37 results about "Semantic pattern" patented technology

The disclosure relates to methods, systems and other embodiments directed to determining an information domain match for a natural language (NL) input (e.g., a spoken utterance), and confirming whether the NL input is correctly matched to the information domain. For example, after receiving an NL input, a first information domain to which the NL input belongs and a feature value set may be determined based on a semantic pattern matching technique. Further, a second information domain to which the NL input belongs, and a corresponding confidence score related to the second information domain may be determined. The second information domain may be determined based on a first statistical classification technique. Based on the determined feature value set and the confidence score related to the second information domain, it may be confirmed whether the NL input correctly belongs to the first information domain, e.g., based on a second statistical classification technique.

A semantic discovery and exploration system is disclosed where an environment enabling a developer or user to uncover, navigate, and organize semantic patterns and structures in a document collection with or without the aid of structured knowledge. The semantic discovery and exploration system provides techniques for searching document collections, categorizing documents, inducing lists of related concepts, and identifying clusters of related terms and documents. This system operates both without and with infusions of structured knowledge such as gazetteers, thesauruses, taxonomies and ontologies. System performance improves when structured knowledge is incorporated. The semantic discovery and exploration system may be used as a first step in developing an information extraction system such as to categorize or cluster documents in a particular domain or to develop gazetteers and as a part of a deployed run-time information extraction system. It may also be used as standalone utility for searching, navigating, and organizing document collections and structured knowledge bases such as dictionaries or domain-specific reference works.

An apparatus and a method for automated semantic annotation of a process model having model elements named by natural language expressions, wherein said apparatus comprises at least one semantic pattern analyser which analyses the textual structure of each natural language expression on the basis of predefined semantic pattern descriptions to establish a semantic linkage between each model element to classes and instances of a reference process ontology for generating a semantically annotated process model.

An information retrieval method includes pre-processing a set of historical query information and processing a user query. Pre-processing a set of historical query information includes determining a plurality of semantic patterns based on a plurality of queries in the set of historical query information; establishing correspondence relationships between the plurality of semantic patterns and a plurality of filtering and ranking operations. Processing a user query comprises receiving the user query; retrieve a plurality of results in response to the user query; determining a semantic pattern that corresponds to the user query; determining a set of filtering and ranking operations that corresponds to the semantic pattern based on the correspondence relationships; and performing the set of filtering and ranking operations on the plurality of results to generate a set of filtered and ranked results.

A video annotation method by integrating visual features and frequent patterns is disclosed. This method is featured in integrating a statistical model based on visual features with a sequential model and an association model constructed by data mining skills for automatically annotating unknown videos. This method takes both of visual features and semantic patterns into consideration simultaneously through the combination of three different models so as to enhance the accuracy of annotation.

Natural Language Requirement (NLR) descriptions are parsed to generate syntactic verb structures. These structures are matched with a set of pre-defined semantic patterns to form semantic networks of semantic pattern instances. The networks are searched; any missing concepts identified and any incorrect or ambiguous concepts modified or clarified by user interaction. This interaction creates new semantic pattern instances that are used to generate an analysis model represented by a Unified Modelling Language (UML) or Entity-Relationship (ER) diagram, which can then be subsequently used to generate a computer software system.

The present invention relates to a content recommendation method in which pieces of information collected over an IP Multimedia Subsystem (IMS) network are analyzed through data mining, a semantic pattern is identified from the information and described based on ontology, the characteristics of content to be offered are recorded in ontology and language morphological pattern, and a recommendation filter in terms of various viewpoints and methods is operated in an integrated recommendation framework, thus enabling content recommendation suitable for various contexts to be performed.The method includes the steps of receiving user information, creating personal preference information based on the user information, deciding a recommendation strategy based on the preference information for content, combining recommendation functions using the recommendation strategy and the content information, personalizing recommendation results with respect to the combination, and providing the personalized content information.Furthermore, the method for recommending content with context awareness according to the present invention has an advantage in that it can offer more efficient and accurate content to mobile terminal users as a mobile communication network is expanded into an IMS basis and opened and therefore the types and number of content accessible by mobile terminals as well as mobile phones increase abruptly. Furthermore, the method for recommending content with context awareness according to the present invention is advantageous in that it can analogize the life pattern of a mobile terminal user, etc. based on the user's current context information and offers content matching the inferred life pattern at the right time and place.

