公开(公告)号：US20140188482A1

公开(公告)日：2014-07-03

申请号：US13872188

申请日：2013-04-29

Applicant: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE

Inventor： Hsin-Chang Chang ,  Jia-Jang Tu ,  Jian-Yung Hung ,  Chih-Chung Kuo

IPC: G10L21/00

CPC classification number: G10L15/00

Abstract: A voice control method is provided. At least one object name-action prompt correspondence document is received and processed into an object name-action prompt correspondence document set that defines at least one object name and at least one corresponding action prompt. The object name-action prompt correspondence document set is processed to establish an object name-action prompt correspondence list. A voice is recognized as one or multiple voice recognition results to generate one or multiple corresponding candidate object names. At least one corresponding candidate action prompt is outputted according to the candidate object name(s) and the object name-action prompt correspondence list. A selected action prompt is received, and a module providing the selected action prompt is requested to execute an operation.

Abstract translation: 提供语音控制方法。 至少一个对象名称 - 动作提示对应文档被接收并处理成定义至少一个对象名称和至少一个相应动作提示的对象名称 - 动作提示对应文档集合。 处理对象名称 - 动作提示对应文档集以建立对象名称 - 动作提示对应列表。 语音被识别为一个或多个语音识别结果以生成一个或多个相应的候选对象名称。 根据候选对象名称和对象名称 - 动作提示对应列表输出至少一个相应的候选动作提示。 接收到所选择的动作提示，并且请求提供所选动作提示的模块来执行操作。

公开(公告)号：US20180173694A1

公开(公告)日：2018-06-21

申请号：US15653536

申请日：2017-07-19

Applicant: Industrial Technology Research Institute

Inventor： Chao-Hong Liu ,  Tzi-Cker Chiueh ,  Chih-Chung Kuo ,  Chung-Han Lee ,  Jian-Yung Hung

IPC: G06F17/27 ,  G06F17/30 ,  G06N99/00

CPC classification number: G06F17/278 ,  G06F16/3338 ,  G06N20/00

Abstract: The disclosure provides methods and computer systems for named entity verification, named entity verification model training, and phrase expansion. The method for named entity verification includes to receive an unknown type phrase, to generate a query phrase according to the unknown type phrase, to perform auto-completion on the query phrase to receive one or more returned phrases, to extract feature information from the returned phrases, and to determine a named entity type of the unknown type phrase based on the feature information verify whether or not the unknown type phrase belongs to the target named entity type based on the feature information and a target verification model to accordingly output a verification result.