312results about How to "Resolve identifiability" patented technology

The invention provides a physical education teaching auxiliary system based on a motion identification technology and an implementation method of the physical education teaching auxiliary system. The system is applicable to a personal computer (PC) or an embedded host. The system comprises a movement data collection module, a movement data acquisition module, an identification and training module and a virtual teaching environment module. The device is characterized in that: a micro-inertia measurement unit and an inertia parameter extraction unit are arranged in the movement data collection module; and a movement information resolving unit transmits data which is output by the inertia parameter extraction unit to a multi-sensor data fusion unit for resolving. The movement situation of a target is reflected comprehensively in an inertia tracking mode and an optical tracking mode, so a tracking range is effectively expanded, measurement accuracy is improved, and the problems that the integral information of the target cannot be acquired in the inertia tracking mode, complicated movement identification cannot be performed and sensitivity is poor are solved. A brand new teaching mode is provided for physical education teaching, and a physical education teaching method is digitalized, multi-media and scientifically standardized.

The embodiment of the invention discloses a malicious traffic detection implementation method and device based on deep learning. The method can include: obtaining the flow session of malicious code through dynamic sandbox technology; mapping the traffic session of malicious code to a gene map and extracting the map features; using the map features of traffic session for clustering and marking theclustering results by a malicious code family; training the preset depth learning model by using the tagged gene map of the malicious code family to establish the malicious traffic detection model; using the malicious traffic detection model to detect real-time network traffic, and realizing malicious traffic detection. Through the embodiment, many problems existing in the conventional detection technology such as artificial feature extraction difficulty, privacy disclosure, encryption and confusion difficult to identify, machine learning feature manual extraction and the like are solved to acertain extent, and the method has the characteristics of high robustness, high speed, high accuracy, low false alarm rate, cross-platform detection and the like.

The invention discloses an unlocking method and a device of a touch screen and terminal equipment. The method comprises the following steps of: displaying a region to be filled by the touch screen; receiving touch operation of the region to be filled and determining a filled region obtained by filling the region to be filled according to the touch operation; and unlocking the touch screen under the condition that the filled region and the region to be filled satisfy an unlocking policy. By adopting the invention, the unlocking operation of the touch screen is intuitive, convenient and quick, and user experience is improved.

The invention provides a touch control equipment control method and device and touch control equipment. The touch control equipment control method includes the steps of detecting at least two pressure values of touch operations on a touch screen and controlling the touch control equipment to carry out a preset pressure triggering event when the at least two pressure values comprise at least two pressure values in different pressure ranges. According to the technical scheme, the mis-operation problem can be effectively solved, a user can conveniently operate the touch control equipment and user experience is effectively improved.

The invention discloses a detection and determination method of a network navy. Three modules of user behavior acquisition, user behavior statistics and network navy classifier training are comprised. A flow comprises the user behavior acquisition, the user behavior statistics, network navy prediction, and network navy determination. The method of the invention is characterized by: after a user behavior sample is acquired, carrying out the statistics on the user behavior; then, using a machine learning method to establish a prediction model; finally, detecting the network navy. By using the method for detecting the network navy based on the user behavior of the invention, a disadvantage of a current mainstream technology can be made up. A tendentiousness identification problem can be avoided so as to solve the network navy detection and identification problem without an obvious tendency. Simultaneously, by using the method, an author does not need to publish a lot of posts with a same theme, which solves a group network navy detection problem. In addition, by using the method of the invention, the network navy detection possesses a clear organizational structure which is convenient for expanding subsequent network navy behavior characteristics.

The invention is suitable for the field of computer technology, and provides a webpage recognition method, a device and a system. The method comprises acquiring the page information of an inputted webpage; and analyzing the page information by a pre-constructed analyzer in a preset time period, and outputting information representing whether the webpage is a fraud webpage or not. By analyzing the page information through the pre-constructed analyzer and outputting the information representing whether the webpage is the fraud webpage or not, the method provided by the invention solves the problems caused by adopting a webpage matching method to recognize the fraud webpage in the prior art, such as low fraud webpage recognition rate and low recognition efficiency, and can improve the recognition rate and recognition efficiency, thereby enhancing the network security.

