Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

59results about How to "Achieve the purpose of identification" patented technology

Display apparatus having fingerprint identification function

The invention provides a display apparatus having a fingerprint identification function, relating to the technical field of display and solving the problems that a finger and a fingerprint identification device are large in distance, and the identification precision is low. The fingerprint identification device includes a plurality of identification units that are arranged in an array, and a light-sensitive element is arranged in each identification unit. The light-sensitive elements perform the photoelectric conversion on the incident light. In addition, the fingerprint identification device further includes a collimating filter layer arranged in the light-receiving sides of the light-sensitive elements. The collimating filter layer includes a plurality of strip-like light guide portions spaced apart and arranged in parallel and irradiate the incident light to the light-sensitive elements in parallel. The display apparatus having the fingerprint identification function is used for fingerprint detection.
Owner:BOE TECH GRP CO LTD

Method utilizing HPLC to test seventeen phenol substances contained in grapes and oranges

The invention discloses a method utilizing the HPLC (High Performance Liquid Chromatography) to test seventeen phenol substances contained in grapes and oranges, which comprises the following steps: firstly, separating the peel and pulp of the oranges or the grapes; secondly, drying and crushing the peel and pulp, and adding DMSO (Dimethyl Sulfoxide) : methanol (1:1) or a methanol solution into the peel and pulp to execute extraction; thirdly, after the collection of supernatant fluid, repeatedly extracting and compounding the supernatant fluid to execute HPLC detection; and lastly, identifying the sorts of the grapes and the oranges according to different sorts, content analysis of various phenol substances measured in different producing areas, and different chemical compound contents. The method disclosed by the invention adopts the HPLC to synchronously separate and test the seventeen phenol substances, and achieves the test to the ingredients and contents of the seventeen chemical compounds in different sorts of fruits such as the orange and the grapes and in wine, is simple in the pretreatment of the sample and low in cost, can synchronously test the ingredients and the contents of the phenol substances in the fruits, fruit juices and fruit wine.
Owner:INST OF AGRI ENG TECH FUJIAN ACAD OF AGRI SCI

Network data flow recognizing system and method

The system includes recognition module for data stream and character base for data stream. The character base for data stream includes multiple characters of network data streams. Based on characters of network data stream in character base for data stream, the recognition module for data stream identifies specific data stream. The invention also discloses relevant method for identifying network data stream. Through matching to characters of network data streams, the invention identifies application type of data stream. Identifying classified data stream reduces amount of calculation for matching character effectively so as to reach purpose for recognizing application service of P2P network television.
Owner:江苏钊阳冷暖科技有限公司

User relation recognition method and device

The invention discloses a user relation recognition method and device and belongs to the field of network technology. According to the method, a user relation classification model obtained through training by use of property information of users and interaction information among the users is utilized to perform relation recognition on to-be-recognized users. Since model training is performed basedon the property information of the users, the interaction information among the users, etc., the user relation classification model can represent accurate relations among the users, and accordingly the purpose of recognizing the relations among the users is achieved. Moreover, the user relations obtained through recognition are high in accuracy and beneficial for pertinently making application strategies for the relations among the users subsequently, and a powerful basis is provided for commercial operation, etc.
Owner:TENCENT TECH (SHENZHEN) CO LTD

Communication radar radiation source identification method in presence of unsteady SNR (Signal Noise Ratio)

InactiveCN105426832AAchieve the purpose of identificationOvercoming the requirement for signal-to-noise ratio stabilityCharacter and pattern recognitionFeature vectorSignal-to-noise ratio (imaging)
The invention provides a communication radar radiation source identification method in the presence of an unsteady SNR (Signal Noise Ratio). The communication radar radiation source identification method comprises the steps of performing discrete normalization respectively for different types of radiation source signals; capturing the same discrete point number for signals of each radiation source so as to respectively compose a respective radiation source signal sequence; regrouping the composed radiation source signal sequences to obtain a series of feature vectors; selecting a multi-fractal dimension, then calculating the feature vector of the multi-fractal dimension feature of the signals in the presence of multiple different signal noise ratios and then storing the feature vector of the multi-fractal dimension feature as a feature database; training the feature vectors in the database by utilizing a neural network so as to obtain public features of the same type of the radiation source signals; and training and testing a neural network system by regarding a to-be-identified signal as an input so as to realize identification of the radiation source signals in the presence of the unsteady SNR.
Owner:SHANGHAI DIANJI UNIV

