Patents by Inventor Sachin Midha
Sachin Midha 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: 11869490Abstract: Techniques for tuning parameters for machine learning models are described. Different values for a parameter are tested to determine the value that results in an optimized model. A parameter value may be selected for testing using a search algorithm based on how the model performs with respect to other values for the parameter. Different values may be tested until a stopping criterion (such as time for testing, number of trials, amount of enhancement in performance, etc.) is met. In some embodiments, the techniques may be used to determine parameter values for natural language processing models.Type: GrantFiled: August 14, 2020Date of Patent: January 9, 2024Assignee: Amazon Technologies, Inc.Inventors: Rahul Gupta, Jwala Dhamala, Melanie C B Gens, Sachin Midha, Jennifer Yuen, Dewan Muhammed Ibtesham, Wael Hamza, Xinhong Zhang, Md Humayun Arafat
-
Publication number: 20230334547Abstract: The systems and methods disclosed herein can increase the speed and ease with which a user can discover compatible replacement parts for a specified model of a product by automatically determining when the user is interested in replacement parts. A replacement part system can conclude that a user is looking for replacement parts based on the user's search queries, the user's browsing behavior, or the user's prior purchases. By automatically deducing an intention to purchase a replacement part, the replacement part system can make it easier for a user to locate suitable replacement parts. In addition, the replacement part system can be configured to tailor listing set of replacement parts search results it provides to a user. The set of search results can be tailored based on a number of criteria to increase the speed with which the user finds a compatible replacement part.Type: ApplicationFiled: June 23, 2023Publication date: October 19, 2023Inventors: Meghan Lagoni, Chad Pham Driesbach, Andrew Robert Toner, Sachin Midha, Jai P. Chabria, Nirav Praful Desai, Brad P. Bonnett, Nicholas Stephen Bogert, Thiyagarajan Ramasamy
-
Patent number: 11727459Abstract: The systems and methods disclosed herein can increase the speed and ease with which a user can discover compatible replacement parts for a specified model of a product by automatically determining when the user is interested in replacement parts. A replacement part system can conclude that a user is looking for replacement parts based on the user's search queries, the user's browsing behavior, or the user's prior purchases. By automatically deducing an intention to purchase a replacement part, the replacement part system can make it easier for a user to locate suitable replacement parts. In addition, the replacement part system can be configured to tailor listing set of replacement parts search results it provides to a user. The set of search results can be tailored based on a number of criteria to increase the speed with which the user finds a compatible replacement part.Type: GrantFiled: July 17, 2020Date of Patent: August 15, 2023Assignee: Amazon Technologies, Inc.Inventors: Meghan Lagoni, Chad Pham Driesbach, Andrew Robert Toner, Sachin Midha, Jai P. Chabria, Nirav Praful Desai, Brad P. Bonnett, Nicholas Stephen Bogert, Thiyagarajan Ramasamy
-
Publication number: 20230142272Abstract: Techniques for evaluating a natural language understanding (NLU) component and determining an action to resolve an issue processing a user input are described. The system determines which component is invoked by a baseline NLU component is processing the user input, and which component is invoked by an updated NLU component. Based on that information, the system selects the action to resolve the updated NLU component generating an undesired response to the user input.Type: ApplicationFiled: October 26, 2022Publication date: May 11, 2023Inventors: Pavel Bhowmik, Melanie C B Gens, Sachin Midha, Rahul Gupta, Sriram Venkatapathy, Xinhong Zhang, Anoop Kumar, Pooja Sanjay Sonawane, Samuel Harry Ingbar
-
Patent number: 11507752Abstract: Techniques for evaluating a natural language understanding (NLU) component and determining an action to resolve an issue processing a user input are described. The system determines which component is invoked by a baseline NLU component is processing the user input, and which component is invoked by an updated NLU component. Based on that information, the system selects the action to resolve the updated NLU component generating an undesired response to the user input.Type: GrantFiled: August 26, 2020Date of Patent: November 22, 2022Assignee: Amazon Technologies, Inc.Inventors: Pavel Bhowmik, Melanie C B Gens, Sachin Midha, Rahul Gupta, Sriram Venkatapathy, Xinhong Zhang, Anoop Kumar, Pooja Sanjay Sonawane, Samuel Harry Ingbar