Systems, methods and computer-storage media are provided for identifying query formulation suggestions in response to receiving a search query. A portion of a search query is received. Query formulation suggestions are identified by semantically analyzing the search query. The query formulation suggestions are used to further formulate the received search query. The query formulation suggestions include semantic-pattern-based query suggestions that are derived from semantic query patterns, one or more entities, and information associated with these entities. The query formulation suggestions are transmitted for presentation.

A malware detection system for evaluating sample programs for malware incorporates an evasion code detector. The evasion code detector includes semantic patterns for identifying conditional statements and other features employed by evasion code. The system inserts breakpoints at conditional statements, compares expected and actual evaluated values of conditional variables of the conditional statements, and changes the execution path of the sample program based on the comparison. Changing the execution path of the sample program to an expected execution path counteracts the evasion code, allowing for the true nature of the sample program to be revealed during runtime.

Dynamic data discovery can identify variables or changes in a business environment which can impact existing business rules and can match identified triggers. A business rule associated with a business rule management system can be identified. The business rule management system can be a component of an enterprise organization. The rule can be an operation, a definition, and a constraint associated with the organization. The organization can be a person, a process, a product, a service, or a computing device. Relevant information can be determined from a dynamic data associated with a data source. The determination can be made through the use of semantic analysis. A business pattern associated with the rule can be semantically matched with a dynamic pattern associated with the information. The pattern can be a semantic pattern of the information. A new business rule can be automatically generated from the dynamic data analysis.

The invention belongs to the field of natural language processing, and particularly relates to an emotion reason mining method based on dependency syntax and a generalized causal network. The emotionreason mining method mainly comprises the following steps: crawling news data and inputting data by utilizing a crawler framework; performing pretreatment; extracting a semantic mode of the text; conducting judgment; outputting the causal relationship in the statement; identifying a pair of causal relationship events; performing extraction; performing extraction; constructing a network; and performing generalized processing and evaluation. According to the emotion reason mining method, implicit meanings among words in sentences are fully interpreted; and generalized processing is carried out on the event, and the matching degree of the event is improved.

The invention relates to a Chinese semantic structure and finely segmented word bank combination based emotional analysis method. The emotional analysis method comprises: 1) inputting a to-be-tested text at least consisting of a statement into a computer system; 2) performing word segmentation processing on each statement of the to-be-tested text and marking emotional words and other words in each statement; 3) performing matching on the to-be-tested text subjected to word segmentation processing to obtain a semantic mode of each semantic unit; and 4) correspondingly converting the semantic mode of each semantic unit of the to-be-tested text to an emotional value, and performing accumulation on the emotional values of all the semantic units in the text to obtain an emotional value of the to-be-tested text. According to the method, the emotional words, connective words, transitional words and the like are segmented from a non-structured text; according to actual arrangement of the words, sentence patterns are matched to obtain the emotional values of the semantic units; and the emotional value of a sentence is comprehensively calculated according to the emotional values of the semantic units to achieve the purpose of quantizing the emotional value of a financial news comment sentence.

A print data semantic analysis system may comprise a print data handler and a database. The print data handler may include a semantic analyzer and a computer. The semantic analyzer may include a semantic identifier and a semantic operator. Semantic pattern(s), rule(s), and / or semantic category or categories may be stored in mutually associated fashion at the database. The print data handler may be a printer driver having a page description language (PDL) generator. The print data handler may be a raster image processor (RIP), a print server, or a printer having a PDL interpreter. The database may take the form of source code, function(s), lookup or other such table(s), and / or any other suitable format(s). The database may be a function table containing function(s) incorporating the semantic pattern(s), rule(s), and / or semantic category or categories.

