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

US20190034402A1 COGNITIVE MEDIATOR FOR GENERATING BLOCKCHAIN SMART CONTRACTS 审中-公开
公开(公告)号：US20190034402A1
公开(公告)日：2019-01-31
申请号：US15663141
申请日：2017-07-28
申请人： International Business Machines Corporation
发明人： Ryan Anderson , Joseph Kozhaya , Christopher M. Madison , John Wolpert
IPC分类号： G06F17/24 , H04L9/06 , G06Q40/02
摘要： In an approach to generating blockchain smart contracts, one or more computer processors receive a request for a service from a user. The one or more computer processors extract one or more features from the request. The one or more computer processors determine one or more smart contract templates associated with the request based, at least in part, on the extracted one or more features. The one or more computer processors receive one or more responses to the request from one or more service providers. The one or more computer processors generate a draft smart contract based, at least in part on the determined one or more smart contract templates and the one or more received responses.

2. 发明申请

US20170076223A1 Cognitive System Virtual Corpus Training and Utilization 审中-公开
标题翻译：认知系统虚拟语料库培训与利用
公开(公告)号：US20170076223A1
公开(公告)日：2017-03-16
申请号：US14854108
申请日：2015-09-15
申请人： International Business Machines Corporation
发明人： Joseph N. Kozhaya , Christopher M. Madison , Sridhar Sudarsan
IPC分类号： G06N99/00 , G06F17/30
CPC分类号： G06N99/005 , G06F17/30011 , G06F17/30657
摘要： Mechanisms are provided for implementing a virtual corpus engine that receives an inquiry to be processed and analyzes the inquiry to extract one or more features of the inquiry. The virtual corpus engine selects a weight matrix associated with a virtual corpus based on the extracted one or more features of the inquiry. The virtual corpus comprises a plurality of actual corpora of information. The weight matrix comprises a separate weight value for each actual corpus in the plurality of actual corpora. The virtual corpus engine processes the inquiry using a set of selected actual corpora selected from the plurality of actual corpora based on the weight values in the weight matrix and receives results of the processing of the inquiry using the set of selected actual corpora. The virtual corpus engine outputs the results of the processing of the inquiry.
摘要翻译：提供了用于实现接收要处理的查询的虚拟语料库引擎的机制，并分析查询以提取查询的一个或多个特征。虚拟语料库引擎基于所提取的一个或多个查询特征来选择与虚拟语料库相关联的加权矩阵。虚拟语料库包括多个实际的信息语料库。权重矩阵包括多个实际语料库中每个实际语料库的单独权重值。虚拟语料库引擎使用基于权重矩阵中的权重值的从多个实际语料库中选择的一组选定的实体语料库来处理查询，并且使用所选择的实际语料库的集合接收处理查询的结果。虚拟语料库引擎输出查询的处理结果。

3. 发明授权

US10558711B2 Defining dynamic topic structures for topic oriented question answer systems 有权
公开(公告)号：US10558711B2
公开(公告)日：2020-02-11
申请号：US14860784
申请日：2015-09-22
申请人： International Business Machines Corporation
发明人： Corville O. Allen , Joseph N. Kozhaya , Christopher M. Madison , Sai P. Peddi
IPC分类号： G06F16/93 , G06F16/28 , G06F16/901
摘要： According to one exemplary embodiment, a method for dynamically defining topics from content objects used to answer a question in a question answering system is provided. The method may include receiving the content objects. The method may include identifying the topics within the received content objects. The method may include generating a graph based on the identified plurality of topics, whereby nodes map to the topics. The method may include calculating edge weights associated with each edge based on semantic relations associated with the topics. The method may include determining if the calculated edge weight associated an edge exceeds a threshold value. The method may include generating a combination topic based on determining that the edge weight associated with the edge exceeds the threshold value.

