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

WO2022250916A1 CONTENT-BASED MULTIMEDIA RETRIEVAL WITH ATTENTION-ENABLED LOCAL FOCUS 审中-公开
公开(公告)号：WO2022250916A1
公开(公告)日：2022-12-01
申请号：PCT/US2022/027751
申请日：2022-05-05
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： ABRAHAM, Robin , ROHANI, Neda , PESALA, Rohith, Venkata , SMOCK, J., Brandon , DELGADO, Natalia, Larios
IPC分类号： G06F16/432
摘要： Examples of the present disclosure describe systems and methods for content-based multimedia retrieval with attention-enabled local focus. In aspects, a search query comprising multimedia content may be received by a search system. A first semantic embedding representation of the multimedia content may be generated. The first semantic embedding representation may be compared to a stored set of candidate semantic embedding representations of other multimedia content. Based on the comparison, one or more candidate representations that are visually similar to the first semantic embedding representation may be selected from the stored set of candidate semantic embedding representations. The candidate representations may be ranked, and top 'N' candidate representations (or corresponding multimedia items) may be retrieved and provided as search results for the search query.

2. 发明申请

WO2020101990A1 SEARCH ENGINE FUNCTIONALITY USING SHARED AI MODELS 审中-公开
公开(公告)号：WO2020101990A1
公开(公告)日：2020-05-22
申请号：PCT/US2019/060170
申请日：2019-11-07
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： DU, Liang , NARAYANAN, Ranjith , ABRAHAM, Robin , MITAL, Vijay
IPC分类号： G06F16/332 , G06F16/33
摘要： Performing collaborative search engine searching. The method includes receiving user input at a user interface for performing a plurality searches on a first search engine. The method further includes receiving user input at the user interface applying one or more augmentation AI models to searches in the plurality of searches. The method further includes creating a shareable, executable package executable by one or more search engines based on the plurality of searches and the applied AI models that when executed by the search engines causes the search engines to apply the AI models to searches performed at the search engines.

3. 发明申请

WO2017004293A1 RECORDING OF INTER-APPLICATION DATA FLOW 审中-公开
标题翻译：记录应用程序数据流
公开(公告)号：WO2017004293A1
公开(公告)日：2017-01-05
申请号：PCT/US2016/040238
申请日：2016-06-30
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： MITAL, Vijay , SURESH, Sandeep , ABRAHAM, Robin
IPC分类号： G06F9/44
CPC分类号： H04L43/0876 , G06F9/4484 , G06F2201/865 , H04L43/04 , H04L43/062
摘要： Mechanism for two portions of an application to communicate so as to facilitate a transition from synchronous to asynchronous communication. In order to prepare for a possible transition, data flow is monitored between the two portions of the application, each portion interacting with a different hardware entity. The data flow between the first portion and the second portion of the application is recorded. If the second hardware entity is not available at the time, the recorded data flow from the first portion may be replayed by the second portion of the application for the benefit of the second hardware entity. If the second portion of the application is to be reassigned to another hardware entity, the target hardware entity may be sent the second portion of the application, as well as the recorded information. This allows the target hardware entity to replay what has happened thus far for context.
摘要翻译：应用程序的两部分进行通信的机制，以便于从同步到异步通信的过渡。为了准备可能的转换，在应用程序的两个部分之间监视数据流，每个部分与不同的硬件实体进行交互。记录应用程序的第一部分和第二部分之间的数据流。如果第二硬件实体当时不可用，则来自第一部分的记录数据流可以被应用程序的第二部分重放，以利于第二硬件实体。如果应用程序的第二部分被重新分配给另一个硬件实体，则目标硬件实体可以被发送到应用程序的第二部分以及所记录的信息。这允许目标硬件实体重播上下文发生的事情。

