65 results about "Structural representation" patented technology

Techniques are provided for segmenting text into categorized discourse constituents and attaching discourse constituents into a structural representation of discourse. Techniques for determining hybrid structural and non-structural summaries of a text are also provided. A text is segmented based on a theory of discourse analysis into at least a main discourse constituent containing spatio-temporal information about a single event in a possible world view. The discourse constituents are then inserted into a structural representation of discourse. Non-structural techniques are used to determine relevance scores and important discourse constituents are determined. Relevance scores are percolated through the structural representation of discourse to determine supporting preceding discourse constituents that preserve grammaticality. A hybrid text summary is then determined based on the structural representation of the discourse and relevance scores.

Techniques for enabling real-time automated interpretation of clinical narratives are disclosed. The automated interpretation can be achieved by translating narrative text into a clinical terminology-encoded structural representation such as the Systemized Nomenclature of Medicine-Clinical Terms (SNOMED-CT) example of such a clinical terminology. The translation process enables the generation of both pre-coordinated and post-coordinated SNOMED CT concept expressions.

A method of parsing a markup language document comprising syntactic elements is disclosed, said method comprising, for one of said syntactic elements, the steps of identifying (310) a type of the element, processing (318) the element by determining a hash representation thereof if said type is a first type, and augmenting (314) an at least partial structural representation of the document using the hash representation if said type is said first type.

A technique for writing analysis using the theory of discourse that categorizes text into content, operator and modifier text building units and provides for relating the categorized text building units together using coordination, subordination and binary relationships. A graphical representation of the discourse can be shown since the structural representation of discourse created by the interrelationships can be easily displayed. The analysis and graphical visualization of the writing structure of texts helps writers to analyze and compare writings.

The invention discloses a deep-learning-based multi-mode medical image non-rigid registration method and system. The registration method comprises: on the basis of lots of medical data, a PCANet is trained; a floating image and a reference image are inputted into the trained PCANet to obtain structural representation maps of the floating image and the reference image; and according to the structural representation maps of the floating image and the reference image, a registration image is obtained. According to the invention, on the basis of the PCANet deep learning network, the structural representation map of the image is constructed and the registration problem of the non-rigid multi-modal medical image is transformed into a single-mode medical image registration problem, so that the accuracy and robustness of non-rigid multi-mode medical image registration are improved substantially.

The invention provides a semantic-based information prototype vector composition and order parameter reconstruction method in image understanding. The method comprises the following steps: 1. the prototype vector representation of scene and target semantic information; 2. the structural representation of scene and target prototype vectors; 3. the reduction treatment of the scene and target prototype vectors; and 4. the reconstruction of scene and target order parameters. The method is based on the synergetics and the synergetic pattern recognition principles, extracts and reconstructs the features of the scene and the target in an image and carries out the feature description which is added by semantic information of the scene and the target in the scene to achieve the purpose of recognizing the image, the computational complexity is low, the study ability is strong, the recognition efficiency is high and the algorithm robustness is stronger.

The invention discloses a webpage theme information extraction method. The method comprises the following steps that a structural representation method of tree-shaped information is used for representing individual service problems; logical representation of structured problems is conducted; orderly solving of the individual problems is conducted. Due to the fact that the structural representation method of the tree-shaped information is used for describing the individual service problems, the individual service problems of various fields and modes are represented by using three basic elements which refer to the service content element, the service object element and other elements, the individual service problem is divided into a basic element layer, a basic information layer and a sub information layer, so that the individual service problems of information systems in most of fields are structuralized, and the recommendation rules of individual service can be set. According to the webpage theme information extraction method, a weighted search solving method is used, the weight of a reasoning result related to the current purchase history of a customer is maximum, sequential lowering according to a purchase sequence in later is achieved, and new resources interested by a server object is recommended.

The invention discloses an entity alignment method and device suitable for a multi-modal knowledge graph. The method comprises the following steps of: acquiring data of two multi-modal knowledge graphs; projecting the data of each mode to a hyperbolic space; learning structural features and visual features of entities by using a hyperbolic graph convolutional neural network; fusing the multi-modalfeatures; representing the entity similarity by using the distance in the hyperbolic space; and performing entity identification alignment according to the similarity. According to the method, Euclidean representation is expanded to a hyperboloid manifold, and structural representation of the entities is learned by adopting the hyperbolic graph convolutional network; for visual information, imageinserts are generated by using a densenet model, and the image inserts are inserted into the hyperbolic curve space by using the hyperbolic graph convolutional network; finally, structure inserts andthe image inserts are combined in the hyperbolic space to predict a potential alignment mode. and therefore, the method is particularly suitable for entity alignment and fusion of the multi-modal knowledge graph.