4. 发明申请

US20160364449A1 COGNITIVE ARCHITECTURE WITH CONTENT PROVIDER MANAGED CORPUS 有权
标题翻译：内容提供商管理公司的认知架构
公开(公告)号：US20160364449A1
公开(公告)日：2016-12-15
申请号：US14739350
申请日：2015-06-15
申请人： International Business Machines Corporation
发明人： Joseph N. Kozhaya , Christopher M. Madison , Sridhar Sudarsan
IPC分类号： G06F17/30
CPC分类号： G06F17/30598
摘要： A method for controlled sharing, in a cognitive computing system having a memory and a processor, of content from a variety of content providers may include receiving, by the cognitive computing system, an inquiry, wherein the inquiry is directed to at least one content topic. The method may then include identifying, by the cognitive computing system, the at least one content topic, and determining that a cognitive component of the cognitive computing system managed by a content provider has access to a content repository addressing the at least one content topic. The method may further include distributing, by the cognitive computing system, the inquiry to the cognitive component. The method may additionally include receiving a response from the cognitive component.
摘要翻译：在具有来自各种内容提供商的内容的存储器和处理器的认知计算系统中的受控共享的方法可以包括由认知计算系统接收询问，其中查询针对至少一个内容主题。该方法然后可以包括由认知计算系统识别至少一个内容主题，并且确定由内容提供商管理的认知计算系统的认知组件可以访问解决该至少一个内容主题的内容存储库。该方法还可以包括由认知计算系统向认知组件分发查询。该方法可以另外包括从认知组件接收响应。

5. 发明申请

US20190251473A1 Cognitive System Virtual Corpus Training and Utilization 审中-公开
公开(公告)号：US20190251473A1
公开(公告)日：2019-08-15
申请号：US16391398
申请日：2019-04-23
申请人： International Business Machines Corporation
发明人： Joseph N. Kozhaya , Christopher M. Madison , Sridhar Sudarsan
IPC分类号： G06N20/00 , G06F16/93 , G06N5/02 , G06F16/33
CPC分类号： G06N20/00 , G06F16/3331 , G06F16/93 , G06N5/02
摘要： Mechanisms are provided for implementing a virtual corpus engine that receives an inquiry to be processed and analyzes the inquiry to extract one or more features of the inquiry. The virtual corpus engine selects a weight matrix associated with a virtual corpus based on the extracted one or more features of the inquiry. The virtual corpus comprises a plurality of actual corpora of information. The weight matrix comprises a separate weight value for each actual corpus in the plurality of actual corpora. The virtual corpus engine processes the inquiry using a set of selected actual corpora selected from the plurality of actual corpora based on the weight values in the weight matrix and receives results of the processing of the inquiry using the set of selected actual corpora. The virtual corpus engine outputs the results of the processing of the inquiry.

6. 发明申请

US20190034404A1 COGNITIVE MEDIATOR FOR GENERATING BLOCKCHAIN SMART CONTRACTS 审中-公开
公开(公告)号：US20190034404A1
公开(公告)日：2019-01-31
申请号：US15844577
申请日：2017-12-17
申请人： International Business Machines Corporation
发明人： Ryan Anderson , Joseph Kozhaya , Christopher M. Madison , John Wolpert
IPC分类号： G06F17/24 , H04L9/06 , G06Q40/02 , G06Q30/00
摘要： In an approach to generating blockchain smart contracts, one or more computer processors receive a request for a service from a user. The one or more computer processors extract one or more features from the request. The one or more computer processors determine one or more smart contract templates associated with the request based, at least in part, on the extracted one or more features. The one or more computer processors receive one or more responses to the request from one or more service providers. The one or more computer processors generate a draft smart contract based, at least in part on the determined one or more smart contract templates and the one or more received responses.

7. 发明申请

US20160371393A1 DEFINING DYNAMIC TOPIC STRUCTURES FOR TOPIC ORIENTED QUESTION ANSWER SYSTEMS 审中-公开
公开(公告)号：US20160371393A1
公开(公告)日：2016-12-22
申请号：US14740508
申请日：2015-06-16
申请人： International Business Machines Corporation
发明人： Corville O. Allen , Joseph N. Kozhaya , Christopher M. Madison , Sai P. Peddi
IPC分类号： G06F17/30
CPC分类号： G06F16/93 , G06F16/285 , G06F16/9024
摘要： According to one exemplary embodiment, a method for dynamically defining topics from content objects used to answer a question in a question answering system is provided. The method may include receiving the content objects. The method may include identifying the topics within the received content objects. The method may include generating a graph based on the identified plurality of topics, whereby nodes map to the topics. The method may include calculating edge weights associated with each edge based on semantic relations associated with the topics. The method may include determining if the calculated edge weight associated an edge exceeds a threshold value. The method may include generating a combination topic based on determining that the edge weight associated with the edge exceeds the threshold value.

