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. 发明申请

US20170199928A1 METHOD AND DEVICE FOR PARSING QUESTION IN KNOWLEDGE BASE 审中-公开
公开(公告)号：US20170199928A1
公开(公告)日：2017-07-13
申请号：US15472279
申请日：2017-03-29
申请人： HUAWEI TECHNOLOGIES CO., LTD. , INSTITUTE OF AUTOMATION, CHINESE ACADEMY OF SCIENCES
发明人： Jun Zhao , Kang Liu , Shizhu He , Yibo Zhang
IPC分类号： G06F17/30 , G06N99/00 , G06F17/27 , G06F17/11
摘要： A method for parsing a question in a knowledge base includes: receiving a question entered by a user; performing phrase detection on the question to determine candidate phrases; mapping the candidate phrases to resource items in the knowledge base; further determining values of observed predicates and possible question parse spaces; performing uncertain inference on each proposition set in the possible question parse spaces according to the values of the observed predicates and values of hidden predicates, and calculating confidence; acquiring a combination of true propositions in a proposition set whose confidence satisfies a preset condition; generating a formal query statement according to the combination of true propositions.

2. 发明授权

US10706084B2 Method and device for parsing question in knowledge base 有权
公开(公告)号：US10706084B2
公开(公告)日：2020-07-07
申请号：US15472279
申请日：2017-03-29
申请人： HUAWEI TECHNOLOGIES CO., LTD. , Institute of Automation, Chinese Academy of Sciences
发明人： Jun Zhao , Kang Liu , Shizhu He , Yibo Zhang
IPC分类号： G06F16/00 , G06F16/332 , G06N20/00 , G06F16/242 , G06F16/901 , G06F16/2457 , G06N5/04 , G06F16/2452 , G06F40/268 , G06F40/289 , G06F17/11 , G06N7/00
摘要： A method for parsing a question in a knowledge base includes: receiving a question entered by a user; performing phrase detection on the question to determine candidate phrases; mapping the candidate phrases to resource items in the knowledge base; further determining values of observed predicates and possible question parse spaces; performing uncertain inference on each proposition set in the possible question parse spaces according to the values of the observed predicates and values of hidden predicates, and calculating confidence; acquiring a combination of true propositions in a proposition set whose confidence satisfies a preset condition; generating a formal query statement according to the combination of true propositions.

3. 发明申请

US20210383798A1 Human-Computer Interaction Method and Electronic Device 有权
公开(公告)号：US20210383798A1
公开(公告)日：2021-12-09
申请号：US17284122
申请日：2018-10-10
申请人： Huawei Technologies Co., Ltd.
发明人： Qing Zhang , Jinhui Zhang , Yibo Zhang
IPC分类号： G10L15/18 , G06F16/332 , G06F40/279 , G06F40/30
摘要： This application relates to the field of communications technologies, and provides a human-computer interaction method and an electronic device, to help accurately recognize a user intention, meet a user requirement, and improve user experience. The method specifically includes: In a human-computer dialog interaction process, when a server performs slot extraction on user discourse, if there is a slot corresponding to which information fails to be extracted and the slot is an optional key slot, the server asks the user a question, to determine whether the information corresponding to the slot is necessary. If the information is necessary, the server further extracts the information corresponding to the slot. If the information is unnecessary, the server does not extract the information corresponding to the slot.

4. 发明申请

US20160117405A1 Information Processing Method and Apparatus 审中-公开
标题翻译：信息处理方法与装置
公开(公告)号：US20160117405A1
公开(公告)日：2016-04-28
申请号：US14988959
申请日：2016-01-06
申请人： Huawei Technologies Co., Ltd.
发明人： Jie Zhang , Yibo Zhang
IPC分类号： G06F17/30 , H04L29/06
CPC分类号： G06F16/9535 , G06F16/235 , G06F16/2358 , G06F16/24573 , G06F16/24575 , G06F16/951 , G06Q50/01 , H04L65/403
摘要： Information processing method and apparatus relating to the field of communications and information processing technologies is presented. The method and apparatus can include acquiring a search criterion entered by a user, where the search criterion includes a name of an entity and selecting, according to the name of the entity, a target triplet including the name of the entity from a knowledge base that is created in advance, where the target triplet further includes an attribute of the entity and an attribute value of the attribute, and displaying the name of the entity, the attribute of the entity, and the attribute value of the attribute.
摘要翻译：介绍了与通信和信息处理技术领域相关的信息处理方法和设备。该方法和装置可以包括获取由用户输入的搜索标准，其中搜索标准包括实体的名称，并且根据实体的名称选择包括来自知识库的实体的名称的目标三元组，事先创建，其中目标三元组还包括实体的属性和属性的属性值，并且显示实体的名称，实体的属性和属性的属性值。

5. 发明授权

US08892671B2 Message processing method, terminal and system 有权
公开(公告)号：US08892671B2
公开(公告)日：2014-11-18
申请号：US14145262
申请日：2013-12-31
申请人： Huawei Technologies Co., Ltd.
发明人： Yibo Zhang , Baofeng Zhang
IPC分类号： G06F15/16 , H04L12/58
摘要： A message processing method, terminal and system. The method includes: obtaining a user's historical message interaction information and first context data associated with the user's historical message interaction information, where the user's historical message interaction information includes historical message interaction content and historical message replying status; determining the user's message interaction preferences according to the user's historical message interaction information and the first context data, where the message interaction preferences include a message reply policy and/or a message writing style; receiving a current message sent to the user, and obtaining second context data associated with the current message; and replying to the current message according to the message interaction preferences, the current message, and the second context data. With the present invention, the user's message interaction preferences are determined, and the current message can be replied automatically, thereby enhancing user experience.

6. 发明申请

US20220208182A1 Semantic Parsing Method and Server 有权
公开(公告)号：US20220208182A1
公开(公告)日：2022-06-30
申请号：US17607657
申请日：2020-04-22
申请人： Huawei Technologies Co., Ltd.
发明人： Qing Zhang , Wei Yang , Lianghe Zhang , Yibo Zhang
IPC分类号： G10L15/18 , G10L15/30 , G10L15/22 , G06F40/30 , G06F40/279 , G10L15/07
摘要： A semantic parsing method includes extracting, by a first server, a first entity of a first slot from a first user sentence, modifying the first entity to a second entity of a second slot when the first entity is a pronoun, sending a first server request to a second server, and obtaining a first service result from the second server in response to the first service request. The first service request includes indication information of a first intention and the first entity, the second server is an application server that provides a first skill, and the first service result is based on the first intention and the first entity. The first server returns the first service result to a device to output by the device.

7. 发明授权

US10230668B2 Information replying method and apparatus 有权
公开(公告)号：US10230668B2
公开(公告)日：2019-03-12
申请号：US15163337
申请日：2016-05-24
申请人： Huawei Technologies Co., Ltd.
发明人： Zongcheng Ji , Yibo Zhang , Hang Li
IPC分类号： G06F17/27 , G06F17/30 , H04L12/58 , G06N99/00
摘要： The information replying method includes: receiving to-be-replied information, where the to-be-replied information includes text content and contact information; searching a database for corresponding dialog style information according to the text content and the contact information; performing preprocessing on the text content, where the preprocessing includes word segmentation processing and stop word removal processing; and searching, according to data that has undergone the preprocessing, the database corresponding to the dialog style information, to determine reply information.

8. 发明申请

US20160306891A1 METHOD AND APPARATUS FOR DISCOVERING CLOSELY RELATED USER 审中-公开
标题翻译：发现相关用户的方法和装置
公开(公告)号：US20160306891A1
公开(公告)日：2016-10-20
申请号：US15195928
申请日：2016-06-28
申请人： Huawei Technologies Co., Ltd.
发明人： Huafei Li , Yibo Zhang
IPC分类号： G06F17/30 , H04L29/08
CPC分类号： G06F17/30867 , G06F17/3053 , G06Q50/01 , H04L67/22
摘要： Embodiments of the present invention provide a method and an apparatus for discovering a closely related user. The method includes: acquiring first data of a first user on social media and second data of a second user on the social media, where the second user is a user following the first user and/or a user followed by the first user; then, establishing a user model of the first user according to the first data and the second data; then, acquiring third data of a third user in social media, where the third user and the first user do not follow each other; afterward, performing matching between the third data and the user model to perform calculation, to obtain a matching result; and finally, if the matching result is greater than a preset value, determining that the third user is a closely related user of the first user.
摘要翻译：本发明的实施例提供了一种用于发现密切相关的用户的方法和装置。该方法包括：在社交媒体上获取社交媒体上的第一用户的第一数据和社交媒体上的第二用户的第二数据，其中第二用户是跟随第一用户的用户和/或跟随第一用户的用户; 然后根据第一数据和第二数据建立第一用户的用户模型; 然后，在社交媒体中获取第三用户的第三数据，其中第三用户和第一用户不相互依赖; 之后，执行第三数据和用户模型之间的匹配以进行计算，以获得匹配结果; 最后，如果匹配结果大于预设值，则确定第三用户是第一用户的密切相关的用户。

