-
31.发明授权公开(公告)号：US06578019B1
公开(公告)日：2003-06-10
申请号：US08551850
申请日：1995-11-07
IPC分类号： G06F1700
CPC分类号： G06N5/02
摘要： An information processing system which understands the input information as a situation, infers the requirements that situation merits and the preferred responses to those requirements using a knowledge base which has knowledge about the situations, requirements and their responses and the relations among them, and by generating these inferences further understands the input and the situation, which enables it to perform efficiently and effectively, given small amount of input information. If input information is in natural language, the linguistic knowledge base is used to analyze the input natural language information. Further, a knowledge of the user, the operations performed by the user and knowledge of the relationship between the operations of the user and the attribute of the user may also be used by the system to appropriately operate for each user.
摘要翻译： 将输入信息理解为情境的信息处理系统，使用知识库了解情况，要求及其响应及其关系的知识库，并通过生成信息来了解情境值得的要求和对这些要求的首选响应 这些推论进一步了解输入和情况，使得它能够在给定少量输入信息的情况下高效有效地执行。 如果输入信息是自然语言，则使用语言知识库来分析输入的自然语言信息。 此外，系统可以使用用户的知识，用户执行的操作以及用户的操作与用户的属性之间的关系的知识来适当地为每个用户操作。
-
公开(公告)号：US07822735B2
公开(公告)日：2010-10-26
申请号：US09865773
申请日：2001-05-25
IPC分类号： G06F7/00
CPC分类号： G06F17/30861
摘要： A system saves browsed data in a database in response to a user request by assigning a predetermined index to the data, wherein the user is not requested for any index. The system sorts indices of the data in the database and displays the sorted indices, then the system retrieves, in response to a selection of an index from the displayed indices by a user, the data corresponding to the selected index from the database. Accordingly if a user wants to save a data currently browsed, he can make store the data in the database easily only by issuing an instruction to save without specifying any index.
摘要翻译： 系统通过向数据分配预定的索引来响应于用户请求将数据浏览的数据保存在数据库中，其中用户不被请求用于任何索引。 系统对数据库中的数据的索引进行排序并显示排序的索引，然后响应于用户从显示的索引中选择的索引，系统检索与数据库中所选索引对应的数据。 因此，如果用户想要保存当前浏览的数据，则他可以通过在没有指定任何索引的情况下发出保存指令来轻松地将数据存储在数据库中。
-
33.发明授权
公开(公告)号：US6029123A
公开(公告)日：2000-02-22
申请号：US571195
申请日：1995-12-12
CPC分类号： G06F17/273 , G06F17/2765 , G06K9/726 , G06K2209/01
摘要： A natural language processing system and method in which, in order to achieve a high accuracy of recognition of natural language information, a series of natural language information groups is progressively and sequentially recognized, with reference to a knowledge base which contains knowledge concerning the types of natural language information to be processed and knowledge concerning restriction in regard to the sequence of units of the series of natural language groups. In the course of the sequential recognition, the kind of the object to be recognized subsequently is expected based on the kinds of objects in the series of information groups which have been recognized, and a recognition result of the type which coincides with the expected type is delivered as a candidate output.
摘要翻译： 一种自然语言处理系统和方法，其中为了实现对自然语言信息的高度准确度的识别，参考包含有关类型的知识的知识库，知识库逐渐地并且顺序地识别一系列自然语言信息组 要处理的自然语言信息和关于一系列自然语言组的单位序列的限制的知识。 在连续识别的过程中，随后识别的对象的类型是基于所识别的一系列信息组中的对象的种类，并且与预期类型一致的类型的识别结果是 作为候选人输出。
-
34.发明授权System for generating natural language information from information expressed by concept and method therefor 失效用于通过概念和方法表达的信息产生自然语言信息的系统
公开(公告)号：US6023669A
公开(公告)日：2000-02-08
申请号：US580311
申请日：1995-12-28
CPC分类号： G06F17/279 , G06F17/2881
摘要： When information expressed by concept is input to a natural language processing system, the form of expressing the input concept is selected by referring to a knowledge base having the knowledge of languages, general knowledge, and the knowledge of specific areas. In addition, the information expressed by the concept is split into individual concepts, one natural language expression is selected from among one or more natural language expressions with respect to the split individual concepts, and the selected natural language expression is output. In this way, information for natural language appropriate for the situation is generated from the same concept.
摘要翻译： 当将概念表达的信息输入到自然语言处理系统时，通过参考具有语言知识，一般知识和具体领域的知识的知识库来选择表达输入概念的形式。 另外，由概念表达的信息被分为单独的概念，相对于分割的个体概念，从一个或多个自然语言表达中选择一个自然语言表达，并且输出所选择的自然语言表达。 以这种方式，从相同的概念产生适合于这种情况的自然语言的信息。
-
35.发明授权Information processing system for completing or resolving ambiguity of input information and method therefor 失效用于完成或解决输入信息歧义的信息处理系统及其方法
公开(公告)号：US5957520A
公开(公告)日：1999-09-28
申请号：US579582
申请日：1995-12-28
CPC分类号： G06F17/2785 , G06N5/04
摘要： Incomplete and fuzzy portions in input information are detected by making a reference to world knowledge and knowledge of a specific field in a knowledge base prior to understanding the input information indicating a concept. The detected incomplete portion is completed and the detected fuzzy portion is resolved. The knowledge base makes a reference to knowledge of other concepts when the value of an instructed attribute of a specific concept is acquired. Moreover, a concept common to and upper than a plurality of concepts can be determined so that another word, concept or meaning is searched for from one word, concept or meaning.
