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

US11200509B2 Method for processing information by intelligent agent and intelligent agent 有权
公开(公告)号：US11200509B2
公开(公告)日：2021-12-14
申请号：US15196932
申请日：2016-06-29
申请人： Huawei Technologies Co., Ltd.
发明人： Qiang Yang , Yangqiu Song , Wing Ki Leung , Zhengdong Lu
IPC分类号： G06N20/00 , G06F16/2458 , G06N5/04 , G06N5/02
摘要： A method for processing information by an intelligent agent and the intelligent agent, where the method comprises: a first intelligent agent sends a request message to a second intelligent agent, where the request message includes an invitation message or a recommendation message; the first intelligent agent receives a decision message fed back by the second intelligent agent, where the decision message is determined according to the invitation message or the recommendation message and a knowledge model of the second intelligent agent; and the first intelligent agent updates, according to the decision message, a knowledge model of the first intelligent agent or sends a notification message to a first user account corresponding to the first intelligent agent. By using these technical solutions, information on a social network may be learned and processed by means of interaction with another intelligent agent, thereby implementing mining of data on the social network.

2. 发明申请

US20190179905A1 SEQUENCE CONVERSION METHOD AND APPARATUS IN NATURAL LANGUAGE PROCESSING 审中-公开
公开(公告)号：US20190179905A1
公开(公告)日：2019-06-13
申请号：US16276627
申请日：2019-02-15
申请人： HUAWEI TECHNOLOGIES CO.,LTD.
发明人： Zhaopeng Tu , Xiaohua Liu , Zhengdong Lu , Hang Li
IPC分类号： G06F17/27
摘要： The present application relates to natural language processing and discloses a sequence conversion method. The method includes: obtaining a source sequence from an input signal; converting the source sequence into one or more source context vectors; obtaining a target context vector corresponding to each source context vector; combining the target context vectors to obtain the target sequence; and outputting the target sequence. A weight vector is applied on a source context vector and a reference context vector, to obtain a target context vector. The source sequence and the target sequence are representations of natural language contents. The claimed process improves faithfulness of converting the source sequence to the target sequence.

3. 发明授权

US11449678B2 Deep learning based dialog method, apparatus, and device 有权
公开(公告)号：US11449678B2
公开(公告)日：2022-09-20
申请号：US16369579
申请日：2019-03-29
申请人： HUAWEI TECHNOLOGIES CO., LTD.
发明人： Zhengdong Lu , Shan He , Qiang Jiang
IPC分类号： G06F40/30 , G06F16/00 , G06N99/00 , G06F40/35 , G06F40/56 , G06F40/216 , G06F16/2455 , G06N3/08
摘要： A deep learning based dialog method, apparatus, and device are provided and belong to the field of artificial intelligence. The method includes: obtaining a to-be-replied statement, encoding the to-be-replied statement to obtain a first vector , where the first vector is a representation of the to-be-replied statement; obtaining dialog history information corresponding to the to-be-replied statement, and the attention vector is used to represent search intent; making each dialog statement interact with the attention vector, so as to extract information related to the search intent from the dialog statement to obtain a plurality of result vectors, generating a to-be-decoded vector based on the plurality of result vectors, and decoding the to-be-decoded vector to obtain a next word in the reply statement. In the method, the reply statement refers to a dialog history.

4. 发明授权

US10467342B2 Method and apparatus for determining semantic matching degree 有权
公开(公告)号：US10467342B2
公开(公告)日：2019-11-05
申请号：US15087065
申请日：2016-03-31
申请人： Huawei Technologies Co., Ltd.
发明人： Zhengdong Lu , Hang Li
IPC分类号： G06F17/27 , G06N3/04 , G06F16/36
摘要： A method and an apparatus for determining a semantic matching degree. The method includes acquiring a first sentence and a second sentence, dividing the first sentence and the second sentence into x and y sentence fragments, respectively, performing a convolution operation on word vectors in each sentence fragment of the first sentence and word vectors in each sentence fragment of the second sentence, to obtain a three-dimensional tensor, performing integration and/or screening on adjacent vectors in the one-dimensional vectors of x rows and y columns, until the three-dimensional tensor is combined into a one-dimensional target vector, and determining a semantic matching degree between the first sentence and the second sentence according to the target vector.