The invention relates to an industrial control network information security monitoring method based on a funnel type white list. The industrial control network information security monitoring method comprises the following steps that (1) industrial communication data are deeply parsed; (2) a credible framework is established for legal operation in an industrial control network; and (3) a white list funnel is established based on the credible framework. The beneficial effects of the industrial control network information security monitoring method are that reductive analysis is performed on multiple industrial communication protocols so that abnormal monitoring of the production control behavior can be realized; and the credible framework is established through combination of the industrial control network environment so that the white list funnel with the industrial characteristics is generated, filtering precision is high and the communication behavior in the industrial control network is monitored in real time, early warning time for perception of the unknown threat is enhanced, and thus the industrial control information system environment is stabilized as the core guiding thought and a monitoring system is constructed.

The invention discloses a Chinese character inputting system to integrate the voice input and hand-written input function in the applying technical domain of Chinese character inputting method, which comprises the following parts: hand-written/voice input mode, hand-written/voice signal character generating mode, hand-written/voice candidate Chinese character array generating mode, integrating mode, Chinese character identifying and displaying mode, hand-written/voice model exercising mode and hand-written/voice database. The invention improves the identifying rate of Chinese character during hand-written input with voice input as accessory, which accelerates the identifying step without changing the custom of user.

The invention provides a face recognition technology, which comprises two layers of classifiers. The technology comprises the following steps: establishing a first-layer classifier which can recognize disguise by studying a plurality of disguise face samples; recognizing undisguised faces and disguised faces by two classifiers at the second layer respectively; in combination with a visible light sensor and an infrared sensor, acquiring a face visible light image and an infrared image of a recognition object respectively; and transmitting the visible light image and an infrared image to a computer for layered recognition so as to determine whether the object is one in a database or not in the database. Through the technology, the problem that the disguised face cannot be recognized or the recognition rate is low by the traditional face recognition technology is effectively solved, and the technology has a wide application prospect.

The invention discloses a card distributing mechanism for an automatic card shuffling machine. A card distributing device (22) is in a rail shape; a card feeding rubber wheel (1) and a card splitting rubber wheel (2) of the card distributing device (22) feed playing cards in a card collecting bin (6) into a card distributing port (9) through a card feeding belt (4) and a pressing plate (3); and a detection device (8) positioned in the center of the rail calculates the number of the playing cards, detects the positive and negative surfaces of the playing cards, turns the playing cards which need turning through a card turning clip (7) and feeds the playing cards into the card distributing port (9). Due to the technical scheme, the problems that the card shuffling machine cannot automatically distribute the playing cards, identify the positive and negative surfaces of the cards or turn the cards in the prior art are solved, the playing cards are prevented from being contacted with people, and the fairness of games is ensured; two sets of playing cards are played, the playing methods of poker games can be flexibly set, and time for waiting for the games is shortened; and the work efficiency and randomness of the automatic card shuffling machine are improved, and game players can fairly play the games.

The invention discloses an access control system, a client and an access control identity authentication method. The access control system comprises a signal receiver which receives near field communication signals comprising signal content and signal intensity, a memory which is used for storing an access control permission list and at least comprises client identification information and access control authority, an authority determination module which is used for determining if the near field communication signal content matches with the access control permission list, a distance judgement module which is used for determining a distance between a client and a corresponding access control device according to intensity of the matching near field communication signals and transmitting an opening signal to a door opening device when the distance is less than a first distance threshold value, and the door opening device which opens the corresponding access control device according to the opening signal. Through judgment of signal content and signal intensity, basic functions of the automatic access control device are realized. The access control system supports and authorizes user self-updating when a mobile phone is replaced, realizes work attendance recording of multiple people and is safe and portable.