4. 发明申请

WO2017004287A1 BUILDING OF COMPOUND APPLICATION CHAIN APPLICATIONS 审中-公开
标题翻译：复合应用链应用的建设
公开(公告)号：WO2017004287A1
公开(公告)日：2017-01-05
申请号：PCT/US2016/040231
申请日：2016-06-30
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： MITAL, Vijay , ABRAHAM, Robin , POOZHIYIL, Suraj T. , RUBIN, Darryl E.
IPC分类号： G06F9/44 , G06Q10/06 , G06Q10/10
CPC分类号： G06F8/48 , G06F8/34 , G06F9/4494 , G06Q10/06 , G06Q10/067 , G06Q10/101 , G06Q10/103
摘要： The incremental formulating an application in response to detecting events (such as user input) in an environment. Upon detecting one or more events, it is determined from this use input that an instance of a first transformation chain class is to be joined with an instance of a second transformation chain class. In response, the instance of the first transformation class is joined with the instance of the second transformation class along one or more data flow dependencies to formulate an aggregated instance. The aggregated instance may then be operated. This process may be repeated in response to different user input to thereby increase the size of the aggregated instance as more and more transformation chain instances join into the aggregated instance at appropriate chains of dependency.
摘要翻译：响应于在环境中检测到事件（例如用户输入），递增地制定应用程序。在检测到一个或多个事件时，从该使用输入确定第一转换链类的实例将与第二转换链类的实例相连接。作为响应，第一个转换类的实例与沿着一个或多个数据流依赖关系的第二个转换类的实例相结合，以形成聚合实例。然后可以操作聚合的实例。可以响应于不同的用户输入重复该过程，从而随着越来越多的转换链实例在适当的依赖链连接到聚合实例中，从而增加聚合实例的大小。

5. 发明申请

WO2023038729A1 MACHINE-LEARNING OF DOCUMENT PORTION LAYOUT 审中-公开
公开(公告)号：WO2023038729A1
公开(公告)日：2023-03-16
申请号：PCT/US2022/038607
申请日：2022-07-28
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： LI, Yao , DU, Liang , ABRAHAM, Robin
IPC分类号： G06F16/31 , G06F16/93
摘要： Machine learning to predict a layout type that each of a plurality of portions of a document appears in. This is done even though the computer-readable representation of the document does not contain information at the granularity of the prediction to be made that identifies which layout type that each of the plurality of document portions belongs in. For each of a plurality of the portions, the machine-learning system predicts the layout type that the respective portion appears in, and indexes the document using the predictions so as to result in a computer-readable index. The index represents a predicted layout type associated with each of the plurality of portions of the document. Thus, the index can be used to search based on position of a searched term within the document.

6. 发明申请

WO2020163109A1 FACILITATING INTERACTION WITH PLURAL BOTS USING A MASTER BOT FRAMEWORK 审中-公开
公开(公告)号：WO2020163109A1
公开(公告)日：2020-08-13
申请号：PCT/US2020/015279
申请日：2020-01-28
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： ABRAHAM, Robin
IPC分类号： G06F16/332 , G06F16/95
摘要： A computer-implemented technique is described herein which uses a master BOT framework to facilitate a user's interaction with plural BOTs. The BOT framework includes a BOT registry that stores information regarding a plurality of BOTs that may be activated to handle different tasks (and associated intents). The BOT framework also includes various components that facilitate the transition from one BOT to another in the course of a multi-BOT transaction. According to one technical feature, the technique automatically invokes a new BOT without requiring the user to explicitly identify it. This provision simplifies the user's activation of a new BOT. According to another feature, the technique automatically forwards current state information to the new BOT. This provision expedites the user's transaction because it reduces the need for the user to repeat information that has already been supplied in one more prior turns of the transaction.

7. 发明申请

WO2019226312A1 AI MODEL CANVAS 审中-公开
公开(公告)号：WO2019226312A1
公开(公告)日：2019-11-28
申请号：PCT/US2019/030976
申请日：2019-05-07
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： MITAL, Vijay , DU, Liang , NARAYANAN, Ranjith , ABRAHAM, Robin
IPC分类号： G06F16/9032
摘要： Providing an improved user interface to a user for facilitating data management produced by artificial intelligence. A method includes receiving user input adding an input dataset to an active area of a user interface. The method further includes receiving user input adding an artificial intelligence model to the active area of the user interface. The method further includes, based on the user adding the artificial intelligence model to the active area of the user interface, providing feedback on the user interface to the user indicating an effect of adding the artificial intelligence model to the active area of the user interface.

