Patents by Inventor Abhijit SAVARKAR
Abhijit SAVARKAR has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11847151Abstract: A method of disambiguating user intent in conversational interactions for information retrieval is disclosed. The method includes providing access to a set of content items with metadata describing the content items and providing access to structural knowledge showing semantic relationships and links among the content items. The method further includes providing a user preference signature, receiving a first input from the user that is intended by the user to identify at least one desired content item, and determining an ambiguity index of the first input. If the ambiguity index is high, the method determines a query input based on the first input and at least one of the structural knowledge, the user preference signature, a location of the user, and the time of the first input and selects a content item based on comparing the query input and the metadata associated with the content item.Type: GrantFiled: May 10, 2021Date of Patent: December 19, 2023Assignee: Veveo, Inc.Inventors: Murali Aravamudan, Rakesh Barve, Sashikumar Venkataraman, Vineet Agarwal, Abhijit Savarkar, Ganesh Ramamoorthy, Ahmed Nizam Mohaideen Pathurudeen, K China Srinivasulu Reddy
-
Publication number: 20230205798Abstract: A method of disambiguating user intent in conversational interactions for information retrieval is disclosed. The method includes providing access to a set of content items with metadata describing the content items and providing access to structural knowledge showing semantic relationships and links among the content items. The method further includes providing a user preference signature, receiving a first input from the user that is intended by the user to identify at least one desired content item, and determining an ambiguity index of the first input. If the ambiguity index is high, the method determines a query input based on the first input and at least one of the structural knowledge, the user preference signature, a location of the user, and the time of the first input and selects a content item based on comparing the query input and the metadata associated with the content item.Type: ApplicationFiled: February 28, 2023Publication date: June 29, 2023Inventors: Murali Aravamudan, Rakesh Barve, Sashikumar Venkataraman, Vineet Agarwal, Abhijit Savarkar, Ganesh Ramamoorthy, Ahmed Nizam Mohaideen Pathurudeen, K China Srinivasulu Reddy
-
Publication number: 20220365994Abstract: Systems and methods are described herein for updating links between keywords associated with a trending topic. Control circuitry may identify a plurality of communications associated with a plurality of users, the plurality of communications being related to a topic. The communications may comprise, for example, emails, text messages, online social media posts, websites or portions of a website, or any other online communication. The control circuitry may determine whether the topic is trending and increase a strength of association between a first symbol associated with the topic and a second symbol associated with the topic such that when a search query is received that includes the first symbol, search results related to the second symbol have a higher probability of being returned.Type: ApplicationFiled: June 1, 2022Publication date: November 17, 2022Inventors: Sankar Ardhanari, Daren Gill, Abhijit Savarkar, Ganesh Ramamoorthy, Ajay Gupta, Vineet Agarwal, Sashikumar Venkataraman
-
Patent number: 11430435Abstract: Techniques for selectively requesting feedback from users are described. A system may receive a user input and perform an action responsive to the user input. The system may determine whether feedback should be requested from the user. Such determination may be based on various signals such as the user's present emotional state, whether the user input included profanity, whether the user input interrupted an output of the system, etc. When the system determines feedback should be requested, the system may select a feedback prompt pre-established by a domain, skill, or the like. After the system outputs the response to the user input, the system may output the feedback prompt.Type: GrantFiled: December 13, 2018Date of Patent: August 30, 2022Assignee: Amazon Technologies, Inc.Inventors: Eliav Kahan, David Smith, Matthew Fuller Sly, Joel Toledano, Abhijit Savarkar
-
Patent number: 11379544Abstract: Systems and methods are described herein for updating links between keywords associated with a trending topic. Control circuitry may identify a plurality of communications associated with a plurality of users, the plurality of communications being related to a topic. The communications may comprise, for example, emails, text messages, online social media posts, websites or portions of a website, or any other online communication. The control circuitry may determine whether the topic is trending and increase a strength of association between a first symbol associated with the topic and a second symbol associated with the topic such that when a search query is received that includes the first symbol, search results related to the second symbol have a higher probability of being returned.Type: GrantFiled: August 31, 2018Date of Patent: July 5, 2022Assignee: Rovi Guides, Inc.Inventors: Sankar Ardhanari, Daren Gill, Abhijit Savarkar, Ganesh Ramamoorthy, Ajay Gupta, Vineet Agarwal, Sashikumar Venkataraman
-
