40 results about "Concept space" patented technology

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.

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.

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 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 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.

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.

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.

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.