classifying and displaying method and device can be applied to automatic classifying of photos photographed by a mobile terminal and photos downloaded from the Internet, the photo album is more detailed and more comfortable to classify, operation is convenient, and efficiency is high.
Owner:BEIJING ANYUNSHIJI TECH CO LTD
Building decoration garbage classifying equipment
InactiveCN102430466AImplement automatic classificationReduce manual laborWet separationImpellerEngineering
The invention relates to building decoration garbage classifying equipment, which consists of a feeding portion, a separating portion and a discharging portion. The feeding portion comprises a hopper, a first support, a first conveying belt and a first transmission mechanism, the separating portion comprises a water tank, a rotary impeller, a framework and a third transmission mechanism, and the discharging portion comprises a second conveying belt, a second support and a second transmission mechanism. In the building decoration garbage classifying equipment in the technical scheme, building decoration garbage is separated by the aid of buoyancy of water in the water tank and rotation of the rotary impeller, automatic classification of the building decoration garbage can be realized, a large quantity of labor is saved, construction efficiency is improved, and furthermore cost and expense are lowered.
Owner:叶甲华
Mobile terminal application classification method and apparatus
InactiveCN105955757AImplement automatic classificationSave search timeExecution for user interfacesInput/output processes for data processingClassification methodsApplication software
The invention discloses a mobile terminal application classification method and apparatus. The method comprises the steps of obtaining a class name of a class that an application belongs to from a preset server; judging whether a first folder named after the class name exists or not on a desktop of a mobile terminal; and if the first folder exists, moving an application icon corresponding to the application into the first folder. The apparatus comprises a class name acquisition module, a judgment module and a classification module. With the adoption of the mobile terminal application classification method and apparatus provided by the invention, automatic classification of local applications in the mobile terminal is realized based on related data in the server provided by an application supplier.
Owner:LETV HLDG BEIJING CO LTD +1
COB (chip on board) optical component automatic testing sorting machine
The invention discloses a COB (chip on board) optical component automatic testing sorting machine, comprising a cabinet, a conveyor belt, a PLC (programmable logic controller) control system, an image system, a constant-current constant-voltage source system, a spectral analysis system, a data analysis system, as well as a feeding mechanism, a testing mechanism, a discharging mechanism, a classifying and receiving mechanism and a turnplate mechanism which are respectively arranged on the cabinet. The function of the automatic testing sorting machine is to realize auto-feeding and auto-discharging, the parameters such as the wavelength, the voltage drop, the luminous flux and the chromaticity coordinates of the COB optical component can be automatically tested online by sampling the light diffusely reflected through an integrating sphere by controlling the constant-current constant-voltage source system, lighting the COB component, and starting the spectral analysis system, and the automatic classification can be realized in combination with the PLC control system, and a subsequent package mechanism can perform the classified package conveniently; the testing and the sorting of the whole COB optical component are automatically performed, the production efficiency is high, the influence from a plurality of human factor is avoided, the detection precision is high, the labor can be substituted, the labor intensity is reduced, and the labor cost is reduced.
Owner:东莞市中谱光电设备有限公司
Method for distinguishing varieties of crop seeds
InactiveCN101738373AStrong penetrating powerWon't hurtMaterial analysis by optical meansOrganic moleculesQualitative analysis
The invention aims to provide a method for rapidly distinguishing varieties of crop seeds by near infrared spectrum and biomimetic pattern recognition. The method establishes a biomimetic pattern recognition model in a near infrared spectrum wavelength region of the crop seed varieties and identifies variety samples of the crop seeds through the biomimetic pattern recognition model. The near infrared spectrum can be used for obtaining characteristic information of all organic molecule hydrogen-containing groups in the samples, and has the advantages of strong substance penetration capacity, no need for performing any pretreatment on the samples, no harm to human body, no pollution to the environment and capacity of implementing automatic classification of the crop seed varieties through a computer by the biomimetic pattern recognition. The near infrared spectrum and the biomimetic pattern recognition are combined to perform rapid, lossless and efficient qualitative analysis on the crop seed varieties, so the method has an important theoretical and realistic significance for distinguishing crop varieties.
Owner:CHINA AGRI UNIV
Video classification method, model training method and device
ActiveCN109919087AImplement automatic classificationImprove processing efficiencyCharacter and pattern recognitionNeural architecturesClassification methodsMotion prediction
Owner:TENCENT TECH (SHENZHEN) CO LTD
Method and system for classification and detection of sleep snoring
ActiveCN107358965AImplement automatic classificationAvoid affecting the recognition effectSpeech analysisSupport vector machineHypopnea
The invention discloses a method and system for classification and detection of sleep snoring. The method includes the steps of picking up the sleep snoring of a patient all night long, and extracting each snoring signal according to the sleep snoring signals of the patient all night long; calculating related features of fourth types of snoring including the snoring before and after a breathing disorder event, apnea snoring, hypopnea snoring and general snoring in the sleep snoring all night long; performing feature dimension reduction using principal component analysis (PCA), classifying the sleep snoring all night long respectively according to the snoring before and after the breathing disorder event, apnea snoring, hypopnea snoring and general snoring through a multi-class support vector machine (SVM), and realizing the recognition of the four types of snoring; and conducting statistics on the snoring signals all night long to obtain statistical results of the number of times of the four types of snoring, and predicting an AHI value according to the statistical results. According to the invention, the automatic classification of four types of snoring is realized accurately, the number of breathing disorder events all night long is determined by using the classification of snoring and the types of snoring before and after to predict the AHI value, and a data reference is provided for the patient with the OSAHS.
