32 results about "Concept tree" patented technology

The invention discloses a text similarity matching method on the basis of a vector space model. The text similarity matching method includes extracting keywords of texts, clustering all the keywords and generating a keyword concept tree; and computing the similarity of the texts according to the created keyword concept tree of the keywords in the texts to be translated, and acquiring texts in a translation depository according to the similarity. The texts in the translation depository are matched with the texts to be translated. According to the technical scheme, the test similarity matching method has the advantages that relations among the texts can be relatively accurately reflected, so that the similarity of the texts can be sufficiently reflected.

Systems, methods, and computer storage media for handling failures in generating structured queries from natural language queries. One of the methods includes obtaining, through a natural language front end, a natural language query from a user; converting the natural language query into structured operations to be performed on structured application programming interfaces (APIs) of a knowledge base, comprising: parsing the natural language query, analyzing the parsed query to determine dependencies, performing lexical resolution, forming a concept tree based on the dependencies and lexical resolution; analyzing the concept tree to generate a hypergraph, generate virtual query based on the hypergraph, and processing the virtual query to generate one or more structured operations; performing the one or more structured operations on the structured APIs of the knowledge base; and returning search results matching the natural language query to the user.

A data processing technique is provided with improved convenience.

A data processing apparatus includes: a concept tree setting unit 22 which sets a concept tree that indicates the user's purposes or intentions; a classification unit 24 which, based upon the concept tree, classifies a data set created by or acquired by the user; a book display unit 26 which displays the data set thus classified; a search request unit 28 which makes a request for a search using the concept tree or the data set classified based upon the concept tree as a query; and a search result acquisition unit 32 which acquires, as a result of the search, the data set classified based upon the concept tree.

The invention provides a concept-based unstructured text big data analysis mining method and a device thereof. The method comprises the following steps of: (1) performing pre-processing, including word segmentation and named entity recognition; (2) performing concept extraction and concept expression identification on an input text; (3) performing analysis mining on the concept expression of the input text according to mining rules; (4) calculating confidence levels of the mining results; (5) outputting the mining results according to the confidence levels; and (5) visually showing the mining results. A mining model of the method comprises three trees, including an ontology tree, an element tree and a concept tree. The device comprises a modelling unit (1), a pre-processing unit (2), a concept extraction and expression identifying unit (3), an analysis mining unit (4) and a visual show unit (5). The method and the device have the following advantages that: diversity of services and natural language expressions is separated in the modelling process, and investment in service maintenance is lowered; and the mining method can greatly improve accuracy of analysis mining.

The invention provides a semantic-based text retrieval method, and solves the problems that polysemy or synonymy cannot be distinguished and retrieval results are mistakenly selected or missed in the retrieval process. According to the method, concepts of words replace words for searching and retrieval, and the retrieved files are sorted; the method specifically comprises steps as follows: S1, a concept tree is established according to the concepts of words, and a word similarity matrix is calculated; S2, the concept of a target file is extracted in reference of a preset body, the target file is subjected to indexing processing according to the concept, and an index file is generated; S3, word segmentation is performed on initial query of a user, similar items whose similarity to the query words is larger than the threshold value M are found out from the word similarity matrix, and the similar items are added to the user query in an OR manner; S4, a search engine searches the target file according to the user query; S5, according to the similarity of words, the similarity of the files is evaluated, and the files are sorted; and S6, file data are read, and a sorting result is output.

The invention provides a text enhancement method, a text classification method and a related device. The method comprises the steps: acquiring a statement content in a text corpus, performing word segmentation on the statement content, and obtaining words obtained after word segmentation; screening out similar words of which the similarity with the segmented words exceeds a threshold value from the concept tree, and randomly replacing the statement content by using the similar words to obtain a plurality of statements; training a generative adversarial network by using a plurality of statements to obtain a generative adversarial network model; generating an expansion statement sample by using a generative adversarial network model; and combining the expanded statement sample with the statement content in the text corpus to obtain an enhanced text data set. In the implementation process, the expanded statement sample is generated by using the generative adversarial network model obtained by training, and the generative adversarial network model learns the newly added change rule between the similar words with the similarity exceeding the threshold value in the concept tree, so a specific category sample can be better generated.

The embodiment of the invention provides a text similarity processing method which comprises the following steps: acquiring Internet information and generating a metadata characteristic vector; constructing a concept tree according to the generated metadata characteristic vector, and generating subtrees based on the constructed concept tree; and calculating the similarity among texts in the acquired Internet information via the subtrees. The text similarity processing method has the advantages that manual operation is avoided, so as to reduce labor cost; and the accuracy is high.

