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

150 results about "Character analysis" patented technology

Image processing apparatus, image processing method, and storage medium

The present invention provides an image processing apparatus that efficiently identifies input characters and the like by an intensity image analysis based on range information. The image processing apparatus performs distance measurement by performing three-dimensional measurement by pattern projection to characters written to a manuscript, whiteboard, and the like, gets an intensity image used as a so-called actual image and an image for distance measurement in parallel, and identifies input characters by an intensity image analysis based on range information. The image processing apparatus picks up characters, patterns, and the like written onto paper or the like with a pen, performs geometric transformation for picked-up images, and performs natural input character analysis and reading processing. Furthermore, by comparing images picked up in a time-series, noise elimination and manuscript position modifications become possible.
Owner:FUJIFILM BUSINESS INNOVATION CORP

Video abstraction generating method based on sketch

The invention discloses a video abstraction generating method based on sketches, which belongs to the field of man-machine interaction. The method comprises the following steps: (1) carrying out shot segmentation and shot screening on the video to obtain key frames; (2) carrying out character analysis and scene analysis on the key frames, and determining the semantic significance level of each key frame according to the character analysis; (3) calculating an image quality assessed value of each key frame, and screening the key frames according to the image quality assessed value and the semantic significance level value; (4) generating a video object sketch according to each key frame determined in step (3); (5) resetting the size of the corresponding sketch according to the size of the abstraction drawing region and the significance level of the video contents corresponding to each sketch; and (6) determining the position of each sketch by utilizing the scene analysis result, generating connecting lines among the sketches, and connecting the sketches to generate a video abstraction. By using the method of the invention, the sketch abstraction can intensively and effectively reflect the main plot semanteme of the video, thereby conforming to the perception habits of users.
Owner:INST OF SOFTWARE - CHINESE ACAD OF SCI

Rapid three-dimensional dynamic gesture recognition method and system based on character value subdivision method

The invention relates to a rapid three-dimensional dynamic gesture recognition method and system based on a character value subdivision method. To solve the problems existing in the prior art, the invention designs a hardware platform with a small appearance; an accelerometer is used for acquiring the 3-axis acceleration of a user gesture; a gyroscope is used for acquiring the 3-axis angle velocity of the user gesture; a magnetometer is used for acquiring the 3-axis magnetic induction intensity of the user gesture; data error is eliminated through a filtering algorithm, and then attitude algorithm is performed to work out real-time three attitude angles (a course angle, a roll angle, and a pitch angel), three-dimensional dynamic gestures with a certain discrimination such as movement, rotation, ticking, cross making, shaking, and knocking are recognized through the information data by adoption of a character analysis algorithm on the basis of ensuring a certain accuracy and real-time performance, and in this way, corresponding applications can be achieved.
Owner:HARBIN INST OF TECH SHENZHEN GRADUATE SCHOOL

Music brain electricity analytical method

The invention discloses a music electroencephalological analyzing method, which comprises the following steps: a. gathering electroencephalological signal and graph; b. processing the signal; proceeding signal character analysis for electroencephalological graph; establishing character quantity data of electroencephalological signal and corresponding map regular of music character quantity data at power law distribution; mapping the electroencephalological signal into music character quantity data; c. producing MIDI pattern music according to music character quantity data or mapping regular; reconstructing electroencephalological graph based on MIDI music.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA

Method for improving oil gas pipe leakage and performance of instruction testing distributed optical fibre sensor

The invention relates to a method for improving performance of a distributed optical fibre sensor for detecting oil gas conduit leakage and inbreak by using Golay code. Detection signals in the sensing optical fibre are continuous optical pulse sequences modulated by Golay code and complement code thereof. The optical pulse sequences are sampling signals of sensing optical fiber transportation consumption. By reducing pulse width of optical pulse sequences, not only sampling frequency of sensing fiber transportation consumption is increased to analyze characters of new transportation consumption in the sensing optical fibre caused by conduit leakage and third party inbreak case in a larger frequency spectrum range, but also spatial resolution of synthesized backscattering optical signals is increased by analyzing to increase positioning accuracy of the new consumption. In another aspect, by adding optical pulse amount in sequences, not only sampling amount of transportation consumption is increased to facilitate characters analysis for new transportation consumption signals in the sensing optical fibre, but also intensity of synthesized backscattering optical signals and signal-to-noise ratio are increased, and the distance of conduit is increased.
Owner:ZHENGZHOU UNIV

