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

WO2021094920A1 FUSING MULTIMODAL DATA USING RECURRENT NEURAL NETWORKS 审中-公开
公开(公告)号：WO2021094920A1
公开(公告)日：2021-05-20
申请号：PCT/IB2020/060577
申请日：2020-11-10
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION , IBM UNITED KINGDOM LIMITED , IBM (CHINA) INVESTMENT COMPANY LIMITED
发明人： DANG, Xuan-Hong , SHAH, Syed, Yousaf , ZERFOS, Petros , GRECO, Nancy, Anne
IPC分类号： G06N3/08
摘要： Embodiments relate to a system, program product, and method for employing deep learning techniques to fused data across modalities. A multi-modal data set is received, including a first data set having a first modality and a second data set having a second modality, with the second modality being different from the first modality. The first and second data sets are processed, including encoding the first data set into one or more first vectors, and encoding the second data set into one or more second vectors. The processed multi-modal data set is analyzed, and the encoded features from the first and second modalities are iteratively and asynchronously fused. The fused modalities include combined vectors from the first and second data sets representing correlated temporal behavior. The fused vectors are then returned as output data.

2. 发明申请

WO2021224720A1 DETERMINING MULTIVARIATE TIME SERIES DATA DEPENDENCIES 审中-公开
公开(公告)号：WO2021224720A1
公开(公告)日：2021-11-11
申请号：PCT/IB2021/053445
申请日：2021-04-27
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION , IBM UNITED KINGDOM LIMITED , IBM (CHINA) INVESTMENT COMPANY LIMITED
发明人： DANG, Xuan-Hong , GUO, Yunqi , SHAH, Syed Yousaf , ZERFOS, Petros
IPC分类号： G06N3/02
摘要： Techniques and a system regarding multivariate time series data analysis are provided. The system comprises a memory that stores computer executable components. The system also comprises a processor, operably coupled to the memory, and that executes the computer executable components stored in the memory. The computer executable components comprise a time series analysis component that generates a machine learning model that discovers a dependency between multivariate time series data using an attention mechanism controlled by an uncertainty measure.

3. 发明申请

WO2019219799A1 DYNAMIC DISCOVERY OF DEPENDENCIES AMONG TIME SERIES DATA USING NEURAL NETWORKS 审中-公开
公开(公告)号：WO2019219799A1
公开(公告)日：2019-11-21
申请号：PCT/EP2019/062587
申请日：2019-05-16
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION , IBM UNITED KINGDOM LIMITED
发明人： SHAH, Syed, Yousaf , DANG, Xuan-Hong , ZERFOS, Petros
IPC分类号： G06N3/04
摘要： Techniques for determining temporal dependencies and inter-time series dependencies in multi-variate time series data are provided. For example, embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor that can execute the computer executable components stored in the memory. The computer executable components can include: a computing component that encodes recurrent neural networks (RNNs) with time series data and determines decoded RNNs based on temporal context vectors, to determine temporal dependencies in time series data; a combining component that combines the decoded RNNs and determines an inter-time series dependence context vector and an RNN dependence decoder; and an analysis component that determines inter-time series dependencies in the time series data and forecast values for the time series data based on the inter-time series dependence context vector and the RNN dependence decoder.

4. 发明申请

WO2017046729A1 NATURAL LANGUAGE INTERFACE TO DATABASES 审中-公开
标题翻译：自然语言界面到数据库
公开(公告)号：WO2017046729A1
公开(公告)日：2017-03-23
申请号：PCT/IB2016/055494
申请日：2016-09-15
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION , IBM UNITED KINGDOM LIMITED , IBM (CHINA) INVESTMENT COMPANY LIMITED
发明人： SHEININ, Vadim , PATWARDHAN, Siddharth, Ajeet , BOGURAEV, Branimir, Konstantinov , KHORASANI, Elahe , ZERFOS, Petros
IPC分类号： G06F17/30
CPC分类号： G06F17/30401 , G06F17/2705 , G06F17/2765 , G06F17/2795 , G06F17/3043
摘要： An embodiment of the invention provides a method wherein a natural language query is received from a user with an interface. An ontological representation of data in a database is received with an input port, including names of concepts and names of concept properties. Template rules are received with the input port, the templates rules being language dependent and ontology independent, the template rules including widely used constructs of a language. Rules are automatically generated with a rule generation engine with the ontological representation of the data in the database and the template rules to identify entities and relations in the natural language query. Entities and relations are identified with a processor, the entities and relations being identified in the natural language query with the rules. The structured data language query is generated with a query generation engine from the entities and relations.
摘要翻译：本发明的实施例提供了一种从具有接口的用户接收到自然语言查询的方法。使用输入端口接收数据库中数据的本体表示，包括概念名称和概念属性名称。使用输入端口接收模板规则，模板规则与语言相关并且本体独立，模板规则包括广泛使用的语言结构。使用规则生成引擎自动生成规则，数据库中的数据本体表示和模板规则用于识别自然语言查询中的实体和关系。实体和关系用处理器识别，实体和关系在自然语言查询中被标识为规则。结构化数据语言查询是通过实体和关系的查询生成引擎生成的。

5. 发明申请

WO2022174792A1 AUTOMATED TIME SERIES FORECASTING PIPELINE RANKING 审中-公开
公开(公告)号：WO2022174792A1
公开(公告)日：2022-08-25
申请号：PCT/CN2022/076660
申请日：2022-02-17
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION , IBM (CHINA) CO., LIMITED
发明人： CHEN, Bei , VU, Long , PATEL, Dhavalkumar C. , SHAH, Syed Yousaf , BRAMBLE, Gregory , KIRCHNER, Peter Daniel , SAMULOWITZ, Horst Cornelius , DANG, Xuan-Hong , ZERFOS, Petros
IPC分类号： G06N20/00
摘要： A method and a system for ranking time series forecasting machine learning pipelines in a computing environment are provided. Time series data may be incrementally allocated from a time series data set for testing by candidate machine learning pipelines based on seasonality or a degree of temporal dependence of the time series data. Intermediate evaluation scores may be provided by each of the candidate machine learning pipelines following each time series data allocation. One or more machine learning pipelines may be automatically selected from a ranked list of the one or more candidate machine learning pipelines based on a projected learning curve generated from the intermediate evaluation scores.