29 micro-haplotype sites, screening method, multiplex amplification system and application

The invention discloses 29 micro-haplotype sites, a screening method, a multiplex amplification system and an application. The screening method comprises the following steps: acquiring population data, acquiring micro-haplotype genotypes and allele frequencies from the population data, calculating forensic related parameters of candidate sites in different populations and excluding sites affectingsubsequent sequencing typing to obtain the 29 micro-haplotype sites; designing primers and amplification conditions according to the 29 micro-haplotype sites, and establishing the multiplex amplification system based on three-round PCR amplification systems. According to the multiplex amplification system, DNA templates extracted from mixed biological samples are amplified, amplification resultsare subjected to large-scale parallel sequencing, value of the sequencing depth of each micro-haplotype site in the DNA templates is obtained, and finally, the purpose of typing the mixed biological samples is achieved. The multiplex amplification system is suitable for large-scale parallel sequencing technology and has the advantages of high detection flux, high detection speed, large quantity ofobtained data, more accurate detection results and the like.
Owner:NANJING MEDICAL UNIV

Modulating signal recognition method based on complexity feature under low signal to noise ratio

The invention provides a modulating signal recognition method based on a complexity feature under low signal to noise ratio. The method comprises the following steps: extracting multi-fractal dimension features of different communication modulating signals, protruding features of different probability points in a time signal sequence so as to extract the features of different communication modulating signal types; furthermore, grouping pre-processed discrete-time signal sequences so as to simplify the computation of the multi-fractal dimension on the one hand, and translate the long time signal sequence into small sequence sections to observe and compute on the other hand, thereby performing small-range feature expression on the signal, and extracting the feature of the signal in a more refined manner; moreover, performing grey correlation processing on the extracted multi-fractal dimension feature of the unknown communication modulating signal and the computed multi-fractal dimension feature of the known communication modulating signal in a database, selecting the modulating type of the signal with large correlation degree as the modulating type of the unknown communication modulating signal, and then realizing the classification recognition of the modulating type.
Owner:SHANGHAI DIANJI UNIV

Asset identification method and device

ActiveCN110535727AAchieve the purpose of identificationSolve technical problems with low recognition efficiencyOther databases queryingData switching networksIp addressWorld Wide Web
The invention provides an asset identification method and device, and relates to the technical field of network security, and the method comprises the steps: obtaining asset data of to-be-identified assets, and enabling the asset data to comprise an access IP address, an access port parameter, a service IP address, a service port parameter, and a protocol used by the to-be-identified assets; judging whether a database contains asset data or not; and if the database does not contain the asset data and the first preset IP address range contains the access IP address of the to-be-identified asset, the to-be-identified asset being an internal asset, and the internal asset being an asset corresponding to the first preset IP address range, so that the technical problem of relatively low identification efficiency of an existing asset identification method on unknown assets is solved.
Owner:HANGZHOU ANHENG INFORMATION TECH CO LTD

Weak modal identification and time domain reconstruction method for ocean structure

The invention relates to a weak modal identification and time domain reconstruction method for an ocean structure, and particularly provides a method for the weak modal identification of the ocean structure when the test signal of the ocean structure contains a high-level noise. The method comprises the steps of S1, acquiring the really measured signal of the ocean structure; S2, conducting the anharmonic decomposition on the really measured signal; S3, separating and identifying the extreme values of a weak modal; S4, constructing the time domain signal of the weak modal. According to the technical scheme of the invention, the defect in the prior art that based on the conventional modal recognition method, the weak modal submerged in a high-level noise is difficult to extract can be overcome. Based on the fact that both extreme values and residue values are complex numbers, the time sequence form of really measured signals is constructed. Therefore, time-domain signals can be reconstructed more accurately. Meanwhile, the method provides a novel means for the weak modal extraction of the ocean structure and the time domain reconstruction, thus being wide in the prospect of engineering application.
Owner:OCEAN UNIV OF CHINA