The invention discloses a method and a system for locating a moving target in a mine based on binocular CCD vision. The system for implementing the method comprises surface equipment and an underground device. The surface equipment comprises a base station controller, a location server, an Ethernet switch and a monitoring terminal. The underground device comprises a mine intrinsically safe base station and a wireless radio frequency identification tag. The method for implementing the system comprises the following steps: (1) using an RSSI algorithm to estimate the location of a moving target; (2) carrying out matching feature extracting and training on the wireless radio frequency identification tag of the moving target; (3) carrying out feature matching on images after sampling through an ORB algorithm; (4) using a binocular CCD vision sensor to stereoscopically calibrate the left and right images of the moving target; (5) getting an internal and external parameter matrix of the binocular CCD vision sensor, and calibrating the world coordinates of the moving target; and (6) carrying out location correction on the world coordinate information of the moving target, and getting the accurate location information of the moving target in a mine. The problem on how to accurately locate a moving target in a mine NLOS environment is solved. The reliability and robustness of the system are improved.

The invention discloses a wireless communication method and system. The wireless communication method comprises the following steps that: S1, master equipment generates a sequence code through a specific encoder according to a communication requirement, and continuously sends the sequence code to each slave equipment within a preset time period, wherein the specific encoder is a feedback shift register which consists of specific polynomials, coefficients and orders of the specific polynomials are relevant to the communication requirement, the coefficients and initial value of the polynomials are not 0, the preset time period is longer than or equal to the sum of the dormancy period and detection period of the slave equipment, and the sum of the dormancy period and the detection period forms a dormancy awaking cycle; and S2, the specific slave equipment receives a continuous section of the sequence code in the detection period, decodes the sequence code by using a decoder corresponding to the encoder, and performs corresponding operation according to the decoding result. By using the technical scheme of the invention, the anti-interference property is high, the reliability and the communication efficiency are improved, and the power consumption of the communication system is reduced.

The invention discloses a method for identifying a triangular star map, and belongs to the field of navigation, guidance and control of spacecraft. The method comprises the following steps of: 1, establishing a navigation database, namely constructing characteristic triangles, calculating a plane unit normal vector, solving an optimal projection principal axis and projection point values, and normalizing magnitude; 2, forming an observation triangle; and 3, searching a characteristic triangle which is most matched with the observation triangle from the navigation database, sequentially retrieving a projection point value block index stable, a characteristic triangle table and a magnitude normalizing table in a hierarchical retrieval mode, and finishing the matching of the observation triangle. The method for identifying the triangular star map solves the problems of low noise robustness, more redundant matching and low identification rate of the conventional method for identifying the triangular star map, obviously improves the search speed of the navigation database, reduces redundant matching, improves the identification rate, and has higher noise robustness.

The invention relates to an automobile artificial and informal license plate identification logical judgment method based on the radio frequency identification technology and the automobile license plate identification technology. The identification logical judgment method includes the steps that if a radio frequency identification reader-writer does not identify automobile electronic identification but a snapshot camera identifies an automobile license plate number, an automobile is regarded as a suspicious automobile; if the radio frequency identification reader-writer identifies the automobile electronic identification, the electronic identification is electronic identification registered in a database, and meanwhile the snapshot camera identifies the automobile license plate number, it is judged that the automobile is a legal automobile if the automobile electronic identification is coincident with the identified automobile license plate number, and it is judged that the automobile is an artificial and informal license plate automobile if the automobile electronic identification is not coincident with the identified automobile license plate number; if the automobile electronic identification is identified and is the electronic identification registered in the database, but the snapshot camera does not identify the automobile license plate number, it is judged that the automobile is the legal automobile; if the radio frequency identification reader-writer identifies the automobile electronic identification, but the automobile electronic identification is not the electronic identification registered in the database, it is judged that the automobile is the suspicious automobile regardless of whether the snapshot camera identifies the automobile license plate number or not.

