-
1.
公开(公告)号:US20180349473A1
公开(公告)日:2018-12-06
申请号:US15614727
申请日:2017-06-06
发明人: Andrew J. SMITH , Saravana Perumal SHANMUGAM , Adam Kenneth HOSP , Ted P. SANDERS, Jr. , Michael K. FORBIS , Sarala BURADAGUNTA
CPC分类号: G06F17/3064 , G06F17/30401
摘要: A method and system are described that provide responses to natural language queries regarding the performance of a business. The method and system provide for crowd-sourced data to determine natural language query suggestions to transmit to a user, based upon previously submitted questions of the user and/or similar merchants to the user. Natural language query suggestions may be provided as utterances to a keyboard of a merchant user. The merchant user may select one or more suggestions provided. The use of natural language queries and responses allows a merchant without a business intelligence background to obtain business insights easily and accurately assess his performance (e.g., against similar merchants, etc.) without personally identifiable or confidential information of other merchants being compromised.
-
公开(公告)号:US20180307770A1
公开(公告)日:2018-10-25
申请号:US15719114
申请日:2017-09-28
发明人: John P. Sadauskas, JR. , Erik R. Racho , Xindeling Pan , Lynn Chang , Anne Hong , Keith Jones , Miles T. Loring , Paul C. Grudnitski , Vishal Kapoor
IPC分类号: G06F17/30
CPC分类号: G06F17/30876 , G06F17/30401 , G06F17/3053 , G06F17/30554 , G06F17/30613 , G06F17/30696 , G06Q10/06398 , G06Q50/205 , G09B7/02
摘要: Systems and methods for automated aggregated content commenting are disclosed herein. Such a system can include a memory including a content database; an evaluation criteria database; and a comment database. The system can include at least one server. The at least one server can: receive a content identifier; receive a user identifier; provide a representation of the piece of content to the user; receive a comment from the user identifying a portion of the piece of content; generate a portion of the comment database linked to the user and the content; generate an entry in the portion of the comment database linked to the user and the content; and store the comment in the entry in the portion of the comment database.
-
公开(公告)号:US20180307738A1
公开(公告)日:2018-10-25
申请号:US16016959
申请日:2018-06-25
CPC分类号: G06F17/30595 , G06F17/278 , G06F17/30401 , G06F17/30528 , G06F17/3053 , G06F17/30867 , H04L51/32 , H04L67/1044 , H04L67/22 , H04L67/306
摘要: A method for identifying at least one contact associated with a user and an online communication network. The method may include receiving at least one search term or a social media post entered by the user. The method may also include performing text analytics on the received search term or the social media post to determine at least one subject. The method may further include identifying a plurality of contacts associated with the user, whereby the user and the plurality of contacts are associated with the online communication network. The method may additionally include performing text analytics on a plurality of communications associated with the identified plurality of contacts to determine a plurality of context information. The method may include comparing the determined subject to the determined plurality of context information. The method may include identifying at least one contact within the identified plurality of contacts based on the comparing.
-
公开(公告)号:US20180307724A1
公开(公告)日:2018-10-25
申请号:US15961158
申请日:2018-04-24
申请人: Oath Inc.
发明人: Davood Shamsi , Wan Kim Mok , William Edward Pence
CPC分类号: G06F17/30398 , G06F17/2785 , G06F17/30401 , G06F17/30864 , G06F17/30958
摘要: Embodiments of the present invention provide systems, methods, and computer storage media directed at interpreting a query related to a dataset to reduce ambiguity of the query. In embodiments, a method includes determining potential meanings of words of a natural language query related to a particular dataset. A matching graph can be generated for the words of the query and the potential meanings for the words including similarity scores for the potential meanings. The method further includes reducing ambiguity of the matching graph by assigning selected potential meanings to the words. Upon reducing ambiguity of the matching graph, the matching graph can be used to provide a response to the query. Other embodiments may be described and/or claimed herein.
-
公开(公告)号:US20180225337A1
公开(公告)日:2018-08-09
申请号:US15941997
申请日:2018-03-30
申请人: Google LLC
发明人: Young Hoon Jung , Dong Hyun Kim
CPC分类号: G06F17/30528 , G06F17/243 , G06F17/30342 , G06F17/30401 , G06F17/30867 , G06Q10/00
摘要: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for populating a form using a search query. In one aspect, a method include actions of providing a form for display on a user device. Additional actions include, while a particular field of the form is selected, receiving a request to perform a search query, in response to receiving the request, receiving one or more query terms, obtaining a result of performing a search query that includes the one or more query terms, and automatically populating the particular field of the form with the result of the search query.
