734 results about "Semantic representation" patented technology

Embodiments of the present invention provide a method and apparatus for searching using an active ontology. One embodiment of a method for searching a database includes receiving a search string, where the search string comprises one or more words, generating a semantic representation of the search string in accordance with an ontology, searching the database using the semantic representation, and outputting a result of the searching.

The system and method provide for data interactions between interconnect nodes so that they can create outcomes cooperatively with responsiveness and flexibility. Each node may transmit data and events of interest to other nodes. The other nodes may receive notification of data and event transmissions. Delegated actions may be created for off-node (e.g. network-based) execution that may act as delegates for corresponding nodes without the need for the nodes to be connected to a network nor for data and event transmissions to be processed directly by the nodes. The system and method may provide for translation of data and events received, from a node, in a first semantic representation to be translated to a second semantic that is compatible with one or more other nodes.

Embodiments of the present invention provide a method and a system for analyzing and learning behavior based on an acquired stream of video frames. Objects depicted in the stream are determined based on an analysis of the video frames. Each object may have a corresponding search model used to track an object's motion frame-to-frame. Classes of the objects are determined and semantic representations of the objects are generated. The semantic representations are used to determine objects' behaviors and to learn about behaviors occurring in an environment depicted by the acquired video streams. This way, the system learns rapidly and in real-time normal and abnormal behaviors for any environment by analyzing movements or activities or absence of such in the environment and identifies and predicts abnormal and suspicious behavior based on what has been learned.

A composable software bundle is created by retrieving a semantic representation of a set of software modules. A functional representation of a set of operations is retrieved. Each operation in the set of operations is to be performed on the set of software modules during at least one virtual image life-cycle phase in a set of virtual image life-cycle phases. A set of artifacts including a set of executable instructions associated with the set of operations is identified. The semantic representation, the functional representation, and the set of artifacts, are stored in a composable software bundle.

System and method for the indexing and retrieval of semantically annotated information units from a collection of semantically annotated indexed information units in response to a query using an ontology-based IR model. The retrieval method comprises: receiving a semantically annotated query with semantic annotations to individuals or classes within a determined populated base ontology; embedding, as a set of weighted-mentions to individuals or classes within the populated base ontology, the semantically annotated query in a semantic representation space of an ontology-based metric space IR model; obtaining the representation in the semantic representation space for every indexed information unit; computing the Hausdorff distance between the space representation of the query and the space representation of all the indexed information units of the collection; retrieving and ranking, the relevant information units based on the computed Hausdorff distance.

A machine-learning engine is disclosed that is configured to recognize and learn behaviors, as well as to identify and distinguish between normal and abnormal behavior within a scene, by analyzing movements and / or activities (or absence of such) over time. The machine-learning engine may be configured to evaluate a sequence of primitive events and associated kinematic data generated for an object depicted in a sequence of video frames and a related vector representation. The vector representation is generated from a primitive event symbol stream and a phase space symbol stream, and the streams describe actions of the objects depicted in the sequence of video frames.

A computer system and method generate a semantic representation of one or more XML language inquiries across relational and non-relational data sources. A semantic intermediate language representation explicitly describes the meaning of the one or more XML language inquiries. The semantic intermediate language may be a graph structure with nodes which describe the operations of the original query. Operators assigned to the nodes in the semantic graph allow an unambiguous definition of the original XML query. The semantic intermediate language may be used to perform XML queries over single or multiple data sources. A method includes receiving at least one inquiry, defining at least one node object for every operation within the received inquiry, translating each node object using operators, and generating a semantic representation from the operators.

A method and an apparatus for semantic parsing of electronic text documents. The electronic text documents can comprise a plurality of sentences with several language components. The method comprises analyzing at least one sentence of the electronic text document and dynamically generating a graph from the analyzed sentence of the text document. The graph represents a semantic representation of the analyzed one or more sentences. The method continues the analysis until an ambiguous sentence is determined and analyzed by evaluating at least a portion of the generated graph.