The invention belongs to the field of intelligent robots, particularly relates to a method for authenticating and tracking the identity of an interaction person for an intelligent dialogue robot, andespecially particularly relates to an interactive identity authenticating and tracking method and system based on a multi-modal intelligent robot. The interactive identity authenticating and trackingmethod based on the multi-modal intelligent robot comprises the following steps that: collecting the multichannel information of an interaction object; adopting a deep neural network to extract activation characteristics, and forming the multimodal characteristics of the multichannel interaction information; adopting ensemble learning of cross-modal probability cognition, and carrying out identityauthentication on face image characteristics and vocal print characteristics; and carrying out registration and tracking by the identity, which is authenticated by the cross-modal attribute, of the interaction person. The interactive identity authenticating and tracking system based on the multi-modal intelligent robot comprises a multichannel information collection module, a multi-modal characteristic extraction module, a cross-modal identity authentication module and an interaction object registering and tracking module. By use of the method, the problem that single modal information is inshortage and the interaction identity can not be identified and tracked is solved.

The invention discloses a wireless communication system and method. The wireless communication method comprises the steps: S1, a main device encodes an information code sequence including a communication request into an awakening sequence and continuously sends the awakening sequence to each slave device within a preset time period, wherein the awakening sequence comprises at least two portions, the at least two portions have preset relevancy, the preset time period is larger than or equal to the sum of a sleeping period and a detection period of the slave device, and the sum of the sleeping period and the detection period form a sleeping-awakening period; S2, the slave devices receive the awakening sequence in the detection period, decode the awakening sequence, judge the relevancy of the at least two portions, decide to perform awakening or not and perform corresponding response according to decoded information. By implementing the technical scheme, the power consumption of wireless communication is reduced, the encoding efficiency is improved, and the communication process is simple.

The invention relates to a coal coke oven charring room position measuring method based on laser image measurement, wherein an oven opposite to the door of coal coke oven charring room is arranged with a reference body, an engine is arranged with a straight laser emitter and a camera to pick the laser image information of reference body, to recognize the reference body via the relationship between the orthogonal coordinate of laser line in the image and the surface concave-convex size of the oven, to calculate the position error between the engine and the target door of the charring room, via the horizontal pixel of reference body in the image. Or else, the invention uses a solid bar code to replace the reference body, to read inside code information via picked solid bar code laser image, to recognize the serial number of the charring room door via the code, and calculate out the position error between the horizontal pixel and the charring room door via the bar code. The inventive measuring method belongs to non-contact absolute position measuring technique, with strong adaptability on the coke oven producing condition, to realize oven number recognition and accurate measurement of door position error.

The invention provides a vehicle type recognition method and apparatus. The method comprises: extracting a first sub-image corresponding to a to-be-queried vehicle in a to-be-queried image; obtaining the visual feature similarity between the first sub-image and each vehicle type in a pre-established database; and when determining that the visual feature similarity is greater than a preset first threshold, taking a vehicle type corresponding to a maximum value in the visual feature similarity greater than the preset first threshold as an output recognition result, wherein the database comprises a plurality of vehicle type databases, each vehicle type database comprises a set of multiple sample images of the vehicle type, and the sample images of the vehicle type include vehicle images in different lighting conditions, vehicle images of different shooting angles and vehicle images of different scenes. The method can solve the problem of incapability of realizing vehicle recognition due to license plate recognition precision limitation, fake license plate, no license plate or license plate damage, and improve the accuracy of vehicle recognition.

