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. 发明授权

US09720982B2 Method and apparatus for natural language search for variables 有权
公开(公告)号：US09720982B2
公开(公告)日：2017-08-01
申请号：US15219361
申请日：2016-07-26
申请人： Bank of America Corporation
发明人： Viju Kothuvatiparambil , Ramakrishna R. Yannam
IPC分类号： G06F17/00 , G06F17/30
CPC分类号： G06F17/3053 , G06F17/30011 , G06F17/30554 , G06F17/30654 , G06F17/30675 , G06F17/30867 , G06F17/30958
摘要： A method for natural language search for variables is provided. The method may include searching an index using key words from a user's natural language question and the context of the user's question. The index may reference variables and/or web service calls in a domain model. The method may also include saving documents obtained in response to the search. The method may also include mapping each of the documents as a node into an object graph. Each node may be associated with a parent node, except when the node is a root node. The method may also include identifying the root node of each document. The method may also include identifying the path of each node from the node to the node's root node. The method may also include identifying matching paths. Each matching path may provide an answer to the user's question.

2. 发明申请

US20160335267A1 METHOD AND APPARATUS FOR NATURAL LANGUAGE SEARCH FOR VARIABLES 有权
公开(公告)号：US20160335267A1
公开(公告)日：2016-11-17
申请号：US15219361
申请日：2016-07-26
申请人： Bank of America Corporation
发明人： Viju Kothuvatiparambil , Ramakrishna R. Yannam
IPC分类号： G06F17/30
CPC分类号： G06F17/3053 , G06F17/30011 , G06F17/30554 , G06F17/30654 , G06F17/30675 , G06F17/30867 , G06F17/30958
摘要： A method for natural language search for variables is provided. The method may include searching an index using key words from a user's natural language question and the context of the user's question. The index may reference variables and/or web service calls in a domain model. The method may also include saving documents obtained in response to the search. The method may also include mapping each of the documents as a node into an object graph. Each node may be associated with a parent node, except when the node is a root node. The method may also include identifying the root node of each document. The method may also include identifying the path of each node from the node to the node's root node. The method may also include identifying matching paths. Each matching path may provide an answer to the user's question.

3. 发明申请

US20150324455A1 METHOD AND APPARATUS FOR NATURAL LANGUAGE SEARCH FOR VARIABLES 有权
标题翻译：自然语言搜索方法与装置
公开(公告)号：US20150324455A1
公开(公告)日：2015-11-12
申请号：US14271571
申请日：2014-05-07
申请人： Bank of America Corporation
发明人： Viju Kothuvatiparambil , Ramakrishna R. Yannam
IPC分类号： G06F17/30
CPC分类号： G06F17/3053 , G06F17/30011 , G06F17/30554 , G06F17/30654 , G06F17/30675 , G06F17/30867 , G06F17/30958
摘要： A method for natural language search for variables is provided. The method may include searching an index using key words from a user's natural language question and the context of the user's question. The index may reference variables and/or web service calls in a domain model. The method may also include saving documents obtained in response to the search. The method may also include mapping each of the documents as a node into an object graph. Each node may be associated with a parent node, except when the node is a root node. The method may also include identifying the root node of each document. The method may also include identifying the path of each node from the node to the node's root node. The method may also include identifying matching paths. Each matching path may provide an answer to the user's question.
摘要翻译：提供了一种用于自然语言搜索变量的方法。该方法可以包括使用来自用户的自然语言问题的关键词和用户问题的上下文来搜索索引。索引可以引用域模型中的变量和/或Web服务调用。该方法还可以包括保存响应于搜索而获得的文档。该方法还可以包括将每个文档作为节点映射到对象图中。每个节点可以与父节点相关联，除非节点是根节点。该方法还可以包括识别每个文档的根节点。该方法还可以包括从节点到节点的根节点识别每个节点的路径。该方法还可以包括识别匹配路径。每个匹配路径可以提供用户问题的答案。

4. 发明授权

US10943185B1 Supervised machine-learning training platform with isolated update testing and bi-directional update propogation 有权
公开(公告)号：US10943185B1
公开(公告)日：2021-03-09
申请号：US16167811
申请日：2018-10-23
申请人： Bank of America Corporation
发明人： David H. Witting , Maruthi Z Shanmugam , Jamaal C. Long , Matthew Hsieh , Luis Gerardo Mojica de la Vega , Viju Kothuvatiparambil , Mahalakshmi Chandra Sekaran , Donatus Asumu , Karen Trevino
IPC分类号： G06N20/00 , G06F9/451 , G06F16/2457
摘要： Aspects of the disclosure relate to supervised machine-learning (“ML”) training platforms for artificial intelligence (“AI”) computer systems. The ML training platform may include isolated update testing. The isolated update testing may feature a plurality of environments with various levels of isolation. The ML training platform may also include bi-directional channels for controlled update propagation.

