520 results about "Semantic matching" patented technology

Techniques are provided for semantic matching. A semantic index is created for one or more schemas, wherein each of the one or more schemas includes one or more word attributes, and wherein each of the one or more word attributes includes one or more tokens, wherein the semantic index identifies one or more keys and one or more values for each key, wherein each value specifies one of the one or more schemas, a word attribute from the specified schema, and a token of the specified word attribute, and wherein the specified token is a synonym of the key. For a source word attribute from one of the one or more schemas, the source word attribute is used as a key to index the semantic index to identify one or more matching word attributes.

The invention relates to a deep learning-based question and answer matching method. The method comprises the following steps of: 1) sufficiently learning word orders and sentence local features of a question text and an answer text by utilizing two underlying deep neural networks: a long short-term memory network LSTM and a convolutional neural network CNN; and 2) selecting a keyword with best semantic matching on the basis of a pooling manner of an attention mechanism AM. Compared with existing methods, the method has the advantages of being in low in feature engineering workload, strong in cross-field performance and relatively high in correctness, and can be effectively applied to the fields of commercial intelligent customer service robots, automatic driving, internet medical treatment, online forum and community question answering.

The method for processing data in a relational database wherein ontology data that specifies terms and relationships between pairs of said terms expressed in an OWL document is stored in the database, database queries that include a semantic matching operator are formed which identify the ontology data and further specify a stated relationship between two input terms, and the query is executed to invoke the semantic matching operator to determine if the two input terms are related by the stated relationship by consulting said ontology data.

The embodiment of the invention discloses a method and a device for establishing a picture search correlation prediction model, and a picture search method and device. The method for establishing the picture search correlation prediction model comprises the following steps: using a training sample to train a pre-constructed original deep neural network, wherein the training sample comprises a query and picture data, and the original deep neural network comprises a representation vector generation network and a relevant computational network; and taking the original deep neural network which finishes training as the picture search correlation prediction model. The technical scheme of the invention optimizes the traditional picture search technology, and is better than the traditional technology and various fusion and variation capabilities on multiple aspects including the semantic matching of the query and a picture text, the semantic matching of the query and picture contents, click generalization and the like, and relevancy between a picture search result and the query input by the user can be greatly improved.

The invention relates to a construction method of a knowledge map question answering system in the field of electric power communication based on deep learning, which comprises the following steps: Step 1, semantic analysis, that is, preprocessing a question q put forward by a user in a natural language, extracting a keyword of a user inquiry, a focus of a query sentence and the like as an entityw of a question sentence from the question q; Step 2: semantic expression, namely, vectorization of the natural language question after preprocessing, and vectorization of the candidate set of answera, are used to calculate the matching degree of the question q and the answer a; and Step 3, the answer a most matched with the question q and most accurate is found through the method of semantic matching degree calculation, query and inference, so that the score S (q, a) of the question-answer pair (q, a) is the highest. The invention studies the feasibility of the question answering system constructed by the knowledge map in the field of communication of the State Grid.

A method for rapidly identifying terms that are associated with a given root term by a transitive relationship defined by hierarchical ontology data stored in a relational database. A transitive closure table is created that comprises a plurality of rows each of which specifies a term and an associated one of a plurality of root terms. The table is sorted and indexed by the root terms to group together rows associated with each of said root terms. The resulting transitive closure table may be consulted to rapidly identify terms associated with said given root term.

The method for processing data in a relational database wherein ontology data that specifies terms and relationships between pairs of said terms expressed in an OWL document is stored in the database, database queries that include a semantic matching operator are formed which identify the ontology data and further specify a stated relationship between two input terms, and the query is executed to invoke the semantic matching operator to determine if the two input terms are related by the stated relationship by consulting said ontology data.

The invention provides a keyword grouping method and a keyword grouping system. The keyword grouping method comprises: A, based on the attribute of the keywords, keywords in a current promoted account are classified through a preset keyword classification module, and the weight of each key word is ensured; B, based on the semantic matched degree between the keywords and originality, keywords with the semantic matched degree satisfying requirements of a preset matched degree between the keywords and the originality in the current promoted account are selected from the keywords in each category as seed words; and C, based on the weight of each keyword, surplus keywords in the current promoted account are clustered with the seed words in each category as cores to get a grouping result of the keywords. Clustering is that the keywords are clustered in a category satisfying requirements of a preset diversity factor by calculating a diversity factor between the keywords and the seed words. The keyword grouping method and the keyword grouping system improve accuracy of matched relations between the keywords and the originality.

