181 results about "Structured analysis" patented technology

A personal emergency response system employs a structured terminology of body activities. Measurements of primary body activities using accelerometers, heart-bit monitors, etc. are converted to secondary and tertiary level body activities such as walk and fall, further sequenced and combined to determine a personal condition such as walk, stumble and fall, and to identify sequences of such conditions. The structured terminology enables a language supporting a functional description of body activities associated with physical and physiological measurements and enables a machine to understand physical activities.

The invention discloses a multi-examples-learning-based method for identifying a horror video scene. The multi-examples-learning-based method comprises the following steps of: carrying out shot segmentation and key frame selection on a video scene, wherein the video scene corresponds to a multi-examples learning bag, and a shot corresponds to the examples in the bag; respectively extracting visual characteristics, audio characteristics and color affective characteristics on the basis of the shot and a key frame to form a characteristic space; training a corresponding multi-examples learning classifier in the characteristic space; structurally analyzing a video sample to be tested, and extracting related characteristics; and predicting the category, namely horror or non-horror, of the video sample through the trained classifier. According to the invention, the novel color affective characteristics are provided and applied to the method for identifying the horror video scene, and the multi-examples-learning-based method has wide application prospect.

Identifying service candidates in legacy source code, including a source code analyzer performing structured and unstructured analyses of computer software source code procedures, a repository storing results of the analyses, a target profile analyzer analyzing a target service description of a Service Oriented Architecture and formulating a query therefrom, a search module querying the repository to identify source code elements that match the target service description, and combining any matches within a predefined distance from each other within the source code, a ranking engine ranking the combined matches in accordance with predefined heuristics, and a procedure aggregator aggregating the combined matches by their location in propinquity to the procedures, comparing interface definitions defined for the service description to entry and exit points of the procedures to identify candidate procedures having similar input and output parameters, and producing a ranked list of candidate procedures that map into the target element.

The application discloses a man-machine interaction method and device based on artificial intelligence; the method comprises the following steps: forming multi-dimensional structured analysis results according to historical interaction information between a preset analysis strategy and a user and present multi-mode input information; using characteristic resources of a plurality of dialogue sources to obtain a plurality of results matched with the analysis results; determining the multi-mode output information matched with the multi-mode input information from the plurality of results according to a preset screening strategy, and pushing same to the user. The man-machine interaction method and device can improve dialogue content richness, thus satisfying user customized, interest and intellectual dialogue demands.

The invention discloses a searching method and device based on artificial intelligence and electronic equipment. The searching method based on the artificial intelligence comprises the steps of obtaining an input query sentence; segmenting the query sentence to obtain split word sentences composed of multiple split words; conducting structuralized analysis on the split word sentences to generate atext structure; based on the text structure, conducing knowledgeable analysis on the split word sentences to generate a semantic analysis result; according to the text structure and the semantic analysis result, determining an understanding result corresponding to the query sentence. By means of the searching method and device based on the artificial intelligence and the electronic equipment, byconducting structuralized analysis and knowledgeable analysis on the query sentence, the text structure and the semantic analysis result are obtained, thus the understanding result corresponding to the query sentence is determined, erroneous recalling of the searching result is lowered, the accuracy is improved, and the user requirements are met.

Methods, systems, and apparatus for providing compartmented, collaborative, integrated, automated analytics to analysts are provided. In a first aspect, the present invention provides a computer-implemented method for providing compartmented, collaborative, integrated, automated analytics to analysts including: selecting a computer-encoded project-specific workflow; determining a computer-encoded compartment manager, said computer-encoded compartment manager including computer-encoded information about the context of said project-specific workflow; retrieving said computer-encoded information about the context; selecting a computer-implemented automated analytic using said computer-encoded project-specific workflow; providing under control of said computer-encoded compartment manager said information about the context to said automated analytic; processing said computer-encoded information using said computer-implemented automated analytic, to generate thereby analytical information representing an outcome to said analysts; and processing said analytical information in accordance with said computer-encoded compartment manager and said computer-encoded project-specific workflow.

An online data storage system (100) is disclosed in which users may store a variety of personal documents in accordance with a common document structure that can include tag structures that are tailored to specific types of documents. The document and tag structures permit convenient access of the documents and enable providers of goods and services to generate targeted conditional offers while ensuring the privacy of individuals storing the documents.

