40 results about "Concept space" patented technology

A system and method for efficiently generating cluster groupings in a multi-dimensional concept space is described. A plurality of terms is extracted from each document in a collection of stored unstructured documents. A concept space is built over the document collection. Terms substantially correlated between a plurality of documents within the document collection are identified. Each correlated term is expressed as a vector mapped along an angle θ originating from a common axis in the concept space. A difference between the angle θ for each document and an angle σ for each cluster within the concept space is determined. Each such cluster is populated with those documents having such difference between the angle θ for each such document and the angle σ for each such cluster falling within a predetermined variance. A new cluster is created within the concept space those documents having such difference between the angle θ for each such document and the angle σ for each such cluster falling outside the predetermined variance.

A variety of technologies are applied in matching techniques for job candidate information. For example, a match forecaster can propose query modifications when the number of candidates meeting criteria specified in a query is outside of a desired range. Cloning techniques can find job candidate matches having characteristics similar to those of a desirable candidate. The match techniques can be used in conjunction with conceptualization techniques in which concepts such as job skills, job title, management, and the like, are extracted from a job candidate's resume. A set of concepts can be represented as a point in n-dimensional concept space. Thus, candidates and desired candidate criteria can be represented in the concept space. Those candidates closest to the desired candidate criteria in the concept space can be designated as matches for the desired candidate criteria. In addition, required criteria can be supported.

A variety of technologies are applied to conceptualization of job candidate information. For example, concepts can be extracted from a job candidate's resume via an ontology. Concepts can be arranged hierarchically within the ontology, and parent concepts can be extracted. Concepts relating to job skills, job title, management, and the like can be extracted. A set of concepts can be represented as a point in n-dimensional concept space. Thus, candidates and desired candidate criteria can be represented in the concept space. Those candidates closest to the desired candidate criteria in the concept space can be designated as matches for the desired candidate criteria.

Techniques are described for ranking the relevance of electronic documents, such as web pages. An algorithm extracts keywords and recurring phrases from the anchor tag data in electronic documents to define a set of concepts. The algorithm then uses link, concept pairs to create nodes in a graph. In this graph, edges can represent both explicit and implicit conceptual links between nodes. By including conceptual data, the algorithm may model and utilize inter-concept relationships when using graph ranking algorithms. This may improve result accuracy by not only retrieving links which are more authoritative given a users' context, but also by utilizing a larger pool of web pages that are limited by concept-space, rather than keyword-space.

A system and method for performing context based document searching is provided. A grid of content tiles is constructed corresponding to a desired concept space. Each content tile is assigned a content tag and is associated with a series of feature values. The feature values are trained to correspond to various regions of the content space. Documents are associated with one or more content tags based on a comparison of document feature values with content tile feature values. A search query is modified to include one or more content tags based on the terms in the search query and / or user preferences. The search query is then matched to documents associated with content tags contained in the search query.

The invention discloses a deep layer data processing method combined with a knowledge base. The method comprises the following steps that concept tuple sets in a body base are merged; link routes of predicates in different types and corresponding logic rule sets are obtained; the logic rule sets are screened preliminarily, candidate rule sets are obtained; a deep layer probabilistic graphical model is obtained; structuring tuples are obtained based on data to be processed and are mapped to a layering concept space; target tuples are generated, semantic extension is carried out; logic rule sets and evidence tuple sets are obtained; a Markov logical net is subjected to instantiation, the conditional probability for target tuple founding is computed, and data processing results are obtained. The invention further provides a deep layer data processing system which comprises a structuring module, a conceptualization module, a target generating module, an extension module, an activating module and a probability computing module. Context and background knowledge can be fully merged, and accordingly, the purpose of semantic comprehension is really achieved.