A video annotation method by integrating visual features and frequent patterns is disclosed. This method is featured in integrating a statistical model based on visual features with a sequential model and an association model constructed by data mining skills for automatically annotating unknown videos. This method takes both of visual features and semantic patterns into consideration simultaneously through the combination of three different models so as to enhance the accuracy of annotation.

The invention provides a video-cloud-based early warning method and system of public security threat of an urban region. A video stream converges to a cloud server by a video cloud technology and is analyzed intelligently to obtain a processing result; the processing result is compared with a video pattern base and a semantic pattern base to obtain comparison results; when the comparison results reaches an early warning condition, early warning information is generated; a time stamp, position information, and the early warning information are overlapped; and then the early warning information is distributed to complete early warning. Therefore, an emergency response speed is accelerated; the public can obtain information of occurrence of incoming potential security threat timely and thus losses caused by sudden occurrence of disasters can be reduced.

Generating a description of compiler code selector rules from an architecture description. A method comprises accessing a target architecture model written in an architecture description language (ADL) and extracting semantic information therefrom to generate a plurality of semantic statements. Rules that map from source code operations to semantic patterns are accessed. The semantic statements are searched for matches for the semantic patterns to generate mappings that serve as a description of compiler code selector rules.

The invention discloses an identification method of a spatial motion behavior semantic pattern. The method comprises the following steps that a stay behavior based on spatial location is collected andjudged; a mathematical description and a visualize expression of the stay behavior are established, a spatial behavior semantic pattern map is established; spatio temporal frequent pattern mining based on the spatial behavior semantic pattern map is conducted. The spatial behavior pattern mapping mechanism and metric calculation method proposed in this method provide a foundation for discoveringspatial semantic information. Because of the regularity of statistical distribution of the spatial behavior patterns fits the internal expressions of spatial behaviors of different occupational groups, through the method, people can indirectly understand the activity purpose and the motivation of a traveler, especially an unusual and dangerous behavior, in the hidden behavior patterns, hidden secret relationships are revealed which are valuable for social security prevention and control, therefore, the application of social security and actual combat based on spatial motion big data abnormal behavior monitoring becomes possible.

A method, apparatus, system, and computer readable storage medium provide the ability to transition between two different profile curves in a swept surface extrusion. Each curve has section sequences that include consecutive sections, which in turn include constant attributes, which in turn include graphic attributes and semantic attributes. The section sequences define a semantic pattern for each profile curve. A globally optimal match is computed between the sections of the different curves. Adapted curves are generated that are structurally identical but geometrically resemble their respective original curves. An actual profile curve is computed for a given position on an extrusion line using a one-to-one vertex position morphing based on the adapted curves. The swept surface extrusion is performed and the result is displayed.

The invention provides a portlet interoperation tool based on a semantic model. The portlet interoperation tool comprises an information acquiring module, a portlet filter, a portlet login module, a parameter analysis module and a portlet matching module. The portlet interoperation tool based on a semantic model is characterized in that semantic rules can be maintained in a semantic library and flexible matching between portlets; portlet interoperation can be realized without modifying the portlets in a portal system, and investment is reduced; and the portlet interoperation is realized through shared property, and the safety is increased further.

Dynamic data discovery can identify variables or changes in a business environment which can impact existing business rules and can match identified triggers. A business rule associated with a business rule management system can be identified. The business rule management system can be a component of an enterprise organization. The rule can be an operation, a definition, and a constraint associated with the organization. The organization can be a person, a process, a product, a service, or a computing device. Relevant information can be determined from a dynamic data associated with a data source. The determination can be made through the use of semantic analysis. A business pattern associated with the rule can be semantically matched with a dynamic pattern associated with the information. The pattern can be a semantic pattern of the information. A new business rule can be automatically generated from the dynamic data analysis.