A system and method for composing application services includes an indexing module configured to index words in a request and available application descriptions to create a semantic similarity map. A semantic matcher is configured to determine semantic similarity between concepts / terms in both domain-independent and domain-specific ontologies for the semantic similarity map. A prefiltering module is configured to determine candidate compositions for the request based on the semantic similarity map and the available descriptions. A metric guided composition method is configured to run algorithms to generate a set of alternative compositions by determining which applications can be composed with which others using the semantic similarity map.

Embodiments of the invention disclose a method for semantic matching. The method comprises: receiving a to-be-matched first statement; inputting the first statement as a word segmentation model, through the word segmentation model, outputting a first word sequence after word segmentation is performed on the first statement; converting the first word sequence to a first word vector sequence; inputting the first word vector sequence to a twinborn bidirectional long short-term memory LSTM network, and outputting a second statement matched with the first statement through the twinborn bidirectional long short-term memory LSTM network. An embodiment also provides a semantic matching server, used for improving accuracy of semantic matching.

The embodiment of the invention discloses a question answering method and device, relates to the technical field of semantic understanding and aims to solve the problem that accurate semantic matchingcannot carried out on questions of users by servers due to various input modes of the users. According to the specific scheme, the method comprises the steps of receiving a question input by a user and obtaining keywords of the question; obtaining a candidate question-and-answer pair set from pre-stored question-and-answer pairs according to the keywords, wherein the candidate question-and-answerpair set comprises at least one candidate question and an answer corresponding to each candidate question; calculating the topic similarity between the question and the candidate question and determining the candidate question with the highest topic similarity, in at least one candidate question, as the target question; and returning the answer to the target question to the client. When the method disclosed by the embodiment of the invention is applied to a question answering system, the accuracy of semantic matching can be increased.

The invention discloses an information retrieval-based question and answer system and method for knowledge graph energization, which integrally improve the question and answer effect of the system, expand the user consultation range and improve the question feedback accuracy. According to the technical scheme, the system comprises a knowledge map database for storing domain knowledge map information; a word segmentation and part-of-speech tagging module which segments the user questions and tags the part-of-speech of the user questions; an entity identification and link module which identifiesentities in the user questions and links the entities to nodes in the knowledge graph database; an intention understanding module which obtains an intention understanding result of the user problem based on the entity link result and the distributed representation vector; a retrieval module which retrieves a plurality of corresponding question and answer pairs as roughing results according to theinformation in the user questions based on the retrieval data source; a sorting module which is used for resorting the roughing results by utilizing the distributed representation vectors of the entities; and a semantic matching module which scores the reordering result by using the distributed representation vector of the entity and finally outputs an answer.

Apparatus for determining a meaning of an ontology term, the apparatus including an electronic processing device that compares the ontology term to a number of potential ontology term meanings, generates a matching score for the results of each comparison, the matching score being based on a similarity of the ontology term and the potential ontology term meaning and selects a potential ontology term as the ontology term meaning using the matching scores.

A system for and method of matching of web service policies, which includes matching of non-functional properties of first and second Web Services while considering inter-domain interactions of the first and second Web Services using semantics. Methods for semantic matching of web service policies are also described.

The invention discloses an answer selection method for non-fact questions and answers, and belongs to the technical field of intelligent retrieval. The method comprises the steps of processing a question sentence and a to-be-selected answer statement by adopting a convolutional neural network based on an attention mechanism to obtain a first semantic vector and a second semantic vector, wherein the first semantic vector represents a semantic vector of the question sentence, and the second semantic vector represents a semantic vector of the to-be-selected answer statement; and matching the first semantic vector with the second semantic vector, and returning the to-be-selected answer statement corresponding to the second semantic vector with the highest matching degree as a correct answer. According to the method, the semantic vector representation of the sentence is generated by utilizing the convolutional neural network based on the attention mechanism, and a weight is given to an input by an importance degree in the semantic representation process, so that the influence of contents irrelevant to an answer theme is reduced, the high-quality semantic representation is automaticallygenerated, the semantic matching degree between the question sentence and the answer statement is improved, and the correct rate of answer selection is improved.

The embodiment of the invention provides a knowledge data providing method and device, electronic equipment and a storage medium. The knowledge data providing method comprises the steps of obtaining aquery request statement; Performing word segmentation processing on the query request statement to obtain at least one query word; Respectively obtaining extended keywords corresponding to each queryword from an extended dictionary; Respectively matching each obtained query word or the combination of the expansion keywords corresponding to the query word with a plurality of semantic matching expressions to obtain information of a query intention; Obtaining knowledge data corresponding to the query intention from a knowledge base; Providing the knowledge data. The query request put forward ina natural language mode can be understood; The method comprises the following steps: establishing a semantic understanding framework, analyzing, carrying out demand matching on key information extracted from a query request through the established semantic understanding framework, and providing corresponding knowledge data in a knowledge base according to a query intention obtained by matching, thereby providing knowledge data accurately matched with the query intention for a query user.

