专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

61. 发明专利

KR20210024861A KR20210024861A - Electronic apparatus and method for providing conversation service 审中-公开
公开(公告)号：KR20210024861A
公开(公告)日：2021-03-08
申请号：KR1020190104573A
申请日：2019-08-26
申请人： 삼성전자주식회사
发明人： 함진아 , 이강욱 , 김수필 , 박예원 , 최원종
IPC分类号： G06F16/332 , G06F16/33 , G06F40/40 , G06K9/00 , G10L15/22 , H04L12/58
CPC分类号： G10L15/22 , G06F16/3329 , G10L15/1822 , G06F16/24575 , G06F16/3343 , G06F16/3346 , G06F40/30 , G06F40/40 , G06K9/00221 , G06K9/00288 , G10L15/02 , G10L15/1815 , G10L15/197 , G10L15/25 , G10L15/30 , H04L51/02 , G10L2015/025 , G10L2015/223
摘要： 일 실시 예에 따른 전자 디바이스가 대화 서비스를 제공하는 방법은, 사용자의 발화 입력을 수신하는 단계, 상기 발화 입력으로부터 획득된 텍스트로부터 시간을 나타내는 시간 표현을 식별하는 단계, 상기 시간 표현에 기초하여 상기 발화 입력에 관련된 시점을 결정하는 단계, 상기 대화 서비스를 이용한 상기 사용자의 대화 이력에 관한 정보를 저장하는 복수의 데이터베이스들 중에서, 상기 발화 입력에 관련된 시점에 대응하는 데이터베이스를 선택하는 단계, 상기 선택된 데이터베이스로부터 획득되는 상기 사용자의 대화 이력에 관한 정보에 기초하여 상기 텍스트를 해석하는 단계, 상기 해석 결과에 기초하여 상기 수신된 발화 입력에 대한 응답 메시지를 생성하는 단계, 및 상기 생성된 응답 메시지를 출력하는 단계를 포함할 수 있다.

62. 发明申请

WO2019139718A1 CONTEXT-SENSITIVE METHODS OF SURFACING COMPREHENSIVE KNOWLEDGE IN AND BETWEEN APPLICATIONS 审中-公开
公开(公告)号：WO2019139718A1
公开(公告)日：2019-07-18
申请号：PCT/US2018/065308
申请日：2018-12-13
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： KOHLMEIER, Bernhard S. J. , TAYLOR, Douglas Maxwell , POZNANSKI, Victor
IPC分类号： G06F16/2457 , G06F16/953
CPC分类号： G06F16/24575 , G06F16/24578 , G06F16/248 , G06F16/284 , G06F16/953 , G06F16/9535
摘要： Context from a content creation application is used to focus both on the types of files and the types of content searched by a search application, as well as the type of results provided to the content creation application for use by the user, instead of simply improving relevancy of a result. A query of structured, contextual information can be formulated based on the discernable intent and context information provided with the request. Queries are sent to search applications to search appropriate file types and/or content types. Context-sensitive results returned from the search application(s) can be grouped by performing a clustering process according to semantic similarity in order to group the context-sensitive results into groups, and selected ones of the context-sensitive results can be provided to a user.

63. 发明申请

WO2019135986A1 METHOD AND APPARATUS FOR CHARACTERIZING AND DETERMINING RELATIONSHIPS BETWEEN ITEMS AND MOMENTS 审中-公开
公开(公告)号：WO2019135986A1
公开(公告)日：2019-07-11
申请号：PCT/US2018/067816
申请日：2018-12-28
申请人： CORAVIN, INC.
发明人： SILVAIN, Francois Claude Raoul
IPC分类号： G06Q30/06 , G06Q30/02
CPC分类号： G06F16/24575 , G06F16/24578 , G06Q30/0278 , G06Q30/0631
摘要： A moment engine is arranged to characterize and/or determine relationships between items, such as a wine, or moments, such as an event, emotional experience and/or an activity. Characteristics for the items or moments may be used to define how the items or moments relate to a two-dimensional grid, e.g., to allow the items or moments to be displayed on an X- Y grid. Relationships between items and/or moments can be determined based on the item/moment characterization on the X-Y grid, e.g., to allow for the recommendation of an item for a particular moment, or the recommendation of a moment for a particular item.

64. 发明申请

WO2019118254A1 CHATBOT INTEGRATING DERIVED USER INTENT 审中-公开
公开(公告)号：WO2019118254A1
公开(公告)日：2019-06-20
申请号：PCT/US2018/064147
申请日：2018-12-06
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： WU, Xianchao , TOMITA, Kyohei , FUJIWARA, Keizo
IPC分类号： G06F17/27
CPC分类号： G06N7/005 , G06F16/24575 , G06F17/2785 , H04L51/02
摘要： A method provides information to a user as a function of derived user intent. The method includes receiving input from a user, generating an intent vector by processing the received input though an artificial intelligence model that has been trained with data representative of the user's intention, wherein the intent vector comprises a probability for each intent in a known set of possible intents, executing a trigger control model to determine whether to respond to the user as a function of the input from the user and the intent vector, utilizing the trigger control model, received input, and intent vector input to generate a response via a trained chatbot, and providing the response via an output device.

