Patents by Inventor Prakash Khatri
Prakash Khatri 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: 11194973Abstract: A system that can engage in a dialog with a user may select a system response to a user input based on how the system estimates a user may respond to a potential system response. Models may be trained to evaluate a potential system response in view of various available data including dialog history, entity data, etc. Each model may score the potential system response for various qualitative aspects such as whether the response is likely to be comprehensible, on-topic, interesting, likely to lead to the dialog continuing, etc. Such scores may be combined to other scores such as whether the potential response is coherent or engaging. The models may be trained using previous dialog/chatbot evaluation data. At runtime the scores may be used to select a system response to a user input as part of the dialog.Type: GrantFiled: March 25, 2019Date of Patent: December 7, 2021Assignee: Amazon Technologies, Inc.Inventors: Rahul Goel, Chandra Prakash Khatri, Tagyoung Chung, Raefer Christopher Gabriel, Anushree Venkatesh, Behnam Hedayatnia, Sanghyun Yi
-
Publication number: 20210312914Abstract: Described herein is a system for rescoring automatic speech recognition hypotheses for conversational devices that have multi-turn dialogs with a user. The system leverages dialog context by incorporating data related to past user utterances and data related to the system generated response corresponding to the past user utterance. Incorporation of this data improves recognition of a particular user utterance within the dialog.Type: ApplicationFiled: June 7, 2021Publication date: October 7, 2021Inventors: Behnam Hedayatnia, Anirudh Raju, Ankur Gandhe, Chandra Prakash Khatri, Ariya Rastrow, Anushree Venkatesh, Arindam Mandal, Raefer Christopher Gabriel, Ahmad Shikib Mehri
-
Patent number: 11043214Abstract: Described herein is a system for rescoring automatic speech recognition hypotheses for conversational devices that have multi-turn dialogs with a user. The system leverages dialog context by incorporating data related to past user utterances and data related to the system generated response corresponding to the past user utterance. Incorporation of this data improves recognition of a particular user utterance within the dialog.Type: GrantFiled: November 29, 2018Date of Patent: June 22, 2021Assignee: Amazon Technologies, Inc.Inventors: Behnam Hedayatnia, Anirudh Raju, Ankur Gandhe, Chandra Prakash Khatri, Ariya Rastrow, Anushree Venkatesh, Arindam Mandal, Raefer Christopher Gabriel, Ahmad Shikib Mehri
-
Publication number: 20210056265Abstract: In various example embodiments, a system and method for a Target Language Engine are presented. The Target Language Engine augments a synonym list in a base dictionary of a target language with one or more historical search queries previously submitted to search one or more listings in listing data. The Target Language Engine identifies a compound word and a plurality of words present in the listing data that have a common meaning in the target language. Each word from the plurality of words is present in the compound word. The Target Language Engine causes a database to create an associative link between the portion of text and a word selected from at least one of the synonym list or the plurality of words.Type: ApplicationFiled: November 9, 2020Publication date: February 25, 2021Inventors: Chandra Prakash Khatri, Selcuk Kopru, Nish Parikh, Justin Nicholas House, Sameep Navin Solanki
-
Publication number: 20200320370Abstract: Systems, methods and media are provided for training a snippet extractor to create snippets based on information extracted from published descriptions. In one example, a computer-implemented method includes creating, based on a non-RNN (Recurrent Neural Network) extraction technique performed on the published descriptions, a plurality of base models, each base model including one or more sample description summaries; evaluating the base models using an evaluation technique; selecting an optimum base model; developing a classification model using RNN extraction, the classification model based on description summaries contained in the optimum base model; and using the classification model to train the snippet extractor by machine learning.Type: ApplicationFiled: April 24, 2020Publication date: October 8, 2020Inventors: Chandra Prakash Khatri, Nish Parikh, Sameep Navin Solanki, Justin Nicholas House, Gyanit Singh
-