The invention provides a distributed simulation system for deep space multi-relay satellite communication. The system employs a structure based on a high-level architecture (HLA) standard and has reusability and interoperability; the system can realize data communication among multiple protocols and different simulation system platforms, and solves the problems of incapability of identifying data among the different protocols and non-standardized interfaces of simulation systems; the system can realize real-time and real transmission of each data packet, the transmission effects are obvious, and the performance analysis is high; through externally connected software, real transmission scenes can be simulated, and real-time dynamic communication environment data is provided; through two relay federal members, multiple relays are simulated and multi-node segment data transmission for a deep space DTN is demonstrated, and through multi-relay multi-hop segment transmission, transmission efficiency in a deep space long distance and long time delay environment is improved; and an acquisition scheduling module is taken as a control center of a simulation platform, on one hand, real-time related data of current simulation platform operation is acquired and displayed in real time, and on the other hand, effective analysis can be performed on acquired data, and related decisions are made. The simulation system provided by the invention has three characteristics of interrupted connection, storage forwarding and keep transmission, thereby being well adaptive to the transmission characteristics of a space DTN.

The invention discloses a support vector machine high-voltage circuit breaker fault diagnosis method based on fuzzy clustering. The method comprises the steps of firstly, extracting a feature vector from a stroke-time curve of a circuit breaker moving contact, using the feature vector as a database of fault diagnosis, secondly, conducting fizzy clustering processing on a data sample, generating a new clustering center matrix, thirdly, using the clustering center matrix as a training sample, applying a support vector machine to conduct training, and fourthly applying the high-voltage circuit breaker fault diagnosis method to diagnose test data. According to the support vector machine high-voltage circuit breaker fault diagnosis method based on the fuzzy clustering, the efficiency of the high-voltage circuit breaker fault diagnosis can be effectively improved, the time of the fault diagnosis is reduced, the quality of the fault diagnosis is improved, and the support vector machine high-voltage circuit breaker fault diagnosis method has great significance for research on the safety and the reliability of the power grid.

The invention discloses a statistical analysis method and a system for store passenger flow, which introduces a dual recognition mechanism of a face image and/or a body image, can effectively reduce the occurrence of the situation that the customer can not be recognized due to the poor shooting angle of the image, and provides accurate and effective passenger flow reference data for managers. Themethod comprises the following steps of: acquiring an image of a customer in a store and detecting a pedestrian rectangular frame of each customer in the image; recognizing face image and body image based on pedestrian rectangular frame, judging whether a face image and/or a body image are encoded, matching and encoding the face image and/or the body image in the same pedestrian rectangular framewhen the face image and/or the body image are not encoded, and simultaneously recording time and position information of the image taken by the customer; when encoded, directly recording the time andposition information of the customer being picked up; According to the customer's coding information and the time and position information of the image, drawing the path of each customer. The system uses the method proposed in the technical proposal.

The invention discloses a classifier construction method for target detection and a target detection method. The classifier construction method comprises a negative sample generation process, a positive sample generation process and a classifier conformation process, wherein the negative sample generation process comprises the steps of processing an obtained scene original image set to obtain a background set not containing a target and generating a negative sample according to the background set; the positive sample generation process comprises the steps of processing a positive sample original image set containing the target to obtain a positive sample set which comprises a plurality of positive samples; the classifier conformation process comprises the steps of obtaining sub-classifiers corresponding to all the positive samples through combining negative samples and misrecognition samples, and further obtaining required classifiers according to sets of all classifiers. Compared with the prior art, the method has the advantages of higher detection rate and higher capture rate.

The invention discloses a super-long-range radar and video linkage control system comprising a radar and a radar information processing system; a telephoto lens, a digital high-definition video camera and an all-round digital high-precision cloud terrace are arranged at the top part of an observation post; a video linkage control computer, a digital vector control keyboard and a monitor are arranged in a control room of the observation post; the system further comprises a monitoring center; and the components are connected through a network. The super-long-range radar and video linkage control system realizes the integration of optical and electronic observation means and the comprehensive use of information of the radar system, thereby solving the problems of lower search speed and poorer accuracy of the prior artificial optical observation and realizing the digitalization, the networking and the automation of the optical observation. The system can greatly improve target searching and tracking speed and precision, and reduce labor intensity of staff on duty.