The invention provides a video abstraction generation method based on space-time recombination of active events. According to the method, an original video is pre-treated, blank frames are removed, and the video after pretreatment is subjected to structured analysis as follows: moving targets in the original video are taken as an object, videos of all key moving target events are extracted, time correlation between the moving target events is weakened, and time sequence recombination is performed on the moving target events based on the principle that activity ranges are not conflicted; meanwhile, background images are extracted reasonably based on the reference of the visual perception of a user, and a delayed dynamic background video is generated; and finally, the moving target events and the delayed dynamic background video are sutured seamlessly, a video abstraction with short time, concise content and comprehensive information is formed, and a plurality of moving targets can occur simultaneously in the finally generated video abstraction. The video abstraction generation method can generate the video abstraction used for video browsing or searching efficiently and rapidly, and the video abstraction can express semantic information of the video more reasonably and better meets the visual perception of the user.

The invention discloses an HSV color histogram and DCT perceptual Hash based lens boundary detection method. The HSV color histogram and DCT perceptual Hash based lens boundary detection method comprises a first step of calculating a histogram difference degree between two adjacent frames of images by using the HSV color space based histogram statistic method; a second step of judging the difference degree between the two adjacent frames by adopting a adaptive threshold value, and judging the place between the two adjacent frames is the lens boundary if the difference degree is greater than the threshold value; and a third step of rechecking an early detection result by adopting a DCT based perceptual Hash algorithm and obtaining a final video lens boundary set. Through the early detection of the HSV color histogram and the DCT perceptual Hash algorithm based rechecking, the lens boundary position in a video frame sequence is detected efficiently and accurately, and a firm foundation for the structural analysis of the multimedia video data is accordingly laid.

The invention discloses a news video retrieving method based on subtitle extraction, which comprises the following steps of news image division, special image detection, news structural analysis, shot frame merging, text title positioning, character identification, title subtitle index building and the like. The method overcomes the defects in the prior art, the title subtitle in the video can beextracted to be organized and managed, and the method is used for the video retrieval based on the contents.

The invention provides an electronic examination paper inputting method. The method comprises the following steps of 1, obtaining a text of an electronic examination paper, and performing formatting processing; 2, performing structured analysis on the electronic examination paper, and according to test question numbers, dividing the electronic examination paper into a plurality of big questions and small questions; 3, recognizing classification of question types and segmenting test question structures, wherein the test question structures include question stems, options, answers, analysis and scores; 4, converting the segmented and recognized electronic examination paper into a template of an XML format and storing the template; 5, according to the stored template of the XML format, generating the electronic examination paper of an HTML format, wherein the electronic examination paper comprises a test question portion and an answer and analysis portion, and matching of the test question portion and the answer and analysis portion is built. By adopting structured analysis, various question types and answers can be distinguished and therefore various formats of electronic examination papers can be input.

Identifying service candidates in legacy source code, including a source code analyzer performing structured and unstructured analyses of computer software source code procedures, a repository storing results of the analyses, a target profile analyzer analyzing a target service description of a Service Oriented Architecture and formulating a query therefrom, a search module querying the repository to identify source code elements that match the target service description, and combining any matches within a predefined distance from each other within the source code, a ranking engine ranking the combined matches in accordance with predefined heuristics, and a procedure aggregator aggregating the combined matches by their location in propinquity to the procedures, comparing interface definitions defined for the service description to entry and exit points of the procedures to identify candidate procedures having similar input and output parameters, and producing a ranked list of candidate procedures that map into the target element.

A method of horizontally structured CAD / CAM / CAE modeling for analysis comprising: establishing a horizontally structured model of an object in a CAD / CAM / CAE modeling system; creating an analysis model from the horizontally structured model; and performing analysis employing the analysis model. A horizontally structured analysis model formulated with a CAD / CAM / CAE modeling system comprising: a horizontally structured model of an object; an analysis model created from the horizontally structured model, wherein the analysis model is employed for performing analysis.