8. 发明授权

US10521505B2 Cognitive mediator for generating blockchain smart contracts 有权
公开(公告)号：US10521505B2
公开(公告)日：2019-12-31
申请号：US15844577
申请日：2017-12-17
申请人： International Business Machines Corporation
发明人： Ryan Anderson , Joseph Kozhaya , Christopher M. Madison , John Wolpert
IPC分类号： G06F17/24 , G06Q40/02 , H04L9/06 , H04L9/32 , G06Q30/00
摘要： In an approach to generating blockchain smart contracts, one or more computer processors receive a request for a service from a user. The one or more computer processors extract one or more features from the request. The one or more computer processors determine one or more smart contract templates associated with the request based, at least in part, on the extracted one or more features. The one or more computer processors receive one or more responses to the request from one or more service providers. The one or more computer processors generate a draft smart contract based, at least in part on the determined one or more smart contract templates and the one or more received responses.

9. 发明授权

US10380257B2 Generating answers from concept-based representation of a topic oriented pipeline 有权
公开(公告)号：US10380257B2
公开(公告)日：2019-08-13
申请号：US14867720
申请日：2015-09-28
申请人： International Business Machines Corporation
发明人： Corville O. Allen , Joseph N. Kozhaya , Christopher M. Madison , Sai P. Peddi
IPC分类号： G06F17/30 , G06F17/27
摘要： According to one exemplary embodiment, a method for generating an answer in a question answering system is provided. The method may include receiving a question. The method may also include identifying a candidate answer from a corpus. The method may then include determining a plurality of sentences based on the identified candidate answer. The method may further include calculating a similarity value for each sentence within the plurality of sentences based on comparing the plurality of sentences to the candidate answer and the received question. The method may also include identifying at least one sentence within the plurality of sentences with a calculated similarity value that exceeds a threshold value. The method may then include generating the answer based on the candidate answer and the identified at least one sentence.

10. 发明申请

US20170076226A1 CATEGORIZING CONCEPT TERMS FOR GAME-BASED TRAINING IN COGNITIVE COMPUTING SYSTEMS 审中-公开
标题翻译：在认知计算系统中分类用于游戏式培训的概念条款
公开(公告)号：US20170076226A1
公开(公告)日：2017-03-16
申请号：US14919819
申请日：2015-10-22
申请人： International Business Machines Corporation
发明人： Corville O. Allen , Phaedra Boinodiris , Joseph N. Kozhaya , Christopher M. Madison , Sridhar Sudarsan
IPC分类号： G06N99/00 , G06N5/04 , G06F17/30
CPC分类号： G06N5/04 , A63F13/35 , A63F13/46 , A63F13/79 , G06F16/3329 , G06F16/3344 , G06F16/36
摘要： A first list that includes a first set of one or more concept terms may be obtained. The first set of one or more concept terms may be candidates for being conceptually related to a seed concept term. Prior to the obtaining, a first client computing device may provide a first plurality of individual characters and the seed concept term to a first user using the first client computing device. The first client computing device may prompt the first user to generate the first set of one or more concept terms that are conceptually related to the seed concept term using one or more of the first plurality of individual characters. In response to the obtaining, one or more particular categories to which each of the first set of one or more concept terms belongs to may be determined.
摘要翻译：可以获得包括一个或多个概念术语的第一组的第一列表。第一组一个或多个概念术语可以是在概念上与种子概念术语相关的候选。在获得之前，第一客户端计算设备可以使用第一客户端计算设备向第一用户提供第一多个单独字符和种子概念项。第一客户端计算设备可以提示第一用户使用第一多个单独字符中的一个或多个来生成概念上与种子概念项相关的一个或多个概念项的第一组。响应于获得，可以确定一个或多个概念术语的第一组中的每一个属于哪一个或多个特定类别。

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