Character extracting method from complecate background color image based on run-length adjacent map

InactiveCN1588431AHigh correct extraction rateCharacter and pattern recognitionImage extractionCharacter analysis
The invention is a character extracting method in complex background color image based on runlength adjacency graph, which belongs to character extracting field in preprocess of color image character identification. All color connection sections are acquired with CRAG (color run-length adjacency graph) region growing algorithm after the digital color image is acquired, then the color average is carried on with color classification, acquires several color centers, forms different color layers with the color centers, then the color connection regions accordant to connection region differentiation rule are distributed onto several color layers. Finally the character is selected out through character analysis and size consistency differentiation, and acquires the character image. The method has a high speed and accuracy.
Owner:TSINGHUA UNIV

E-book typesetting method and e-book typesetting system

The invention provides an e-book typesetting method for typesetting an e-book on e-book reading devices of different screen sizes, which comprises the following steps of: reading the text data in the e-book; then analyzing the format of the text data; then performing typesetting optimization processes including new-line character analysis, context detection and long-paragraph analysis on the text data in combination with the environmental parameters of the e-book reading device; typesetting the text data according to the format of typesetting optimization process; finally displaying the typeset e-book text data. The invention further provides an e-book typesetting system. By using the invention, optimized typesetting function can be realized, and the user can achieve favorable reading effect on all the e-book reading devices having different screen sizes or parameters.
Owner:ALLWINNER TECH CO LTD

Interrogative sentence similarity measurement method based on deep convolutional neural network

InactiveCN108021555AAvoid the impact of subsequent analysisAvoiding Sentence Fragmentation ProblemsNatural language data processingNeural architecturesCharacter analysisChinese characters
The invention provides an interrogative sentence similarity measurement method based on a deep convolutional neural network. The method comprises the following steps that: S1: through a knowledge domain related page, generating a raw corpus, crawling Chinese characters which appear in raw language materials, and generating a word vector corresponding to each Chinese character; S2: replacing each Chinese character in an interrogative sentence by the corresponding word vector to obtain a word vector set corresponding to the interrogative sentence, wherein the word vector set carries out calculation through the convolutional neural network to obtain a corresponding sentence meaning vector; and S3: carrying out pairwise combination on the interrogative sentences, and calculating the cosine function absolute values of the sentence meaning vectors corresponding to two interrogative sentences to obtain a similarity between two interrogative sentences. By use of the method, an individual-character analysis method is adopted to avoid an influence on subsequent analysis by word segmentation errors, the convolutional neural network takes the whole interrogative sentence as a whole to extractwhole sentence characteristics, and a sentence meaning splitting problem brought by using word similarity matrixes is avoided.
Owner:INSPUR FINANCIAL INFORMATION TECH CO LTD

Mode extraction apparatus and mode extraction method for conductive interference noise

The invention relates to a conducted interference noise structure extracting device and structure extracting method, which dose structure extracting and feature analyzing to the EMI noise to obtain the structure extracting network capability method and device. The device is formed by a conducted noise identifying device (1), a noise character analysis network (2), an interference noise receiver (3) and a tested device (4), wherein the input end of the conducted noise identifying device (1) is connected with the stage line, the earth line and the center line of the power system; the output end of the conducted noise identifying device (1) is connected with the stage line, the earth line and the center line of the tested device (4) and the input end of the noise character analysis network (2); the output end of the noise character analysis network (2) is connected with the interference noise receiver (3).
Owner:NANJING NORMAL UNIVERSITY

Fluid-solid coupling analysis based erosion destruction invalidation quantitative forecast method

InactiveCN101059417AQuantitative prediction of erosion damage failurePredict failure hazardWeather/light/corrosion resistanceInvestigating abrasion/wear resistanceCharacter analysisTectorial membrane
The invention discloses an abrasion destroy failure quantitative prediction method, based on flow-solid couple analysis, comprising abrasion product protective film character analysis and failure prediction analysis under flow function. Based on the real condition of tube, via flow mechanics similar theory, the invention finds the standard, test condition and flow medium of object tube, via electrochemical test method, processes instant character test of abrasion destroy, builds flow-solid couple model to set characteristic parameter values of abrasion product protective film, uses finite element analysis software to process flow-solid couple simulation, combined with test, corrects the characteristic parameter values of the abrasion product protective film, based on real tube system typical tube, processes flow-solid couple simulation, to realize abrasion destroy failure quantitative prediction of tube system, which can accurately predict the failure points of whole tube system, to support the safe protection technique of pressure tube system.
Owner:ZHEJIANG SCI-TECH UNIV