Mined semantic analysis techniques (MSA) include generating a first subset of concepts, from a NL corpus, that are latently associated with an NL candidate term based on (i) a second subset of concepts from the corpus that are explicitly or implicitly associated with the candidate term and (ii) a set of concept association rules. The concept association rules are mined from a transaction dictionary constructed from the corpus and defining discovered latent associations between corpus concepts. A concept space of the candidate term includes at least portions of both the first and second subset of concepts, and includes indications of relationships between latently-associated concepts and the explicitly / implicitly-associated concepts from which the latently-associated concepts were derived. Measures of relatedness between candidate terms are deterministically determined based on their respective concept spaces. Example corpora include digital corpora such as encyclopedias, journals, intellectual property datasets, health-care related datasets / records, financial-sector related datasets / records, etc.

A system and method for arranging concept clusters in thematic neighborhood relationships in a two-dimensional visual display space is presented. A set of clusters is selected from a concept space. The concept space includes a multiplicity of clusters with concepts visualizing document content based on extracted concepts. A theme in each of a plurality of the clusters is identified. Each theme includes at least one such concept ranked within the cluster. A plurality of unique candidate spines is logically formed. Each candidate spine includes clusters commonly sharing at least one such concept. The clusters are assigned to one such candidate spine having a substantially best fit. Each such sufficiently unique best fit candidate spine is identified and placed in a visual display space. Each non-identified best fit candidate spine is placed in the visual display space relative to an anchor cluster on one such identified best fit candidate spine.

A system and method for efficiently generating cluster groupings in a multi-dimensional concept space is described. A plurality of terms is extracted from each document in a collection of stored unstructured documents. A concept space is built over the document collection. Terms substantially correlated between a plurality of documents within the document collection are identified. Each correlated term is expressed as a vector mapped along an angle θ originating from a common axis in the concept space. A difference between the angle θ for each document and an angle σ for each cluster within the concept space is determined. Each such cluster is populated with those documents having such difference between the angle θ for each such document and the angle σ for each such cluster falling within a predetermined variance. A new cluster is created within the concept space those documents having such difference between the angle θ for each such document and the angle σ for each such cluster falling outside the predetermined variance.

The invention provides a method, a mobile terminal and a server for carrying out the intelligent search at a mobile terminal. The method comprises the following steps: acquiring the lexical space of network resources, and carrying out the conceptual clustering on the information to be searched in a search request, to form a conceptual space; retrieving lexes identical with the content semantics of the conceptual space from the content of the lexical space, to form a semantic space; analyzing user behavior to generate a user behavior space; generating an associated business library according to the mapping relation between the feasible business recorded in a business space and provided by operators and the content of the user behavior space; establishing the association relation between the content in the associated business library and the lexes in the semantic space; and selecting the search results from the network resources. By introducing the analysis on the user behavior, the invention improves the accuracy of search, so the search can be more convenient, direct and effective, and the information exchange via the network can be more user-friendly; and by analyzing the user behavior, the favorite advertising information and the most acceptable advertising information of the user can be recommended at the mobile terminal.

The present invention extends to methods, systems, and computer program products for identifying and extracting game video highlights. Game highlights are identified and extracted from game video recorded or streamed from video games. Game highlights are created by identifying low-level sounds in a game video. Then, game concepts are detected based on identified low-level sounds. A game concept space is created for different types of game concepts. One or more highlights are generated using the concept space based on game knowledge and / or user preference. Multiple highlights can be fused together into a compilation of highlights.

The present invention extends to methods, systems, and computer program products for identifying and extracting game video highlights. Game highlights are identified and extracted from game video recorded or streamed from video games. Game highlights are created by identifying low-level features in a game video. Then, game concepts are detected based on identified low-level features. A game concept space is created for different types of game concepts. One or more highlights are generated using the concept space based on game knowledge and / or user preference. Multiple highlights can be fused together into a compilation of highlights.

A computer based method for monitoring innovation activity including: accumulating first metadata associated with a first plurality of intellectual knowledge files; extracting a first plurality of patterns from the first plurality of intellectual knowledge files; creating a first plurality of concept spaces, using rules-based processing, the first metadata, and the first patterns; grouping, using rules-based processing, the first metadata, and the first plurality of patterns, the first plurality of intellectual knowledge files into first respective concept spaces in the first plurality of concept spaces; and generating a report, the report correlating the first plurality of intellectual knowledge files and the first respective concept spaces. The steps of accumulating, extracting, creating, grouping, and generating are performed by a general-purpose computer specially programmed to perform the steps of accumulating, extracting, creating, grouping, and generating.