Finite-state systems and methods allow multiple input streams to be parsed and integrated by a single finite-state device. These systems and methods not only address multimodal recognition, but are also able to encode semantics and syntax into a single finite-state device. The finite-state device provides models for recognizing multimodal inputs, such as speech and gesture, and composes the meaning content from the various input streams into a single semantic representation. Compared to conventional multimodal recognition systems, finite-state systems and methods allow for compensation among the various input streams. Finite-state systems and methods allow one input stream to dynamically alter a recognition model used for another input stream, and can reduce the computational complexity of multidimensional multimodal parsing. Finite-state devices provide a well-understood probabilistic framework for combining the probability distributions associated with the various input streams and for selecting among competing multimodal interpretations.

The invention discloses a Chinese named entity recognition method based on BERT-BiGRU-CRF. The method comprises three stages: in the first stage, preprocessing mass text corpora, and pre-training a BERT language model; in the second stage, preprocessing the named entity recognition corpus, and encoding the named entity recognition corpus through the trained BERT language model; and at the third stage, inputting the encoded corpus into a BiGRU+CRF model for training, and performing named entity recognition on the to-be-recognized statement by using the trained model. Construction of the Chinesenamed entity recognition method based on BERT-BiGRU-CRF is carried out, semantic representation of characters is enhanced through a BERT pre-training language model, semantic vectors are dynamicallygenerated according to contexts of the characters, and the ambiguity of the characters is effectively represented. Compared with a method based on fine tuning of a language model, the method has the advantages that training parameters are reduced, and the training time is saved.

A method and apparatus for deriving information from a textual representation of a sentence are provided, the sentence having a plurality of words. The apparatus comprises an input, a processing unit and an output. The input is for receiving data elements indicative of the textual representation of the sentence. The processing unit is operative for processing the textual representation of the sentence to derive an information record on the basis of a set of information extraction rules, the information record being indicative of a semantic representation of at least part of the sentence. The information record is then released at the output. A computer readable medium comprising a program element suitable for execution by a computing apparatus for deriving information from a textual representation of a sentence is also provided.

One embodiment of the present method, program, and apparatus for natural language generation enables a language generation system to generate a grammatically correct natural language sentence by retrieving and adapting one or more stored sentences having semantic features similar to semantic features of a system-generated semantic representation. The retrieval of stored sentences is guided at least in part by the ease with which the stored sentences may be adapted to produce a grammatically correct sentence, enabling rapid generation of accurate output.

The invention provides an artificial-intelligence auxiliary interrogation diagnosis system which comprises a corpus training module, a question classification module, a chat processing module, an automatic response module for medical commonsense questions and an interrogation diagnosis interaction module, wherein the corpus training module automatically extracts a patient's illness sign information, treatment and medicine use information and diagnosis suggestion information in historical conversations between a doctor and the patient, semantic representation is conducted according to the various types of extracted information, the information is converted into numerical vectors, training learning is conducted on the numerical vectors, and a diagnosis model which contains relations between the illness sign information existing in historical doctor-patient interactions and the doctor's diagnosis suggestions is obtained; and the question classification module judges and classifies information consulted by the patient into an online interrogation diagnosis question or a question outside the interrogation diagnosis service scope or a medical commonsense question, and the questions are answered by the interrogation diagnosis interaction module, the chat processing module and the automatic response module of the medical commonsense question respectively. The system is characterized in that by various models obtained through training, an interrogation diagnosis mechanism can be learned independently and perfected; and system universality and diagnosis accuracy are increased.

Apparatus and methods of revealing the hierarchical structure of a document having content of a characteristic type of content are described (100). The hierarchical structure may be expressed, independently of document content type, as a tree structure of one or more nodes (126) A semantic representation for interpreting the tree structure may also be provided, document description files are used to encapsulate structural and meta information associated with a document stored on a computer-readable medium (156). Document description files are external to native application files and have a set of required fields. Document description files point to the referenced document data using uniform resource locators (URLS) and serve as virtual documents. In addition to the required fields, applications can choose to encode additional structural information in the document description files.

Generating a simulator from an architecture description. A target architecture model described in an architecture description language (ADL) is accessed. The model comprises a semantic representation of an instruction set for the target architecture. The semantic representation is translated to a behavioral representation. The simulator is automatically generated from the behavioral representation. A compiler may also be generated from the semantic representation.

