摘要:
In a method for providing multimedia services in a communication system, a request message for requesting contract information on users' multimedia services are received from a terminal according to service requests of the multimedia services to be received by the users. A query message for searching for the contract information in a database is generated corresponding to the request message, and the query message is transmitted to the database. The contract information is searched in the database through a Moving Picture Experts Group (MPEG) query format protocol based on the query message, and a query result message containing the contract information is received from the database in response to the query message. The contract information is acknowledged in the query result message, and a response message containing the contract information is generated. Then, the response message is transmitted to the terminal.
摘要:
Disclosed are a system for providing a broadcast service and a method for providing a broadcast service. An example of the method for providing a broadcast service includes receiving a broadcast signal including broadcast contents and side information to provide the broadcast contents; reading out at least one of objects from question data that is input regarding the broadcast contents and primarily analyzing the read-out object to read out a subject of the question data; searching a social media site and collecting social media data relating to the subject from the searched social media site; secondarily analyzing the social media data and the side information in the broadcast signal on the basis of the subject; and configuring answer data corresponding to the subject using the analysis result and providing the answer data, and provides information which is extended and varied in real time.
摘要:
Disclosed are a method and an apparatus for mobile intelligent advertizing service based on mobile user contextual matching. An apparatus for mobile intelligent advertizing service based on mobile user contexts includes: a contextual information collecting unit collecting user contextual information under a mobile environment; a contextual information analyzing unit analyzing the collected contextual information and classifying and storing the analyzed contextual information for each category; a contextual information modeling unit comparing and mapping the analyzed contextual information with a previously built-up contextual information database to formalize the compared and mapped contextual information and generalizing the formalized contextual information by using a wired/wireless communication network; a user action analyzing unit analyzing a user's action on the basis of the modeled contextual information and predicting the user's next action; and an advertisement contents recommending unit recommending advertisement contents suitable for the predicted user's next action.
摘要:
The present invention relates generally to a voice-based mobile search apparatus and method, and, more particularly, to a voice-based mobile search apparatus and method, which can present optimized search results suitable for a mobile status while allowing a user to conveniently use a search service in a mobile environment. The voice-based mobile search apparatus according to the present invention includes a voice recognition unit for recognizing a user's voice transferred through a mobile terminal and then receiving a query. A status information collection unit collects status information of the mobile terminal and profile information of the user. An answer search unit searches a knowledge base based on the query, and extracts short answers matching the query. An answer provision unit processes the short answers in conformity with the status information of the mobile terminal and the profile information of the user, and provides the processed short answers.
摘要:
Provides is an apparatus for question answering based on answer trustworthiness including: an answer indexer that indexes documents of which document trustworthiness satisfying a threshold value among documents included in a document collection and stores it in a knowledge Bases; an answer candidate extractor that extracts answer candidate documents for a user's question from the knowledge Bases; an answer source trustworthiness measurement unit; an answer extraction strategy trustworthiness measurement unit; and a trustworthiness integrator that generates an answer candidate trustworthiness list by ranking the answer candidate documents on the basis of the document trustworthiness, the source trustworthiness, and the extraction strategy trustworthiness of the answer candidate documents.
摘要:
A question type and domain identifying apparatus includes: a question type identifier for recognizing the number of words of a user's question to identify whether the user's question is a query for performing information searching or a question for performing a question and answer (Q&A); a question domain distributor for distributing one of plural preset domain specialized Q&A engines, as a Q&A engine of the user's question based on the recognized word number; and a Q&A engine block, including the domain specialized Q&A engines, for selectively performing information searching or a Q&A with respect to the user's question in response to the distribution of the question domain distributor.
摘要:
A method for stabilizing a knowledge graph includes: generating a knowledge graph in which same entities in a semantic relation list between entities provided as an input are represented as a single node based on names and types of the entities; computing, on the knowledge graph, semantic similarities between all potential entity pairs of same entity types by comparing, for each potential entity pair, a type of relation associated with an entity in the entity pair and an opponent entity to the entity; and selecting, based on the semantic similarities, a representative entity from each of semantically similar entity pairs on the knowledge graph and integrating an opponent entity to the representative entity into the representative entity. The method further includes computing relation weighted values between the entities by using a graph analysis and statistic information, and adding the weighted values to the knowledge graph.
摘要:
A method for stabilizing a knowledge graph includes: generating a knowledge graph in which same entities in a semantic relation list between entities provided as an input are represented as a single node based on names and types of the entities; computing, on the knowledge graph, semantic similarities between all potential entity pairs of same entity types by comparing, for each potential entity pair, a type of relation associated with an entity in the entity pair and an opponent entity to the entity; and selecting, based on the semantic similarities, a representative entity from each of semantically similar entity pairs on the knowledge graph and integrating an opponent entity to the representative entity into the representative entity. The method further includes computing relation weighted values between the entities by using a graph analysis and statistic information, and adding the weighted values to the knowledge graph.
摘要:
A method for automatically extracting information of products, includes searching documents based on product names; and extracting sentences including advantages and disadvantages for products having the product names from the searched documents. Further, the method for automatically extracting the information of the products includes classifying the sentences by similar contents among the extracted sentences; selecting representative sentences among the classified sentences; and calculating each weight of the selected representative sentences.
摘要:
Disclosed is an apparatus and method for retrieving multimedia contents represented in a Moving Picture Experts Group (MPEG) 7 by transforming a user query into an MPEG-7 query format. The method for retrieving multimedia contents includes: representing a user query by using an indicator indicating a specific region of a Moving Picture Experts Group 7 (MPEG-7) document and a reference for referring to the indicator; analyzing a meaning of the user query represented by using the indicator and the reference to thereby produce an analysis result; and retrieving multimedia contents according to the analysis result. The present research can satisfy more than two retrieval conditions within the same structure in an MPEG-7 query format and it can also clearly represent that two different MPEG-7 documents are referred to. Since the meaning of a user query is analyzed accurately during retrieval process, it is possible to precisely retrieve multimedia contents.