Owner:SOUTH CHINA UNIV OF TECH
Method and device for sorting coding and integrated exchange and management of heterogeneous data of enterprise
InactiveCN104111998ARealize automatic collectionImplement automatic classificationSpecial data processing applicationsClassification ruleData mining
The invention provides a method and device for sorting coding and integrated exchange and management of heterogeneous data of an enterprise. Due to the fact that the expressive forms of standard formats of heterogeneous data are unified and heterogeneous data acquiring middleware is programmed, remote and local heterogeneous data of the enterprise are acquired; the acquired heterogeneous data are clustered according to different modes and different topic attribute units, topic attribute units and modes are formed through clustering and can be used for sorting, mode regrouping is performed on the topic attribute units which can be used for sorting and formed through clustering according to sorting restraint, topic data formed by clustering are sorted by selecting one mode with restraint, and a sorting rule of intelligent heterogeneous data is derived; on the basis of an original information system of the enterprise, original codes are converted into new codes through an interface converting mode, and a new code system is gradually achieved through transition; a sharing and exchanging mechanism of the heterogeneous data is constructed based on a uniform service interface. The method and device solve the problems that data are not consistent, data semantic conflict is caused, and a large number of data are in redundancy.
Owner:JIANGXI UNIV OF SCI & TECH
A method and a system for automatically identifying surrounding rock levels by applying while-drilling parameters
ActiveCN109635461AImprove work efficiencyEasy to useDesign optimisation/simulationSpecial data processing applicationsMachine learningIdentification scheme
The invention discloses a method and a system for identifying a surrounding rock level by applying while-drilling parameters. The method comprises the following steps of: preprocessing a data set of the acquired while-drilling parameters; Analyzing the preprocessed data set of the parameters while drilling; determining the contribution rate of each variable in the parameters while drilling by applying different data dimension reduction methods; using an ordered weighted average operator method to carry out weighted average calculation on the calculated contribution rates, carrying out sortingand preferential selection according to the contribution rates obtained after calculation and carrying out combination, determining main characteristic variables of the while-drilling parameters, andon the basis, sample sets of the main characteristic parameters are classified; The established neural network and expert knowledge system is applied to train main characteristic parameters of different classifications, stable weight coefficients and thresholds are obtained, and surrounding rock recognition verification is carried out on the established neural network mathematical model by applying sample data. According to the invention, a machine automatic identification scheme which is higher in working efficiency, more convenient to use and higher in precision can be realized.
Owner:CHINA RAILWAY CONSTR HEAVY IND
Intelligent garbage sorting device, terminal and intelligent garbage sorting system
ActiveCN105620974AIntelligently determine classification categoriesDetermine the classification categoryWaste collection and transferRefuse receptaclesEngineeringClassification types
The invention provides an intelligent garbage sorting device, a terminal and an intelligent garbage sorting system. The intelligent garbage sorting device comprises a garbage throwing opening, a detection component and a conveying passage, wherein the garbage throwing opening is used for receiving current thrown garbage; the detection component is communicated with the garbage throwing opening, and is used for obtaining the attribute information of the current thrown garbage and determining the classification types of the current thrown garbage according to the attribute information; and the conveying passage is connected with the detection component, and is used for conveying the current thrown garbage in corresponding accommodating devices according to the classification types of the current thrown garbage. Through the technical scheme, the classification types of the garbage can be determined intelligently, so as to realize the automatic sorting of the garbage, meet the requirement of the garbage sorting advocated by the modern society, increase the recovery rate of garbage resources, and improve the user experience.
Owner:YULONG COMPUTER TELECOMM SCI (SHENZHEN) CO LTD
Vulnerability automatic classification method supporting vulnerability correlation mining
ActiveCN106897625ASuitable for vulnerability correlation miningMutually exclusiveCharacter and pattern recognitionPlatform integrity maintainanceClassification methodsData mining
The invention relates to a vulnerability automatic classification method supporting vulnerability correlation mining, and belongs to the technical field of information security. The method comprises the specific steps of 1, establishing a vulnerability database, and collecting vulnerability records; 2, determining a category of a privilege set; 3, training a classifier; and 4, testing data. Compared with an existing method, the vulnerability automatic classification method supporting the vulnerability correlation mining has the following advantages that (1) a vulnerability classification result is suitable for the vulnerability correlation mining; (2) categories have mutual exclusiveness and the classification is remarkable; and (3) vulnerability automatic classification is realized, so that the classification efficiency is improved and the labor cost is reduced.
