-
公开(公告)号：KR1020070092005A
公开(公告)日：2007-09-12
申请号：KR1020060021875
申请日：2006-03-08
Applicant: 학교법인 포항공과대학교 , 포항공과대학교 산학협력단
CPC classification number: G06F17/278 , G06F17/24
Abstract: A method and a system for recognizing a biological entity name based on a workbench are provided to reduce expense for constructing a biological document learning corpus and enhance entity name recognition for automatically extracting the biological entity name from a biological document on the basis of the workbench. An entity name recognizer(12) recognizes the biological entity name from the biological document by using a biological entity name recognition model(16). An entity name corrector(14) receives and corrects corrected data if a biological entity name recognition result needs correction. A machine learning part(15) constructs the new biological entity name recognition module by performing machine learning for a corrected result. The biological entity name recognition module is a statistics-based biological entity name recognition model constructed by the machine learning based on the biological document learning corpus. A document receiver(11) receives the biological document and an entity name recognition result output part(13) provides the recognition result to a user. A correction database(18) receives and stores the corrected data if the biological entity name recognition result needs the correction.
Abstract translation: 提供了一种用于基于工作台识别生物实体名称的方法和系统，以减少构建生物文献学习语料库的费用，并增强实体名称识别，以便根据工作台从生物文件自动提取生物实体名称。 实体名称识别器（12）通过使用生物实体名称识别模型（16）从生物文件识别生物实体名称。 如果生物实体名称识别结果需要校正，则实体名称校正器（14）接收并校正校正数据。 机器学习部分（15）通过执行校正结果的机器学习来构建新的生物实体名称识别模块。 生物实体名称识别模块是基于生物学文档学习语言的机器学习构建的基于统计的生物实体名称识别模型。 文档接收器（11）接收生物文档，并且实体名称识别结果输出部分（13）向用户提供识别结果。 如果生物实体名称识别结果需要校正，校正数据库（18）接收并存储校正数据。
-
公开(公告)号：KR1020080026782A
公开(公告)日：2008-03-26
申请号：KR1020060091790
申请日：2006-09-21
Applicant: 학교법인 포항공과대학교 , 포항공과대학교 산학협력단
Abstract: A method and an apparatus for comprehending spoken words by using an information extraction method are provided to comprehend essential elements selectively in comprehending the spoken words on the basis of a meaning structure suitable for each specific domain, thereby improving a degree of comprehension for the spoken words. A method for comprehending spoken words by using an information extraction method comprises the following steps of: standardizing the meaning structure of the spoken words previously(210); embodying the standardized meaning structure to be suitable for a specific domain(220); inputting spoken words recognized through a voice recognition unit(230); performing the natural language processing of the inputted spoken words(240); selecting quality with a specific meaning for determining the meaning structure by a result analyzed through the natural language processing(250); performing mechanical studying by using the selected quality(260); and comprehending the spoken words based on the meaning structure formed by determining corresponding elements configuring the meaning structure through the mechanical studying(270).
Abstract translation: 提供了一种通过使用信息提取方法来理解口语的方法和装置，用于在基于适合于每个特定领域的意义结构的基础上理解说出的单词的选择性的基本元素，从而提高口语单词的理解程度 。 一种通过使用信息提取方法来理解口语的方法包括以下步骤：对先前语音词汇的含义结构进行标准化（210）; 体现了适用于特定领域的标准化意义结构（220）; 输入通过语音识别单元（230）识别的口语单词; 对所输入的口语（240）进行自然语言处理; 通过自然语言处理（250）分析结果，选择具有意义的质量来确定意义结构; 使用所选质量进行机械学习（260）; 并基于通过机械学习确定构成意义结构的相应元素形成的意义结构来理解口语（270）。
-
公开(公告)号：KR100825687B1
公开(公告)日：2008-04-29
申请号：KR1020060021875
申请日：2006-03-08
Applicant: 학교법인 포항공과대학교 , 포항공과대학교 산학협력단
Abstract: 본 발명은 생물학 문헌으로부터 생물학적 개체명을 자동으로 인식하기 위한 워크벤치 기반의 생물학적 개체명 인식 방법 및 시스템을 제공한다. 상기 본 발명에 따른 워크벤치 기반의 생물학적 개체명 인식 방법은 생물학적 개체명을 인식하고자 하는 생물학 문서를 수신하는 단계; 생물학적 개체명 인식 모델을 이용하여 상기 수신된 생물학 문서로부터 생물학적 개체명을 인식하는 단계; 상기 생물학적 개체명 인식 결과의 교정이 필요한 경우 교정된 자료를 수신하는 단계; 상기 교정된 자료를 기초로 기계 학습을 하는 단계; 및 상기 기계 학습의 결과를 생물학적 개체명 인식 모델에 적용하는 단계;를 포함한다. 본 발명에 따르면 생물학적 개체명을 통계 기반의 방식을 사용하여 자동적으로 인식하는데 있어서 생물학 문헌 학습 코퍼스(corpus)를 구축하기 위해 필요한 비용을 줄이며, 개체명 인식 성능을 지속적으로 향상시킬 수 있다.