6. 发明申请

WO2013040926A1 SMART ONLINE SERVICES PRESENCE IN A CELLULAR NETWORK 审中-公开
标题翻译：智能在线服务在细胞网络中存在
公开(公告)号：WO2013040926A1
公开(公告)日：2013-03-28
申请号：PCT/CN2012/077826
申请日：2012-06-29
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION , IBM (CHINA) CO., LIMITED , AGRAWAL, Dakshi , BISDIKIAN, Chatschik , VERMA, Dinesh C. , ZERFOS, Petros
发明人： AGRAWAL, Dakshi , BISDIKIAN, Chatschik , VERMA, Dinesh C. , ZERFOS, Petros
IPC分类号： H04L29/06
CPC分类号： H04W4/00
摘要： A method and system for providing on-line services to a user from a services provider over a wireless cellular network. The cellular network is located between the user and the services provider, and a distributed computer system such as the Internet is located between the services provider and the cellular network for transmitting data between the services provide and the cellular network. In one embodiment, the services provider transmits software and operating characteristics over the distributed computer system to the cellular network, and the cellular network installs this software on one or more nodes of the network. When a user connects to the cellular network for services from the service provider, the network operates the software on the one or more nodes in accordance with the operating characteristics, to provide one or more services from this one or more nodes to the user from the service provider.
摘要翻译：一种用于通过无线蜂窝网络从服务提供商向用户提供在线服务的方法和系统。蜂窝网络位于用户和服务提供商之间，诸如因特网之类的分布式计算机系统位于服务提供商和蜂窝网络之间，用于在服务提供和蜂窝网络之间传输数据。在一个实施例中，服务提供商通过分布式计算机系统向蜂窝网络传送软件和操作特性，蜂窝网络将该软件安装在网络的一个或多个节点上。当用户连接到蜂窝网络用于来自服务提供商的服务时，网络根据操作特性在一个或多个节点上操作软件，以从该一个或多个节点向用户提供一个或多个服务服务提供者。

7. 发明申请

WO2012145845A1 PREDICTIVE PLACEMENT OF CONTENT THROUGH NETWORK ANALYSIS 审中-公开
标题翻译：通过网络分析预测内容的布局
公开(公告)号：WO2012145845A1
公开(公告)日：2012-11-01
申请号：PCT/CA2012/050265
申请日：2012-04-27
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION , IBM CANADA LIMITED-IBM CANADA LIMITEE
发明人： AGRAWAL, Dakshi , LOBO, Jorge , PAPPAS, Vasileios , ZERFOS, Petros
IPC分类号： H04L12/16 , H04N21/222 , H04W4/14
CPC分类号： G06Q50/01 , H04L67/2819 , H04L67/2857 , H04N21/258 , H04N21/4331 , H04N21/44222 , H04N21/4524 , H04N21/8586
摘要： Described herein are methods, systems, apparatuses and products for predictive placement of content through network analysis. An aspect provides for intercepting content upload data provided by one or more users indicating content at a network location; ascertaining one or more users predicted to access said content based on said one or more users providing said content upload data; and placing said content to one or more other network locations based on said one or more users predicted to access said content. Other embodiments are disclosed.
摘要翻译：这里描述了通过网络分析来预测性地放置内容的方法，系统，装置和产品。一方面提供用于拦截由一个或多个用户在网络位置指示内容提供的内容上载数据; 基于提供所述内容上载数据的所述一个或多个用户来确定预测访问所述内容的一个或多个用户; 以及基于所述一个或多个预测访问所述内容的用户将所述内容放置到一个或多个其他网络位置。公开了其他实施例。

8. 发明申请

WO2014062296A1 STATE MIGRATION OF EDGE-OF-NETWORK APPLICATIONS 审中-公开
标题翻译：边缘网络应用的状态迁移
公开(公告)号：WO2014062296A1
公开(公告)日：2014-04-24
申请号：PCT/US2013/056589
申请日：2013-08-26
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： AGRAWAL, Dakshi , BISDIKIAN, Chatschik , VERMA, Dinesh, C. , ZERFOS, Petros
IPC分类号： H04W36/00
CPC分类号： H04W36/30 , H04L67/02 , H04L67/1097 , H04W4/00 , H04W8/08 , H04W72/087 , H04W76/10
摘要： A system and method that extenalizes mobile device state migration (i.e., checkpointing) without being dependent upon any particular Edge Application (EdgeApp) proxy server or cellular network base station. In this manner, the Edge Application (edgeApp) proxy server does not have to be aware of a migration process, yet will enable state information to be provided to other EdgeApp proxy/server nodes at the edge of the network (cell tower).
摘要翻译：一种在不依赖于任何特定边缘应用（EdgeApp）代理服务器或蜂窝网络基站的情况下，对移动设备状态迁移（即，检查点）进行扩展的系统和方法。以这种方式，边缘应用程序（edgeApp）代理服务器不必了解迁移过程，而是将状态信息提供给网络边缘的其他EdgeApp代理/服务器节点（单元塔）。

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