公开(公告)号：US07840565B2

公开(公告)日：2010-11-23

申请号：US11471538

申请日：2006-06-21

申请人： Hiroshi Kutsumi ,  Eiichi Naito ,  Jun Ozawa ,  Hideyuki Yoshida

发明人： Hiroshi Kutsumi ,  Eiichi Naito ,  Jun Ozawa ,  Hideyuki Yoshida

IPC分类号： G06F17/30

CPC分类号： G06F17/2735 ,  H04N21/482

摘要： A dictionary creation device and dictionary creation method are provided which optimally create and update a dictionary for classifying, searching, or extracting text information in accordance with a changes in content of text information groups. The dictionary creation device includes a keyword extraction unit that extracts a keyword from inputted text information and a keyword statistics unit that finds statistics regarding an appearance of the keyword. The dictionary creation device further includes a keyword assessment value calculation unit that calculates an assessment value of the extracted keyword based on the statistics regarding the appearance of the keyword, a determination unit that determines whether or not to register or delete the keyword based on the calculated assessment value, a dictionary registration and deletion unit which registers or deletes the keyword in or from a dictionary database based on a result of the determination performed by the determination unit, and the dictionary database.

摘要翻译： 提供了一种字典创作装置和字典创作方法，其最佳地创建和更新字典，以便根据文本信息组内容的变化对文本信息进行分类，搜索或提取。 字典创建装置包括从输入的文本信息中提取关键字的关键字提取单元和查找关于关键字的外观的统计的关键字统计单元。 字典创建装置还包括关键词评估值计算单元，其基于关于关键字的出现的统计来计算提取的关键字的评估值;确定单元，其基于所计算的关键字来确定是否注册或删除关键字 评估值，字典登记和删除单元，其基于由确定单元执行的确定的结果和字典数据库，在字典数据库中注册或从字典数据库中注册或删除关键字。

公开(公告)号：US20060242191A1

公开(公告)日：2006-10-26

申请号：US11471538

申请日：2006-06-21

申请人： Hiroshi Kutsumi ,  Eiichi Naito ,  Jun Ozawa ,  Hideyuki Yoshida

发明人： Hiroshi Kutsumi ,  Eiichi Naito ,  Jun Ozawa ,  Hideyuki Yoshida

IPC分类号： G06F17/00

CPC分类号： G06F17/2735 ,  H04N21/482

摘要： There is provided a dictionary creation device and dictionary creation method which optimally creates and updates a dictionary for classifying, searching, or extracting text information in accordance with a changes in content of text information groups. The dictionary creation device includes: a keyword extraction unit that extracts a keyword from inputted text information; a keyword statistics unit that finds statistics regarding an appearance of the keyword; a keyword assessment value calculation unit that calculates an assessment value of the extracted keyword based on the statistics regarding the appearance of the keyword; a determination unit that determines whether or not to register or delete the keyword based on the calculated assessment value; a dictionary registration and deletion unit which registers or deletes is the keyword in or from a dictionary database based on a result of the determination performed by the determination unit; and the dictionary database.

摘要翻译： 提供了一种词典创建装置和字典创建方法，其最佳地创建和更新用于根据文本信息组的内容的变化对文本信息进行分类，搜索或提取的字典。 字典创建装置包括：关键词提取单元，从输入的文本信息中提取关键字; 关键词统计单元，查找关于关键字的外观的统计信息; 关键词评估值计算单元，其基于关于所述关键字的出现的统计来计算所提取的关键字的评估值; 确定单元，其基于所计算的评估值来确定是否注册或删除所述关键字; 基于由确定单元执行的确定的结果，登记或删除的字典注册和删除单元是字典数据库中的关键字; 和字典数据库。

公开(公告)号：US20060271527A1

公开(公告)日：2006-11-30

申请号：US11497357

申请日：2006-08-02

申请人： Hiroshi Kutsumi ,  Eiichi Naito ,  Jun Ozawa ,  Hideyuki Yoshida

发明人： Hiroshi Kutsumi ,  Eiichi Naito ,  Jun Ozawa ,  Hideyuki Yoshida

IPC分类号： G06F17/30

CPC分类号： G06F17/2735 ,  H04N21/482

摘要： There is provided a dictionary creation device and dictionary creation method which optimally creates and updates a dictionary for classifying, searching, or extracting text information in accordance with a changes in content of text information groups. The dictionary creation device includes: a keyword extraction unit that extracts a keyword from inputted text information; a keyword statistics unit that finds statistics regarding an appearance of the keyword; a keyword assessment value calculation unit that calculates an assessment value of the extracted keyword based on the statistics regarding the appearance of the keyword; a determination unit that determines whether or not to register or delete the keyword based on the calculated assessment value; a dictionary registration and deletion unit which registers or deletes the keyword in or from a dictionary database based on a result of the determination performed by the determination unit; and the dictionary database.