5. 发明授权

US10650812B2 Deterministic multi-length sliding window protocol for contiguous string entity 有权
公开(公告)号：US10650812B2
公开(公告)日：2020-05-12
申请号：US16101734
申请日：2018-08-13
申请人： Bank of America Corporation
发明人： Viju Kothuvatiparambil , Maruthi Z. Shanmugam , Donatus Asumu
IPC分类号： G10L15/197 , G10L15/26 , G10L15/30 , H04M3/493 , H04M3/51 , G06F16/33 , G06F16/9535 , G06F16/903 , G06F40/289
摘要： A system for extracting verifiable entities from a user-utterance received on an automated calling service is provided. The system may include a receiver configured to receive a user-utterance, a processor and a non-transitory computer-readable media comprising computer-executable instructions. The processor may be configured to execute the instructions which, canonicalize the user-utterance into a plurality of tokens, determine the number of tokens of the user-utterance, and generate, using a sliding-window protocol, a comprehensive number of n-gram sequences from the user-utterance. The processor may be configured to process a plurality of threads of execution that may include a series of actions executed on the n-gram sequences to identify and extract verified entities from the user-utterance.

6. 发明授权

US09424344B2 Method and apparatus for natural language search for variables 有权
标题翻译：自然语言搜索变量的方法和装置
公开(公告)号：US09424344B2
公开(公告)日：2016-08-23
申请号：US14271571
申请日：2014-05-07
申请人： Bank of America Corporation
发明人： Viju Kothuvatiparambil , Ramakrishna R. Yannam
IPC分类号： G06F17/30
CPC分类号： G06F17/3053 , G06F17/30011 , G06F17/30554 , G06F17/30654 , G06F17/30675 , G06F17/30867 , G06F17/30958
摘要： A method for natural language search for variables is provided. The method may include searching an index using key words from a user's natural language question and the context of the user's question. The index may reference variables and/or web service calls in a domain model. The method may also include saving documents obtained in response to the search. The method may also include mapping each of the documents as a node into an object graph. Each node may be associated with a parent node, except when the node is a root node. The method may also include identifying the root node of each document. The method may also include identifying the path of each node from the node to the node's root node. The method may also include identifying matching paths. Each matching path may provide an answer to the user's question.
摘要翻译：提供了一种用于自然语言搜索变量的方法。该方法可以包括使用来自用户的自然语言问题的关键词和用户问题的上下文来搜索索引。索引可以引用域模型中的变量和/或Web服务调用。该方法还可以包括保存响应于搜索而获得的文档。该方法还可以包括将每个文档作为节点映射到对象图中。每个节点可以与父节点相关联，除非节点是根节点。该方法还可以包括识别每个文档的根节点。该方法还可以包括从节点到节点的根节点识别每个节点的路径。该方法还可以包括识别匹配路径。每个匹配路径可以提供用户问题的答案。

7. 发明申请

US20210019611A1 DEEP LEARNING SYSTEM 有权
公开(公告)号：US20210019611A1
公开(公告)日：2021-01-21
申请号：US16511482
申请日：2019-07-15
申请人： Bank of America Corporation
发明人： Viju Kothuvatiparambil
IPC分类号： G06N3/08 , G06N20/20 , G06N3/04
摘要： A system for determining intents associated with human utterances at a voice response system is provided. The system may involve a machine learning classifier and a deep learning classifier. The machine learning classifier may receive labeled training data. The labeled training data may be sample utterances. Each sample utterance may be assigned an intent. The intent may be the label of the utterance. The intent may be included in a predefined plurality of intents. The machine learning classifier may include a feature engineering and extraction module. The feature engineering and extraction module may identify features specific to each intent. The machine learning classifier may label previously unlabeled utterances received in a production environment. The newly labeled utterances received in the production environment may be used as training data to train a deep learning classifier. After being trained, the deep learning classifier may receive and label previously unlabeled utterances.