5. 发明申请

US20160307117A1 METHOD FOR PROCESSING INFORMATION BY INTELLIGENT AGENT AND INTELLIGENT AGENT 审中-公开
标题翻译：智能代理和智能代理处理信息的方法
公开(公告)号：US20160307117A1
公开(公告)日：2016-10-20
申请号：US15196932
申请日：2016-06-29
申请人： Huawei Technologies Co., Ltd.
发明人： Qiang Yang , Yangqiu Song , Wing Ki Leung , Zhengdong Lu
IPC分类号： G06N99/00 , G06F17/30 , G06N5/02
CPC分类号： G06N20/00 , G06F16/2465 , G06N5/022 , G06N5/043
摘要： A method for processing information by an intelligent agent and the intelligent agent, where the method comprises: a first intelligent agent sends a request message to a second intelligent agent, where the request message includes an invitation message or a recommendation message; the first intelligent agent receives a decision message fed back by the second intelligent agent, where the decision message is determined according to the invitation message or the recommendation message and a knowledge model of the second intelligent agent; and the first intelligent agent updates, according to the decision message, a knowledge model of the first intelligent agent or sends a notification message to a first user account corresponding to the first intelligent agent. By using these technical solutions, information on a social network may be learned and processed by means of interaction with another intelligent agent, thereby implementing mining of data on the social network.
摘要翻译：一种智能代理和智能代理处理信息的方法，所述方法包括：第一智能代理向第二智能代理发送请求消息，其中所述请求消息包括邀请消息或推荐消息; 第一智能代理接收由第二智能代理反馈的判定消息，其中根据邀请消息或推荐消息确定判定消息，以及第二智能代理的知识模型; 并且所述第一智能代理根据所述判定消息，更新所述第一智能代理的知识模型，或者向与所述第一智能代理对应的第一用户账户发送通知消息。通过使用这些技术解决方案，可以通过与另一智能代理的交互来学习和处理关于社交网络的信息，从而实现社交网络上的数据挖掘。

6. 发明申请

US20160217129A1 Method and Apparatus for Determining Semantic Matching Degree 审中-公开
标题翻译：用于确定语义匹配度的方法和装置
公开(公告)号：US20160217129A1
公开(公告)日：2016-07-28
申请号：US15087065
申请日：2016-03-31
申请人： Huawei Technologies Co., Ltd.
发明人： Zhengdong Lu , Hang Li
IPC分类号： G06F17/27
CPC分类号： G06F17/2785 , G06F16/36 , G06F17/277 , G06N3/0454
摘要： A method and an apparatus for determining a semantic matching degree. The method includes acquiring a first sentence and a second sentence, dividing the first sentence and the second sentence into x and y sentence fragments, respectively, performing a convolution operation on word vectors in each sentence fragment of the first sentence and word vectors in each sentence fragment of the second sentence, to obtain a three-dimensional tensor, performing integration and/or screening on adjacent vectors in the one-dimensional vectors of x rows and y columns, until the three-dimensional tensor is combined into a one-dimensional target vector, and determining a semantic matching degree between the first sentence and the second sentence according to the target vector.
摘要翻译：一种用于确定语义匹配度的方法和装置。该方法包括获取第一句和第二句，分别将第一句和第二句分成x和y句片段，对第一句的每个句片段中的字矢量进行卷积运算，并在每个句中使用字向量第二句的片段，以获得三维张量，对x行和y列的一维向量中的相邻向量进行整合和/或筛选，直到三维张量被组合成一维目标向量，并根据目标向量确定第一句和第二句之间的语义匹配度。