摘要翻译： 提供了一种词典创建装置和字典创建方法，其最佳地创建和更新用于根据文本信息组的内容的变化对文本信息进行分类，搜索或提取的字典。 字典创建装置包括：关键词提取单元，从输入的文本信息中提取关键字; 关键词统计单元，查找关于关键字的外观的统计信息; 关键词评估值计算单元，其基于关于所述关键字的出现的统计来计算所提取的关键字的评估值; 确定单元，其基于所计算的评估值来确定是否注册或删除所述关键字; 字典登记和删除单元，其基于由所述确定单元执行的确定的结果，在字典数据库中或从字典数据库中注册或删除关键字; 和字典数据库。

公开(公告)号：US07921113B2

公开(公告)日：2011-04-05

申请号：US11497357

申请日：2006-08-02

申请人： Hiroshi Kutsumi ,  Eiichi Naito ,  Jun Ozawa ,  Hideyuki Yoshida

发明人： Hiroshi Kutsumi ,  Eiichi Naito ,  Jun Ozawa ,  Hideyuki Yoshida

IPC分类号： G06F17/30

CPC分类号： G06F17/2735 ,  H04N21/482

摘要： A dictionary creation device and dictionary creation method which optimally create and update a dictionary for classifying, searching, or extracting text information in accordance with a changes in content of text information groups. The dictionary creation device includes a keyword extraction unit that extracts a keyword from inputted text information; a keyword statistics unit that finds statistics regarding an appearance of the keyword; a keyword assessment value calculation unit that calculates an assessment value of the extracted keyword based on the statistics regarding the appearance of the keyword; a determination unit that determines whether or not to register or delete the keyword based on the calculated assessment value; a dictionary registration and deletion unit which registers or deletes the keyword in or from a dictionary database based on a result of the determination performed by the determination unit; and the dictionary database.

摘要翻译： 字典创作装置和字典创作方法，根据文本信息组内容的变化，最佳地创建和更新字典，以对文本信息进行分类，搜索或提取。 字典创建装置包括从输入的文本信息中提取关键字的关键词提取单元; 关键词统计单元，查找关于关键字的外观的统计信息; 关键词评估值计算单元，其基于关于所述关键字的出现的统计来计算所提取的关键字的评估值; 确定单元，其基于所计算的评估值来确定是否注册或删除所述关键字; 字典登记和删除单元，其基于由所述确定单元执行的确定的结果，在字典数据库中或从字典数据库中注册或删除关键字; 和字典数据库。

公开(公告)号：US06993517B2

公开(公告)日：2006-01-31

申请号：US09859609

申请日：2001-05-17

申请人： Eiichi Naito ,  Shoichi Araki ,  Hiroshi Kutsumi ,  Jun Ozawa ,  Susumu Maruno

发明人： Eiichi Naito ,  Shoichi Araki ,  Hiroshi Kutsumi ,  Jun Ozawa ,  Susumu Maruno

IPC分类号： G06F17/30

CPC分类号： G06F17/3071 ,  G06F17/30634 ,  G06F17/3069 ,  Y10S707/99933 ,  Y10S707/99943

摘要： Questions and answers associated with each other are stored in a document storage section. A clustering section classifies the answers in the document storage section into clusters based on feature vectors of the answers. When a natural language question is input by the user, a database retrieval/updating section retrieves a question similar to the input question, and presents answers associated with the retrieved question together for each cluster to the user or an expert. In addition, the database retrieval/updating section automatically updates the document storage section based on an answer selected as most appropriate by the user or the expert if selected, or based on an answer newly input by the expert if no appropriate answer is available. The natural language answer input by the expert is presented to the user as it is.

