Patents by Inventor Alan Xinyu GUO
Alan Xinyu GUO 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: 11847168Abstract: A method of training a conversational computing system. The method includes providing an initial query to a machine learning model previously trained to generate actions for responding to a query. Based on the initial query, a plurality of candidate actions are received from the machine learning model and presented via a training interface. Based on input provided by the human annotator, a selected candidate action is recognized and associated with the initial query in a labeled data example.Type: GrantFiled: December 20, 2019Date of Patent: December 19, 2023Assignee: Microsoft Technology Licensing, LLCInventors: Alan Xinyu Guo, Jesse Daniel Eskes Rusak
-
Patent number: 11790897Abstract: A computer-implemented method of responding to a conversational event is presented. The method comprises receiving a conversational event at a conversational computing interface. Based on the received conversational event, an applicable generation rule of a plurality of candidate generation rules is selected. The applicable generation rule is configured with one or more parameters. A computer-executable plan is then selected based on the selected generation rule. The one or more parameters are passed from the selected generation rule to one or more additional generation rules. The one or more additional generation rules configured with the one or more parameters are recursively applied to extend the selected computer-executable plan. One or more candidate responses to the conversational event are output via the conversational computing interface based on the recursive application of the one or more additional generation rules configured with the one or more parameters.Type: GrantFiled: August 8, 2022Date of Patent: October 17, 2023Assignee: Microsoft Technology Licensing, LLCInventors: Jacob Daniel Andreas, Jayant Sivarama Krishnamurthy, Alan Xinyu Guo, Andrei Vorobev, John Philip Bufe, III, Jesse Daniel Eskes Rusak, Yuchen Zhang
-
Publication number: 20220382996Abstract: A computer-implemented method of responding to a conversational event is presented. The method comprises receiving a conversational event at a conversational computing interface. Based on the received conversational event, an applicable generation rule of a plurality of candidate generation rules is selected. The applicable generation rule is configured with one or more parameters. A computer-executable plan is then selected based on the selected generation rule. The one or more parameters are passed from the selected generation rule to one or more additional generation rules. The one or more additional generation rules configured with the one or more parameters are recursively applied to extend the selected computer-executable plan. One or more candidate responses to the conversational event are output via the conversational computing interface based on the recursive application of the one or more additional generation rules configured with the one or more parameters.Type: ApplicationFiled: August 8, 2022Publication date: December 1, 2022Applicant: Microsoft Technology Licensing, LLCInventors: Jacob Daniel ANDREAS, Jayant Sivarama KRISHNAMURTHY, Alan Xinyu GUO, Andrei VOROBEV, John Philip BUFE, III, Jesse Daniel Eskes RUSAK, Yuchen ZHANG
-
Patent number: 11410643Abstract: A computer-implemented method of responding to a conversational event. The method comprises enacting, by a conversational computing interface, an initial computer-executable plan based on a conversational event received by the conversational computing interface, wherein the initial computer-executable plan is configured to output an initial value based on the conversational event. The method further comprises selecting, by the conversational computing interface, an extended computer-executable plan based on determining that the initial value is insufficient for generating an extended description responsive to the conversational event. The method further comprises enacting, by the conversational computing interface, the extended computer-executable plan to output additional information beyond what the initial computer-executable plan is configured to output, the additional information sufficient for generating the extended description responsive to the conversational event.Type: GrantFiled: October 18, 2019Date of Patent: August 9, 2022Assignee: Microsoft Technology Licensing, LLCInventors: Jacob Daniel Andreas, Jayant Sivarama Krishnamurthy, Alan Xinyu Guo, Andrei Vorobev, John Philip Bufe, III, Jesse Daniel Eskes Rusak, Yuchen Zhang
-
Patent number: 11195523Abstract: A method comprising recognizing a user utterance including an ambiguity. The method further comprises using a previously-trained code-generation machine to produce, from the user utterance, a data-flow program including a search-history function. The search-history function is configured to select a highest-confidence disambiguating concept from one or more candidate concepts stored in a context-specific dialogue history.Type: GrantFiled: July 23, 2019Date of Patent: December 7, 2021Assignee: Microsoft Technology Licensing, LLCInventors: David Leo Wright Hall, David Ernesto Heekin Burkett, Jesse Daniel Eskes Rusak, Jayant Sivarama Krishnamurthy, Jason Andrew Wolfe, Adam David Pauls, Alan Xinyu Guo, Jacob Daniel Andreas, Daniel Louis Klein
-
Publication number: 20210192283Abstract: A method of training a conversational computing system. The method includes providing an initial query to a machine learning model previously trained to generate actions for responding to a query. Based on the initial query, a plurality of candidate actions are received from the machine learning model and presented via a training interface. Based on input provided by the human annotator, a selected candidate action is recognized and associated with the initial query in a labeled data example.Type: ApplicationFiled: December 20, 2019Publication date: June 24, 2021Applicant: Microsoft Technology Licensing, LLCInventors: Alan Xinyu GUO, Jesse Daniel Eskes RUSAK
-
Publication number: 20210050006Abstract: A computer-implemented method of responding to a conversational event. The method comprises enacting, by a conversational computing interface, an initial computer-executable plan based on a conversational event received by the conversational computing interface, wherein the initial computer-executable plan is configured to output an initial value based on the conversational event. The method further comprises selecting, by the conversational computing interface, an extended computer-executable plan based on determining that the initial value is insufficient for generating an extended description responsive to the conversational event. The method further comprises enacting, by the conversational computing interface, the extended computer-executable plan to output additional information beyond what the initial computer-executable plan is configured to output, the additional information sufficient for generating the extended description responsive to the conversational event.Type: ApplicationFiled: October 18, 2019Publication date: February 18, 2021Applicant: Microsoft Technology Licensing, LLCInventors: Jacob Daniel ANDREAS, Jayant Sivarama KRISHNAMURTHY, Alan Xinyu GUO, Andrei VOROBEV, John Philip BUFE, III, Jesse Daniel Eskes RUSAK, Yuchen ZHANG
-
Publication number: 20210027771Abstract: A method comprising recognizing a user utterance including an ambiguity. The method further comprises using a previously-trained code-generation machine to produce, from the user utterance, a data-flow program including a search-history function. The search-history function is configured to select a highest-confidence disambiguating concept from one or more candidate concepts stored in a context-specific dialogue history.Type: ApplicationFiled: July 23, 2019Publication date: January 28, 2021Applicant: Microsoft Technology Licensing, LLCInventors: David Leo Wright HALL, David Ernesto Heekin BURKETT, Jesse Daniel Eskes RUSAK, Jayant Sivarama KRISHNAMURTHY, Jason Andrew WOLFE, Adam David PAULS, Alan Xinyu GUO, Jacob Daniel ANDREAS, