专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

EP3416163B1 SPEECH CONTINUATION DETERMINATION METHOD, SPEECH CONTINUATION DETERMINATION DEVICE, AND RECORDING MEDIUM 有权
公开(公告)号：EP3416163B1
公开(公告)日：2020-02-26
申请号：EP18176721.1
申请日：2018-06-08
申请人： Panasonic Intellectual Property Management Co., Ltd.
发明人： USHIO, Takashi , YAMAGAMI, Katsuyoshi , ENDO, Mitsuru
IPC分类号： G10L15/22 , G10L25/78 , G10L15/065 , G10L15/16 , G10L15/18

2. 发明公开

EP3333722A1 NATURAL LANGUAGE DIALOG FOR NARROWING DOWN INFORMATION SEARCH RESULTS 审中-公开
公开(公告)号：EP3333722A1
公开(公告)日：2018-06-13
申请号：EP17204036.2
申请日：2017-11-28
申请人： Panasonic Intellectual Property Management Co., Ltd.
发明人： YAMAGAMI, Katsuyoshi , ENDO, Mitsuru , USHIO, Takashi
IPC分类号： G06F17/27 , G06Q10/00 , G10L15/22 , G06F17/30
CPC分类号： G10L15/22 , G06F17/2785 , G06F17/3053 , G06F17/30684 , G10L15/265
摘要： An information processing method for information stored in a storage includes: holding a dialog history of a dialog including a question to a user and a reply from the user to the question, determining whether a manner in which a third reply indicating neither a first reply nor a second reply appears in a reply history of the reply included in the held dialog history satisfies a predetermined condition, the first reply indicating an affirmative in response to the question, the second reply indicating a negative in response to the question; and performing presentation regarding the information stored in the storage if the manner is determined to satisfy the predetermined condition.

3. 发明公开

EP3260996A1 DIALOGUE ACT ESTIMATION METHOD, DIALOGUE ACT ESTIMATION APPARATUS, AND STORAGE MEDIUM 审中-公开
标题翻译：对话行为评估方法，对话行为评估装置和存储介质
公开(公告)号：EP3260996A1
公开(公告)日：2017-12-27
申请号：EP17176522.5
申请日：2017-06-19
申请人： Panasonic Intellectual Property Management Co., Ltd.
发明人： USHIO, Takashi
IPC分类号： G06F17/30 , G06F17/27 , G06N3/04
CPC分类号： G10L15/063 , G06F17/279 , G06F17/30707 , G06N3/0445 , G10L15/08 , G10L15/16 , G10L15/1815 , G10L15/22 , G10L17/22 , G10L21/0272
摘要： A dialogue act estimation method, in a dialogue act estimation apparatus, includes acquiring first training data indicating, in a mutually associated manner, text data of a first sentence that can be a current uttered sentence, text data of a second sentence that can be an uttered sentence immediately previous to the first sentence, speaker change information indicating whether a speaker of the first sentence is the same as a speaker of the second sentence, and dialogue act information indicating a class of the first sentence, learning an association between the current uttered sentence and the dialogue act information by applying the first training data to a model, and storing a result of the learning as learning result information in a memory.
摘要翻译：在对话动作估计设备中的对话动作估计方法包括获取第一训练数据和第二训练数据，第一训练数据以相互关联的方式指示可以是当前发音句子的第一句子的文本数据，第二句子的文本数据可以是获取表示第一句子的说话者是否与第二句子的说话者相同的说话者改变信息以及指示第一句子的类别的对话行为信息;获取当前发出的话语通过将第一训练数据应用于模型，并将学习的结果作为学习结果信息存储在存储器中，从而生成句子和对话行为信息。