The invention relates to a method for retrieving similar video clips based on sports competition videos. The method comprises the following steps of: preprocessing all videos in a video library by using an off-line part to form a video feature library; performing video structured analysis and feature extraction on the queried clips by using an on-line part; and performing two-round vari-size grained retrieval in the video feature library, wherein a candidate video set is determined in the first-round coarse-grained retrieval process, and the accurate positions of the similar clips in a video object are determined in the second-round fine-grained retrieval process. The query process is accelerated by organizing all video features through a K-dimension (K-D) tree; and the influence of vision, a time sequence and an interference factor on similarities is comprehensively considered, and the similarities of the similar chips are calculated and sequenced.

The invention discloses a warehouse receipt pledge financing management system and method based on a block chain in the supply chain industry. A protocol layer, a data layer, a function layer and a service layer which are fully covered by a warehouse receipt pledge financing service system based on a block chain are designed. A practical Byzantine fault-tolerant node consensus mechanism, a data distributed evidence storage feature, an information transparency feature, a distributed operation and maintenance feature and the like adopted by a protocol layer based on a block chain are more convenient for big data structured analysis and processing, relatively accurate enterprise portraits are realized, and real-time data synchronization and data security are realized. Therefore, unified business decision optimization arrangement and risk control are facilitated, and convenience is provided for penetration type supervision. The system and the method can completely cover the links of warehouse receipt pledge article value dynamic evaluation, pledge release, credit extension and examination, financing subject credit risk control, penetration type supervision and the like, and avoid the problems of repeated warehouse receipt pledge, serious false warehouse receipt pledge phenomenon and low credit extension safety evaluation quality of financial institutions.

The invention discloses an intelligent monitoring fusion system based on computer vision analysis. The intelligent monitoring fusion system comprises a video monitoring system, a face recognition system, a video structured analysis system and a video fusion system. The video monitoring system is responsible for collecting video information and factory important area temperature information. The face recognition system is responsible for recognizing identities of employees in a factory. The video structured analysis system can judge whether the employee wears the safety helmet, whether the vehicle enters an unauthorized area, whether the employee work clothes are consistent with the work area of the employee and whether the employee carries the parcel. The video fusion system is responsiblefor performing unified management on various information of the video monitoring system, the face recognition system and the video structured analysis system. The system can monitor and analyze the factory area in real time, find out abnormal conditions of the factory area in time and give an early warning, and therefore guarantee is provided for normal operation of the factory area.

The present invention discloses a video structure-based vehicle congestion analysis method and system, and relates to the technical field of road traffic monitoring. The method is characterized in that: by performing video structure analysis on the real-time video of the intersection, the number of vehicles passing through the intersection can be obtained; and the difference of the number of vehicles obtained in the adjacent intersections in a preset time interval is compared to determine the road congestion condition, so that the method is simple and accurate. According to the video structure-based vehicle congestion analysis system provided by the present invention, the road congestion condition can be determined by using the method provided by the present invention, so that the user canknow the real-time road condition in time to select a clear road for driving.

Embodiments of the invention provide a video processing method and a control platform. The method includes the steps of receiving a parsing request sent by a client, the parsing request carrying attribute information of to-be-processed image data, configuring the to-be-processed image data with GPU resources according to the attribute information, receiving the to-be-processed image data through the GPU resources, performing a decoding operation on the to-be-processed image data, performing an acceleration operation on a deep neural network model through a multi-stage compression optimizationmethod, obtaining a deep neural network model after the acceleration operation to perform a video structural analysis on the to-be-processed image data after the decoding operation, obtaining a feature set, and sending the feature set to the client. The embodiments of the invention can improve the efficiency of video structural analysis.

The invention discloses a video retrieval method based on a sample image, and the video retrieval method is used for achieving searching of images through an image. The video retrieval method based on the sample image comprises the following steps that 1), a sample image is imported; 2), the sample image is analyzed in a structured mode; 3), sample image information is put into a library; 4), an original video is imported; 5), video transcoding is conducted; 6), video structured analysis is conducted; 7), video information is put in a library; 8), the sample image is compared with the original video information; 9), the result is shown. According to the video retrieval method based on the sample image, the video retrieval technology enables complex semantic description to be replaced by the vivid sample image, and the effect of searching the images through an image in huge amounts of videos is achieved.