The invention provides a concept space navigation method based on concept association. The method includes the following steps that 1, a user selects a certain concept C as an initial concept for navigation; 2, the similarity between the concept C and other concepts in concept space are calculated, and similarity old values (if exist) are updated; 3, semantic association information {<C, related concepts, association types >} of the concept C is acquired; 4, two indexes of the similarity value between each of the other concepts and the concept C and existence of semantic association are integrated and standardized; 5, according to the two indexes in the step 4, the correlation degree value of each of the other concepts and the concept C is calculated, the values are ranked from large to small hereby, and Top K concepts are taken; 6, the K concepts and the similarity values and semantic association information of the K concepts and the concept C are displayed visually through a concept map; 7, the user finds the target concept, and navigation is completed; or the concept needing to be further extended (explored) is selected, and the steps are repeated. The designated concept is navigated to association concept groups thereof, the user can conveniently find the target concept, and the retrieval efficiency is improved.

The invention provides a video retrieval method based on a novel semantic space. The video retrieval method based on the novel semantic space comprises the steps of firstly creating a concept space for all of concepts and creating a detector for each concept and used for mapping low-level features in videos into the concept space; performing spectral factorization to the created concept space to obtain the semantic space formed by multiple 'key concepts'; and creating an overall body semantic space for evaluating similarity of different concepts according to the semantic space. By means of the method, the problem that different concepts cannot be directly compared uniformly and overall in the retrieval process is solved, and accordingly the video retrieval accuracy is improved.

Being divided into training and classifying two phases, the method includes steps: (1) constructing data of classified words and expressions (WE) matrix; (2) based on the said matrix to build frequency data table of inverse sorted classes; (3) based on the said table to build effective set of WE; (4) based on the said set to rebuild data of classified WE matrix; (5) based on the said rebuilt matrix to build frequency data table of inverse sorted WE in each class; (6) based on classified WE matrix, and frequency data table of inverse sorted WE to build vector representations of WE based on space of class concept; (7) based on frequencies of words and frequencies of sorted classes to construct vector data of document to be classified in vector space of class concept; (8) based on magnitude of each component in vector of document to be classified to obtain class of the document. The invention is suitable to information classifying, filtering, and monitoring etc.

A computer-implemented system and method for generating a display of document clusters is described. Clusters of documents are presented in a multi-dimensional concept space. At least one document is selected from a collection of documents to be clusters. An angle θ of the document relative to a common origin of the multi-dimensional concept space is computed. The selected document is compared with each of the clusters. An angle σ from the common origin is determined for each cluster. A difference between the angle θ for the document and the angle σ for the cluster is determined. The difference is compared to the variance, and a new cluster is created when the difference exceeds the variance for all the clusters.

The invention provides a video retrieving method based on context space. The video retrieving method includes constructing a concept similarity matrix by analyzing basic concept space objects, then subjecting the concept similarity matrix to spectral factorization to obtain a group of basic concept sets, finally mapping known concepts to space spanned by the group of basic concept sets, and measuring similarity among the concept objects on the space. According to the video retrieving method based on the context space, by means of the way of constructing the concept space, problems of locality, inconsistency and the like caused by measurement standards under traditional ontology concept sets are avoided, so that the measurement standards among the concept objects mapped to the space are uniform and wholly consistent, an effective solution is provided for solving video retrieving problems, relationships of basic abstract conceptions are closer, and accuracy of video retrieval is effectively improved.

The invention relates to a knowledge processing method and device based on multilayer network space knowledge representation. The method comprises the steps of constructing multilayer network space knowledge representation of a multilayer structure from top to bottom, wherein the multi-layer structure comprises a macroscopic layer, an implementation layer, an attribute layer, a resource layer anda relationship layer from top to bottom; for each multi-layer structure, according to the knowledge of the corresponding subject field, extracting the ontology corresponding to the multi-layer structure and the spatial relationship between the ontologies; constructing a six-tuple knowledge representation for the multi-layer network space knowledge representation, wherein the six-tuple knowledge representation comprises a head entity, a relationship, a tail entity, a time concept, a space concept and a processing operator; and carrying out knowledge processing on the multilayer network space knowledge representation according to the six-tuple knowledge representation. By adopting the method, the multi-path interaction and complex association relationship between cross-domain elements of thenetwork space can be comprehensively represented.