생물학적 개체명, 개체명 인식, 워크벤치-
公开(公告)号：WO2012165929A2
公开(公告)日：2012-12-06
申请号：PCT/KR2012/004405
申请日：2012-06-04
CPC classification number: G06F17/3053 , G06F17/2765 , G06F17/2785 , G06F17/3069 , G10L13/027 , G10L15/26
Abstract: 웹을 이용한 정보 검색 방법 및 이를 사용하는 음성 대화 방법은 제공된 사용자 질의 및 언어 분석 결과 중 적어도 하나에 대한 기본 단어 벡터를 생성하고, 기본 단어 벡터를 이용하여 벡터 공간 데이터베이스에서 기본 단어 벡터에 대응되는 벡터 공간을 검색한 후, 기본 단어 벡터와 검색된 벡터 공간과의 유사도가 미리 설정된 기준 이하인 경우, 사용자 질의 및 언어 분석 결과 중 적어도 하나를 이용하여 수행된 웹 검색 결과로부터, 생성한 확장 단어 벡터를 이용하여 벡터 공간 데이터베이스에서 확장 단어 벡터에 대응되는 벡터 공간을 검색하고, 기본 검색 단계 또는 확장 검색 단계에서 검색된 벡터 공간에 기초하여 지식 정보를 검색한다. 따라서, 사용자 질의에 대하여 보다 나은 검색 결과를 제공할 수 있다.
Abstract translation: 根据本发明，使用Web搜索信息的方法和使用它的语音对话方法涉及为所提供的用户查询和语言分析结果中的至少一个生成基本词向量; 使用基本的单词向量，在向量空间数据库中搜索与基本单词向量对应的向量空间; 搜索基本词向量和找到的向量空间之间的相似度低于预设参考值时，使用从Web搜索结果生成的扩展字矢量对应于扩展字向量的向量空间数据库 使用用户查询和语言分析结果中的至少一个; 以及基于在基本搜索步骤或扩展搜索步骤中找到的向量空间来搜索知识信息。 因此，可以响应于用户查询来提供改进的研究结果。
-
公开(公告)号：KR1020120110751A
公开(公告)日：2012-10-10
申请号：KR1020110028816
申请日：2011-03-30
Applicant: 포항공과대학교 산학협력단
Abstract: PURPOSE: A speech processing device and a method thereof are provided to automatically recognize a speech for modification without special modification as soon as a speech is inputted. CONSTITUTION: A speech recognizing module(100) recognizes a speech of a user. The speech recognizing module outputs qualification information for determining an intention of a speech of a user. A speech intension determining module(300) determines an intension of a speech of the user. A character input module(500) inputs a character according to the intension. [Reference numerals] (100) Speech recognizing module; (200) Error extracting module; (300) Speech intension determining module; (400) Training word chunk database; (500) Character input module; (AA) User speech
Abstract translation: 目的：提供一种语音处理装置及其方法，一旦输入语音，便自动识别用于修改的语音，而无需特别修改。 构成：语音识别模块（100）识别用户的语音。 语音识别模块输出用于确定用户的语音的意图的资格信息。 语音强度确定模块（300）确定用户的语音的意图。 字符输入模块（500）根据意图输入字符。 （附图标记）（100）语音识别模块; （200）错误提取模块; （300）语音识别模块; （400）培训字块数据库; （500）字符输入模块; （AA）用户演讲
-
Patent Agency Ranking
公开(公告)号：KR1020140058817A
公开(公告)日：2014-05-15
申请号：KR1020120125121
申请日：2012-11-07
Applicant: 포항공과대학교 산학협력단 , 한국생산기술연구원 , 부산대학교 산학협력단
CPC classification number: G06Q30/0202 , G06F17/30734 , G06Q10/0639
Abstract: Disclosed are a system and a method for scouting supplier companies based on an ontology which reflects requirements of demander companies. The system for scouting supplier companies comprises an ontology managing unit which generates ontology based on demander company requirement information, which is configured by using collected requirements of the demander companies, and domain knowledge information, which is formed by analyzing information related to the industry to which the supplier company belongs; a search request processing unit which receives selecting conditions for the supplier company and information on a key capacity of the supplier company to generate an instance file based on the ontology, and receives search information requesting a search related to the supplier company to convert the search information to the selecting conditions for the supplier company; and a result processing unit which searches for the supplier company, that matches the converted selecting conditions for the supplier company, by using the instance file. Therefore, the demander company is allowed to systematically receive information on a manufacturing capacity and a Research and Development (R&D) capacity, which are the key capacities of the supplier company, and search for the supplier company that satisfies various demand requirements of the demander companies.