The invention discloses a semantic training system and method based on a business model. The system comprises an input module which is used for receiving input operation of a business model and obtaining business model data, and the business model data comprises an object, an attribute or a method; connecting the analysis module with the input module and used for analyzing and processing the object, the attribute or the method, obtaining user language knowledge, a semantic structure or a semantic event, constructing a semantic mode according to the user language knowledge, and generating a basic corpus; connecting the training case generation module with the analysis module and make it generate training case data according to the basic corpus;and the training execution module is connectedwith the analysis module and the training case generation module and is used for generating an SPD file, a TCD file and a mapping relation file according to the semantic mode and the training case data. The method solves the problem that semantic training operation tools are difficult to use and master by application developers; and the threshold that developers in the application field have access to the semantic analysis capability is lowered.

The invention discloses technology for converting unformatted data into formatted data in a web website. The technology comprises the following steps of: establishing a webpage content aggregation service, and capturing the specified webpage; then establishing a website intelligent resolution service and a website semantic pattern base; and purifying heterogeneous website data to obtain standard formatted data. The technology greatly reduces the cost of enterprises and improves the reliability of webpage information transplanting by uniformly converting multiple kinds of heterogeneous information in the web website into the formatted data which is convenient to store and is easy to screen.

A method and system is disclosed herein for generating a plurality of equivalent sentence patterns from a declared sentence pattern for a specific language. The declared pattern is fed into a pattern selector. The pattern selector reads a predetermined library of equivalent pattern sets and selects an equivalent pattern set for the declared pattern. The selected equivalent pattern set corresponds to the declared pattern and represents a set of equivalent declared patterns. The set of equivalent declared patterns and the declared pattern are fed to a rules generator. The rules generator outputs executable semantic pattern recognition rules. The reader module, using the generated executable semantic pattern recognition rules, reads the given information source to determine the information of interest.

An information retrieval method includes pre-processing a set of historical query information and processing a user query. Pre-processing a set of historical query information includes determining a plurality of semantic patterns based on a plurality of queries in the set of historical query information; establishing correspondence relationships between the plurality of semantic patterns and a plurality of filtering and ranking operations. Processing a user query comprises receiving the user query; retrieve a plurality of results in response to the user query; determining a semantic pattern that corresponds to the user query; determining a set of filtering and ranking operations that corresponds to the semantic pattern based on the correspondence relationships; and performing the set of filtering and ranking operations on the plurality of results to generate a set of filtered and ranked results.

The invention relates to a management system and method of sensor network data. The management system comprises: a sensing layer comprising a sensor node and a router node; an original data processing layer comprising an original data processing module and an original database; a semantic layer comprising a sensor main body and an industrial application field main body; a middleware layer used for processing an HTTP request of a browser or an application program, inquiring a semantic pattern database and returning HTTP response to a user; and an application layer comprising the browser and / or the application program. The technical scheme provided by the invention can solve the problems that the intelligence of the traditional sensor network is low, and that the analysis processing works of mass data need to be accomplished by manpower.

An apparatus and a method for automated semantic annotation of a process model having model elements named by natural language expressions, wherein said apparatus comprises at least one semantic pattern analyzer which analyses the textual structure of each natural language expression on the basis of predefined semantic pattern descriptions to establish a semantic linkage between each model element to classes and instances of a reference process ontology for generating a semantically annotated process model.

The invention provides an active defense method for image protection. The method comprises the following steps: receiving a real image; adding hidden information to the received real image to generate a first image; generating a semantic pattern in a specified area of the first image based on the hidden information so as to generate a second image; and adjusting the hidden information to make the semantic pattern similar to a predefined semantic pattern and make the second image similar to the real image. The invention further discloses a corresponding active defense device for image protection.