The invention discloses a legal document analysis method based on a case element, which comprises the following steps of: 1, extracting case description information from a legal document by utilizinga machine learning algorithm, and labeling case description according to the priority of case element labeling; 2, carrying out data preprocessing: identifying the case elements marked in the step 1;and 3, carrying out case element identification based on the deep neural network: taking the labeled document data as the original input of the labeling model to realize end-to-end case element identification. By carrying out flattening associated case element labeling on legal documents, processing labeled document data into a classical BIO sequence labeling format by taking sentences as units, and identifying case elements in documents by adopting a related sequence labeling model, case element recognition is beneficial to structural representation of legal documents, supports fusion analysis of legal documents and other application researches, and brings great convenience to information retrieval, automatic review and other practice applications of the legal documents.

An educational institution (also referred as a university) is rich with multiple kinds of data: students, faculty members, departments, divisions, and at university level. Relating and correlating this data at and across various levels help in obtaining a perspective about the educational institution. A structural representation captures the essence of all of the relationships in a unified manner and an important aspect of the relationship is the so-called “influence factor.” This factor indicates influencing effect of an entity over another entity, wherein the entities are a part of the structural representation. Given such a structural representation, a system and method that propagates the influence factors of the entities to arrive at a stable representation from the point of view of influences is discussed.

The invention discloses a knowledge graph pre-training method based on structured context information, and the method comprises the steps: constructing an instance composed of context triples for a target triple, employing a triple integration module to code each context triple of the instance, and obtaining an integration vector; forming a context vector sequence by the integrated vectors of allthe context triples of the instance, and encoding the context vector sequence by adopting a structured information module to obtain structural representation vectors of the triples; and calculating the structure representation vector of the triple by adopting a universal task module to obtain a label prediction value of the triple, and updating the structure representation vector of the triple based on the cross entropy loss of the label prediction value of the triple and the label true value until the training is finished to obtain an optimized structure representation vector of the target triple. The structural representation vector of the triple obtained by the method combines contextual information.

The invention discloses a knowledge representation method based on the combination of text embedding and structure embedding, and the method comprises the steps: 1, carrying out the preprocessing of an entity description text in a knowledge base, and extracting a subject term from each entity description; 2, encoding the subject term into a term vector by using fasttext, wherein each entity description is expressed as a multi-dimensional term vector; step 3, inputting the processed multi-dimensional word vectors into a bidirectional long-short memory network (A-BiLSTM) with an attention mechanism or a long-short memory network (A-LSTM) with an attention mechanism for encoding, processing the multi-dimensional word vector representing each entity into a one-dimensional vector, namely text representation, and training an existing StransE model to obtain structural representation of the entity; 4, introducing a gating mechanism, and proposing four methods related to text embedding and structure embedding combination to obtain a final entity embedding matrix; and 5, inputting the entity embedding matrix into a ConvKB knowledge graph embedding model, a TransH knowledge graph embedding model, a TransR knowledge graph embedding model, a Distmult knowledge graph embedding model and a Hole knowledge graph embedding model, and improving a knowledge completion task.

The invention relates to a phosphate zirconium nano magnetic particle with the structural representation on the right, and the preparation and application thereof; the preparation method comprises the steps that phosphate groups are induced to the surface of the nano magnetic particle which is wrapped with silicon dioxide on the surface and takes ferriferrous oxide as a magnetic inner core; then, a phosphate zirconium layer is formed on the surface by the mutual action between zirconium ions and the phosphate groups on the surface, thereby successively preparing a nano magnetic particle having high efficiency, high-selectivity separation and enrichment feature to peptide phosphate. The nano magnetic particle is mainly used for separating the enriched peptide phosphate from biological samples, with high efficiency and under the action of a magnetic field. The extracted peptide phosphate can be directly analyzed and represented by mass spectrum.

