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

WO2018164918A1 SELF-DEBUGGING OF ELECTRONIC MESSAGE BUGS 审中-公开
公开(公告)号：WO2018164918A1
公开(公告)日：2018-09-13
申请号：PCT/US2018/020345
申请日：2018-03-01
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： BANSAL, Chetan , ENCARNACION, Mark , PANTEL, Patrick , WONG, Woon Kiat
IPC分类号： H04L12/58
CPC分类号： H04L51/30 , H04L51/02 , H04L51/12 , H04L51/18 , H04L63/1441
摘要： Electronic messages are automatically debugged. An electronic message sent by a sender to one or more recipients is received and analyzed to identify any issues in the message. Whenever one or more issues are identified in the message, a reply message may be sent to the sender that describes each of the identified issues and includes a proposed fix for each of the identified issues. Each of the issues identified in the message may also be fixed resulting in a fixed version of the message, and the fixed version of the message may be sent to the sender for their approval. The fixed version of the message may also be sent to each of the recipients. Whenever no issues are identified in the message, a reply message may be sent to the sender informing them that no issues were found.

2. 发明申请

WO2015191652A1 MODELING INTERESTINGNESS WITH DEEP NEURAL NETWORKS 审中-公开
标题翻译：建立与深层神经网络的兴趣
公开(公告)号：WO2015191652A1
公开(公告)日：2015-12-17
申请号：PCT/US2015/034994
申请日：2015-06-10
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： GAO, Jianfeng , DENG, Li , GAMON, Michael , HE, Xiaodong , PANTEL, Patrick
IPC分类号： G06F17/30
CPC分类号： G06N3/04 , G06F17/30967 , G06N3/0427 , G06N3/082
摘要： An "Interestingness Modeler" uses deep neural networks to learn deep semantic models (DSM) of "interestingness." The DSM, consisting of two branches of deep neural networks or their convolutional versions, identifies and predicts target documents that would interest users reading source documents. The learned model observes, identifies, and detects naturally occurring signals of interestingness in click transitions between source and target documents derived from web browser logs. Interestingness is modeled with deep neural networks that map source-target document pairs to feature vectors in a latent space, trained on document transitions in view of a "context" and optional "focus" of source and target documents. Network parameters are learned to minimize distances between source documents and their corresponding "interesting" targets in that space. The resulting interestingness model has applicable uses, including, but not limited to, contextual entity searches, automatic text highlighting, prefetching documents of likely interest, automated content recommendation, automated advertisement placement, etc.
摘要翻译： “有趣的建模者”使用深层神经网络来学习“趣味性”的深层语义模型（DSM）。 DSM由深度神经网络的两个分支或其卷积版本组成，识别并预测将感兴趣用户阅读源文档的目标文档。所学习的模型观察，识别和检测从Web浏览器日志导出的源文档和目标文档之间的点击转换中的自然发生的兴趣信号。有趣的是用深层神经网络建模，将源目标文档对映射到潜在空间中的特征向量，考虑到源文件和目标文档的“上下文”和可选的“焦点”，对文档转换进行了训练。学习网络参数以最小化源文档与其空间中相应的“有趣”目标之间的距离。所产生的兴趣模型具有适用的用途，包括但不限于上下文实体搜索，自动文本突出显示，预取可能感兴趣的文档，自动内容推荐，自动广告投放等。

3. 发明申请

WO2019125875A1 AI SYSTEM TO DETERMINE ACTIONABLE INTENT 审中-公开
公开(公告)号：WO2019125875A1
公开(公告)日：2019-06-27
申请号：PCT/US2018/065309
申请日：2018-12-13
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： LIN, Chu-Cheng , GAMON, Michael , KANG, Dongyeop , PANTEL, Patrick , KHABSA, Madian , AWADALLAH, Ahmed Hassan
IPC分类号： G06Q10/10
CPC分类号： G06F17/2785 , G06F17/241 , G06N3/0445 , G06N3/08 , G06Q10/107
摘要： A method includes receiving an email addressed to a recipient user, processing the received email using a reparametrized recurrent neural network model to identify an action based on the received email, and wherein the reparametrized recurrent neural network model has been trained on an email dataset annotated with recipient corresponding actions and reparametrized on unannotated conversation data having structures similar to email data.

4. 发明申请

WO2018125583A1 DETECTION AND DELEGATION OF ACTION TASKS 审中-公开
公开(公告)号：WO2018125583A1
公开(公告)日：2018-07-05
申请号：PCT/US2017/066235
申请日：2017-12-14
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： ENCARNACION, Mark , ZHOVTOBRIUKH, Ievgeniia , PANTEL, Patrick , AWADALLAH, Ahmed , BANSAL, Chetan , GAMON, Michael , AYKAN, Cem , BANKO, Michele , SNOW, Mike , GEHRKE, Johannes
IPC分类号： G06Q10/10
摘要： Systems and methods are presented for detecting an action intent within received content, identifying an action completion bot for carrying out the corresponding action, and initiating the action through an action request to the action completion bot. An action delegation agent executing on a computer system, receives notice of received content, where the action delegation agent is not the target of the received content. An analysis of the received content is conducted to identify an action intent of the received content. Based on the action intent, an action registry is consulted to identify a corresponding action completion bot for carrying out the intended action. A request is submitted to the action completion bot to carry out the action.