Abstract translation: 公开了一种基于反映需求者公司要求的本体论的供应商公司的系统和方法。 用于搜索供应商公司的系统包括本体管理单元，其基于需求者公司需求信息生成本体，其通过使用需求者公司的收集的要求配置，以及通过分析与其相关的行业的信息而形成的领域知识信息 供应商公司所属; 接收供应商公司的选择条件的搜索请求处理单元和供应商公司的关键能力的信息，基于本体生成实例文件，并且接收请求与供应商公司相关的搜索的搜索信息以转换搜索信息 供应商公司的选择条件; 以及结果处理单元，通过使用该实例文件来搜索与供应商公司的转换的选择条件相匹配的供应商公司。 因此，要求公司被允许系统地收到关于制造能力和研发（R＆D）能力的信息，这是供应商公司的关键能力，并寻找满足需求者公司各种需求要求的供应商公司 。
-
公开(公告)号：KR101255957B1
公开(公告)日：2013-04-24
申请号：KR1020110131504
申请日：2011-12-09
Applicant: 포항공과대학교 산학협력단
IPC: G06F17/20
CPC classification number: G06F17/218 , G06F17/2735 , G06F17/278 , G06F17/2795
Abstract: PURPOSE: An entity name tagging method and a device thereof are provided to improve the performance of a conversation system by tagging an accurate entity name to a word included in a corpus. CONSTITUTION: An acquisition unit(21) acquires an entity name candidate group from a word included in a corpus based on a dictionary for a predetermined domain. A tagging unit(22) tags an entity name to the entity name candidate group by applying an unsupervised learning method including a restriction condition to the entity name candidate group. The acquisition unit acquires the entity name candidate group according to a characteristic in which words included in a corpus are repeated. The restriction condition is a number which indicates the entity name in a sentence in which the words belong to the corpus. [Reference numerals] (21) Acquisition unit; (22) Tagging unit;
Abstract translation: 目的：提供实体名称标记方法及其装置，以通过将准确的实体名称标记到包含在语料库中的单词来提高会话系统的性能。 构成：获取单元（21）基于用于预定域的字典从包含在语料库中的单词获取实体名称候选组。 标签单元（22）通过向实体名称候选组应用包括限制条件的无监督学习方法来将实体名称标记给实体名称候选组。 采集单元根据重复包含在语料库中的单词的特性来获取实体名称候选组。 限制条件是一个数字，表示单词属于语料库的句子中的实体名称。 （附图标记）（21）采集单元; （22）标签单位;
-
公开(公告)号：KR1020120135449A
公开(公告)日：2012-12-14
申请号：KR1020110053400
申请日：2011-06-02
Applicant: 포항공과대학교 산학협력단
CPC classification number: G06F17/3053 , G06F17/2765 , G06F17/2785 , G06F17/3069 , G10L13/027 , G10L15/26
Abstract: PURPOSE: An information search method by using the web and a voice conversation method using the method are provided to supply a better search result for a user query by extending knowledge information and information about the user query based on the web. CONSTITUTION: A basic word vector for a user query and a language analysis result is generated to search a vector space database for a vector space corresponding to the basic word vector(S420). Similarity between the basic word vector and the searched vector space are determined(S430). If the similarity is less than standards, an extended word vector is generated from a web search result performed by using the user query and the language analysis result(S440). The vector space database is searched for the vector space corresponding to the extended word vector by using the extended word vector. Knowledge information is searched based on the vector space. [Reference numerals] (1000) Knowledge information DB; (2000) Vector space; (2100) Vector space basic DB; (2200) Vector space extension DB; (AA) No; (BB) Yes; (CC) Search result; (S410) User query and language analysis result; (S420) Basic search; (S430) Determination?; (S440) Extended search; (S450) Generating vector space