4. 发明公开

EP3258390A1 MEANING GENERATION METHOD, MEANING GENERATION APPARATUS, AND STORAGE MEDIUM 审中-公开
标题翻译：意义生成方法，意思是生成装置和存储介质
公开(公告)号：EP3258390A1
公开(公告)日：2017-12-20
申请号：EP17173957.6
申请日：2017-06-01
申请人： Panasonic Intellectual Property Management Co., Ltd.
发明人： USHIO, Takashi , YAMAGAMI, Katsuyoshi
IPC分类号： G06F17/27
CPC分类号： G10L15/063 , G06F17/2785 , G06N3/0445 , G10L15/16 , G10L15/1815
摘要： A meaning generation method, in a meaning generation apparatus, includes acquiring meaning training data including text data of a sentence that can be an utterance sentence and meaning information indicating a meaning of the sentence and associated with the text data of the sentence, acquiring restatement training data including the text data of the sentence and text data of a restatement sentence of the sentence, and learning association between the utterance sentence and the meaning information and the restatement sentence. The learning includes learning of a degree of importance of a word included in the utterance sentence, and the learning is performed by applying the meaning training data and the restatement training data to a common model, and storing a result of the learning as learning result information.
摘要翻译：意义生成设备中的意义生成方法包括：获取意义训练数据，该意义训练数据包括可以是发声语句的语句的文本数据和指示该语句的意义并且与该语句的文本数据相关联的意思信息;获取重述训练包括句子的文本数据和句子的重述句子的文本数据的数据，并且学习话语句子与意思信息和重述句子之间的关联。学习包括学习包括在发声句子中的单词的重要程度，并且通过将意义训练数据和重述训练数据应用于共同模型并将该学习结果存储为学习结果信息来执行学习。

5. 发明授权

EP3333729B1 INFORMATION PROCESSING METHOD, INFORMATION PROCESSING APPARATUS, AND RECORDING MEDIUM HAVING PROGRAM RECORDED THEREON 有权
公开(公告)号：EP3333729B1
公开(公告)日：2019-07-03
申请号：EP17204324.2
申请日：2017-11-29
申请人： Panasonic Intellectual Property Management Co., Ltd.
发明人： ENDO, Mitsuru , YAMAGAMI, Katsuyoshi , USHIO, Takashi
IPC分类号： G06F16/332

6. 发明公开

EP3282446A1 DIALOGUE ACT ESTIMATION METHOD, DIALOGUE ACT ESTIMATION APPARATUS, AND MEDIUM 有权
标题翻译：对话行为评估方法，对话行为评估装置和媒体
公开(公告)号：EP3282446A1
公开(公告)日：2018-02-14
申请号：EP17183949.1
申请日：2017-07-31
申请人： Panasonic Intellectual Property Management Co., Ltd.
发明人： USHIO, Takashi , SHI, Hongjie , ENDO, Mitsuru , YAMAGAMI, Katsuyoshi
IPC分类号： G10L15/18 , G06F17/27 , G10L17/04
CPC分类号： G06F17/2755 , G06F17/2785 , G06F17/279 , G06N3/0445 , G06N3/0454 , G06N99/005 , G10L15/1822 , G10L17/04 , G10L21/0272
摘要： A dialogue act estimation method includes acquiring learning data including a first sentence to be estimated in the form of text data of a first uttered sentence uttered at a first time point, a second sentence which is text data of a second uttered sentence uttered, at a time point before the first time point, successively after the first uttered sentence, act information indicating an act associated to the first sentence, property information indicating a property information associated to the first sentence, and dialogue act information indicating a dialogue act in the form of a combination of an act and a property associated to the first sentence, making a particular model learn three or more tasks at the same time using the learning data, and storing a result of the learning as learning result information in a memory.
摘要翻译：一种对话动作估计方法，包括：获取学习数据，所述学习数据包括以第一时间点发出的第一发音句子的文本数据的形式被估计的第一句子和作为发出的第二发音句子的文本数据的第二句子，在第一时间点之前的时间点，连续地在第一发音句子之后的时间点，指示与第一句子相关联的动作的动作信息，指示与第一句子相关联的属性信息的属性信息以及指示对话动作的对话动作信息将与第一句子相关联的动作和属性的组合，使得特定模型使用学习数据同时学习三个或更多个任务，并将学习的结果作为学习结果信息存储在存储器中。

7. 发明公开

EP3144860A2 SUBJECT ESTIMATION SYSTEM FOR ESTIMATING SUBJECT OF DIALOG 审中-公开
标题翻译： UR S S S S S S S S S S S S S S S
公开(公告)号：EP3144860A2
公开(公告)日：2017-03-22
申请号：EP16187517.4
申请日：2016-09-07
申请人： Panasonic Intellectual Property Management Co., Ltd.
发明人： SHI, Hongjie , USHIO, Takashi , ENDO, Mitsuru , YAMAGAMI, Katsuyoshi
IPC分类号： G06N3/04 , G06F17/20
CPC分类号： G10L15/16 , G06F17/2785 , G06N3/0454 , G10L15/063 , G10L2015/0635
摘要： A subject estimation system includes a convolutional neural network to estimate a subject label of a dialog. The convolution neural network includes: one or more topic-dependent convolutional layers and one topic-independent convolutional layer, each of the one or more topic-dependent convolutional layers performing, on an input of a word-string vector sequence corresponding to dialog text transcribed from a dialog, a convolution operation dependent on a topic, and the topic-independent convolutional layer performing, on the input of the word-string vector sequence, a convolution operation not dependent on the topic; a pooling layer performing pooling process on outputs of the convolutional layer; and a fully connected layer performing full connection process on outputs of the pooling layer.
摘要翻译：主题估计系统包括用于估计对话的主题标签的卷积神经网络。卷积神经网络包括：一个或多个主题依赖卷积层和一个话题独立卷积层，一个或多个主题依赖卷积层中的每一个在对应于对话文本的字串向量序列的输入上执行转录从对话，取决于主题的卷积运算，以及话题独立卷积层，在字串向量序列的输入上执行不依赖于该主题的卷积运算; 汇集层对卷积层的输出执行池化处理; 以及完全连接的层在池层的输出上执行完全连接处理。