A method for supporting semantic matching queries in a database management system (DBMS) by extracting and storing the transitive / subsumption relationships from a given ontology data in a DBMS with native XML support. These transitive relationships are transformed into a set of XML documents that are natural mappings of the hierarchical structure of the transitive relationships. A table function construct expresses semantic matching queries in a declarative manner. The semantic matching queried are automatically rewritten or translated into standard SQL / XML search operators such as XQuery, XPath and XMLExists, and executed by the SQL / XML DBMS on the given instance data and the extracted transitive relationships data.

The invention provides a judgment document retrieval method based on semantic matching and a server. The judgment document retrieval method based on the semantic matching and the server have the advantages that when a case is retrieved, the direct inputting of words which are precisely matched with keywords in a judgment document is not needed, the matched judging document can be found by directly describing the law problems or cases through a natural language, thus the problem is solved, the use threshold of the document retrieval server is greatly decreased, and the retrieval efficiency is improved.

The invention discloses a matching method of semantic WEB service and a system thereof. Based on similarity between request and candidate service, the matching method and the system synthetically consider functional and non-functional factors, and introduce a phasing filtering mechanism. The matching method and the system adopt single-concept semantic matching algorithm, take depth, inheritance relation and binary relation into full account so that a body relationship structure is formed into a graphic structure rather than a tree-shaped structure, and the multiple inheritance problems and loop problems are processed during calculation of semantic distance based on the graph. The adopted multi-concept semantic matching algorithm has introduced a processing of repeated matching. During input and output matching, the number of parameters are taken into account, a method for calculating similarity in three levels is adopted, therefore,, the matching is more efficient; and the matching method and the system also takes into account factors of user preferences and service quality, therefore, the precision of matching and efficiency of response can be further improved.

The invention provides a method and equipment for building indexes and matching inquiry input information of a user. According to text information, structural information is determined and subject words are extracted; according to a subject corresponding to the subject words, label words corresponding to the subject are determined; and the indexes are built form the subject words and the label words. Moreover, the subject words and the label words are obtained through analysis of the inquiry input information input by the user, matching inquiry is carried out in the built indexes, and candidate text information is obtained; according to the semantic matching degree of the candidate text information and the inquiry input information, and target text information matched with the inquiry input information is determined. Compared with the prior art, on the basis of encyclopedia or other network resource knowledge, extracting of subjects and titles is carried out, effective description of resource knowledge content is formed, and accordingly semantic searching of the resource knowledge is more efficient, the searching requirements of the user for complicated descriptions which the user cannot accurately express by means of key words are met, and use experience of the user is improved.

The invention relates to a software homology detection method and a device based on an abstract syntax tree and semantic matching. The method comprises the following steps: generating an abstract syntax tree corresponding to software source codes, and regulating subtrees which match with the same semantic feature rule and have the same semantics in the abstract syntax tree to a unified structure; calculating the hash values of subtrees in the abstract syntax tree; and performing software homology detection through judging whether the hash values of subtrees with the same number of nodes are consistent, thereby performing accurate and effective software homology detection by combining semantics in grammatical level.

The invention discloses a convolutional neural network-based document automatic question and answer system construction method. The method comprises the following steps of: 1, constructing a theme document library; 2, constructing a word vector model; 3, carrying out theme matching; 4, constructing a word vector matrix; 5, carrying out semantic matching on the basis of a semantic model of a convolutional neural network, wherein the semantic model of the convolutional neural network is divided into three layers, the first layer is a convolutional neural network layer, the second layer is an attention layer and the third layer is a full connection layer; and 6, an answer selection process: selecting a matched answer. According to the method, a synonym dictionary does not need to be manuallyconstructed so that plenty of manpower and time cost are saved, semantic meanings of word contexts can be purposely sampled in a model training process, and an attention mechanism is added in the network so that the contribution degrees, to semantic meanings of whole sentences, of certain representative words can be enhanced.

The invention discloses a knowledge graph inference method based on relation detection and reinforcement learning. The method comprises the steps that on the basis of character string fuzzy matching between a domain knowledge graph and an entity dictionary and a CNN-LSTM-CRF-based entity recognition model, an entity in a question input by a user is detected, and entity detection is completed; relation detection is completed by a neural network based semantic matching model, and the relation detection model is characterized in that low-dimension manifold expression is obtained through the neural network according to the input question, the relation related to the question and the relation not related to the question, on the basis of the low-dimension manifold expression, rank loss optimization model parameters are adopted, so that the question can search the relation set for the relation most similar to the semantics; according to knowledge graph inference based on reinforcement learning, for each time step, on the basis of a strategy function pi theta, under the current entity et, one out-going relation rt+1 is selected, the next entity et+1 is executed, the final entity eT is reached through a preset sequential decision with the maximum inference path length T, and the entity eT is adopted as an answer of the question to be output.