65. 发明申请

WO2019060351A1 SYSTEM AND METHOD FOR UTILIZING MEMORY-EFFICIENT DATA STRUCTURES FOR EMOJI SUGGESTIONS 审中-公开
公开(公告)号：WO2019060351A1
公开(公告)日：2019-03-28
申请号：PCT/US2018/051643
申请日：2018-09-19
申请人： MZ IP HOLDINGS, LLC
发明人： WANG, Pidong , KANNAN, Shivasankari , BOJJA, Nikhil
IPC分类号： G06F17/22 , G06F17/27
CPC分类号： G06F16/24575 , G06F3/04817 , G06F3/0482 , G06F9/451 , G06F16/2246 , G06F16/248 , G06F17/2205 , G06F17/2217 , G06F17/2735 , G06F17/276
摘要： Implementations of the present disclosure are directed to a method, a system, and an article for suggesting emojis in electronic communication. An example method can include: providing a trie data structure on a client device, the trie data structure storing a dictionary and including a plurality of nodes, wherein at least one node in the trie data structure includes a children array including at least one of: an integer index for identifying a child node; and an array size corresponding to a number of child nodes for the at least one node; and detecting, by the client device, at least one character entered by a user in a user interface of the client device; identifying, using the trie data structure, at least one emoji corresponding to the at least one character; and presenting the at least one emoji in the user interface for user selection.

66. 发明申请

WO2018075372A1 PROJECT ENTITY EXTRACTION WITH EFFICIENT SEARCH AND PROCESSING OF PROJECTS 审中-公开
标题翻译：有效搜索和项目处理的项目实体提取
公开(公告)号：WO2018075372A1
公开(公告)日：2018-04-26
申请号：PCT/US2017/056701
申请日：2017-10-16
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： SOMECH, Haim , PRINESS, Ido , DOTAN-COHEN, Dikla
IPC分类号： G06F17/30 , G06Q10/06
CPC分类号： G06Q10/063118 , G06F16/24575 , G06F16/285 , G06F16/95 , G06Q10/06 , G06Q10/06311 , H04L47/826 , H04L67/22
摘要： Systems and methods are provided for associating project entities with projects. In various implementations, user activity data is monitored based on sensor data from at least one user device associated with a user. From the monitored user activity data, entity features are determined of project entities corresponding to the user activity data. Time slots are extracted from the project entities. The time slots are clustered based the entity features of ones of the project entities corresponding to the time slots. The project entities are grouped into projects based on the clustered time slots. Project tags corresponding to the projects are applied to the project entities based on the grouping of the project entities. Content is personalized to the user based on the project tags applied to the project entities.
摘要翻译：
系统和方法提供了关联项目实体和项目。在各种实现中，基于来自与用户相关联的至少一个用户设备的传感器数据来监视用户活动数据。根据监控的用户活动数据，确定与用户活动数据对应的项目实体的实体特征。时隙是从项目实体中提取的。时隙是根据与时隙对应的某些项目实体的实体特征聚集的。项目实体根据群集时间段分组为项目。根据项目实体的分组将项目对应的项目标签应用于项目实体。内容是根据应用于项目实体的项目标签为用户个性化的。

67. 发明申请

WO2018013385A1 CONTEXTUAL SUGGESTIONS FROM USER HISTORY 审中-公开
标题翻译：来自用户历史的上下文建议
公开(公告)号：WO2018013385A1
公开(公告)日：2018-01-18
申请号：PCT/US2017/040643
申请日：2017-07-05
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： KESAMREDDY, Venkata Pavan Kumar
IPC分类号： G06F17/30
CPC分类号： G06F16/24578 , G06F16/24575 , G06F16/3322 , G06F16/90324 , G06F16/9535
摘要： Non-limiting examples of the present disclosure describe pattern recognition determined based on evaluation of contexts associated with a user history of a user. Input may be received from a processing device of a user. A plurality of contexts associated with user history data of the user history may be evaluated. In examples, the evaluating comprises: generating, for each of the plurality of contexts, a score based on: at least one time period of the user history that is associated with a searching of a context and a frequency of searching for the context within the at least one time period. The evaluating may further comprise ranking the plurality of contexts based on the score corresponding with each of the plurality of contexts. One or more contextual suggestions may be generated and output for the received input based on the ranked plurality of contexts.
摘要翻译：本公开的非限制性示例描述了基于对与用户的用户历史相关联的上下文的评估而确定的模式识别。输入可以从用户的处理设备接收。可以评估与用户历史的用户历史数据相关联的多个上下文。在示例中，评估包括：针对多个上下文中的每一个生成分数，所述分数基于：与搜索上下文相关联的用户历史的至少一个时间段和搜索上下文内的上下文的频率至少一个时间段。评估可以进一步包括基于与多个上下文中的每一个对应的分数对多个上下文进行排名。基于排序的多个上下文，可以为接收到的输入生成并输出一个或多个上下文建议。

