公开(公告)号：US20210343185A1

公开(公告)日：2021-11-04

申请号：US17373712

申请日：2021-07-12

申请人： Yeyi Wang

发明人： Yeyi Wang

IPC分类号： G09B23/18

摘要： A modular building block easy to assemble comprises a base plate, basic parts, and electronic individual components. First protrusions are disposed on the base plate and the basic parts, and slots are formed in the basic parts and the electronic individual components. First conductive pins and conductive metal sheets are disposed inside the basic parts. Control panels, electronic devices and conductive contacts are disposed inside the electronic individual components The invention designs the base plate, basic parts and electronic individual components of original electronic building blocks as individual modules.

公开(公告)号：US07574347B2

公开(公告)日：2009-08-11

申请号：US11329956

申请日：2006-01-11

申请人： YeYi Wang

发明人： YeYi Wang

IPC分类号： G06F17/28

CPC分类号： G06F17/271 ,  Y10S707/99942

摘要： The present invention provides a method for improving the efficiency of parsing text. Aspects of the invention include representing parse tokens as integers where a portion of the integer indicates the location in which a definition for the token can be found. In a further aspect, an integer representing a token points to an array of tokens that can be activated by the token. In another aspect, a list of pointers to partial parses is created before attempting to parse a next word in the text string. The list of pointers includes pointers to partial parses that are expecting particular semantic tokens.

摘要翻译： 本发明提供了一种提高解析文本效率的方法。 本发明的方面包括将解析令牌表示为整数，其中整数的一部分指示可以找到令牌的定义的位置。 在另一方面，表示令牌的整数指向可被令牌激活的令牌阵列。 在另一方面，在尝试解析文本字符串中的下一个字之前，创建指向部分解析的指针列表。 指针列表包括指向特定语义令牌的部分解析的指针。

公开(公告)号：US06985852B2

公开(公告)日：2006-01-10

申请号：US09934313

申请日：2001-08-21

申请人： YeYi Wang

发明人： YeYi Wang

IPC分类号： G06F17/27 ,  G06F17/28

CPC分类号： G06F17/274 ,  G06F17/2785

摘要： The present invention provides a dialogue system in which semantic ambiguity is reduced by selectively choosing which semantic structures are to be made available for parsing based on previous information obtained from the user or other context information. In one embodiment, the semantic grammar used by the parser is altered so that the grammar is focused based on information about the user or the dialogue state. In other embodiments, the semantic parsing is focused on certain parse structures by giving preference to structures that the dialogue system has marked as being expected.

公开(公告)号：US20050203728A1

公开(公告)日：2005-09-15

申请号：US11119023

申请日：2005-04-29

申请人： YeYi Wang

发明人： YeYi Wang

IPC分类号： G06F17/27 ,  G06F17/28

CPC分类号： G06F17/274 ,  G06F17/2785

摘要： The present invention provides a dialogue system in which semantic ambiguity is reduced by selectively choosing which semantic structures are to be made available for parsing based on previous information obtained from the user or other context information. In one embodiment, the semantic grammar used by the parser is altered so that the grammar is focused based on information about the user or the dialogue state. In other embodiments, the semantic parsing is focused on certain parse structures by giving preference to structures that the dialogue system has marked as being expected.

摘要翻译： 本发明提供了一种对话系统，其中通过根据从用户获取的先前信息或其他上下文信息选择性地选择哪些语义结构可用于解析来减少语义歧义。 在一个实施例中，解析器使用的语义语法被改变，使得基于关于用户的信息或对话状态的信息来集中语法。 在其他实施例中，语义解析通过给对象系统已经被标记为被预期的结构给予偏好来集中于某些解析结构。

公开(公告)号：US07047183B2

公开(公告)日：2006-05-16

申请号：US09934224

申请日：2001-08-21

申请人： YeYi Wang

发明人： YeYi Wang

IPC分类号： G06F17/27

CPC分类号： G06F17/2785

摘要： A method and apparatus perform semantic parsing by designating one or more words in an input text stream as wildcards. Under some embodiments, partially constructed parses formed from other words in the text stream are used to control when a later word will be identified as a wildcard. In particular, if a partial parse is expecting a semantic token that begins with a wildcard, the next word in the input text segment is designated as a wildcard term. If none of the existing partial parses are expecting a semantic token that begins with a wildcard, the next word is not designated as a wildcard