The invention provides a method and a device for excavating synonymous attribute words, wherein the method includes: based on an existing entity word dictionary and an existing attribute word dictionary, carrying out structured analysis on each query in a query set, extracting standard query which is formed by the combination of entity words and attribute words; aiming at each standard query, respectively calculating the click similarity between each non-standard query and the standard query, and confirming the non-standard query which has the same entity words as the current standard query, wherein the click similarity of the non-standard query meets the requirement of the preset similarity; removing the entity words identical to the current standard query in the confirmed non-standard query to obtain candidate synonymous attribute words; and scoring each synonymous attribute word, and based on the scores, confirming the synonymous attribute word of the attribute word in the current standard query. The manpower resource can be saved, and efficiency and a recall rate can be improved.

The invention relates to a DSM-based satellite coupling design flow structured analysis and retrieval method and belongs to the field of design of spacecrafts. The method includes the first step of sorting and summarizing the general flow of designing remote sensing satellites or other types of spacecrafts on the basis of a traditional process expression mode, the second step of conducting mapping to generate a DSM matrix, conducting statistics on DSM items and conducting structured quantitative analysis item by item to obtain a perfect parameter correlation list, and the third step of utilizing the spreadsheet-based middleware technology to achieve storage of a spreadsheet in a database, and retrieving the coupling design process of the satellites according to the storage information about DSM correlation subitems in the database. According to the DSM-based satellite coupling design flow structured analysis and retrieval method, on the basis of the existing design process of the spacecrafts, the design process is mapped to generate a DSM, the DSM is stored into the database for maintenance, the Excel spreadsheet is used as a front-end interface, and consequently a foundation is laid for follow-up optimization.

The invention discloses a psychological assessment method based on human-machine interaction and electronic equipment. The method includes: acquiring the interaction data of a subject, wherein the interaction data includes: interaction content, interaction behavior and psychological data of the subject; on the basis of the interaction data and the psychological model, analyzing the interaction data to obtain the psychological data of the subject, and performing structural analysis on the psychological data to obtain the psychological assessment result. The psychological assessment method integrates artificial intelligence, psychological principle, psychological counseling and evaluation technology, so that scientific, standard, systemic and convenient psychological assessment service is supplied to population. On the basis of offline mature psychological researching, psychological assessment evaluation conversation and professional psychological evaluation, human-machine interaction content is designed to ensure the standardization, structuralization and systematization of collection of the psychological health data, so that the defects that the psychological assessment service islack in professionality and convenience can be solved.

The invention discloses a pirate video identification method and system, wherein the method comprises the steps of carrying out the structured analysis on a to-be-identified video, and obtaining a first video stream; performing feature extraction on the time variable motion track of the first video stream; splitting the first video stream into a plurality of first key frames; respectively performing feature extraction on the colors, shapes and textures of the plurality of first key frames; calculating according to the extracted features to obtain a video fingerprint of the to-be-identified video; positioning similar genuine videos according to the video fingerprints of the to-be-identified videos and the genuine video feature sequence index files; and respectively calculating a Hamming distance and the cosine similarity according to the video fingerprint, and judging whether the to-be-identified video is a pirate video or not by utilizing cross validation between the Hamming distance and the cosine similarity. Compared with the prior art, the precision and the accuracy of the comparison result of the pirate video and the genuine video can be improved.

The invention discloses a visual natural language analysis mining system and a modeling method thereof. The system comprises a visual algorithm component module, a background analysis module, a storage module, a result display module and a model retraining module. The modeling method comprises the steps that a pre-designed graphical algorithm assembly is selected and dragged to canvas to constructa specific natural language analysis mining process, the data flow direction between algorithms in the process is determined, a process description language is generated, and a request is sent to a background analysis module; the background analysis module performs logic analysis on the process DAG, and generates a calling sequence of the components by adopting a topological sorting algorithm; executing specific mining analysis logic according to the process description language; generating a structured analysis result by using a process technology, and storing the structured analysis resultby using a storage module; checking and auditing an analysis result; and performing optimization training on the audited data through a user algorithm model.