A system and method is described for using descriptive logic (DL) representations to validate consistency in component business model (CBM) maps. Semantic constraints are generated from a semantic model of a component business model meta-model and inconsistency conditions of CBM maps. The semantic model of the CBM meta-model is applied to transform CBM maps into corresponding semantic representations. An inference engine applies the semantic constraints to the semantic representations to determine inconsistencies between one CBM map and another and between a CBM map and the component business model meta-model.

The invention discloses a data mining method based on extraction of Web numerical value tables. The method is based on domain knowledge base, adopts generation of numerical value knowledge element base as a basic target, and mainly comprises construction of domain knowledge base basic set, positioning of Web numerical value tables, recognition of table structure, integration of table content, semantic representation of extract result, data retrieval, automatic learning of domain knowledge and data mining processing and the like. The invention is based on the method of extraction of Web numerical value tables in specific domain, can carry out extraction to data, information and knowledge included in numerical value tables in Web pages, converts semi-structured data into structured data and provides services of data retrieval, data mining analysis and the like. The data mining method can completely and accurately extract valuable numerical value knowledge in large amount of Web numerical tables dispersed on Web and meets the requirements of data query and data analysis of a user.

The invention belongs to the field of language processing, in particular to a cross-language text similarity evaluation technology based on bilingual word embedding. The technical route and workflow of cross-language text similarity evaluation technology based on bilingual word embedding can be divided into three stages: the construction of bilingual word embedding model, the construction of textsimilarity calculation framework based on multi-neural network, and the cross-language similarity calculation. Through this model, a bilingual shared word embedding representation can be generated, which is based on the word vector correlation theory and Skip-Gram model is used to train word vectors on artificially constructed pseudo-bilingual corpus. Secondly, in order to make the generated wordembedding space as complete as possible, monolingual corpus is used as a supplement to learn additional word embedding knowledge. The similarity score of sentences is obtained by combining several neural network structures to learn the semantic representation of sentences. By dividing short text into paragraphs and treating paragraphs as long sentences as sequence input, the similarity iteration on a larger scale can be realized.

Embodiments of the present invention provide a method and a system for analyzing and learning behavior based on an acquired stream of video frames. Objects depicted in the stream are determined based on an analysis of the video frames. Each object may have a corresponding search model used to track an object's motion frame-to-frame. Classes of the objects are determined and semantic representations of the objects are generated. The semantic representations are used to determine objects' behaviors and to learn about behaviors occurring in an environment depicted by the acquired video streams. This way, the system learns rapidly and in real-time normal and abnormal behaviors for any environment by analyzing movements or activities or absence of such in the environment and identifies and predicts abnormal and suspicious behavior based on what has been learned.

A method and computer system for translating sentences between languages from an intermediate language-independent semantic representation is provided. On the basis of comprehensive understanding about languages and semantics, exhaustive linguistic descriptions are used to analyze sentences, to build syntactic structures and language independent semantic structures and representations, and to synthesize one or more sentences in a natural or artificial language. A computer system is also provided to analyze and synthesize various linguistic structures and to perform translation of a wide spectrum of various sentence types. As result, a generalized data structure, such as a semantic structure, is generated from a sentence of an input language and can be transformed into a natural sentence expressing its meaning correctly in an output language. The method and computer system can be applied to in automated abstracting, machine translation, natural language processing, control systems, Internet information retrieval, etc.

A method and system for analyzing a corpus of data artifacts is disclosed. The method comprises obtaining, by a computer, a semantic representation of the data artifacts, where the semantic representation indicates (1) entities identified in the data artifacts, and (2) semantic relationships among the entities as indicated by the data artifacts. The method further comprises clustering the data artifacts into clusters of semantically related data artifacts based on the semantic representation and inferring additional semantic relationships between pairs of the entities. The inferring comprises applying, on a cluster-by-cluster basis, a multi-tiered network of inference engines to a portion of the semantic representation corresponding to the cluster, where the multi-tiered network of inference engines includes a domain-independent inference tier and a domain-specific inference tier.