Fingerprint identification method and device, electronic equipment and storage medium

The embodiment of the invention provides a fingerprint identification method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a to-be-identified fingerprint image; inputting a fingerprint image pair formed by combining the to-be-identified fingerprint image and a target fingerprint image into a fingerprint identification model; and when the matching probability output by the fingerprint identification model meets a preset condition, determining that the to-be-identified fingerprint image is matched with the target fingerprint image. By the adoption of the technical scheme, generalization and accuracy of fingerprint recognition can be improved, meanwhile, feature styles do not need to be designed manually, and time cost is reduced.
Owner:BEIJING JIIOV TECH CO LTD

Target identification method based on cooperative passive detection multidimensional information

The invention relates to a target identification method based on cooperative passive detection multidimensional information. The invention aims at a multi-station radar cooperative detection system, and mainly aims to solve the problem that a target platform equipped with a fixed radar combination cannot be identified as it is impossible to simultaneously identify multiple pieces of radar workingat different bands in single-radar passive detection because of limited frequency resources. The method includes the following steps: (1) a local station exchanges information with other cooperative stations, and the detection band and the detection range are made clear; (2) the local station regularly receives a target EDW and model information of radar to which the target EDW belongs transmittedby a current other station; (3) the local station carries out platform correlation calculation, determines important identification platforms, calculates and updates the minimum determination radar set of each important identification platform, and guides the other stations in detection; and (4) when an EDW and the model of radar to which the EDW belongs acquired at a time can completely cover the minimum determination radar set of a platform, the local station carries out range consistency determination, and outputs a platform determination result. According to the invention, the identification accuracy of a passive detection platform can be improved.
Owner:THE 724TH RES INST OF CHINA SHIPBUILDING IND

Vehicle-mounted image processing method and device and vehicle

The invention discloses a vehicle-mounted image processing method and device and a vehicle. The vehicle-mounted image processing method comprises the steps of obtaining a synthetic aperture radar image of a target object; matching the synthetic aperture radar image of the target object with pre-stored synthetic aperture radar images; and in the case of successful matching, determining an object recognition result corresponding to the synthetic aperture radar image of the target object according to a corresponding relation between the pre-stored synthetic aperture radar images and object recognition results. The vehicle-mounted image processing method solves a technical problem that video data collected by a camera on the vehicle cannot be recognized under poor light or bad weather in the prior art.
Owner:BEIJING AUTOROAD TECH CO LTD

Neural network voice recognition method and system for home spoken language environment

The invention discloses a neural network voice recognition method and system for a home spoken language environment. The method comprises the steps of building a model: adding a long-term and short-term memory network into a deep neural network, and building a combined neural network DNN-LSTM model, preprocessing the acquired voice data set to obtain a feature vector set, taking the feature vectorset as the input of the DNN-LSTM model for iterative training, and training to an optimal acoustic model, respectively obtaining a Chinese output probability vector set and an English output probability vector set from an input voice signal of an unknown language and the trained DNN-LSTM model, and performing language matching according to the Chinese output probability vector set and the Englishoutput probability vector set, and outputting a judgment result. The method can quickly and accurately identify the content of the speaker in the home scene, and can be widely applied to the actual home scene.
Owner:NANJING UNIV OF POSTS & TELECOMM

SNP molecular marker for identifying Shanghai colorful waxy corn NO.1 and identifying method thereof

Disclosed are an SNP molecular marker for identifying Shanghai colorful waxy corn NO.1 and an identifying method thereof. The identifying method comprises the steps of using a sequence of nine SNP sites obtained through degeneracy genomic sequencing of Shanghai colorful waxy corn NO.1 2b-RAD to design nine pairs of AC-PCR primers based on the sequence of the SNP sites; analyzing an obtained fingerprint spectrum through a PCR amplification technology by agarose gel electrophoresis; identifying whether the product is the Shanghai colorful waxy corn NO.1 according to patterns of electrophoretic bands of the nine SNP sites. The number of samples to be detected is small, the method is simple and quick, identified results are accurate, and good application and popularization prospects are achieved.
Owner:SHANGHAI ACAD OF AGRI SCI +1