License plate sheltering detection system and detection method

The invention discloses a license plate sheltering detection system, which belongs to the field of intelligent transportation control and comprises a vehicle snap-shot location module (1), a processing module (3) and a license plate sheltering judgment module (2), wherein the vehicle snap-shot location module (1) is used for shooting vehicle images at detection positions and locating vehicle outlines in the snap-shot vehicle images, the processing module (3) is used for processing situations of spiteful sheltering of license plates, and the license plate sheltering judgment module (2) comprises a license plate location module (21), a license plate character analysis module (22) and a sheltering analysis module (23). The license plate location module (21) is used for locating license plate area in the snap-shot vehicle images, the license plate character analysis module (22) is used for determining appeared character positions and positions where deficiency characters may exist according to the appeared character positions in the license plate area, and the sheltering analysis module (23) judges whether spiteful sheltering exists or not according to textures of deficiency characters positions and enables judgment results to be sent to the processing module. The license plate sheltering detection system solves the technical problem that the existing detection system can not distinguish spiteful sheltering situations.
Owner:BEIJING E HUALU INFORMATION TECH

Large data student personality analysis method

InactiveCN105405082AAnalyze interestsAnalytical activityData processing applicationsSensing record carriersCharacter analysisNetwork model
The present invention discloses a large data student personality analysis method which is used for analyzing personality characteristics, interests and hobbies of a student, determining whether the student has bad living habits and reminding the student, and comprises: analyzing the personality characteristics, the interests and the hobbies of the student based on a student personality analysis system. The student personality analysis system includes an RFID card uniquely corresponding to a student identity, an RFID card reader and a server. The method comprises the following steps: the RFID card reader records card swiping information of the student on the RFID card reader, and the server collects the card swiping information of the student in a certain time period; and through preset empirical model and neural network model, the server compares a card swiping record of the student with a normal value range so as to determine the personality characteristics, the interests, the hobbies and the living habits of the student, and carries out reminding and guidance for the specific case of each student.
Owner:HEBEI UNIV OF ENG

Recruitment method and device based on character analysis, computer device and storage medium

The embodiment of the invention discloses a recruitment method and device based on character analysis, a computer device and a storage medium. The method comprises the following steps: if a user loginoperation instruction is received, behavior data information related to the user is obtained; the user login operation instruction comprises user login information; the behavior data information is analyzed according to a preset analysis prediction model to determine a character characteristic value of a user; a position matching degree corresponding to the preset matching rule is determined according to the preset matching rule and the character characteristic value; If the job matching degree is greater than a preset threshold value, the user login information is identified and added into apre-enrollment database. The invention can quickly and accurately analyze the character of the candidate so as to judge the matching degree of the candidate and the candidate position.
Owner:PINGAN PUHUI ENTERPRISE MANAGEMENT CO LTD

Personal character analysis method, device and storage medium

The invention provides a personal character analysis method, a device and a computer readable storage medium. The method comprises the following steps of collecting sample videos and annotating character types; extracting the image features and audio features of each sample video, and combining to obtain the video features of each sample video; constructing a neural network using the Softmax classifier as an output layer; annotating and training the neural network based on video features and character types, optimizing training parameters, and obtaining a personal character analysis model; collecting a face video of an to-be-analyzed object for a predetermined duration; extracting the image features and the audio features of the video of the to-be-analyzed object, and combining to obtain the video features of the video of the to-be-analyzed object; inputting the of the video features of the video of the to-be-analyzed object into the personal character analysis model to obtain a probability value corresponding to each character type of the to-be-analyzed object; and adopting a character type with the largest probability value as the character type of the to-be-analyzed object. According to the invention, the personality of a person can be objectively analyzed.
Owner:PING AN TECH (SHENZHEN) CO LTD