8. 发明申请

US20200051552A1 DETERMINISTIC MULTI-LENGTH SLIDING WINDOW PROTOCOL FOR CONTIGUOUS STRING ENTITY 审中-公开
公开(公告)号：US20200051552A1
公开(公告)日：2020-02-13
申请号：US16101734
申请日：2018-08-13
申请人： Bank of America Corporation
发明人： Viju Kothuvatiparambil , Maruthi Z. Shanmugam , Donatus Asumu
IPC分类号： G10L15/197 , G06F17/27 , G10L15/26 , G10L15/30 , G06F17/30 , H04M3/493 , H04M3/51
摘要： A system for extracting verifiable entities from a user-utterance received on an automated calling service is provided. The system may include a receiver configured to receive a user-utterance, a processor and a non-transitory computer-readable media comprising computer-executable instructions. The processor may be configured to execute the instructions which, canonicalize the user-utterance into a plurality of tokens, determine the number of tokens of the user-utterance, and generate, using a sliding-window protocol, a comprehensive number of n-gram sequences from the user-utterance. The processor may be configured to process a plurality of threads of execution that may include a series of actions executed on the n-gram sequences to identify and extract verified entities from the user-utterance.

9. 发明申请

US20170147555A1 QUERY ANALYZER 审中-公开
公开(公告)号：US20170147555A1
公开(公告)日：2017-05-25
申请号：US14947055
申请日：2015-11-20
申请人： Bank of America Corporation
发明人： Ramakrishna R. Yannam , Viju Kothuvatiparambil , David H. Witting , Bharathiraja Krishnamoorthy , Mahalakshmi Chandra Sekaran , Sushil Golani
IPC分类号： G06F17/27 , G10L17/06 , G06F3/0484 , G06F17/30 , G06F3/0482
CPC分类号： G06F17/274 , G06F3/0482 , G06F3/04842 , G06F17/2785 , G06F17/30398 , G06F17/30401 , G06F17/30554
摘要： Methods for analyzing a query is provided. Methods may include receiving a query from a user. Methods may include dissecting the query into a plurality of word segments. Methods may include determining, based on a predetermined ontology, which of the plurality of words satisfies a predetermined ontological threshold and which words do not satisfy the predetermined ontological threshold. Methods may include discarding the words that do not satisfy the predetermined ontological threshold. Methods may include determining a part of speech associated with each word based on the content of the query. Methods may include determining a concept associated with each word based on the content of the query. Methods may include displaying to the user word that satisfies the predetermined threshold alongside the associated part of speech and associated concept. Methods may include enabling the user to change each word, each concept and each part of speech.

10. 发明申请

US20160203220A1 METHOD AND APPARATUS FOR NATURAL LANGUAGE SEARCHING BASED ON MCCS 审中-公开
标题翻译：基于MCCS的自然语言搜索方法与装置
公开(公告)号：US20160203220A1
公开(公告)日：2016-07-14
申请号：US14595279
申请日：2015-01-13
申请人： Bank of America Corporation
发明人： Viju Kothuvatiparambil , Stephen L. Yaeger , Marco A. Ramirez , Ramakrishna R. Yannam , David H. Witting
IPC分类号： G06F17/30 , G06Q10/10
CPC分类号： G06Q10/10
摘要： Apparatus, including a processor, for performing a search based, at least in part, on MCC information, is provided. The processor may identify an MCC with greater than a threshold level of correlation to a user's query. The processor may be configured to search a machine-readable memory for documents pertaining to the MCC and/or pertaining to the user's query. The processor may respond to the user's query by providing a set of documents. The processor may provide a reciprocal query. The reciprocal query may be for obtaining a greater quantum of MCC information then was included in the user's query. The reciprocal query may prompt the user to choose from one or more of a plurality of MCCs that correlate to the subject matter area. The reciprocal query may prompt a user to select from a plurality of subject matter areas corresponding to the plurality of MCCs.
摘要翻译：提供了至少部分地基于MCC信息执行搜索的装置，包括处理器。处理器可以识别具有大于用户查询的相关阈值水平的MCC。处理器可以被配置为在机器可读存储器中搜索与MCC有关的文档和/或与用户的查询有关的文档。处理器可以通过提供一组文档来响应用户的查询。处理器可以提供相互查询。相互查询可能是为了获得更大量的MCC信息，然后被包括在用户的查询中。相互查询可以提示用户从与主题区域相关联的多个MCC中的一个或多个MCC中进行选择。相互查询可以提示用户从与多个MCC相对应的多个主题区域中进行选择。

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