公开(公告)号：US07024351B2

公开(公告)日：2006-04-04

申请号：US09934223

申请日：2001-08-21

申请人： YeYi Wang

发明人： YeYi Wang

IPC分类号： G06F17/27

CPC分类号： G06F17/271 ,  Y10S707/99942

摘要： The present invention provides a method for improving the efficiency of parsing text. Aspects of the invention include representing parse tokens as integers where a portion of the integer indicates the location in which a definition for the token can be found. In a further aspect, an integer representing a token points to an array of tokens that can be activated by the token. In another aspect, a list of pointers to partial parses is created before attempting to parse a next word in the text string. The list of pointers includes pointers to partial parses that are expecting particular semantic tokens. A fourth aspect of the invention utilizes a data structure to list the semantic tokens that have been fully parsed for each span in the input text segment. When a token is fully parsed, the list is accessed to determine if the new token should be discarded.

公开(公告)号：US11335211B2

公开(公告)日：2022-05-17

申请号：US17373712

申请日：2021-07-12

申请人： Yeyi Wang

发明人： Yeyi Wang

IPC分类号： G09B23/00 ,  G09B23/18

摘要： A modular building block easy to assemble comprises a base plate, basic parts, and electronic individual components. First protrusions are disposed on the base plate and the basic parts, and slots are formed in the basic parts and the electronic individual components. First conductive pins and conductive metal sheets are disposed inside the basic parts. Control panels, electronic devices and conductive contacts are disposed inside the electronic individual components. The invention designs the base plate, basic parts and electronic individual components of original electronic building blocks as individual modules.

公开(公告)号：US07555426B2

公开(公告)日：2009-06-30

申请号：US11119023

申请日：2005-04-29

申请人： YeYi Wang

发明人： YeYi Wang

IPC分类号： G06F17/27 ,  G10L15/00

CPC分类号： G06F17/274 ,  G06F17/2785

摘要： The present invention provides a dialogue system in which semantic ambiguity is reduced by selectively choosing which semantic structures are to be made available for parsing based on previous information obtained from the user or other context information. In one embodiment, the semantic grammar used by the parser is altered so that the grammar is focused based on information about the user or the dialogue state. In other embodiments, the semantic parsing is focused on certain parse structures by giving preference to structures that the dialogue system has marked as being expected.

摘要翻译： 本发明提供了一种对话系统，其中通过根据从用户获取的先前信息或其他上下文信息选择性地选择哪些语义结构可用于解析来减少语义歧义。 在一个实施例中，解析器使用的语义语法被改变，使得基于关于用户的信息或对话状态的信息来集中语法。 在其他实施例中，语义解析通过给对象系统已经被标记为被预期的结构给予偏好来集中于某些解析结构。

公开(公告)号：US07464032B2

公开(公告)日：2008-12-09

申请号：US11152717

申请日：2005-06-14

申请人： YeYi Wang

发明人： YeYi Wang

IPC分类号： G10L15/04

CPC分类号： G06F17/2785

摘要： A method and apparatus perform semantic parsing by designating one or more words in an input text stream as wildcards. Under some embodiments, partially constructed parses formed from other words in the text stream are used to control when a later word will be identified as a wildcard. In particular, if a partial parse is expecting a semantic token that begins with a wildcard, the next word in the input text segment is designated as a wildcard term. If none of the existing partial parses are expecting a semantic token that begins with a wildcard, the next word is not designated as a wildcard

摘要翻译： 方法和装置通过将输入文本流中的一个或多个单词指定为通配符来执行语义解析。 在一些实施例中，由文本流中的其他单词形成的部分构造的解析用于控制何时将字符识别为通配符。 特别地，如果部分解析期望以通配符开始的语义令牌，则输入文本段中的下一个字被指定为通配符项。 如果现有的部分解析器都没有期望以通配符开头的语义令牌，则下一个单词不会被指定为通配符

公开(公告)号：US07328147B2

公开(公告)日：2008-02-05

申请号：US10406524

申请日：2003-04-03

申请人： YeYi Wang ,  Alejandro Acero

发明人： YeYi Wang ,  Alejandro Acero

IPC分类号： G06F17/27

CPC分类号： G06F17/271 ,  G10L15/18

摘要： A rules-based grammar is generated. Segmentation ambiguities are identified in training data. Rewrite rules for the ambiguous segmentations are enumerated and probabilities are generated for each. Ambiguities are resolved based on the probabilities. In one embodiment, this is done by applying the expectation maximization (EM) algorithm.

摘要翻译： 生成基于规则的语法。 在训练数据中识别分割模糊。 枚举模糊分段的重写规则，并为每个生成概率。 根据概率解决歧义。 在一个实施例中，这通过应用期望最大化（EM）算法来完成。