9. 发明申请

US20160117595A1 INFORMATION RECOMMENDATION METHOD AND APPARATUS IN SOCIAL MEDIA 审中-公开
标题翻译：信息建议方法和社会媒体的设备
公开(公告)号：US20160117595A1
公开(公告)日：2016-04-28
申请号：US14991651
申请日：2016-01-08
申请人： Huawei Technologies Co., Ltd.
发明人： Jie Zhang , Yibo Zhang , Hang Li
IPC分类号： G06N5/04 , G06N99/00
摘要： The present invention provides an information recommendation method and apparatus in a social media. An off-line procedure includes: determining a point of interest of a target user; selecting information related to the point of interest as an annotated corpus; and training an interest classification model of the target user by using the annotated corpus as a training sample. An on-line procedure includes: inputting to-be-recommended information to the interest classification model of the target user, so as to determine whether the to-be-recommended information tallies with an interest of the target user; and if the to-be-recommended information tallies with the interest of the target user, recommending the to-be-recommended information to the target user. According to the present invention, an effect of information recommendation in a social media can be improved.
摘要翻译：本发明提供社交媒体中的信息推荐方法和装置。离线过程包括：确定目标用户的兴趣点; 选择与兴趣点相关的信息作为注释语料库; 并通过使用注释语料库作为训练样本来训练目标用户的兴趣分类模型。在线程序包括：向目标用户的兴趣分类模型输入被推荐的信息，以便确定所建议的信息是否符合目标用户的兴趣; 并且如果要被推荐的信息符合目标用户的兴趣，则向目标用户推荐待建议的信息。根据本发明，可以提高社交媒体中的信息推荐效果。

10. 发明授权

US09195842B2 Information processing method, apparatus, and system 有权
标题翻译：信息处理方法，装置和系统
公开(公告)号：US09195842B2
公开(公告)日：2015-11-24
申请号：US14317182
申请日：2014-06-27
申请人： Huawei Technologies Co., Ltd.
发明人： Wenyang Zang , Yibo Zhang
IPC分类号： G06F17/30 , G06F21/62 , H04L12/58 , G06Q10/10 , H04L29/06
CPC分类号： G06F21/62 , G06F21/6245 , G06F2221/2113 , G06Q10/107 , H04L51/12 , H04L51/14 , H04L63/0245 , H04L63/105
摘要： The present invention relates to an information processing method, apparatus, and system. The method includes: receiving text information; performing calculation on the text information by using a first model to obtain a public sensitivity weight value corresponding to the text information; determining whether the public sensitivity weight value is greater than a first preset threshold; and if yes, displaying first processing prompt information indicating that the text information includes sensitive information; if no, performing calculation on the text information by using a second model to obtain an individual sensitivity weight value corresponding to the text information; and determining whether the individual sensitivity weight value is greater than a second preset threshold; and if yes, displaying second processing prompt information indicating that the text information includes sensitive information. The present invention enables a terminal to automatically detect whether text information involves sensitive information, thereby improving security of a crowdsourcing application.
摘要翻译：信息处理方法，装置和系统技术领域本发明涉及信息处理方法，装置和系统。该方法包括：接收文本信息; 通过使用第一模型对文本信息执行计算，以获得与文本信息相对应的公共敏感度权重值; 确定所述公共灵敏度权重值是否大于第一预设阈值; 如果是，则显示指示文本信息包括敏感信息的第一处理提示信息; 如果否，则通过使用第二模型对文本信息进行计算，以获得与文本信息相对应的个人灵敏度权重值; 以及确定所述个人灵敏度权重值是否大于第二预设阈值; 如果是，则显示指示文本信息包括敏感信息的第二处理提示信息。本发明使得终端能够自动检测文本信息是否涉及敏感信息，从而提高众包应用的安全性。

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