Method for identifying plastic mechanical parameters of metal material by adopting spherical indentation morphology

The invention discloses a method for identifying plastic mechanical parameters of a metal material by adopting spherical indentation morphology, which comprises the following steps of: acquiring an indentation experiment outline snapshot remained on the surface of a test piece, establishing an indentation outline snapshot matrix, establishing a subspace of the indentation outline snapshot by adopting an orthogonal decomposition algorithm, and realizing direct association of the material plasticity mechanical parameters and the indentation contour snapshot subspace coordinates in the subspace; and defining a difference allowable value between the indentation experiment contour snapshot and a series of simulation contour snapshots in the subspace, and obtaining the identification result of the mechanical property parameters of the tested material according to the distribution characteristics of the difference allowable value in the material parameter interval. During material parameter identification, a series of direct comparison between indentation contour data obtained through prediction and indentation experiment contour data is used, the purpose of material parameter identification is achieved, the possible parameter identification local optimum problem in the large-scale numerical iteration process is avoided, and the method is higher in efficiency and more reliable.
Owner:XIDIAN UNIV

Identification method for conventional rice varieties Huai rice No.5 and No.18 based on InDel marks

The invention belongs to the technical field of creature recognition and particularly provides an identification method for conventional rice varieties Huai rice No.5 and No.18 based on InDel marks. 24 pairs of peculiar DNA primers designed according to inserted / missing difference segments obtained through comparison of whole-genome DNA sequences of a japonica rice variety Nipponbare and an indica type rice variety 93-11 are used for performing DNA extraction, DNA segment amplification, electrophoretic separation and electrophoretogram analysis on Huai rice No.5 and No.18 to identify the Huai rice No.5 and No.18 varieties. Specifically, 24 pairs of InDel primers are used for analyzing a fingerprint spectrum obtained on the basis of a polymerase chain reaction and vertical gel plate electrophoresis, and then whether the varieties are conventional rice varieties Huai rice No.5 and No.18 or not is determined according to the electrophoretic band type of 24 InDel loci. The number of required detected samples is small, the method is convenient and rapid to use, the identification result is accurate, and the method is applied to the market for identification of authenticity of the Huai rice No.5 and No.18 varieties.
Owner:JIANGSU TIANFENG SEEDS IND CO LTD

Fruit epidermis micro-damage detection method based on X-ray and contrast enhancer

PendingCN113744204ASolve the problem that it is difficult to identify slightly damaged fruitsAvoid influenceImage enhancementImage analysisBiotechnologyMedicine
The invention relates to a fruit epidermis micro-damage detection method based on X-rays and a radiography enhancer. The method comprises the following steps: step 1, soaking and cleaning the epidermis of a fruit to be detected, and adding a potassium iodide radiography enhancer into a cleaning solution; 2, imaging the fruits to be detected for multiple times through the X-ray imaging device to obtain X-ray images of the fruits to be detected; and step 3, inputting the X-ray image of the to-be-detected fruit into the fruit detection deep learning model, and identifying damage features of the X-ray image of the to-be-detected fruit and outputting an identification result by the fruit detection deep learning model. The damaged fruits can be effectively and quickly screened out, and the damaged fruits are prevented from being affected by diseases to healthy fruits.
Owner:HUAZHONG AGRI UNIV

Processing method and device for making call multi-dimensionally

The invention discloses a processing method and a processing device for making a call multi-dimensionally. The method comprises the steps of display a first control and a second control in a calling interface of a dialing application in the case that a user calls the dialing application via terminal equipment, wherein the first control is used for dialing a number, and the second control is used for instructing the user to select an operation concurrent with dialing; receiving a first trigger signal used for selecting an operation type via the second control; receiving the second triggering signal used for making the call via the first control; and making the call and operating according to the selected operation type according to the second trigger signal, wherein data sent in the operation type is used for displaying the opposite party of the call on an answering interface. According to the method and the device provided by the invention, the technical problem of call missing and call harassment caused by incapability of clearly recognizing identity information of a caller is solved.
Owner:北京佰人科技有限责任公司