Abstract translation: 目的：提供使用该方法的信息搜索方法和使用该方法的语音对话方法，以通过基于网络扩展知识信息和关于用户查询的信息来为用户查询提供更好的搜索结果。 生成用于用户查询和语言分析结果的基本词向量，以搜索向量空间数据库中与基本词向量相对应的向量空间（S420）。 确定基本字向量与搜索向量空间的相似度（S430）。 如果相似度小于标准，则通过使用用户查询和语言分析结果执行的web搜索结果生成扩展字向量（S440）。 通过使用扩展字向量，搜索与扩展字向量相对应的向量空间数据库。 基于矢量空间搜索知识信息。 （附图标记）（1000）知识信息DB; （2000）矢量空间; （2100）矢量空间基本DB; （2200）矢量空间扩展DB; （AA）否 （BB）是的; （CC）搜索结果; （S410）用户查询和语言分析结果; （S420）基本搜索; （S430）测定？ （S440）扩展搜索; （S450）生成向量空间
-
公开(公告)号：KR1020120110392A
公开(公告)日：2012-10-10
申请号：KR1020110028211
申请日：2011-03-29
Applicant: 포항공과대학교 산학협력단
IPC: G10L15/00
Abstract: PURPOSE: A confirmation enabled probabilistic and example-based spoken dialog system is provided to enable a conversation manager to determine whether information is unclear when a voice error occurs in a voice conversation interface, thereby providing an information confirmation conversation to a user. CONSTITUTION: A conversation state managing unit(112) of a confirmation conversation managing unit(110) calculates reliability of current conversation states using reliability in recognizing a user speech, reliability of understanding voice language, and reliability of a previous conversation state. A confirmation conversation request unit(114) of the confirmation conversation managing unit determines whether information is unclear by a confirmation conversation strategy about the reliability of the current conversation states. [Reference numerals] (10) Voice recognizer; (100) Conversation managing unit; (110) Confirmation Conversation managing unit(probability-based); (112) Conversation state managing unit; (114) Confirmation Conversation request unit; (120) Work related conversation managing unit(example-based); (20) Voice language comprehension unit; (200) Confirmation conversation strategy DB; (300) Conversation example DB
Abstract translation: 目的：提供一种确认启用的概率和基于示例的口语对话系统，以使对话管理器能够确定语音对话界面中出现语音错误时信息是否不清楚，从而向用户提供信息确认对话。 构成：确认会话管理单元（110）的会话状态管理单元（112）使用识别用户语音的可靠性，理解语音语言的可靠性和前一会话状态的可靠性来计算当前会话状态的可靠性。 确认会话管理单元的确认会话请求单元（114）通过关于当前会话状态的可靠性的确认对话策略来确定信息是否不清楚。 （附图标记）（10）语音识别器; （100）对话管理单位; （110）确认对话管理单元（基于概率）; （112）对话状态管理单元; （114）确认对话请求单元; （120）工作对话管理单元（以示例为基础）; （20）语音理解单位; （200）确认对话策略DB; （300）对话示例DB
-
公开(公告)号：KR101089450B1
公开(公告)日：2011-12-07
申请号：KR1020090105456
申请日：2009-11-03
Applicant: 포항공과대학교 산학협력단
Abstract: 본 발명은 사용자 시뮬레이션 시스템 및 방법에 관한 것으로서, 이 시스템은, 사용자 의도를 생성하는 사용자 의도 생성부, 그리고 상기 사용자 의도에 따라 문장 구조를 생성하고 상기 문장 구조에 대응하는 복수의 단어열을 생성하고 상기 복수의 단어열로부터 발화 문장을 추출하는 표층 언어 생성부를 포함한다. 본 발명에 의하면, 자연스럽고 다양한 사용자 의도를 생성할 수 있으며 생성된 사용자 의도에 적합한 다양한 표층 언어를 생성할 수 있다.
사용자 시뮬레이션, 대화 시스템, 사용자 의도, 표층 언어, CRF 확률 모델
-
-
-
-
-
-
-
-
-
Search Results
24
records
(took 0.027 seconds)