摘要翻译： 在理解指示概念的输入信息之前，通过参考知识库中的特定领域的世界知识和知识来检测输入信息中的不完整和模糊部分。 检测到的不完整部分完成，检测到的模糊部分被解决。 当获取特定概念的指示属性的值时，知识库引用其他概念的知识。 此外，可以确定与多个概念相同并且高于多个概念的概念，使得从一个单词，概念或意义搜索另一个单词，概念或意义。
-
公开(公告)号：US5802504A
公开(公告)日：1998-09-01
申请号：US492930
申请日：1995-06-21
CPC分类号： G06F17/24
摘要： System and method for preparing a text by using a knowledge base, by which knowledge relating to input information is first retrieved from the knowledge base. Then, a plurality of kinds of information used as elements of a text to be generated is selected from the input information and the retrieved information relating thereto. Subsequently, a describing order, in which the selected elements of the text are described, is determined. Then, a text to be outputted is generated on the basis of the selected elements of the text, the describing order of which has been determined. Thereby, a text, whose contents and structure meet a user's purpose, is generated from the input simple information.
摘要翻译： 通过使用知识库准备文本的系统和方法，通过该知识库首先从知识库检索与输入信息相关的知识。 然后，从输入信息和与其相关的检索信息中选择用作要生成的文本的元素的多种信息。 随后，确定其中描述了所选择的文本元素的描述顺序。 然后，基于所确定的描述顺序的文本的所选择的元素生成要输出的文本。 由此，从输入的简单信息生成其内容和结构符合用户目的的文本。
-
公开(公告)号：US07120641B2
公开(公告)日：2006-10-10
申请号：US10117514
申请日：2002-04-05
CPC分类号： G06F17/30569 , G06F17/30899 , Y10S707/99942 , Y10S707/99943 , Y10S707/99945 , Y10S715/968
摘要： In an information processing apparatus, information is obtained from an internet and a template is selected from a plurality of templates in each of which at least one item is set to be extracted. Data corresponding to the item set in the selected template is extracted from the obtained information and is saved.
摘要翻译： 在信息处理装置中，从因特网获得信息，并且从多个模板中选择模板，每个模板中至少一个项目被设置为被提取。 从所获取的信息中提取与所选模板中设置的项目相对应的数据并被保存。
-
38.发明授权公开(公告)号：US06760717B2
公开(公告)日：2004-07-06
申请号：US10393466
申请日：2003-03-21
IPC分类号： G06F1700
CPC分类号： G06N5/02
摘要： An information processing system which understands the input information as a situation, infers the requirements that situation merits and the preferred responses to those requirements using a knowledge base which has knowledge about the situations, requirements and their responses and the relations among them, and by generating these inferences further understands the input and the situation, which enables it to perform efficiently and effectively, given small amount of input information. If input information is in natural language, the linguistic knowledge base is used to analyze the input natural language information. Further, a knowledge of the user, the operations performed by the user and knowledge of the relationship between the operations of the user and the attribute of the user may also be used by the system to appropriately operate for each user.
摘要翻译： 将输入信息理解为情境的信息处理系统，使用知识库了解情况，要求及其响应及其关系的知识库，并通过生成信息来了解情境值得的要求和对这些要求的首选响应 这些推论进一步了解输入和情况，使得它能够在给定少量输入信息的情况下高效有效地执行。 如果输入信息是自然语言，则使用语言知识库来分析输入的自然语言信息。 此外，系统可以使用用户的知识，用户执行的操作以及用户的操作与用户的属性之间的关系的知识来适当地为每个用户操作。
-
公开(公告)号：US5974370A
公开(公告)日：1999-10-26
申请号：US579735
申请日：1995-12-28
CPC分类号： G10L13/027 , G06F17/273 , G06K9/033
摘要： To accurately perform a process of natural language information, such as a process for generating a sentence from a concept, or a process for recognizing each character which constitutes a sentence, if, after input information is processed and the processed results thereof are output, a part of the output processed results is corrected, the process for the entire input information is reviewed on the basis of the corrected result. As a result, the corrected results of a certain portion can be reflected in another portion.
摘要翻译： 为了准确地执行自然语言信息的处理，例如用于从概念生成句子的处理或用于识别构成句子的每个字符的处理，如果在输入信息被处理并且输出其处理结果之后， 输出处理结果的一部分被更正，整个输入信息的处理将根据校正结果进行审查。 结果，某一部分的校正结果可以反映在另一部分中。
-
40.发明授权公开(公告)号：US06768990B2
公开(公告)日：2004-07-27
申请号：US09912336
申请日：2001-07-26
IPC分类号： G06F1730
CPC分类号： G06F17/30669 , G06F17/2809 , Y10S707/99933 , Y10S707/99934 , Y10S707/99935
摘要： In an information processing apparatus, a SurfaceRule table having surface-layer information, a ConceptRule table having conceptual information, a connection table for correlating the two tables, and a retrieval table storing an ID of a connection table corresponding to a character string are provided in a conceptual database. A conceptual instance corresponding to an input character string is formed by retrieving a retrieval table using the input character string, referring to a connection table using an obtained ID of the connection table, and acquiring information, such as a concept, a part of speech, a tense, a slot and the like, from fields of corresponding SurfaceRule table and ConceptRule table.
摘要翻译： 在信息处理装置中，具有表层信息的SurfaceRule表，具有概念信息的ConceptRule表，用于关联两个表的连接表以及存储与字符串对应的连接表的ID的检索表设置在 一个概念数据库。 通过使用输入字符串检索检索表，参照使用获得的连接表的ID的连接表来形成与输入字符串相对应的概念实例，并且获取诸如概念，部分语音的信息， 一个时态，一个插槽等，从相应的SurfaceRule表和ConceptRule表的字段。
-
-
-
-
-
-
-
-
-
搜索结果
45 条记录 (耗时 0.036 秒)