An educational institution (also referred as a university) is rich with multiple kinds of data: students, faculty members, departments, divisions, and at university level. A structural representation that captures the essence of all of the relationships in a unified manner has concise information about the educational institution, and visualization is a way to bring out all this information in an explicit manner so that the various of the users of the educational institution system understand effectively their system. A system and method for visualization based on the structural representation of a university along a variety of dimensions is discussed.

The invention discloses a three-dimensional structured model reconstruction method based on any view angle pictures. The method comprises the following steps of 1, collecting pictures, and forming a training data set; 2, segmenting object parts of the picture to obtain a bounding box of each part; 3, constructing a deep convolutional network model, and extracting a corresponding depth image from the image; 4, constructing a deep network model, and decoding the structural representation of the object; and 5, constructing and training a deep three-dimensional mesh deformation network, and deforming the bounding box into a three-dimensional model with a good structure. According to the method, the object structure representation is deformed, and a topology self-adaption method is used, so a problem that the topology is not changed when a general graph is used for convolution can be solved, and geometric details and the structure information of object recovery are ensured.

The present invention is related to a quantitative structure-based affinity scoring method for peptide/protein complexes. More specifically, the present invention comprises a method that operates on the basis of a highly specific force field function (e.g. CHARMM) that is applied to all-atom structural representations of peptide/receptor complexes. Peptide side-chain contributions to total affinity are scored after detailed rotameric sampling followed by controlled energy refinement. The method of the invention further comprises a de novo approach to estimate dehydration energies from the simulation of individual amino acids in a solvent box filled with explicit water molecules and applying the same force field function as used to evaluate peptide/receptor complex interactions.

The invention provides an optical system of a hard tube endoscope. The optical system comprises an objective lens set and a relay system. The objective lens set comprises a first lens set, a second lens set, a third lens set and a fourth lens set. An aperture diaphragm is located in the second lens set. The relay system is composed of odd number pairs of transferring lens with the magnifying power being 1:1, the relay system comprises two completely same tri-agglutination bar lenses, the distances between every two adjacent bar lenses are equal, and images formed by objective lenses are transferred in a working telescope many times. A final image is received through the ocular lens human eye or a CCD detector. The full field angle of the system is within 70 degrees, stray light does not exist in an image plane when the system aligns with a light source, the interference on imaging from the stray light entering a lens cone is completely removed, the MTF value is larger than 0.3 at the 1,201p/mm position, and the optical system has the advantages of being large in visual field and field depth, small in field curvature, capable of removing distortion, even in brightness, simple in structure, low in cost and the like. The picture 1 is the structural representation of the optical system of the non-stray-light hard tube endoscope, and the number 1 is the objective lens set.

The disclosed embodiments relate to a representation of a structure/space as a collection of interrelated partitions whereby manipulation of the partitions causes an automated propagation of the manipulation through the other interrelated partitions as a function of the relationships therebetween. Each partition is defined by one or more vertices, the location(s) of which is/are specified either relative to an origin or relative to, i.e. as a function of, or dependent upon, the location of another vertex within the partition (intra-partition) or within another partition (inter-partition). Where the location of a vertex is moved, the change is propagated implicitly to all other vertices whose location is related, i.e. specified as a function of the modified vertex.

An educational institution (also referred as a university) is rich with multiple kinds of data: students, faculty members, departments, divisions, and at university level. A structural representation that captures the essence of all of the relationships in a unified manner has concise information about the educational institution, and visualization is a way to bring out all this information in an explicit manner so that the various of the users of the educational institution system understand effectively their system. A system and method for visualization based on the structural representation of a university along a variety of dimensions is discussed.

The embodiment of the invention discloses a method for determining an interface code and a test script parameter value. The method comprises the following steps of: respectively establishing corresponding interface information internal representations for the information before upgrade and the information after upgrade based on specially appointed structural representation, corresponding component element representation and parameter index representation after the equipment interface is changed and upgraded; comparing the internal representation of the interface information before upgrade with the internal representation of the interface information after upgrade to determine the parameter values of the elements in an information entity definition set; and forming corresponding code and test script of the upgraded interface information based on the internal representation and the element parameter value. The scheme disclosed by the invention can effectively reduce the investment for upgrading the interface code and the test script and assist the technicians in quickly developing interface codes and test scripts, thereby effectively improving the writing efficiency of the interface code and the test information script, ensuring the quality of the interface code and the test information script and solving the problem that the current interface code and test script need substantial investment in labor and time during upgrade.