摘要翻译： 彼此相关的问题和答案存储在文档存储部分中。 聚类部分将文档存储部分中的答案根据答案的特征向量进行分类。 当用户输入自然语言问题时，数据库检索/更新部分检索类似于输入问题的问题，并且将与检索到的问题相关联的答案一起呈现给用户或专家的每个聚类。 此外，数据库检索/更新部分基于如果选择了用户或专家最适合的答案，或者如果没有适当的答案可用，则基于由专家新输入的答案，自动更新文档存储部分。 由专家输入的自然语言答案按原样呈现给用户。

公开(公告)号：US07483921B2

公开(公告)日：2009-01-27

申请号：US11434761

申请日：2006-05-17

申请人： Takashi Tsuzuki ,  Hiroshi Kutsumi ,  Eiichi Naito

发明人： Takashi Tsuzuki ,  Hiroshi Kutsumi ,  Eiichi Naito

IPC分类号： G06F12/00 ,  G06F17/30 ,  G06F17/21 ,  G06F7/00

CPC分类号： G06F17/30672 ,  G06F17/30646 ,  Y10S707/99934 ,  Y10S707/99935 ,  Y10S707/99936

摘要： An apparatus including: a preference word obtainment unit that, when a search condition is input, obtains related words associated with keywords included in the search condition by a predetermined threshold or greater. Further, the preference word obtainment unit decreases the predetermined threshold to obtain related words, from a preference association dictionary when an expansion command is received. Moreover, the apparatus includes (i) a judgment unit which judges whether the related word obtained by the preference word obtainment unit is stored when the expansion command is received, (ii) a general word obtainment unit which obtains a related word from a general dictionary when it is judged that the related word obtained by the preference word obtainment unit is stored, and (iii) a retrieval unit which generates a search condition from the related word, obtains information meeting the generated search condition, and outputs the obtained information as a search result.

摘要翻译： 一种装置，包括：偏好词获取单元，当输入搜索条件时，获取与包括在所述搜索条件中的关键字相关联的相关词预定阈值或更大。 此外，当接收到扩展命令时，偏好词获取单元减少预定阈值以获得相关词，从偏好关联词典。 此外，该装置包括：（i）判断单元，其判断在接收到扩展命令时是否存储由偏好字获取单元获得的相关字，（ii）通用字获取单元，其从通用字典中获取相关词 当判断出由偏好词获取单元获得的相关字被存储时，以及（iii）从相关字生成搜索条件的检索单元获得满足所生成的搜索条件的信息，并将获得的信息作为 搜索结果。

公开(公告)号：US20080195607A1

公开(公告)日：2008-08-14

申请号：US12101539

申请日：2008-04-11

申请人： Hiroshi Kutsumi ,  Shouichi Araki ,  Eiichi Naito ,  Tomoyasu Hiratsuka ,  Yuumi Jitousho

发明人： Hiroshi Kutsumi ,  Shouichi Araki ,  Eiichi Naito ,  Tomoyasu Hiratsuka ,  Yuumi Jitousho

IPC分类号： G06F7/06 ,  G06F17/30

CPC分类号： A23L35/00 ,  G06F16/335 ,  G06F16/9535 ,  G06Q30/02 ,  G06Q30/0273 ,  G06Q30/0277 ,  G06Q30/0631

摘要： An information recommendation apparatus has recommendation means of selecting and recommending contents coincident with or similar to conditions input by condition input means of inputting the conditions represented by predetermined items and attribute values corresponding thereto designated through the terminal of a user via the Internet, from among contents formed of plural pieces of data having plural items and attribute values corresponding thereto and stored in a content database in which the contents are registered by registration means, wherein the recommended contents are output to the terminal by output means via the Internet.

摘要翻译： 信息推荐装置具有如下推荐装置：从条目输入装置输入的条件输入的条件选择推荐内容，所述条件输入装置输入由用户通过因特网指定的预定项目所表示的条件和与之对应的属性值， 由具有多个项目的数据和与其对应的属性值的多个数据形成，并存储在通过注册装置登记内容的内容数据库中，其中推荐内容通过因特网由输出装置输出到终端。

公开(公告)号：US07725486B2

公开(公告)日：2010-05-25

申请号：US11385751

申请日：2006-03-22

申请人： Takashi Tsuzuki ,  Hiroshi Kutsumi ,  Eiichi Naito

发明人： Takashi Tsuzuki ,  Hiroshi Kutsumi ,  Eiichi Naito

IPC分类号： G06F7/00 ,  G06F17/30

CPC分类号： G06F17/30672 ,  G06F17/30646 ,  Y10S707/99934 ,  Y10S707/99935 ,  Y10S707/99936

摘要： An information retrieval apparatus using a preference-based association dictionary, having words stored therein that are dynamically changed according to user's preferences, and using a general association dictionary storing a relationship between keywords included in a database. The apparatus includes: a matching unit which calculates a degree of matching between a search condition inputted from an input unit and a profile; a generation unit which obtains (i) one or more related words from a general association dictionary in a case where the matching degree is smaller than a predetermined threshold, and (ii) one or more related words from a preference-based association dictionary in a case where the matching degree is greater than the predetermined threshold; and a retrieval unit which retrieves information that meets the generated search condition.