8. 发明申请

WO2018136339A1 CLEANSING OF COMPUTER-NAVIGABLE PHYSICAL FEATURE GRAPH 审中-公开
公开(公告)号：WO2018136339A1
公开(公告)日：2018-07-26
申请号：PCT/US2018/013674
申请日：2018-01-13
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： MITAL, Vijay , COLLE, Olivier , FLUTRE, Arnaud Christian , ABRAHAM, Robin , GHASSEMI, Farhad
IPC分类号： G06N5/02 , G06F17/30 , G06K9/00 , H04L29/08
摘要： The controlling of the size and quality of a computer-navigable graph of sensed features. The sensed features were gathered by recognition or estimation of one or more features of physical entities that were sensed over time by sensor(s) within a physical space. Computer-navigation may occur over the graph in response to a query or computation. Thus, computations and queries may be performed over physical space, thereby extending computing to the ambient physical environment. To keep the size of the computer-navigable graph at a manageable levels nodes of the computer-navigable graph are removed or cleansed.

9. 发明申请

WO2018136316A1 AUTOMATED ACTIVITY-TIME TRAINING 审中-公开
公开(公告)号：WO2018136316A1
公开(公告)日：2018-07-26
申请号：PCT/US2018/013429
申请日：2018-01-12
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： MITAL, Vijay , ABRAHAM, Robin , ZHU, Victor , DU, Liang , ZHOU, Ning , SHARMA, Pramod Kumar , CHAKRABORTY, Ishani
IPC分类号： G09B19/00 , G06F3/01
摘要： Automatically training an actor upon the occurrence of a physical condition with respect to that actor. Upon detecting that the actor has the physical condition (e.g., is engaging in or is about to engage in a physical activity), the system determines that training is to be provided for that activity. Upon determining that training is to be provided, the system automatically dispatches training. For instance, the system might cause a human or robot to be dispatched to the actor to show the actor how to perform the activity. Alternatively or instead, a representation of a signal segment may be dispatched to the actor. The representation providing the training to the actor may include a similar target of work to what the actor is presently targeting by the activity. The representation may also include a representation of a person that engaged in the activity properly previously.

10. 发明申请

WO2017007862A1 RULE-BASED LAYOUT OF CHANGING INFORMATION 审中-公开
标题翻译：基于规则的更改信息布局
公开(公告)号：WO2017007862A1
公开(公告)日：2017-01-12
申请号：PCT/US2016/041213
申请日：2016-07-07
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： MITAL, Vijay , RUBIN, Darryl E. , ABRAHAM, Robin , POOZHIYIL, Suraj T.
IPC分类号： G06F9/44 , G06F17/30
CPC分类号： G06F17/212 , G06F9/451 , G06F9/452 , G06F17/30554
摘要： Displaying application output in a manner that is not predetermined by the application, nor by the display. The computing system associated with the display accesses a set of information output by an application and to be displayed on a display. However, rather than explicit instructions on how to display being received from the application itself, the computing system instead accesses a set of one or more display rules that are associated with the set of information. The computing system then uses the set of one or more display rules to determine how to layout the set of information on the display. If the set of information were to change, the rules may be reevaluated to determine how the new information should be laid out. If the associated set of display rules were to also changed, the reevaluation would occur thereby resulting in a potentially different layout on the display.
摘要翻译：以不是由应用程序预定的方式显示应用程序输出，也不显示。与显示器相关联的计算系统访问由应用输出的一组信息并显示在显示器上。然而，计算系统不是显示如何从应用程序本身接收显示的指令，而是访问与该组信息相关联的一个或多个显示规则的集合。计算系统然后使用一组一个或多个显示规则来确定如何在显示器上布置该组信息。如果要更改这些信息，则可能会重新评估规则，以确定新信息的布局方式。如果相关的显示规则集也要更改，则会重新进行评估，从而导致显示屏上的布局可能不同。

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