The invention belongs to the technical field of the internet, and particularly relates to a website homepage content based field information collection and association method. The method includes: performing website information filed determination on website homepage content based on field concept space, and then completing field information collection; and performing field information classification on the collected page content based on the field concept space, and then completing field information association. The method forms field concept description based on conception space and performs field information collection based on website homepage determination; and different website nodes form an associated network based on concept space, and then the user can rapidly and accurately position a required field information cluster.

Provided is a personal big data management hierarchy concept vectorizing incrementation processing method. The method comprises the following steps that 1, when a system run for the first time, all concepts are vectorized, and all branching nodes are subjected to concept vector merging operation; 2, when a user operates a concept tree, the substeps of 2.1 obtaining concept vectors and total word number of operated nodes and father nodes thereof, 2.2 modifying the concept vectors of the father nodes according to a formula, 2.3 conducting recursive implementation from the substep 2.1 by taking the father nodes as the operated nodes till a root node and 2.4 updating an inverse document frequency vector are executed; 3, when errors are accumulated to a certain degree, the substeps of 3.1 obtaining current inverse document frequency vector and an inverse document frequency initial value vector, 3.2 updating all vector weights in a vector space in a batched mode and 3.3 updating the inverse document frequency initial value vector are executed. According to the method, the personal big data management hierarchy concept vectorizing incrementation calculation method is achieved, the concept vectors in the concept space can be rapidly adjusted, and the execution efficiency is improved.

Mined semantic analysis techniques (MSA) include generating a first subset of concepts, from a NL corpus, that are latently associated with an NL candidate term based on (i) a second subset of concepts from the corpus that are explicitly or implicitly associated with the candidate term and (ii) a set of concept association rules. The concept association rules are mined from a transaction dictionary constructed from the corpus and defining discovered latent associations between corpus concepts. A concept space of the candidate term includes at least portions of both the first and second subset of concepts, and includes indications of relationships between latently-associated concepts and the explicitly / implicitly-associated concepts from which the latently-associated concepts were derived. Measures of relatedness between candidate terms are deterministically determined based on their respective concept spaces. Example corpora include digital corpora such as encyclopedias, journals, intellectual property datasets, health-care related datasets / records, financial-sector related datasets / records, etc.

Systems, methods, and devices for information transfer comprising a physical or conceptual space that may be populated by significant spatial and / or conceptual positions or significant gestures. One or more users, including humans and animals such as domesticated dogs, may interact with and / or activate elements of this physical or conceptual space, including by wearing devices configured for sensing the users' position and / or movement. The user's interactions with significant spatial positions or significant gestures may produce one or more outputs, such as audio playback of phonetic sounds, or of prerecorded words or phrases. The user may build sequences of phonetic sounds to produce words. The user may receive feedback that may allow the user to detect and interact with the significant spatial positions and / or significant gestures, including by wearing devices configured to produce haptic feedback when the user interacts with or accesses a significant spatial position and / or significant gesture.

The invention relates to the technical field of cross-modal retrieval, in particular to a cross-modal retrieval algorithm based on text concept extension, which comprises the following steps: preprocessing a video to obtain video embedded feature representation; preprocessing the text to obtain text embedding feature representation; calculating the similarity between the video embedding feature representation and the text embedding feature representation to obtain the hidden space similarity; deepening the video through an encoder to obtain a video concept; analyzing the text by using grammar analysis to obtain an initial concept; expanding the initial concept through a text concept expansion mechanism to obtain a text concept; calculating the similarity between the video concept and the text concept to obtain the concept space similarity; performing weighted calculation on the hidden space similarity and the concept space similarity to obtain a fusion similarity model; and based on the retrieval instruction, retrieval sorting is performed by using the fusion similarity model, so that the problem that the retrieval performance is reduced due to imbalance of the video information amount and the text information amount is solved.