68. 发明申请

WO2019135748A1 MACHINE-LEARNING MODEL FOR RANKING DIVERSE CONTENT 审中-公开
公开(公告)号：WO2019135748A1
公开(公告)日：2019-07-11
申请号：PCT/US2018/012292
申请日：2018-01-04
申请人： FACEBOOK, INC.
发明人： SERNAU, Luke , TWIST, Jonjo
IPC分类号： G06N99/00 , G06Q50/10
CPC分类号： G06F16/24578 , G06F16/24575 , G06F16/285 , G06N20/00 , G06Q50/01
摘要： In one embodiment, a method includes a computing system accessing a content item associated with a content provider, the content item having a first set of attributes and a second set of attributes. The system may generate, using a first machine-learning rnodel, a first ranking score of the content item for a user based on the first set of attributes. The system may generate cluster representations of the second set of attributes of the content item. The system may generate, using a second machine-learning model, a second ranking score of the content item for the user based on the cluster representations. The system may generate, using a third machine- learning model, a third ranking score of the content item for the user based on the first ranking score and the second ranking score. The system may select the content item for presentation to the user based on the third ranking score.

69. 发明申请

WO2018039272A1 SEMANTIC DISTANCE SYSTEMS AND METHODS FOR DETERMINING RELATED ONTOLOGICAL DATA 审中-公开
标题翻译：用于确定相关本体数据的语义距离系统和方法
公开(公告)号：WO2018039272A1
公开(公告)日：2018-03-01
申请号：PCT/US2017/048072
申请日：2017-08-22
申请人： ILLUMINA, INC.
发明人： FARH, Kai-How , HAKENBERG, Jorg , KARANGUTKAR, Milan , CUI, Wenwu , GAO, Hong
IPC分类号： G06F17/30
CPC分类号： G06F16/248 , G06F7/02 , G06F16/24575 , G06F16/367
摘要： Systems, computer-implemented methods, and non-transitory computer readable media are provided for determining related ontological data. The disclosed systems may be configured to receive a first ontology and a second ontology, the first ontology and the second ontology comprising hierarchically organized ontological data. The disclosed systems may also be configured to receive an indication that a first ontological datum in the first ontology is equivalent to a second ontological datum in the second ontology, and a query for ontological data related to a third ontological datum subordinate to the first ontological datum. The disclosed systems may be configured to determine a first semantic distance between the third ontological datum and a fourth ontological datum in the second ontology satisfies a semantic distance criterion, and output the fourth ontological datum based on the determination that the first semantic distance satisfies the semantic distance criterion.
摘要翻译：提供了用于确定相关本体论数据的系统，计算机实现的方法和非暂时性计算机可读介质。所公开的系统可以被配置为接收第一本体和第二本体，第一本体和第二本体包括分层组织的本体数据。所公开的系统还可以被配置为接收第一本体中的第一本体基准等于第二本体中的第二本体基准的指示以及与第一本体基准附属的第三本体基准相关的本体数据的查询。所公开的系统可以被配置为确定第三本体基准和第二本体中的第四本体基准之间的第一语义距离满足语义距离标准，并且基于确定第一语义距离满足语义输出第四本体基准距离标准。

70. 发明申请

WO2018013360A1 CONTEXTUAL INFORMATION FOR A DISPLAYED RESOURCE THAT INCLUDES AN IMAGE 审中-公开
标题翻译：显示资源的上下文信息，包括图像
公开(公告)号：WO2018013360A1
公开(公告)日：2018-01-18
申请号：PCT/US2017/040220
申请日：2017-06-30
申请人： GOOGLE LLC
发明人： PAGAIME DA SILVA, Joao Paulo , AGGARWAL, Vikram
IPC分类号： G06F17/30
CPC分类号： G06F3/0482 , G06F16/24575 , G06F16/248 , G06F16/951 , G06F16/9535 , H04L67/42 , H04W88/02
摘要： Systems, methods and software for providing contextual information for a displayed resource that includes an image. A user device provides, to a contextual information server, a query-independent request for contextual information relevant to a resource displayed in an application environment on the user device. The request specifies content of the active resource and further specifies that the active resource displayed on the user device includes an image, but does not include the image in the request. The user devices receives a request for the image from the contextual information server and provides the image to the contextual information server, and receives a user interface element that includes contextual information regarding the image, and displays the user interface element on the user device with the active resource. The methods and systems reduce processing and bandwidth requirements and/or provide other technical advantages compared to known methods and systems of providing contextual information.
摘要翻译：用于为包括图像的显示资源提供上下文信息的系统，方法和软件。用户设备向上下文信息服务器提供与在用户设备上的应用环境中显示的资源有关的上下文信息的查询独立请求。该请求指定活动资源的内容并进一步指定在用户设备上显示的活动资源包括图像，但不包括请求中的图像。用户设备从上下文信息服务器接收对图像的请求并将该图像提供给上下文信息服务器，并且接收包括关于该图像的上下文信息的用户界面元素，并且将用户界面元素显示在用户设备上活跃的资源。与提供上下文信息的已知方法和系统相比，这些方法和系统减少处理和带宽要求和/或提供其他技术优点。

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