Speech recognition method, device and system

PendingCN111916062AAchieve the purpose of identificationRealize the technical effect of recognitionSpeech recognitionAcoustic modelAcoustics
The invention discloses a speech recognition method, device and system. The method comprises the steps that speech to be recognized is acquired, wherein the speech to be recognized is speech data containing at least one language; the speech to be recognized is recognized based on a recognition model, and a recognition result is obtained, wherein the recognition model at least comprises a mixed acoustic model, a mixed language model and a mixed dictionary, the mixed acoustic model comprises acoustic models of multiple languages, the mixed language model comprises language models of multiple languages, and the mixed dictionary comprises dictionaries of multiple languages. According to the invention, the technical problem that only the speech of a specific language can be recognized and the mixed speech cannot be recognized in the prior art is solved.
Owner:ALIBABA GRP HLDG LTD

Safety and protection equipment detection method for realizing TCP protocol stack information leakage based on ALG protocol

The invention discloses a safety and protection equipment detection method for realizing TCP protocol stack information leakage based on an ALG protocol. The method comprises the following steps thatS1, a client sends a detection message accommodating the ALG protocol stack to a server; S2, the server responds to the detection message, and a response packet of the server responding to the detection message comprises basic information of the detected software and protocol stack information of the safety and protection equipment; and S3, the client receives the response packet. By constructingthe detection message accommodating the protocol stack of the protection equipment, the protection equipment returns corresponding protocol stack information, so that the protection equipment which istransparently deployed is identified, and the purpose of truly identifying the network equipment is achieved.
Owner:WEBRAY TECH BEIJING CO LTD

Method for identifying medicinal material veratrum nigrum

The invention provides a method for identifying a medicinal material veratrum nigrum. The method comprises the following steps: extracting the medicinal material veratrum nigrum to obtain a characteristic extract of the medicinal material veratrum nigrum with an active component group, performing IGD nuclear magnetic resonance carbon spectrum fingerprint spectrum detection on the characteristic extract, obtaining characteristic peak intensities of a plurality of active components in the characteristic extract according to the fingerprint spectrum, measuring the characteristic peak intensities of corresponding standard reference articles of the active components in the same mode, measuring the absolute content of the standard reference articles in the medicinal material veratrum nigrum by using a quantitative analysis method, and calculating the content of the active components in the medicinal material veratrum nigrum and the content of the active component group by using the ratio of the characteristic peak intensities and the absolute content of the standard reference articles. According to the method, the IGD nuclear magnetic resonance carbon spectrum fingerprint spectrum technique is adopted, the compound in the medicinal material veratrum nigrum and the ratio of the compounds are reflected, and the identification on the varieties and the quality of the medicinal material veratrum nigrum is accomplished.
Owner:王顺才

Method, apparatus and system for identifying an object

The invention discloses a method, an apparatus and a system for identifying an object. The method comprises the following steps: obtaining identification information of an object to be identified in apreset area and eye movement data of the object to be identified; Determining fixation information of a fixation target area of an object to be identified according to the identification informationand the eye movement data; The object to be identified is identified according to the fixation information. The invention solves the technical problem that the identification accuracy rate of the existing identity authentication is low.
Owner:BEIJING 7INVENSUN TECH

A non-invasive electrical appliance identification method based on boost model

The invention discloses a non-intrusive electrical appliance identification method based on the Boost model, which comprises the following steps: 1. collecting data from electric meters by adopting unlabeled data collection; , and record the power data of the meter and the corresponding electrical label; 3. First, use the Bootstrap algorithm to expand the labeled set, and combine it with the unlabeled set to form a training set, and then use it to establish a classification model; 4. Collect power mutation events in real time, use the training A good model classifies it and displays the identified electrical consumer results to the user; 5. Add the new sample and new label in the pre-identification stage to the original labeled data set, and repeat steps 3 and 4; 6. Use a model that meets the accuracy requirements to identify electrical appliances, and feed back to users or demanders in real time; the invention can realize the identification of electrical appliances among residential users through the power data of the total electric meter and a small amount of training data.
Owner:无锡英臻科技股份有限公司