The invention relates to a requirement analysis method of an information system integration service, comprising following steps: (1) observing and discussing a service which needs to be integrated, so as to determine a target of integrated service process; (2) building a module of the integrated service process aiming at the target to be realized; (3) examining the module of the integrated service process, and correcting and adjusting repeatedly and circularly the module via finding out differences to be improved in the service process; (4) forming a system function report and a function data report; (5) processing a requirement confirmation for the module gained after being corrected; (6) processing system whole design and integration, running and detecting. The requirement analysis method of the information system integration service provided by the invention takes BPM as center, and processes service process structured analysis via building a service process structured module to realize service requirement analysis, so as to greatly simplify a course of integration information system requirement analysis and improve an efficiency and accuracy of the integration system requirement analysis.

The invention provides a psychological intervention method and device based on man-machine interaction and electronic equipment. The method comprises the steps: acquiring interaction data, including behavior data and physiological data, of a tested person; analyzing the interaction data based on the interaction data and a psychological model to obtain psychological data of the tested person; performing structural analysis on the physiological data or the psychological data according to the behavior data of the tested person and a psychological counseling technology evaluation principle to obtain an analysis result; and determining a corresponding psychological intervention scheme according to the analysis result. According to the invention, interaction data of the tested person is obtainedand analyzed with the psychological model to obtain the psychological data; structured analysis is carried out on physiological data or psychological data according to the behavior data of the testedperson and the psychological counseling technology evaluation principle, then a psychological intervention scheme corresponding to an analysis result is determined, and scientific, standard, systematic and convenient psychological services are provided for the public by combining man-machine intelligence, psychological principles and psychological counseling technologies.

The invention discloses a supply chain demand forecasting and intelligent decision making method based on big data. The supply chain demand forecasting and intelligent decision making method comprises the following steps of performing product demand forecasting on product structured data through various forecasting algorithms, and selecting a forecasting algorithm of which the error is the smallest, so as to obtain demand forecasting data; performing mathematical modeling on enterprise resources; creating decision variables, according to the created decision variables, using a main plan as a reference, creating a limited productivity object function and an unlimited productivity object function, and constructing corresponding limiting conditions according to different productivity object functions; according to the demand forecasting data and through adjusting solving parameters, obtaining a resource allocation manner or demand resources meeting an operation plan of an enterprise. According to the supply chain demand forecasting and intelligent decision making method disclosed by the invention, based on the mass data structured analysis, forecasting is performed through various forecasting algorithms comprising mathematical modeling and the like; according to the demand data obtained by forecasting, and combining conventional productivity condition of the enterprise, a corresponding decision is made; through the adoption of the supply chain demand forecasting and intelligent decision making method, the forecasting accuracy can be guaranteed, and decision making can be assisted.

The invention provides an unstructured text data enhanced distributed large-scale data dimension extracting method. The method includes the steps of text segmentation; word frequency statistics; input text theme extraction and theme term filtering; input text theme extraction, wherein a theme set of a target field is determined according to the target field to which extraction pays attention, the stability that theme terms in an input text and all left words of the theme terms exist at the same time is obtained through calculation, a second threshold value is set through training, the stability and the second threshold value are compared, and when the stability is not smaller than the second threshold value, a set of left theme terms relevant to the input text themes can be obtained. Mass unstructured text data is effectively converted into structured or semi-structured data, and good support is provided for data analysis and mining. A good effect is achieved for solving the complex problem of structured analysis of mass unstructured texts.

The invention discloses a big data collection analysis system and method based on a cloud service. The system comprises a database, a server and an analysis result presentation module, wherein the database and the server are deployed at a cloud end; the database comprises an ideal data module; and the server comprises a data mining module, a user portrait refining module and a data analysis module. The method comprises the steps that: a data collection module acquires information data of a related user object; the data mining module mines effective, novel, potentially-useful and ultimately-understandable data from the mass of acquired data; the user portrait refining module draws out a comprehensive prototype of the user object according to the mined data and the user object; and the data analysis module carries out structured analysis on a user portrait and carries out contrast and comparison with ideal index data in the ideal data module, and the analysis result presentation module carries out result presentation. According to the technical scheme disclosed by the invention, early discovery, early treatment and complete recovery of breast malignant diseases can be ensured, and meanwhile, the big data collection analysis system and method are low in cost, high in efficiency and convenient to popularize.