Publication number: 20200117855Abstract: In various example embodiments, a system and method for a Target Language Engine are presented. The Target Language Engine augments a synonym list in a base dictionary of a target language with one or more historical search queries previously submitted to search one or more listings in listing data. The Target Language Engine identifies a compound word and a plurality of words present in the listing data that have a common meaning in the target language. Each word from the plurality of words is present in the compound word. The Target Language Engine causes a database to create an associative link between the portion of text and a word selected from at least one of the synonym list or the plurality of words.Type: ApplicationFiled: August 21, 2019Publication date: April 16, 2020Inventors: Chandra Prakash Khatri, Selcuk Kopru, Nish Parikh, Justin Nicholas House, Sameep Navin Solanki
-
Patent number: 10521509Abstract: In various example embodiments, a system and method for a Target Language Engine are presented. The Target Language Engine augments a synonym list in a base dictionary of a target language with one or more historical search queries previously submitted to search one or more listings in listing data. The Target Language Engine identifies a compound word and a plurality of words present in the listing data that have a common meaning in the target language. Each word from the plurality of words is present in the compound word. The Target Language Engine causes a database to create an associative link between the portion of text and a word selected from at least one of the synonym list or the plurality of words.Type: GrantFiled: August 15, 2016Date of Patent: December 31, 2019Assignee: eBay Inc.Inventors: Chandra Prakash Khatri, Selcuk Kopru, Nish Parikh, Justin Nicholas House, Sameep Navin Solanki
-
Publication number: 20180046611Abstract: In various example embodiments, a system and method for a Target Language Engine are presented. The Target Language Engine augments a synonym list in a base dictionary of a target language with one or more historical search queries previously submitted to search one or more listings in listing data. The Target Language Engine identifies a compound word and a plurality of words present in the listing data that have a common meaning in the target language. Each word from the plurality of words is present in the compound word. The Target Language Engine causes a database to create an associative link between the portion of text and a word selected from at least one of the synonym list or the plurality of words.Type: ApplicationFiled: August 15, 2016Publication date: February 15, 2018Inventors: Chandra Prakash Khatri, Selcuk Kopru, Nish Parikh, Justin Nicholas House, Sameep Navin Solanki
-
Publication number: 20170213130Abstract: Systems, methods and media are provided for training a snippet extractor to create snippets based on information extracted from published descriptions. In one example, a computer-implemented method includes creating, based on a non-RNN (Recurrent Neural Network) extraction technique performed on the published descriptions, a plurality of base models, each base model including one or more sample description summaries; evaluating the base models using an evaluation technique; selecting an optimum base model; developing a classification model using RNN extraction, the classification model based on description summaries contained in the optimum base model; and using the classification model to train the snippet extractor by machine learning.Type: ApplicationFiled: September 16, 2016Publication date: July 27, 2017Inventors: Chandra Prakash Khatri, Nish Parikh, Sameep Navin Solanki, Justin Nicholas House, Gyanit Singh
-
Publication number: 20170096614Abstract: A lubricant or lubricant additive composed of halogen-, phosphorus- and sulphur-free ionic liquids containing fatty acid anions exhibit superior friction-reducing and anti-wear properties. Preferably, the lubricant composition comprises a base oil and an ionic liquid or mixed of two or more ionic liquids having concentration of 0.5 wt. % or more. These halogen-, phosphorus- and sulphur-free ionic liquids as lubricant or lubricant additive have minimal hazardous and corrosion effect to the environment and engineering surfaces, respectively. General chemical formula of fatty acid anion is represented as RCOO?; whereas R may be C4 to C30 straight chain alkyl, branched alkyl, cycloalkyl, alkyl substituted cycloalkyl, cycloalkyl substituted alkyl, alkenyl (single or more double bonds) includes with or without branched structure and may contain heteroatom.Type: ApplicationFiled: March 17, 2015Publication date: April 6, 2017Inventors: Om Prakash KHATRI, Rashi GUSAIN