A method for automatically extracting text information

The invention provides a method for automatically extracting text information, which can continuously improve the accuracy of automatically extracting marker content and label. The method comprises the following steps: acquiring a text file uploaded by a user, and converting the text file into a document format capable of character-by-character analysis by a computer; preprocessing the text content of the converted document to form a multi-level text unit which is easy to parse by using natural language processing technology; capturing text segments selected by a user, determining markup contents corresponding to the text segments based on the formed multi-level text units, and recommending labels for each markup contents; based on the determined markup content and the recommended tags foreach markup content, an online learning training idea being adopted to train the automatic text extraction model, so as to realize the automatic extraction of markup content and tags. The invention is suitable for automatic text information extraction operation.
Owner:UNIV OF SCI & TECH BEIJING

Character personality analysis method based on recurrent neural network and character personality analysis device based on recurrent neural network and storage medium

The invention provides a character personality analysis method based on a recurrent neural network and a character personality analysis device based on the recurrent neural network and a computer readable storage medium. The method comprises the following steps that a sample video is collected and the personality type is marked; the feature vectors of the sample video image sequence are extracted;a recurrent neural network model with the Softmax classifier acting as the output layer is constructed; the recurrent neural network model is trained by using the feature vectors and the personalitytype mark and the training parameters are optimized so that a character personality analysis model is obtained; the facial video of an object to be analyzed is acquired and the feature vectors of thevideo image sequence are extracted; and the extracted feature vectors are inputted to the character personality analysis model so that the probability value of each corresponding personality type of the object to be analyzed is obtained, and the personality type of the highest probability value is taken as the personality type of the object to be analyzed. The character personality can be objectively analyzed by using the character personality analysis method and the character personality analysis device.
Owner:PING AN TECH (SHENZHEN) CO LTD

System and method for ordering search results

The invention relates to a system and a method for ordering search results. The system and the method are applied into electronic devices. The system for ordering the search results comprises a keyword search module, a comment weight computing module, a search result ordering module and a key information retrieval module, wherein the keyword search module is used for receiving keywords input by a user from a search interface and time intervals selected by the user from the search interface and searching the search results in corresponding time intervals according to the input keywords; the comment weight computing module is used for computing the weight value, according to the comment of the user, of each search result; the search result ordering module is used for reordering the search results according to the weight value of the user comment; the key information retrieval module is used for carrying out keyword character analysis on the search results before several orderings and the corresponding user comment so as to find out key information in the time intervals, display the key information on a display and present the key information to the user. By implementing the system and the method, the search ordering in the time intervals can be strengthened by utilizing the content of the user comment, and hot topics included in the search results or the user comment in the time intervals are retrieved.
Owner:HONG FU JIN PRECISION IND (SHENZHEN) CO LTD +1

Novel method of tailing dry pile process

The invention discloses a novel method of tailing dry pile process. The technical scheme is used for achieving dry pile field survey, tailing character analysis, treatment and analysis of field foundations, analysis of ground water transfusion fields, confirmation of dry pile field parameters and selection of soil engineering woven bag specification. Tailing pulp is injected in soil engineering woven bags by using tailings produced by a dressing plant, water in the tailing pulp flows out through the soil engineering woven bags (3), and coarse grain tailings are left in the bags and finally completely filling the bags. The soil engineering woven bags (3) filled with the tailings are piled from bottom to top according to staggered layers, a finally stockpiling tailing dry pile dam body (6) is a prismatoid structure with a narrow upper portion and a wide lower portion, a discharge and seepage pipeline (4) is arranged in the tailing dry pile dam body, and a slope face earthing protective layer (5) is arranged on the surface of the tailing dry pile dam body (6). The new method of the tailing dry pile process can not only solve the problem caused by the fact that tailing pond terrains for construction is lack nearby a mine, but also reduces long distance delivery cost of the tailings, guarantees normal production of the mine, and quickens building speed of the mine.
Owner:SINOSTEEL MAANSHAN INST OF MINING RES

Workflow data processor and processing method

A method for handling operation flow data includes reading operation flow data presented in character string mode and character analysis table corresponding to operation flow data out from databank by read / write module then storing them in internal memory pool, fetching and operation flow data and character analysis table in internal memory pool and analyzing operation flow data as per character analysis table by analysis module, calling execution mechanism to execute action corresponding to operation flow data by analysis module. The device for realizing said method is also disclosed.
Owner:HUAWEI TECH CO LTD