The invention discloses an interactive video retrieval method based on unsupervised learning and semantic matching features, which comprises the steps of extracting image bottom layer features and model matching sequence features from the video image frame level of a video database; extracting semantic matching features from the high-level semantic level of image bottom layer features; performing unsupervised learning on the extracted model matching sequence features and semantic matching features, establishing retrieval and direct retrieval based on unsupervised learning, and forming an interactive interface by related feedback. The middle layer features, high layer features, unsupervised retrieval mechanism and interactive mechanism of an integrated video compose a set of new complete video retrieval system, which precisely measures the time-space sequence information of a video object, therefore better retrieval effect is achieved, the semantic understand of a sports video theme is developed, the online calculating complexity and retrieval time of a system are reduced, and the interactive interface greatly improves the retrieval performance of the system.

The invention provides a method for publishing advertisement and an advertisement server, the method comprises: performing semantic matching for the advertisement keywords and the media website content to obtain text keywords same as or associated with the advertisement keywords; marking the text keywords in the text of the media website and posting the advertisement content and the link web site corresponding to the advertisement keywords. According to the invention, the media website content can be analyzed, and the advertisement keywords and the corresponding web page text contents concerned by the browsing people are matched accurately by the semantic matching, so that the text keywords same as or associated with the advertisement keywords can be obtained, the advertisement information can be posted on the text keywords, the accuracy for delivering the advertisement by the advertisement user can be effectively improved.

The invention provides a text semantic matching method. The method comprises the steps of obtaining total vectors by using word vectors and character vectors corresponding to words and characters in ato-be-processed text; performing convolution processing, averaging processing and bidirectional LSTM processing on the total vectors, wherein an LSTM method without an attention mechanism is adoptedduring basic text processing, and an LSTM method with the attention mechanism is adopted during target text processing; obtaining pooling vectors; and taking the similarity of the two pooling vectorsas the similarity of two texts. According to the method, not only a semantic relationship among the words in the text but also a semantic relationship among the characters are considered; not only a positive semantic relationship between the characters and the words but also a negative semantic relationship between the characters and the words are considered; and multiple text matching models arecomprehensively applied, so that feature information among text contexts is expressed more comprehensively, accurately and fully, and the text matching accuracy is improved.

The invention belongs to the education and teaching examination technical field and relates to a subjective question checking and scoring method, a subjective question checking and scoring device and a terminal device. The method includes the following steps that: a current subjective question to be scored is determined; a to-be-scored answer to the subjective question is scanned and identified, so that an identified text is obtained; first words which are in semantic matching with preset keywords are searched in the identified text, and preset corresponding relations exist between the keywords and score points in a standard answer to the subjective question; the semantic matching degrees of the first words which are obtained through search relative to the corresponding keywords are calculated; and the score of the to-be-scored answer is obtained according to the preset scores of the keywords corresponding to the first words and the semantic matching degrees of the first words. With the subjective question checking and scoring method, the subjective question checking and scoring device and the terminal device of the invention adopted, processes which workers are required to be participate can be decreased, labor costs can be reduced, and the efficiency of test paper checking and scoring is improved.

The invention relates to a data query method and device, computer equipment and a computer readable storage medium. The data query method includes the steps of receiving search statements of a user; conducting semantic matching on the search statements to obtain at least one intention, wherein each intention in the intentions includes an intention knowledge point matched with the intention and atleast one intention parameter relevant to the matched intention knowledge point, and a knowledge base includes a plurality of intention knowledge points including a plurality of corresponding search answer extraction instruction templates; according to at least one intention parameter relevant to the matched intention knowledge point, and the search answer extraction instruction template corresponding to the matched intention knowledge point, obtaining a search answer extraction instruction; besides, according to the search answer extraction instruction, extracting corresponding data from a dynamic database to serve as search answer data. According to the data query method and device, the computer equipment and the computer readable storage medium, the data query efficiency can be improved, and the answer replying accuracy can be increased.

The invention discloses a question-answer matching method fusing deep representation and an interaction model. The method comprises the following steps: firstly, pre-training word vectors and character vectors of a text pair consisting of spoken questions input by a user and standard questions in a knowledge base; and then fusing the fusion depth representation and the interaction model in a loosecombination or tight combination mode, and performing question and answer matching on spoken questions input by the user by using the fused model. The universality of the service can be enhanced, therecognizable spoken language category can be expanded, the answer matching accuracy can be improved, and accurate semantic matching of wide semantic recognition can be realized.