-
公开(公告)号:US20180189269A1
公开(公告)日:2018-07-05
申请号:US15395961
申请日:2016-12-30
发明人: Christopher Brian Quirk , Kristina Nikolova Toutanova , Wen-tau Yih , Hoifung Poon , Nanyun Peng
IPC分类号: G06F17/27
CPC分类号: G06F17/2775 , G06F17/20 , G06F17/271 , G06F17/275 , G06F17/2755 , G06F17/278 , G06F17/2785 , G06F17/30401 , G06N3/0445 , G06N3/0454 , G06N5/022
摘要: Long short term memory units that accept a non-predefined number of inputs are used to provide natural language relation extraction over a user-specified range on content. Content written for human consumption is parsed with distant supervision in segments (e.g., sentences, paragraphs, chapters) to determine relationships between various words within and between those segments.
-
7.
公开(公告)号:US20180189264A1
公开(公告)日:2018-07-05
申请号:US15617407
申请日:2017-06-08
发明人: Bharath Dandala , Ravi S. Sinha
CPC分类号: G06F17/277 , G06F17/2276 , G06F17/2795 , G06F17/2872 , G06F17/30401
摘要: An approach is provided that returns a simplified set of text to a user of a natural language processing (NLP) system with the simplified set of text having a complexity appropriate to the reading level of the user. The approach receives a word that belongs to a first natural language and retrieves a first set of complexity data pertaining to the word in the first natural language. The approach translates the word to one or more translated words, with each of the translated words corresponding to one or more second natural languages. The approach then retrieves sets of complexity data, with the sets of complexity data corresponding to a different translated word. The approach determines a complexity of the word in the first natural language based on an analysis of the first and second sets of complexity data.
-
公开(公告)号:US09977808B2
公开(公告)日:2018-05-22
申请号:US14746818
申请日:2015-06-22
申请人: SAP SE
发明人: Vimal Sharma , Debasish Panda
CPC分类号: G06F17/30345 , G06F17/30401 , G06F17/30554 , G06Q10/067
摘要: Various embodiments of systems and methods to provide intent based real-time analytical visualizations are described herein. In one aspect, a requirement statement is received at real-time to generate visualization analysis. Further, an analytical requirement statement is generated from the received requirement statement by natural language processing. The analytical requirement statement is mapped with a unique analytical profile of a user associated with the requirement statement and corresponding business data artifacts, and the visualization analysis is generated based on the mapping information. The generated visualization analysis is displayed on a computer generated graphical user interface (GUI).
-
9.
公开(公告)号:US20180089572A1
公开(公告)日:2018-03-29
申请号:US15846044
申请日:2017-12-18
发明人: Eric Aili , Rebecca Jonsson , Siem Uittenhout , Gareth Walters , Andreas Wieweg , Lucas Willering
CPC分类号: G06N5/022 , G06F8/41 , G06F8/71 , G06F9/445 , G06F9/453 , G06F17/241 , G06F17/27 , G06F17/2785 , G06F17/30401 , G06N99/005
摘要: A system for hybrid approach to natural language understanding is provided, comprising a machine learning configured to create a new natural language understanding model from user-provided examples, and provide a natural language understanding model dataset to other components of the system; an integrated development environment configured to retrieve the natural language understanding model dataset, and publish a hybrid runtime solution; and an interaction engine configured to: retrieve the hybrid runtime solution, receive a natural language input, and process the natural language input and generate a log dataset; wherein, the log dataset may be used to retrain and improve existing models.
-
公开(公告)号:US09921680B2
公开(公告)日:2018-03-20
申请号:US15245761
申请日:2016-08-24
发明人: Thomas Francis
CPC分类号: G06F3/0414 , G06F3/016 , G06F3/044 , G06F17/30401 , G06F17/30477 , G06F17/30554 , G06F17/3056 , G06F17/30761 , G06F17/30769 , G06F17/30976 , H04L51/046
摘要: Techniques include receiving a pressure input from a user of a user device at a pressure-sensitive display of the device and determining that the display is covered (e.g., obscured from the user's view) using the device. The techniques further include, in response to receiving the pressure input and determining that the display is covered, receiving a search query from the user at the device via voice input, transmitting the query to a search system via a network using the device, and receiving search results from the system at the device subsequent to transmitting the query. The techniques also include performing one or more actions associated with the search results using the user device (e.g., displaying the results to the user at the display, providing a text-to-speech or playback output for the results to the user, and/or forwarding the results to another computing device for display and/or text-to-speech or playback output).
-
-
-
-
-
-
-
-
-