Owner:BEIJING INSTITUTE OF TECHNOLOGYGY
Combined neural network-based text classification method, device and computer equipment
InactiveCN110489550AImprove accuracyImplement automatic classificationNeural architecturesSpecial data processing applicationsData setNerve network
The invention relates to a combined neural network-based text classification method, a combined neural network-based text classification device, computer equipment and a storage medium. The method comprises the steps of inputting to-be-classified texts into a trained first text classification model, and determining a first classification confidence coefficient, wherein the first text classification model is a neural network obtained by training based on a refined data set; if the first classification confidence coefficient is smaller than a first confidence coefficient threshold value, inputting the to-be-classified text into a trained second text classification model, and determining a second classification confidence coefficient; wherein the second text classification model is a neural network obtained by training based on a full data set; and if the second classification confidence is greater than or equal to the second confidence threshold, determining the classification result ofthe second text classification model as the classification result of the to-be-classified text. By adopting the combined neural network to perform intention classification on the to-be-classified text, the high accuracy of a classification result of the to-be-classified text is ensured. The reliability of the intention classification result is good. The automatic classification of text intentionscan be realized, and the application range is wide.
Owner:招联消费金融股份有限公司
Automatic classification system
ActiveCN109928107AImplement automatic classificationReduce pollutionWaste collection and transferCharacter and pattern recognitionSystems designIsolation layer
The invention discloses an automatic classification system. The automatic classification system is designed based on a YOLOV3 technical framework, so that garbage is classified and recycled, garbage pollution is reduced, and meanwhile waste is recycled to the maximum cost. A box body of a structure with an upper layer and a lower layer is designed in the system, a garbage throwing-in opening is formed in the upper layer of the box body, a camera is mounted, an isolation layer is arranged at the upper top of the upper layer of the box body and used for mounting of a solar panel and a storage battery, and therefore the power supply requirement of the system is met. The camera captures thrown-in garbage, and garbage types are recognized and classified through a recognition algorithm. The lower layer of the box body is designed into dual boxes or multiple boxes according to the garbage classes. A mechanical-electric control part is mounted at the joint of the two layers of the box body, two steering engines control rotation of a classification baffle and a control baffle so as to automatically drive garbage to fall into classification boxes corresponding to the types of the garbage. The automatic classification system can achieve garbage automatic classification.
Owner:JIANGXI UNIV OF SCI & TECH
Point cloud data automatic classification method for power transmission line based on random forest model
InactiveCN107292335AImplement automatic classificationCharacter and pattern recognitionLearning machineLearning based
The invention provides a point cloud data automatic classification method for a power transmission line based on a random forest model. With the development and application of the technology of laser radars, an airborne laser radar is gradually introduced to the routing inspection operation of the power transmission line. The laser radar will generate a large amount of point cloud data after the scanning of a power transmission line corridor, and the classification of the point cloud data is the foundation for the subsequent analysis and processing of the point cloud data. However, a conventional manual classification method is larger in workload, and consumes a lot of time. According to the invention, the method achieves the features of machine learning based on the local features of points, and achieves the gradual calculation of all feature points, and then a learning machine is built through a random forest. The point cloud data of manual classification is taken as the training sample for the building a supervised learning model. After the model training, the model is used for the automatic classification of the point cloud data which is not classified.
Owner:云南电网有限责任公司信息中心 +1
Automatic recyclable garbage sorting and recycling device and method based on machine vision
InactiveCN110654739AImplement automatic classificationRealize deliveryWaste collection and transferRefuse receptaclesEmbedded systemElectric machinery
The invention discloses an automatic recyclable garbage sorting and recycling device based on machine vision. The device includes an upper box and a lower box, the front and back of a top plate of theupper box are provided with garbage input ports, and an information processor is installed nearby one garbage input port; an external camera is installed on the upper surface of the upper box, and aninfrared sensor is installed nearby each garbage input port of the upper box; a built-in camera is installed on the upper box, and an LED light module is arranged beside the built-in camera; a WiFi module and a motor drive module are also installed in the upper box; the interior of the lower box is divided into a plurality of garbage compartments, and an infrared sensor is installed on the upperpart of each garbage compartment; and an automatic sorting mechanism and a mechanical transmission mechanism are arranged in the lower box. The invention also discloses an automatic recyclable garbagesorting and recycling method based on machine vision. By means of the device and method, accurate classification and high working efficiency are achieved.
Owner:XIAN UNIV OF TECH
Who we serve
- R&D Engineer
- R&D Manager
- IP Professional
Why Patsnap Eureka
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com