The invention provides a method and a device for user identification. The method includes acquiring users' visiting information; inquiring first relation tables according to users' IP (internet protocol) addresses, and judging whether corresponding relations exist between the IP addresses and relation pairs or not; and if yes, returning corresponding user identifications according to the users' IP addresses, and identifying users according to the returned user identifications. The visiting information includes the users' IP addresses, domain names of websites visited by the users and the relation pairs of cookie information of the websites visited by the users. User information and information of website domain names and website cookie information relation pairs corresponding to the user information are stored in the first relation tables. The user information includes the IP addresses and the user identifications. By aids of the method and the device, servers can accurately identify client sides and users.

The invention discloses a device and a method for detecting similar texts. The device and the method are used for recognizing the similar texts. The device comprises a Chinese text acquiring unit, a pinyin text acquiring unit, a fingerprint acquiring unit and a detecting unit, wherein the Chinese text acquiring unit is suitable for processing texts so as to acquire Chinese texts; the pinyin text acquiring unit is suitable for transforming Chinese characters in the acquired Chinese texts into pinyin so as to obtain pinyin texts; the fingerprint acquiring unit is suitable for extracting features of the pinyin texts, and forming the feature vector of the pinyin texts by using the extracted features; and the detecting unit is suitable for judging whether the texts to be detected are matched with records in a database or not according to the feature vector. By using the device and the method, the Chinese texts can be obtained by the texts to be detected, then the pinyin texts are obtained, the feature vector of the pinyin texts is formed, whether the texts to be detected are matched with the records in the database or not is judged according to the feature vector, and beneficial effects of reducing operand and accurately recognizing variety of similar texts are achieved.

The invention relates to a writing brush word search method, wherein it comprises: (1) cutting the writing brush words not similar with the sample word in database; (2) matching the left candidate writing brush word with sample word, to provide the matched value; (3), sequencing the matched values from small to large, based on the writing brush word number, obtaining relative original writing brush word image, to generate virtual result; (4), user can use mouse to draw one Chinese word image, input one text Chinese word by keyboard, or guide into one writing brush word image by disc to search writing brush word. The invention can use present optical word recognize technique to recognize the text to search, to provide the search tool of digit writing brush to digit library.

The invention provides a robot grabbing positioning device as well as a robot grabbing system and method. The robot grabbing positioning device comprises a distributing platform, a camera moving mechanism and a camera; the camera moving mechanism corresponds to the distributing platform; the camera is mounted on the camera moving mechanism; and the camera moving mechanism is used for driving the camera to move relative to the distributing platform along the preset track, so that the camera acquires images of multiple preset positions on the distributing platform one by one. Thus, when multiple products are grabbed, multiple visual systems are not required to be set to identify and position the multiple products respectively, and the problem of relatively large occupied space due to the fact that a robot in the prior art is provided with the multiple fixed visual systems for identifying and positioning different products distributed in multiple different positions is solved.

The invention discloses an intelligent robot teaching system and a student learning method. The robot teaching system comprises a student data bank, a student question bank, a voice emotion interaction bank, a voice speech recognition module, an emotion distinguishing module and a voice synthetizing module. According to the technical scheme, the movements and expressions of the human beings are sensed, observed and recognized through the advanced face recognition technology, and the problem that the similar education robot can not carry out the human movement recognition and expression analysis is solved; through the leading voice recognitions technology in the world, and in combination with the data algorithm and the research experience for the language expression, the robot can completethe accurate voice locating and accurately understand the features and expression method of the human language; and the analysis and setting for the characters of different people are completed on theartificial intelligence robot, and the vivid man-machine personalized interaction is realized.

The invention discloses a paper money processing apparatus and a paper money transfer control method. The paper money transfer control method includes the following steps that: first paper money is driven to enter the transfer channel of a paper money processing device; the first paper money is driven to move along the transfer channel; the transfer state of the first paper money is detected; and a spacing distance between second paper money and the first paper money is adjusted according to the transfer state of the first paper money. With the paper money processing apparatus and the paper money transfer control method of the invention adopted, the paper money can be prevented from blocking the transfer channel, and the recognition rate of the paper money can be improved.