Publication number: 20210319048Abstract: A method of disambiguating user intent in conversational interactions for information retrieval is disclosed. The method includes providing access to a set of content items with metadata describing the content items and providing access to structural knowledge showing semantic relationships and links among the content items. The method further includes providing a user preference signature, receiving a first input from the user that is intended by the user to identify at least one desired content item, and determining an ambiguity index of the first input. If the ambiguity index is high, the method determines a query input based on the first input and at least one of the structural knowledge, the user preference signature, a location of the user, and the time of the first input and selects a content item based on comparing the query input and the metadata associated with the content item.Type: ApplicationFiled: May 10, 2021Publication date: October 14, 2021Inventors: Murali Aravamudan, Rakesh Barve, Sashikumar Venkataraman, Vineet Agarwal, Abhijit Savarkar, Ganesh Ramamoorthy, Ahmed Nizam Mohaideen Pathurudeen, K China Srinivasulu Reddy
-
Patent number: 11093538Abstract: A method of disambiguating user intent in conversational interactions for information retrieval is disclosed. The method includes providing access to a set of content items with metadata describing the content items and providing access to structural knowledge showing semantic relationships and links among the content items. The method further includes providing a user preference signature, receiving a first input from the user that is intended by the user to identify at least one desired content item, and determining an ambiguity index of the first input. If the ambiguity index is high, the method determines a query input based on the first input and at least one of the structural knowledge, the user preference signature, a location of the user, and the time of the first input and selects a content item based on comparing the query input and the metadata associated with the content item.Type: GrantFiled: January 15, 2020Date of Patent: August 17, 2021Assignee: Veveo, Inc.Inventors: Murali Aravamudan, Rakesh Barve, Sashikumar Venkataraman, Vineet Agarwal, Abhijit Savarkar, Ganesh Ramamoorthy, Ahmed Nizam Mohaideen Pathurudeen, K China Srinivasulu Reddy
-
Publication number: 20200167376Abstract: A method of disambiguating user intent in conversational interactions for information retrieval is disclosed. The method includes providing access to a set of content items with metadata describing the content items and providing access to structural knowledge showing semantic relationships and links among the content items. The method further includes providing a user preference signature, receiving a first input from the user that is intended by the user to identify at least one desired content item, and determining an ambiguity index of the first input. If the ambiguity index is high, the method determines a query input based on the first input and at least one of the structural knowledge, the user preference signature, a location of the user, and the time of the first input and selects a content item based on comparing the query input and the metadata associated with the content item.Type: ApplicationFiled: January 15, 2020Publication date: May 28, 2020Inventors: Murali Aravamudan, Rakesh Barve, Sashikumar Venkataraman, Vineet Agarwal, Abhijit Savarkar, Ganesh Ramamoorthy, Ahmed Nizam Mohaideen Pathurudeen, K China Srinivasulu Reddy
-
Patent number: 10572520Abstract: A method of disambiguating user intent in conversational interactions for information retrieval is disclosed. The method includes providing access to a set of content items with metadata describing the content items and providing access to structural knowledge showing semantic relationships and links among the content items. The method further includes providing a user preference signature, receiving a first input from the user that is intended by the user to identify at least one desired content item, and determining an ambiguity index of the first input. If the ambiguity index is high, the method determines a query input based on the first input and at least one of the structural knowledge, the user preference signature, a location of the user, and the time of the first input and selects a content item based on comparing the query input and the metadata associated with the content item.Type: GrantFiled: September 27, 2016Date of Patent: February 25, 2020Assignee: VEVEO, INC.Inventors: Murali Aravamudan, Rakesh Barve, Sashikumar Venkataraman, Vineet Agarwal, Abhijit Savarkar, Ganesh Ramamoorthy, Ahmed Nizam Mohaideen Pathurudeen, K China Srinivasulu Reddy
-
Publication number: 20190087502Abstract: Systems and methods are described herein for updating links between keywords associated with a trending topic. Control circuitry may identify a plurality of communications associated with a plurality of users, the plurality of communications being related to a topic. The communications may comprise, for example, emails, text messages, online social media posts, websites or portions of a website, or any other online communication. The control circuitry may determine whether the topic is trending and increase a strength of association between a first symbol associated with the topic and a second symbol associated with the topic such that when a search query is received that includes the first symbol, search results related to the second symbol have a higher probability of being returned.Type: ApplicationFiled: August 31, 2018Publication date: March 21, 2019Inventors: Sankar Ardhanari, Daren Gill, Abhijit Savarkar, Ganesh Ramamoorthy, Ajay Gupta, Vineet Agarwal, Sashikumar Venkataraman
-