7. 发明授权

US12073334B2 Human-computer dialogue method and apparatus 有权
公开(公告)号：US12073334B2
公开(公告)日：2024-08-27
申请号：US17577713
申请日：2022-01-18
申请人： Huawei Technologies Co., Ltd.
发明人： Lifeng Shang , Zhengdong Lu , Hang Li
IPC分类号： G06N5/043 , G06F16/33 , G06F16/332 , G06F40/35 , G10L13/08 , G10L15/22 , H04L51/02
CPC分类号： G06N5/043 , G06F16/3329 , G06F16/3344 , G06F40/35 , G10L13/08 , G10L15/22 , H04L51/02 , G10L2015/225 , G10L2015/228
摘要： A method includes: obtaining a text entered by a user; determining at least one topic related to the text; determining a target dialogue robot from the plurality of dialogue robots based on the at least one topic related to the text and a predefined mapping relationship between a dialogue robot and a topic, where a target topic corresponding to the target dialogue robot is some or all of the at least one topic related to the text; allocating the text to the target dialogue robot; and obtaining a reply for the text from the target dialogue robot, where the reply is generated by the target dialogue robot based on at least one semantic understanding of the text.

8. 发明授权

US11288458B2 Sequence conversion method and apparatus in natural language processing based on adjusting a weight associated with each word 有权
公开(公告)号：US11288458B2
公开(公告)日：2022-03-29
申请号：US16276627
申请日：2019-02-15
申请人： HUAWEI TECHNOLOGIES CO., LTD.
发明人： Zhaopeng Tu , Xiaohua Liu , Zhengdong Lu , Hang Li
IPC分类号： G10L15/16 , G10L15/22 , G06F3/16 , G10L15/30 , G06F40/30 , G06F40/44 , G06F40/268 , G06F40/289
摘要： The present application relates to natural language processing and discloses a sequence conversion method. The method includes: obtaining a source sequence from an input signal; converting the source sequence into one or more source context vectors; obtaining a target context vector corresponding to each source context vector; combining the target context vectors to obtain the target sequence; and outputting the target sequence. A weight vector is applied on a source context vector and a reference context vector, to obtain a target context vector, wherein the weight of one or more elements in the source context vector associated with notional words or weight of a function word in the target context vector is increased. The source sequence and the target sequence are representations of natural language contents. The claimed process improves faithfulness of converting the source sequence to the target sequence.

9. 发明申请

US20200081909A1 Multi-Document Summary Generation Method and Apparatus, and Terminal 审中-公开
公开(公告)号：US20200081909A1
公开(公告)日：2020-03-12
申请号：US16688090
申请日：2019-11-19
申请人： Huawei Technologies Co., Ltd.
发明人： Piji Li , Zhengdong Lu , Hang Li
IPC分类号： G06F16/34 , G06N20/00 , G06F17/16 , G06F17/27
摘要： A multi-document summary generation method includes obtaining a candidate sentence set, training each candidate sentence in the candidate sentence set using a cascaded attention mechanism and an unsupervised learning model in a preset network model, to obtain importance of each candidate sentence, selecting, based on the importance of each candidate sentence, a phrase that meets a preset condition from the candidate sentence set as a summary phrase set, and obtaining a summary of a plurality of candidate documents based on the summary phrase set.

10. 发明申请

US20190341021A1 Human-Computer Dialogue Method and Apparatus 审中-公开
公开(公告)号：US20190341021A1
公开(公告)日：2019-11-07
申请号：US16514683
申请日：2019-07-17
申请人： Huawei Technologies Co., Ltd.
发明人： Lifeng Shang , Zhengdong Lu , Hang Li
IPC分类号： G10L13/08 , G06F17/27 , G10L15/22 , G06N5/04 , G06F16/332
摘要： An apparatus is pre-equipped with a plurality of dialogue robots, and each dialogue robot is configured to conduct a human-computer dialogue based on at least one topic. The method includes: obtaining a text entered by a user; determining at least one topic related to the text, and determining a target dialogue robot from the plurality of dialogue robots based on the at least one topic related to the text and a predefined mapping relationship between a dialogue robot and a topic, where a target topic corresponding to the target dialogue robot is some or all of the at least one topic related to the text; and allocating the text to the target dialogue robot and obtaining a reply for the text from the target dialogue robot, where the reply is generated by the target dialogue robot based on at least one semantic understanding of the text.

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