The invention discloses a deep layer data processing method combined with a knowledge base. The method comprises the following steps that concept tuple sets in a body base are merged; link routes of predicates in different types and corresponding logic rule sets are obtained; the logic rule sets are screened preliminarily, candidate rule sets are obtained; a deep layer probabilistic graphical model is obtained; structuring tuples are obtained based on data to be processed and are mapped to a layering concept space; target tuples are generated, semantic extension is carried out; logic rule sets and evidence tuple sets are obtained; a Markov logical net is subjected to instantiation, the conditional probability for target tuple founding is computed, and data processing results are obtained. The invention further provides a deep layer data processing system which comprises a structuring module, a conceptualization module, a target generating module, an extension module, an activating module and a probability computing module. Context and background knowledge can be fully merged, and accordingly, the purpose of semantic comprehension is really achieved.

Disclosed are a concept platform apparatus and method using schematic diagrams. The concept platform apparatus using a schematic diagram according to one embodiment of the present invention may comprise: a CK canvas module for providing a CK canvas divided into a concept space and a knowledge space, and connecting concepts and knowledge on the C-K canvas through a linking process to assist in a solution search for solving a problem; and a case management module for storing and managing, as one case, the C-K canvas on which the solution search is completed including knowledge, concepts, and information about the interconnection relationship.

A computer based method for monitoring innovation activity including: accumulating first metadata associated with a first plurality of intellectual knowledge files; extracting a first plurality of patterns from the first plurality of intellectual knowledge files; creating a first plurality of concept spaces, using rules-based processing, the first metadata, and the first patterns; grouping, using rules-based processing, the first metadata, and the first plurality of patterns, the first plurality of intellectual knowledge files into first respective concept spaces in the first plurality of concept spaces; and generating a report, the report correlating the first plurality of intellectual knowledge files and the first respective concept spaces. The steps of accumulating, extracting, creating, grouping, and generating are performed by a general-purpose computer specially programmed to perform the steps of accumulating, extracting, creating, grouping, and generating.

The invention discloses a short text feature extraction method, which is based on a knowledge base and a syntax analysis method to perform feature extraction on short texts, including a model training process and a feature extraction process; training is performed on training set data; The weight group W corresponding to the highest accuracy rate and the training model M corresponding to the highest accuracy rate; after the feature extraction process processes the test set data, each category is assigned a weight group W; the ESA algorithm is used to map the short text to the concept space, Get the explanation vector of the short text; get the topic vector through LDA, as the final feature vector of the short text, as the feature of the short text. The method provided by the invention can solve the problems of sparse short text features and unclear topics of short texts; reduce the processing difficulty of short text feature extraction, improve the results of short text feature extraction, and improve the accuracy of text classification.

The invention discloses a method for recommending programs based on EPG. It reads the classification directory in the EPG program list received for the first time, uses the program category in the classification directory as a node, establishes a basic concept space, and receives the EPG program each time At the same time, the new concepts appearing in the received EPG program list should be used as contacts to update the concept space; the query keywords that the user has queried are clustered, and the result of the concept clustering is mapped to the concept space On the corresponding nodes in , form the current user's personality preference space according to the area formed by the mapped nodes: A. call the personality preference space, and read the current EPG program list; B. according to the called personality preference space, With each node in the personality preference space as the retrieval content, the current EPG program list is retrieved, and the EPG program recommendation information is formed and displayed. The application of the present invention can provide users with highly accurate EPG program recommendation information through simple operations.

According to the method, based on the two means of describing the logic knowledge base and the ordered concept space, music which is an art resource difficult to deeply retrieve is converted into concept search on the knowledge base, so that a new retrieval system is favorably realized, and deep retrieval of the music resource is realized. Therefore, the invention provides a music resource organization and access mode based on a description logic knowledge base TBox logic structure, the ordered music resource set is established by defining the TBox concept space meeting the partial order property, the more accurate and efficient music resource retrieval capability is provided by utilizing the ordered relationship, and the shortages of the existing keyword retrieval text information system are made up.