A method and computer system for translating sentences between languages from an intermediate language-independent semantic representation is provided. On the basis of comprehensive understanding about languages and semantics, exhaustive linguistic descriptions are used to analyze sentences, to build syntactic structures and language independent semantic structures and representations, and to synthesize one or more sentences in a natural or artificial language. A computer system is also provided to analyze and synthesize various linguistic structures and to perform translation of a wide spectrum of various sentence types. As result, a generalized data structure, such as a semantic structure, is generated from a sentence of an input language and can be transformed into a natural sentence expressing its meaning correctly in an output language. The method and computer system can be applied to in automated abstracting, machine translation, natural language processing, control systems, Internet information retrieval, etc.

The present invention belongs to the field of intelligent robots and provides an intelligent robot, and an emotional interaction method and system thereof, in order to improve the intelligent level of emotional interaction between intelligent robots and humans. The method comprises: collecting any one or more of user-generated voice, facial expressions and body movements when a user interacts with an intelligent robot; converting any one or more of voice, facial expressions and body movements into corresponding text information or sentence semantic representation; using an emotion engine to process the text information or the sentence semantic representation to determine the answer that matches the text information or the sentence semantic representation; and outputting the answer that matches the text information or the sentence semantic representation as the response of the intelligent robot to the user. With rich emotional color, the intelligent robot provided by the technical scheme of the present invention takes the answer that matches the text information or the sentence semantic representation as the response to the user, so that a higher intelligent level of the intelligent robot is represented.

An apparatus and method for universal programming language conversion between two different sequential programming languages, e.g., sequential procedural and sequential object oriented programming languages. In particular, conversion is between a source program in a first programming language and a target program in a second programming language. Initially, the source program in the first programming language is parsed using a parsing interface specific to the first programming language. All syntax from the parsed source program is then stripped or removed. Classes in a framework are instantiated to capture semantics of the parsed source program independent of syntax and execution model of the sequential programming languages. The classes are C++ classes representing fundamental core constructs of all sequential programming languages. A semantic representation of the parsed source program without any syntax is produced. The semantic representation is received at a printer interface specific to the second programming language and syntax of the target program in the second programming language is added. This same process can be used for either high-level conversion or compilation depending on whether the target programming language is high level or low level, respectively.

The invention discloses a panoramic image fusion method based on a depth convolution neural network and depth information. The method comprises the steps of (S1) constructing a deep learning training data set, selecting overlap regions xe1 and xe2 of two fish eye images to be fused used for training and an ideal fusion area ye of a panoramic image formed after fusing the two fish eye images, and constructing a training set {xe1, xe2, ye} of the images to be fused and a panoramic image block pair, (S2) constructing a convolution neural network model, and (S3) obtaining a fusion area of a test data set based on a test data set and a trained depth convolution neural network model. According to the method, an image can be expressed more comprehensively and deeply, the image semantic representation in a plurality of abstract levels is realized, and the accuracy of image fusion is improved.

The invention belongs to the field of image processing and computer vision, and more particularly discloses an image style transfer method based on a convolutional neural network. Based on a high-level semantic representation in the convolutional neural network, an image content model and an image style model are established, then an initial image is optimized to have a content representation similar to a content image and a style representation similar to a style image in the same convolutional neural network, an image fused with the content of the content image and the style of the style image is therefore generated, and the style transfer function is realized. The method of the invention can achieve style transfer for any style image.

Methods and computer-readable media for associating words or groups of words distilled from content, such as reported speech or an attitude report, of a document to form semantic relationships collectively used to generate a semantic representation of the content are provided. Semantic representations may include elements identified or parsed from a text portion of the content, the elements of which may be associated with other elements that share a semantic relationship, such as an agent, location, or topic relationship. Relationships may also be developed by associating one element that is in relation to, or is about, another element, thereby allowing for rapid and effective comparison of associations found in a semantic representation with associations derived from queries. The semantic relationships may be determined based on semantic information, such as potential meanings and grammatical functions of each element within the text portion of the content.