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

WO2019156939A1 ARTIFICIAL INTELLIGENCE SYSTEM FOR INFERRING GROUNDED INTENT 审中-公开
公开(公告)号：WO2019156939A1
公开(公告)日：2019-08-15
申请号：PCT/US2019/016566
申请日：2019-02-05
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： BENNETT, Paul N. , HASEGAWA, Marcello Mendes , GHOTBI, Nikrouz , WHITE, Ryen William , JHA, Abhishek
IPC分类号： G06N3/00 , G06N5/02 , G06N20/00 , G06F17/20
CPC分类号： G06N3/006 , G06F17/20 , G06F17/276 , G06F17/2785 , G06N5/022 , G06N5/043 , G06N20/00
摘要： Techniques for enabling an artificial intelligence system to infer grounded intent from user input, and automatically suggest and/or execute actions associated with the predicted intent. In an aspect, core task descriptions are extracted from actionable statements identified as containing grounded intent. A machine classifier receives the core task description, actionable statements, and user input to predict an intent class for the user input. The machine classifier may be trained using unsupervised learning techniques based on weakly labeled clusters of the core task description extracted over a training corpus. The core task description may include verb-object pairs.

2. 发明申请

WO2019089326A1 AUTOMATED EXTRACTION AND APPLICATION OF CONDITIONAL TASKS 审中-公开
公开(公告)号：WO2019089326A1
公开(公告)日：2019-05-09
申请号：PCT/US2018/057423
申请日：2018-10-25
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： WHITE, Ryen William , BENNETT, Paul Nathan , HORVITZ, Eric Joel , GHOTBI, Nikrouz , PORTENOY, Jason Henry , HASEGAWA, Marcello Mendes , JHA, Abhishek , MODAK, Chaitanya Yashwant
IPC分类号： G06Q10/10 , G06Q10/06
CPC分类号： G06F9/4806 , G06F3/04842 , G06F9/543 , G06Q10/06311 , G06Q10/109
摘要： Automatic extraction and application of conditional tasks from content is provided. A conditional task system includes a classifier that is trained and used to identify conditional tasks and to learn appropriate times and methods to engage a user for reminding the user about conditional tasks. The conditional task system includes components for enabling an automated detection of a conditional task, extracting of attributes that characterize a condition associated with the task, using information about the condition to determine how to monitor for satisfaction of the condition, determining when and how to engage the user about the task, and notifying the user at an appropriate time and using an appropriate method when the condition is satisfied.

3. 发明申请

WO2016196526A1 VIEWPORT-BASED IMPLICIT FEEDBACK 审中-公开
标题翻译：基于视图的隐含反馈
公开(公告)号：WO2016196526A1
公开(公告)日：2016-12-08
申请号：PCT/US2016/035125
申请日：2016-06-01
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： KEDIA, Gautam , MCDONALD, Kieran , GUO, Qi , JHA, Abhishek , REKHI, Karan Singh , KAHN, Zachary , CROOK, Aidan
IPC分类号： G06Q30/02 , H04N21/466 , H04L29/08 , G06F17/30
CPC分类号： G06N5/04 , G06F3/0481 , G06F17/30699 , G06N99/005 , G06Q30/02 , G09G5/14 , H04L67/22 , H04N21/44222 , H04N21/4667 , H04N21/4668 , H04N21/4826
摘要： Examples of the present disclosure describe systems and methods for improving the recommendations provided to a user by a recommendation system using viewed content as implicit feedback. In some aspects, attention models are created/updated to infer the user attention of a user that has viewed or is viewing content on a computing device. The attention model may be used to convert inferences of user attention into inferences of user satisfaction with the viewed content. The inferences of user satisfaction may be used to generate inferences of fatigue with the viewed content. The inferences of user satisfaction and inferences of user fatigue may then be used as implicit feedback to improve the content selection, content triggering and/or content presentation by the recommendation system. Other examples are also described.
摘要翻译：本公开的示例描述了用于改进由使用观看内容作为隐式反馈的推荐系统提供给用户的建议的系统和方法。在一些方面，创建/更新关注模型以推断在计算设备上观看或正在观看内容的用户的用户注意力。注意模型可以用于将用户关注的推论转换为对观看内容的用户满意度的推论。可以使用用户满意度的推论来产生对所观看内容的疲劳推断。用户满意度的推论和用户疲劳的推论可以被用作暗示反馈，以改进推荐系统的内容选择，内容触发和/或内容呈现。还描述了其它实例。

4. 发明申请

WO2015142625A1 RECOMMENDATION RANKING BASED ON LOCATIONAL RELEVANCE 审中-公开
标题翻译：基于位置相关性的推荐排名
公开(公告)号：WO2015142625A1
公开(公告)日：2015-09-24
申请号：PCT/US2015/020312
申请日：2015-03-13
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： REKHI, Karan Singh , JHA, Abhishek , KEDIA, Gautam , MCDONALD, Kieran Richard , MCGOVERN, Andrew P.
IPC分类号： G06Q10/04 , G06Q30/02
CPC分类号： G06F17/3053 , G06Q10/047 , G06Q30/0261
摘要： One or more techniques and/or systems are provided for ranking recommendations within a set of recommendations. For example, a set of locational relevance boundaries may be generated and/or configured for ranking the set of recommendation. For example, a locational relevance boundary may adjust a rank of a recommendation using a rank influence (e.g., a linear function, a step function, a numerical value, and/or any other function used to increase, decrease, or assign a value to the rank based upon a current location of the user). The locational relevance boundary may be applied based upon the current location of the user corresponding to one or more threshold distances from a target recommendation location. For example, a logarithmic function may be applied to a rank of a theater recommendation when the user is less than 1.2 miles from the theater. Ranked recommendations may be provided to the user.
摘要翻译：提供一个或多个技术和/或系统用于在一组建议内对推荐进行排名。例如，可以生成和/或配置一组位置相关性边界以对该组推荐进行排名。例如，位置相关性边界可以使用秩影响（例如，线性函数，阶梯函数，数值和/或用于增加，减少或分配值的任何其他函数来调整推荐的等级基于用户的当前位置的等级）。可以基于与来自目标推荐位置的一个或多个阈值距离对应的用户的当前位置来应用位置相关性边界。例如，当用户距离剧院不到1.2英里时，对数函数可以应用于剧院推荐的等级。可以向用户提供排名的建议。

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