An educational institution (also referred as a university) is rich with multiple kinds of data: students, faculty members, departments, divisions, and at university level. Relating and correlating this data at and across various levels help in obtaining a perspective about the educational institution. A structural representation captures the essence of all of the relationships in a unified manner and an important aspect of the relationship is the so-called “influence factor.” This factor indicates influencing effect of an entity over another entity, wherein the entities are a part of the structural representation. A system and method for the construction of such a structural representation of an educational institution based on the educational institution specific information is discussed.

The invention discloses a method for splitting one body for making four specimens. The method includes the following steps of selecting an object; stripping the skin; conducting anatomy; stripping muscles, nerves and blood vessels; taking out internal organs and conducting anatomy; anatomizing bones and ligaments; taking out the brain; conducting dewatering, degreasing and resin soaking; making the skin specimen; making the muscle specimen; making the bone and ligament specimen; making the internal organ specimen; conducting restoration, solidification and cleaning. By means of the method, thebody is split into the four specimens, raw materials are saved, convenience is provided for storage, and each split specimen can independently represent respective specific anatomic features and different kinds of survival action form features, and the complexity of hierarchical structural representation of vertebrate anatomic plasticized specimens and the diversity of survival states of the vertebrate anatomic plasticized specimens are satisfied.

An educational institution (also referred as a university) is rich with multiple kinds of data: students, faculty members, departments, divisions, and at university level. Relating and correlating this data at and across various levels help in obtaining a perspective about the educational institution. A structural representation captures the essence of all of the relationships in a unified manner and an important aspect of the relationship is the so-called “influence factor.” This factor indicates influencing effect of an entity over another entity, wherein the entities are a part of the structural representation. Given such a structural representation, a system and method that propagates the influence factors of the entities to arrive at a stable representation from the point of view of influences is discussed.

The invention relates to a knowledge graph visualization method for electric power scientific and technological achievements. Compared with the prior art, the defect that semantic analysis is difficult to carry out due to the fact that the electric power scientific and technological achievements are numerous in data size is overcome. The method comprises the following steps: obtaining electric power scientific and technological achievement data; setting a structural representation model based on the activation vector; setting a text representation model based on the CNN; carrying out knowledgerepresentation based on joint training; and obtaining a visual result of the knowledge graph. According to the method, the structural knowledge representation method based on the activation vector and the text information knowledge representation method based on the CNN are fused, calculation parameters can be effectively reduced, model operation is efficient, features in the text structure and the text information are effectively obtained, and the representation result is more accurate.

The invention discloses an electronic learning method based on a knowledge base. The electronic learning method based on the knowledge base comprises the following steps that a tree-based information structural representation method is used for representing individualized learning problems, a structured problem is represented logically, and the individualized learning problems are resolved orderly. As the individualized learning problems are described according to the tree-based information structural representation method, the individualized learning problems in various fields and forms are represented through three basic elements including the student element, the learning content element and another element, and are divided into a basic element layer, a basic information layer and a sub information layer, and therefore the individualized learning problems of information systems of most fields can be structured, and then the recommended rule of individualized learning can be set. Weighting is adopted for search of all solutions in the method, the weight of an inference result related to knowledge needing to be learnt by students is the largest, and thus new knowledge in which the students are interested is recommended.

The invention relates to a method for predicting common environment poison property/activity on the basis of an intelligent correlation index, which is suitable for predicting the poison property/activity according to the molecular structure information of environment poison compound. The method comprises the following steps: (1) defining an atom type, and dividing the atom into four classes according to the branching coefficient of the atom; (2) defining the property correlative parameter (PCP) and the distance correlative function (DCF) of a non-hydrogen atom by a user according to the structural characteristic of the researched environment poison module; (3) determining an intelligent correlative function; (4) calculating an intelligent correlative index (ICI); and (5) and obtaining anoptimal prediction model according to a statistical result. Experiments prove that the method for representing the molecular structure of the environment poison has the advantages of specific materialization meaning, strong structural representation capability and good expansion performance and can be regulated, and good effect is obtained in the quantitative structure activity prediction research of various types of environment poison modules.