Voice-based medical report forming method and device

The embodiment of the application discloses a voice-based medical report forming method comprising the following steps: obtaining a target voice analysis unit, and identifying the target voice analysis unit as a target character analysis unit; using a pre-trained information analysis model to carry out meaning analysis for the target character analysis unit, thus obtaining target character analysis sub-units and information types corresponding to the target character analysis sub-units; forming a medical report according to the target character analysis sub-units and information types corresponding to the target character analysis sub-units. Even if different doctors have different language habits, the method and device can form a standard medical report according to the voice analysis unit of each doctor, thus improving the medical report standardization and readability, and improving the user reading experiences.
Owner:GENERAL HOSPITAL OF PLA +1

Method for delaminating and districting of 10 KV medium voltage distribution network

The invention discloses a method for delaminating and districting of a 10 KV medium voltage distribution network. The 10 KV medium voltage distribution network comprises a plurality of transformer substations, a plurality of switching stations and a plurality of power distribution stations; each transformer substation is connected with the switching stations, and each switching station is connected with the power distribution stations. The method comprises the following steps that firstly, a main distribution network structure is built according to the space layout between the transformer substations and the switching stations; secondly, a secondary distribution network mode is built according the number of the power distribution stations needing to be arranged within the power supply range of each switching station. The hierarchical structure and function location of the medium voltage distribution network are further refined and defined. On the basis of a power supply ability theoretical calculation method and a main transformer handshaking structure optimization model in a power supply module, a typical power supply handshaking model in a switch station power supply mode, the transformer substations and a binding character analysis mode are built, and specific configuration calculation is performed on the switching stations in a typical power supply mode.
Owner:SHANGHAI MUNICIPAL ELECTRIC POWER CO

Rapid detection method for sorghum halepense and similar species

The invention discloses a rapid detection method for sorghum halepense and similar species based on a near infrared spectrum. The method comprises the following steps: adopting the near infrared spectrum to obtain spectral reflectance characteristic curves of three kinds of sorghum seeds of sorghum, sorghum halepense and sorghum sudanense between 325-1075 nm, adopting a partial least squares method for pattern character analysis, and adopting a cross validation method for judgment to determine that the optimal number of principal components is 9; after character extraction is completed, using the 9 kinds of principal components as the input variable of neural network, establishing three layers of BP (Back Propagation) neural networks, and calculating the category of each seed. The method combines the near infrared spectrum analysis with a chemical measurement method to rapidly and accurately judge the category of the three kinds of sorghum seeds, the detection time is greatly shortened, the detection efficiency is improved, and the detection cost is reduced.
Owner:YANCHENG INST OF TECH

Occupational psychological character analysis method based on social network

The invention discloses an occupational psychological character analysis method based on a social network, and particularly relates to the field of psychological analysis. The occupational psychological character analysis method comprises the following steps: 1) collecting basic information of a user; 2) constructing an MBTI occupational character four-dimensional classifier; 3) sending a new dataset of which the weight is modified to a lower-layer classifier for training; and 4) completing an MBTI analysis report of the object. According to the occupational psychological character analysis method based on a social network, personal social network content is collected and comprehensive and deep quantitative analysis is carried out; the association between the personal microblog content and the professional psychological character is quantified by means of an MBTI model; the recruiter can comprehensively, rapidly and accurately judge the occupational psychological characters of the candidate according to the content published by the candidate in the social network by collecting the samples to train the classifier, so that an objective basis is provided for decision making; and meanwhile, automation of the whole analysis process is achieved through the information technology, and the time cost of analysis is greatly reduced.
Owner:JINAN UNIVERSITY

Method of giving machines artificial intelligence learning based on knowledge of psychology

The invention discloses a method of giving machines artificial intelligence learning based on the knowledge of psychology, comprising the following steps: (a) word classification and intelligent abstract preprocessing are carried out on a document in a document library to get a keyword, a correlation analysis of the keyword is made, values provided by the previous steps are processed, the criticality score of the keyword to the document is calculated out, and a keyword with an assigned value is obtained; (b) the personality of a user is analyzed according to the knowledge of psychology to get the personality tendency value of the user; (c) the personality tendency value obtained in step (b) is matched with the keyword criticality score obtained in step (a) to get a document library with personality tendency attribute; and (d) when the user issues an access request, the document library with personality tendency attribute gives a document with personality tendency attribute. Through a recommending method based on user's personality, the behavior of a user can be accurately predicted under specific space-time dimension and scene dimension. Through the method, the content that users will truly view can be predicted and recommended.
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