The invention provides an image classification method, and particularly relates to an application method of concept cognition in the field of image classification. The image classification method based on the concept cognition process is divided into two modules: a cognition training module used for learning an image concept and finally generating a concept tree for realizing an image classification task; and the image classification module that is used for carrying out image classification by using the concept tree obtained by the training module. The method comprises the following steps: describing an image feature FD, generating an image form background K, generating a necessary attribute set Base by an image set form background K, constructing a coarse level of a concept tree CT by necessary attributes, constructing a fine level of the concept tree CT by the image set form background K, updating the concept tree CT, obtaining an optimal concept tree, and classifying by using the optimal concept tree. The problem that formal concept cognition is difficult to apply to the image aspect is solved through an image feature extraction technology, a feature data processing technology and a concept learning method.

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.

The invention discloses an incremental concept calculation method for a college course system based on a concept tree. According to the method, firstly, the influence of newly added object nodes in a path tree on a concept is analyzed; secondly, according to the conversion relation of the path tree, the concept and a concept tree, the influence of newly added objects on the concept tree is obtained; finally, updated constraint conditions of the concept tree are given by analyzing the characteristics of the newly added objects, and concept tree updating is directly performed. The algorithm uses an object topology theory as the support, does not need actual operation object topology and has no hard requirement for a form background, and concept updating under dynamic data updating is achieved. By adopting the method, incremental form concept calculation is conducted on the form background composed by different semesters of learning courses and graduation requirement data of college students, different semesters of courses are gradually added into the composed concept tree, concept tree updating is performed to obtain the final updated concept tree, and accordingly knowledge systems of all the courses are obtained.

The invention relates to a semantic fidelity-oriented virtual conference method and a three-dimensional virtual conference system. The method comprises the following steps of: forming a tree semantic architecture according to a semantic concept; setting a default signal corresponding to each semantic concept of different hierarchies in the tree semantic architecture; extracting semantic description of a scene where the participants are located from the multi-modal signal and updating a private hierarchical semantic library; updating the public hierarchy semantic library by utilizing the private hierarchy semantic library; the server side sends hierarchical semantic description composed of all the contents in the public hierarchical semantic library to all the user sides, and the corresponding private hierarchical semantic library is updated at each user side according to the hierarchical semantic description composed of all the contents; generating a virtual conference scene in the view angle of the participants; and generating a virtual conference scene in the view angle of the participants in the conference proceeding process. According to the method, the problems that virtual image expressions and actions are rough, a conference scene is not real, and people and the scene are difficult to interact are solved, the virtual conference scale is increased, and the sense of reality of conference participation is improved.

The invention discloses a video content structure representation method based on an incremental concept tree. The video content structure representation method comprises the following steps: converting a video time sequence change into a dynamic form background, carrying out object topology representation on the form background, analyzing the influence of a newly added object on object topology, and classifying the newly added object according to different generated influences; analyzing the relationship between the objects on the premise of taking the newly added object characteristics as thesubstrate; determining a sub-tree which can grow after the object is newly added, and growing the sub-tree at a corresponding position in the concept tree through a sub-tree growth algorithm of the newly added object; completing the updating of the concept tree through a concept tree updating algorithm, thereby carrying out the structural representation of the video content.

The invention relates to the field of natural language processing, in particular to cross application of judicial and artificial intelligence technologies, and provides an interpretable legal judgmentprediction method and device based on a court trial copulation mechanism, electronic equipment and a storage medium. The method comprises the steps of obtaining legal instrument text information to be processed; analyzing and processing the legal document text information to be processed through a concept tree classifier and a multi-classifier, and outputting a first legal judgment prediction result and a second legal judgment prediction result; if the two prediction results are consistent, accepting the current prediction result; if not, starting a court trial congruence mechanism; and through a plurality of arbitration tree classifiers, performing voting analysis processing on the second prediction result information, and determining a final prediction result according to the principlethat a small number obeys a majority. The interpretable legal judgment prediction method and device, the electronic equipment and the storage medium not only have interpretability from features to concept levels, but also further improve classification accuracy on the basis of an original model through a correction mechanism.

The invention discloses a dynamic concept learning and knowledge graph generation method based on a partial order three-branch structure, and the method comprises the following steps: S1, for a given original-form background and an incremental-form background, judging the type of a newly-added object according to the binary relation between the newly-added object and an original object; s2, performing incremental updating on the original concept tree based on the properties of each category according to the category of the newly added object so as to realize dynamic concept cognitive learning; and S3, according to the dynamic change of the concepts in the step S2, performing incremental deletion on each concept node, content and mutual associated edges in the original knowledge graph so as to realize incremental update of the knowledge graph. According to the method, an existing partial sequence three-branch structure generation algorithm is combined, incremental learning operation is introduced, dynamic concept cognitive learning can be achieved on the basis of dynamic data, and incremental generation of the knowledge graph is achieved.