-
Publication number: 20200349626Abstract: The systems and methods disclosed herein can increase the speed and ease with which a user can discover compatible replacement parts for a specified model of a product by automatically determining when the user is interested in replacement parts. A replacement part system can conclude that a user is looking for replacement parts based on the user's search queries, the user's browsing behavior, or the user's prior purchases. By automatically deducing an intention to purchase a replacement part, the replacement part system can make it easier for a user to locate suitable replacement parts. In addition, the replacement part system can be configured to tailor listing set of replacement parts search results it provides to a user. The set of search results can be tailored based on a number of criteria to increase the speed with which the user finds a compatible replacement part.Type: ApplicationFiled: July 17, 2020Publication date: November 5, 2020Inventors: Meghan Lagoni, Chad Pham Driesbach, Andrew Robert Toner, Sachin Midha, Jai P. Chabria, Nirav Praful Desai, Brad P. Bonnett, Nicholas Stephen Bogert, Thiyagarajan Ramasamy
-
Patent number: 10748200Abstract: The systems and methods disclosed herein can increase the speed and ease with which a user can discover compatible replacement parts for a specified model of a product by automatically determining when the user is interested in replacement parts. A replacement part system can conclude that a user is looking for replacement parts based on the user's search queries, the user's browsing behavior, or the user's prior purchases. By automatically deducing an intention to purchase a replacement part, the replacement part system can make it easier for a user to locate suitable replacement parts. In addition, the replacement part system can be configured to tailor listing set of replacement parts search results it provides to a user. The set of search results can be tailored based on a number of criteria to increase the speed with which the user finds a compatible replacement part.Type: GrantFiled: March 3, 2015Date of Patent: August 18, 2020Assignee: Amazon Technologies, Inc.Inventors: Meghan Lagoni, Chad Pham Driesbach, Andrew Robert Toner, Sachin Midha, Jai P. Chabria, Nirav Praful Desai, Brad P. Bonnett, Nicholas Stephen Bogert, Thiyagarajan Ramasamy
-
Patent number: 9665900Abstract: Systems and methods herein can generate sales rankings for parts based on one or more metrics, such as geographic location of purchasers of the parts or based on items owned by users that function in conjunction with the parts. The systems can present the sales rankings to a user based on another item owned by the user. For example, sales rankings of memory can be presented to a user based on a laptop model owned by the user. Thus, users can determine how popular a part is among particular segments of the population, such as among users living in a certain geographic region, or among users who own a particular item designed to operate with the part. Moreover, the sales rankings can be used to generate recommendations of parts based on a corresponding item owned by the user that is configured to function with the part type.Type: GrantFiled: June 7, 2013Date of Patent: May 30, 2017Assignee: Amazon Technologies, Inc.Inventors: Jeremy Todd Claeson, Darshan Dev Bildikar, Christopher Warren Bryant, Edward Charles Grenier, Samuel Stevens Heyworth, Sachin Midha, Balu Ramu, Ambareesha Raghothaman, Andrew Robert Toner
-
Publication number: 20160260152Abstract: The systems and methods disclosed herein can increase the speed and ease with which a user can discover compatible replacement parts for a specified model of a product by automatically determining when the user is interested in replacement parts. A replacement part system can conclude that a user is looking for replacement parts based on the user's search queries, the user's browsing behavior, or the user's prior purchases. By automatically deducing an intention to purchase a replacement part, the replacement part system can make it easier for a user to locate suitable replacement parts. In addition, the replacement part system can be configured to tailor listing set of replacement parts search results it provides to a user. The set of search results can be tailored based on a number of criteria to increase the speed with which the user finds a compatible replacement part.Type: ApplicationFiled: March 3, 2015Publication date: September 8, 2016Inventors: Meghan Lagoni, Chad Pham Driesbach, Andrew Robert Toner, Sachin Midha, Jai P. Chabria, Nirav Praful Desai, Brad P. Bonnett, Nicholas Stephen Bogert, Thiyagarajan Ramasamy