5. 发明申请

WO2020081378A1 MINIMIZATION OF COMPUTATIONAL DEMANDS IN MODEL AGNOSTIC CROSS-LINGUAL TRANSFER WITH NEURAL TASK REPRESENTATIONS AS WEAK SUPERVISION 审中-公开
公开(公告)号：WO2020081378A1
公开(公告)日：2020-04-23
申请号：PCT/US2019/055753
申请日：2019-10-11
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： JAUHAR, Sujay, Kumar , GAMON, Michael , PANTEL, Patrick
IPC分类号： G06F40/20 , G06N7/00 , G06N3/00
摘要： A task agnostic framework for neural model transfer from a first language to a second language, that can minimize computational and monetary costs by accurately forming predictions in a model of the second language by relying on only a labeled data set in the first language, a parallel data set between both languages, a labeled loss function, and an unlabeled loss function. The models may be trained jointly or in a two-stage process.

6. 发明申请

WO2019135880A1 HYBRID INTELLIGENCE APPROACH TO ELICITING KNOWLEDGE FOR INLINE NOTES 审中-公开
公开(公告)号：WO2019135880A1
公开(公告)日：2019-07-11
申请号：PCT/US2018/065570
申请日：2018-12-13
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： KOHLMEIER, Bernhard S.J. , VARGAS HERRING, Luis Carlos , ENCARNACION, Mark J. , PANTEL, Patrick , TEEVAN, Jaime Brooks , POZNANSKI, Victor , WONG, Woon Kiat
IPC分类号： G06F17/27 , G06F17/24
CPC分类号： G06N5/022 , G06F3/04842 , G06F16/93 , G06F17/241 , G06F17/2765 , H04L51/22
摘要： A content creation application can include a feature that receives an inline note within a document and communicates the content of the inline note and a user identifier associated with an author of the inline note to an intelligence service. The intelligence service can identify, from the content of the inline note, one or more agents and a request, the identified one or more agents being the author, one or more person agents, one or more bot agents, or a combination thereof. Based on the identified agent (or lack thereof), the intelligence service can generate a message to each of the one or more agents and communicate the message to the each of the one or more agents over a communication channel. A person agent or the author can receive the message and view the message using the appropriate communication application without accessing the original document.

7. 发明申请

WO2016003954A1 CONSTRUCTING A GRAPH THAT FACILITATES PROVISION OF EXPLORATORY SUGGESTIONS 审中-公开
标题翻译：构建一个有利于提供探索性建议的图表
公开(公告)号：WO2016003954A1
公开(公告)日：2016-01-07
申请号：PCT/US2015/038410
申请日：2015-06-30
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： AWADALLAH, Ahmed Hassan , WHITE, Ryen , PANTEL, Patrick , DUMAIS, Susan , WANG, Yi-Min
IPC分类号： G06F17/30
CPC分类号： G06T11/206 , G06F17/3064
摘要： Various technologies pertaining to exploratory suggestions are described herein. A computer-implemented graph is constructed, where the graph includes nodes that are representative of aspects and edges that are representative of associations between aspects. An aspect is representative of a sub-topic of a topic or a sub-task of a task. The computer-implemented graph is learned based upon content of search logs, and is used to output exploratory suggestions, where a user is exploring a topic or attempting to complete a multi-step task.
摘要翻译：本文描述了与探索性建议相关的各种技术。构建计算机实现的图，其中图包括表示方面和方面之间的关联的方面和边缘的节点。一个方面代表一个主题或一个任务的子任务的子主题。基于搜索日志的内容学习计算机实现的图形，并用于输出探索性建议，用户正在探索主题或尝试完成多步骤任务。

8. 发明申请

WO2019143499A1 AUTOMATED QUICK TASK NOTIFICATIONS VIA AN AUDIO CHANNEL 审中-公开
公开(公告)号：WO2019143499A1
公开(公告)日：2019-07-25
申请号：PCT/US2019/012796
申请日：2019-01-08
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： WHITE, Ryen William , AUDOUIN, Mathieu Etienne Jacques , PANTEL, Patrick , GHOTBI, Nikrouz , UPPALA, Anantha Deepthi , MURDOCK, Vanessa Graham , ENCARNACION, Mark James , CHANDRASEKARAN, Nirupama
IPC分类号： G06Q10/10
CPC分类号： G10L15/22 , G06F3/16 , G06F17/279 , G06F17/28 , G06Q10/107 , G06Q10/109 , G06Q10/1093 , G06Q10/1097
摘要： Aspects of the technology described herein provide an efficient user interface that enables users to respond to tasks quickly by providing automated quick task notifications via an audio channel. An audio channel quick task system includes components for recognizing and extracting quick tasks from content (e.g., interpersonal communications, composed content, line of business (LOB) application documents), and for prioritizing and routing the quick tasks to the user via an audio channel at an appropriate and relevant time. The system is enabled to process a user response, determine an action for handling the quick task, and execute the action on behalf of the user (e.g., pass a reply to a requestor, pass an instruction to an application or service, queue the quick task notification, delegate the quick task to another user or bot, forward the quick task to a companion device, or launch an application on a companion device).

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