Patent number: 10068023Abstract: Systems and methods are described herein for updating links between keywords associated with a trending topic. Control circuitry may identify a plurality of communications associated with a plurality of users, the plurality of communications being related to a topic. The communications may comprise, for example, emails, text messages, online social media posts, websites or portions of a website, or any other online communication. The control circuitry may determine whether the topic is trending and increase a strength of association between a first symbol associated with the topic and a second symbol associated with the topic such that when a search query is received that includes the first symbol, search results related to the second symbol have a higher probability of being returned.Type: GrantFiled: March 30, 2015Date of Patent: September 4, 2018Assignee: Rovi Guides, Inc.Inventors: Sankar Ardhanari, Daren Gill, Abhijit Savarkar, Ganesh Ramamoorthy, Ajay Gupta, Vineet Agarwal, Sashikumar Venkataraman
-
Publication number: 20170017719Abstract: A method of disambiguating user intent in conversational interactions for information retrieval is disclosed. The method includes providing access to a set of content items with metadata describing the content items and providing access to structural knowledge showing semantic relationships and links among the content items. The method further includes providing a user preference signature, receiving a first input from the user that is intended by the user to identify at least one desired content item, and determining an ambiguity index of the first input. If the ambiguity index is high, the method determines a query input based on the first input and at least one of the structural knowledge, the user preference signature, a location of the user, and the time of the first input and selects a content item based on comparing the query input and the metadata associated with the content item.Type: ApplicationFiled: September 27, 2016Publication date: January 19, 2017Inventors: Murali Aravamudan, Rakesh Barve, Sashikumar Venkataraman, Vineet Agarwal, Abhijit Savarkar, Ganesh Ramamoorthy, Ahmed Nizam Mohaideen Pathurudeen, K China Srinivasulu Reddy
-
Patent number: 9465833Abstract: A method of disambiguating user intent in conversational interactions for information retrieval is disclosed. The method includes providing access to a set of content items with metadata describing the content items and providing access to structural knowledge showing semantic relationships and links among the content items. The method further includes providing a user preference signature, receiving a first input from the user that is intended by the user to identify at least one desired content item, and determining an ambiguity index of the first input. If the ambiguity index is high, the method determines a query input based on the first input and at least one of the structural knowledge, the user preference signature, a location of the user, and the time of the first input and selects a content item based on comparing the query input and the metadata associated with the content item.Type: GrantFiled: March 13, 2013Date of Patent: October 11, 2016Assignee: VEVEO, INC.Inventors: Murali Aravamudan, Rakesh Barve, Sashikumar Venkataraman, Vineet Agarwal, Abhijit Savarkar, Ganesh Ramamoorthy, Ahmed Nizam Mohaideen Pathurudeen, K China Srinivasulu Reddy
-
Publication number: 20160188729Abstract: Systems and methods are described herein for updating links between keywords associated with a trending topic. Control circuitry may identify a plurality of communications associated with a plurality of users, the plurality of communications being related to a topic. The communications may comprise, for example, emails, text messages, online social media posts, websites or portions of a website, or any other online communication. The control circuitry may determine whether the topic is trending and increase a strength of association between a first symbol associated with the topic and a second symbol associated with the topic such that when a search query is received that includes the first symbol, search results related to the second symbol have a higher probability of being returned.Type: ApplicationFiled: March 30, 2015Publication date: June 30, 2016Inventors: Sankar Ardhanari, Daren Gill, Abhijit Savarkar, Ganesh Ramamoorthy, Ajay Gupta, Vineet Agarwal, Sashikumar Venkataraman
-
Publication number: 20140040274Abstract: A method of disambiguating user intent in conversational interactions for information retrieval is disclosed. The method includes providing access to a set of content items with metadata describing the content items and providing access to structural knowledge showing semantic relationships and links among the content items. The method further includes providing a user preference signature, receiving a first input from the user that is intended by the user to identify at least one desired content item, and determining an ambiguity index of the first input. If the ambiguity index is high, the method determines a query input based on the first input and at least one of the structural knowledge, the user preference signature, a location of the user, and the time of the first input and selects a content item based on comparing the query input and the metadata associated with the content item.Type: ApplicationFiled: March 13, 2013Publication date: February 6, 2014Inventors: Murali ARAVAMUDAN, Rakesh BARVE, Sashikumar VENKATARAMAN, Vineet AGARWAL, Abhijit SAVARKAR, Ganesh RAMAMOORTHY, Ahmed Nizam MOHAIDEEN PATHURUDEEN, K China Srinivasulu REDDY