8. 发明授权

EP3282446B1 DIALOGUE ACT ESTIMATION METHOD, DIALOGUE ACT ESTIMATION APPARATUS, AND MEDIUM 有权
公开(公告)号：EP3282446B1
公开(公告)日：2019-02-20
申请号：EP17183949.1
申请日：2017-07-31
申请人： Panasonic Intellectual Property Management Co., Ltd.
发明人： USHIO, Takashi , SHI, Hongjie , ENDO, Mitsuru , YAMAGAMI, Katsuyoshi
IPC分类号： G10L15/18 , G06F17/27 , G10L17/04 , G06N3/02

9. 发明公开

EP3144860A3 SUBJECT ESTIMATION SYSTEM FOR ESTIMATING SUBJECT OF DIALOG 审中-公开
标题翻译：对话对象评估的主体评估系统
公开(公告)号：EP3144860A3
公开(公告)日：2017-04-05
申请号：EP16187517.4
申请日：2016-09-07
申请人： Panasonic Intellectual Property Management Co., Ltd.
发明人： SHI, Hongjie , USHIO, Takashi , ENDO, Mitsuru , YAMAGAMI, Katsuyoshi
IPC分类号： G06N3/04 , G06F17/20
CPC分类号： G10L15/16 , G06F17/2785 , G06N3/0454 , G10L15/063 , G10L2015/0635
摘要： A subject estimation system includes a convolutional neural network to estimate a subject label of a dialog. The convolution neural network includes: one or more topic-dependent convolutional layers and one topic-independent convolutional layer, each of the one or more topic-dependent convolutional layers performing, on an input of a word-string vector sequence corresponding to dialog text transcribed from a dialog, a convolution operation dependent on a topic, and the topic-independent convolutional layer performing, on the input of the word-string vector sequence, a convolution operation not dependent on the topic; a pooling layer performing pooling process on outputs of the convolutional layer; and a fully connected layer performing full connection process on outputs of the pooling layer.
摘要翻译：主题估计系统包括用于估计对话的主题标签的卷积神经网络。卷积神经网络包括：一个或多个与主题相关的卷积层和一个与主题无关的卷积层，一个或多个主题相关卷积层中的每一个在与对话文本相对应的字串向量序列的输入上执行转录从对话开始，取决于主题的卷积操作，以及与主题无关的卷积层在字串向量序列的输入上执行不依赖于主题的卷积操作; 合并层对卷积层的输出执行合并处理; 以及在连接层的输出上执行全连接处理的完全连接层。

10. 发明公开

EP3333729A1 INFORMATION PROCESSING METHOD, INFORMATION PROCESSING APPARATUS, AND RECORDING MEDIUM HAVING PROGRAM RECORDED THEREON 有权
公开(公告)号：EP3333729A1
公开(公告)日：2018-06-13
申请号：EP17204324.2
申请日：2017-11-29
申请人： Panasonic Intellectual Property Management Co., Ltd.
发明人： ENDO, Mitsuru , YAMAGAMI, Katsuyoshi , USHIO, Takashi
IPC分类号： G06F17/30
CPC分类号： H04L51/046 , G06F3/0482 , G06F16/3329 , G06F16/3338 , G06F17/243 , H04L51/02 , H04L65/40 , H04L67/30 , H04L67/325
摘要： In an information processing method, display of a question and acquisition of an answer from a user to the question are repeated to narrow down information the user desires to make a search. A question regarding a target of the search is displayed in a first mode on a display included in a terminal. An answer inputted from the user to the question is acquired through the terminal When the question is displayed, first information regarding a situation of a narrowing-down progress is displayed above the question in a second mode, and second information regarding a guide for answering the question is displayed below the question in a third mode,

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式