-
Patent number: 6900163Abstract: A thermal interface material including a compound which has high thermal conductivity, is dry-to-the-touch, but naturally tacky, and may be formed into various shapes, such as sheets and blocks, to serve as a heat transfer material for electronic components. The compound includes a pre-blend of a polyol ester and an antioxidant, a boron nitride filler, a high viscosity oil, and either a solvent, a surfactant, and a polystyrene-based polymer, or aluminum silicate. A method for using the compound includes the steps of providing a heat generating electronic component with a first surface; providing a heat dissipating component with a second surface with which the first surface is to interface; and disposing the compound between the respective surfaces to effectuate efficient heat transfer therebetween. Further, a removable liner can be applied to an exposed surface of the compound.Type: GrantFiled: July 3, 2003Date of Patent: May 31, 2005Assignee: AOS Thermal CompoundsInventor: Prakash Khatri
-
Publication number: 20040018945Abstract: A thermal interface material including a compound which has high thermal conductivity, is dry-to-the-touch, but naturally tacky, and may be formed into various shapes, such as sheets and blocks, to serve as a heat transfer material for electronic components. The compound includes a pre-blend of a polyol ester and an antioxidant, a boron nitride filler, a high viscosity oil, and either a solvent, a surfactant, and a polystyrene-based polymer, or aluminum silicate. A method for using the compound includes the steps of providing a heat generating electronic component with a first surface; providing a heat dissipating component with a second surface with which the first surface is to interface; and disposing the compound between the respective surfaces to effectuate efficient heat transfer therebetween. Further, a removable liner can be applied to an exposed surface of the compound.Type: ApplicationFiled: July 3, 2003Publication date: January 29, 2004Applicant: AOS Thermal CompoundsInventor: Prakash Khatri
-
Patent number: 6610635Abstract: A thermal interface material including a compound which has high thermal conductivity, is dry-to-the-touch, but naturally tacky, and may be formed into various shapes, such as sheets and blocks, to serve as a heat transfer material for electronic components. The compound includes a pre-blend of a polyol ester and an antioxidant, a filler(s), a high viscosity oil, and either a solvent, a surfactant, and a polystyrene-based polymer, or aluminum silicate. A method for using the compound includes the steps of providing a heat generating electronic component with a first surface; providing a heat dissipating component with a second surface with which the first surface is to interface; and disposing the compound between the respective surfaces to effectuate efficient heat transfer therebetween. Further, the compound can be applied alone, e.g.Type: GrantFiled: September 14, 2001Date of Patent: August 26, 2003Assignee: AOS Thermal CompoundsInventor: Prakash Khatri
-
Patent number: 6475962Abstract: A heat sink material for use in electronic assemblies is disclosed. The heat sink material is a thermal grease that due its composition is dry to the touch and thus eliminates the problems associated with thermal greases in electronic assemblies.Type: GrantFiled: September 14, 2000Date of Patent: November 5, 2002Assignee: AOS Thermal Compounds, LLCInventor: Prakash Khatri
-
Publication number: 20020086801Abstract: A thermal interface material including a compound which has high thermal conductivity, is dry-to-the-touch, but naturally tacky, and may be formed into various shapes, such as sheets and blocks, to serve as a heat transfer material for electronic components. The compound includes a pre-blend of a polyol ester and an antioxidant, a filler(s), a high viscosity oil, and either a solvent, a surfactant, and a polystyrene-based polymer, or aluminum silicate. A method for using the compound includes the steps of providing a heat generating electronic component with a first surface; providing a heat dissipating component with a second surface with which the first surface is to interface; and disposing the compound between the respective surfaces to effectuate efficient heat transfer therebetween. Further, the compound can be applied alone, e.g.Type: ApplicationFiled: September 14, 2001Publication date: July 4, 2002Inventor: Prakash Khatri