摘要翻译： 一种使用基于偏好的关联词典的信息检索装置，其中存储有根据用户偏好动态地改变的词，以及使用存储数据库中包括的关键词之间关系的一般关联词典。 该装置包括：匹配单元，其计算从输入单元输入的搜索条件与简档之间的匹配度; 在匹配度小于预定阈值的情况下，从（i）一般关联词典获得（i）一个或多个相关词的生成单元，以及（ii）来自基于关联词典的一个或多个相关词， 匹配度大于预定阈值的情况; 以及检索单元，其检索满足生成的搜索条件的信息。

公开(公告)号：US07373318B2

公开(公告)日：2008-05-13

申请号：US09851791

申请日：2001-05-09

申请人： Hiroshi Kutsumi ,  Shouichi Araki ,  Eiichi Naito ,  Tomoyasu Hiratsuka ,  Yuumi Jitousho

发明人： Hiroshi Kutsumi ,  Shouichi Araki ,  Eiichi Naito ,  Tomoyasu Hiratsuka ,  Yuumi Jitousho

IPC分类号： G06F17/30

CPC分类号： G06F17/30867 ,  A23L35/00 ,  G06F17/30699 ,  G06Q30/02 ,  G06Q30/0273 ,  G06Q30/0277 ,  G06Q30/0631

摘要： An information recommendation apparatus selects and recommends contents coincident with or similar to conditions input. The conditions are represented by predetermined items and attribute values corresponding thereto, from among contents formed of plural pieces of data having plural items and attribute values corresponding thereto and stored in a content database in which the contents are registered, wherein the recommended contents are output to the terminal.

摘要翻译： 信息推荐装置选择并推荐与条件输入一致或类似的内容。 条件由对应于其的预定项目和属性值表示，从由具有多个项目的多个数据和与其对应的属性值形成的内容中存储在其中登记了内容的内容数据库中，其中推荐内容被输出到 终点站。

公开(公告)号：US20060167918A1

公开(公告)日：2006-07-27

申请号：US11385751

申请日：2006-03-22

申请人： Takashi Tsuzuki ,  Hiroshi Kutsumi ,  Eiichi Naito

发明人： Takashi Tsuzuki ,  Hiroshi Kutsumi ,  Eiichi Naito

IPC分类号： G06F17/30

CPC分类号： G06F17/30672 ,  G06F17/30646 ,  Y10S707/99934 ,  Y10S707/99935 ,  Y10S707/99936

摘要： An information retrieval apparatus which can use a preference-based association dictionary, the words stored therein are dynamically changed according to user's preferences, and a general association dictionary storing a relationship between the keywords included in a database, by appropriately switching between the two association dictionaries, and which includes: a matching degree calculation unit which calculates a degree of matching between a search condition inputted from an input unit and a profile; a search condition generation unit which obtains one or more related words from a general association dictionary stored in a general association dictionary storage unit in the case where the calculated matching degree is smaller than a predetermined threshold, and obtains one or more related words from a preference-based association dictionary stored in a preference-based association dictionary storage unit in the case where the matching degree is greater than the predetermined threshold, in order to generate a search condition; and a retrieval unit which retrieves information that meets the generated search condition, and outputs the information as a search result.

摘要翻译： 可以使用基于偏好的关联词典的信息检索装置，根据用户的偏好动态地改变存储在其中的词，以及通过适当地切换两个关联字典之间存储数据库中包括的关键字之间的关系的一般关联词典 并且包括：匹配度计算单元，其计算从输入单元输入的搜索条件和简档之间的匹配度; 搜索条件生成单元，其在所计算的匹配度小于预定阈值的情况下，从存储在通用关联字典存储单元中的一般关联字典中获取一个或多个相关字，并且从偏好获得一个或多个相关词 在匹配度大于预定阈值的情况下，存储在基于偏好的关联字典存储单元中的基于关联字典的关联字典，以便生成搜索条件; 以及检索单元，其检索满足生成的搜索条件的信息，并将该信息作为搜索结果输出。