A Target Recognition Method Based on Cooperative Passive Detection of Multidimensional Information

The invention relates to a target identification method based on cooperative passive detection multidimensional information. The invention aims at a multi-station radar cooperative detection system, and mainly aims to solve the problem that a target platform equipped with a fixed radar combination cannot be identified as it is impossible to simultaneously identify multiple pieces of radar workingat different bands in single-radar passive detection because of limited frequency resources. The method includes the following steps: (1) a local station exchanges information with other cooperative stations, and the detection band and the detection range are made clear; (2) the local station regularly receives a target EDW and model information of radar to which the target EDW belongs transmittedby a current other station; (3) the local station carries out platform correlation calculation, determines important identification platforms, calculates and updates the minimum determination radar set of each important identification platform, and guides the other stations in detection; and (4) when an EDW and the model of radar to which the EDW belongs acquired at a time can completely cover the minimum determination radar set of a platform, the local station carries out range consistency determination, and outputs a platform determination result. According to the invention, the identification accuracy of a passive detection platform can be improved.
Owner:THE 724TH RES INST OF CHINA SHIPBUILDING IND

Transformer area user-transformer relation identification system based on transmitting and decoding equipment

The invention discloses a transformer area user-transformer relation identification system based on transmitting and decoding equipment, and relates to the field of transformer area user-transformer relation identification systems, which comprises a first-stage box transformer area, a second-stage branch box area, a third-stage electric meter and a circuit breaker area behind the electric meter, and is characterized in that code transmitting equipment is connected in parallel to a live line and a null line of a circuit breaker behind the electric meter; a traceability signal is superposed on the live wire, and the traceability signal is uploaded step by step. The decoding device is installed in a live wire of a molded case circuit breaker in a box transformer area or a branch box area, is sleeved in the live wire through the open-type mutual inductor, receives a traceability signal transmitted by the code sending device through the open-type mutual inductor, converts and analyzes the signal through the processor, and finally forms readable information. The traceability of the line topology is completed, the identification of the user change relation is formed, and a topological graph can be formed through an upper application APP; according to the invention, the topology of all the user-to-change relations can be established step by step, and a set of comprehensive user-to-change relation network diagram is formed.
Owner:国网重庆市电力公司营销服务中心 +1

Method and device for identifying grains

The invention discloses a method and a device for identifying grains. The method comprises the following steps: acquiring a picture containing grains; segmenting the picture to obtain a plurality of sub-pictures; and processing the plurality of sub-pictures by using a convolutional neural network model, and identifying grains in each sub-picture. On the basis of the artificial intelligence technology, noise signals in the background are removed through an image segmentation mode, the purpose of grain recognition is achieved, and then the technical problems that in the prior art, the result speed of grain recognition in an image is low, the cost is high and the accuracy is low are solved.
Owner:GREE ELECTRIC APPLIANCES INC

Alphabetic training aid and alphabetic training method

The invention discloses an alphabetic training aid and an alphabetic training method which are applied to the alphabetic practice of alphabetic writings. The alphabetic training aid comprises vowel block bodies, front consonant block bodies and back consonant block bodies. An alphabetic phoneme area block with alphabetic phoneme elements is formed at the circumambient walls of each block body. As each block body is provided with an elastic element and a connecting element, and by fastening the elastic element and the connecting element, the combination of vowel block bodies, front consonant block bodies and back consonant block bodies is realized so as to combine the alphabetic phoneme elements on the circumambient walls to form a phoneme combination indicating alphabetic writings, so that the purposes of practicing relative pronunciation and identification of alphabetic writings are realized, and the ability of analyzing an alphabetic writing structure is improved so as to simplify the difficulty of learning languages, and therefore learning languages is not limited by specific phonetic alphabets.
Owner:吴子源
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
PatSnap group products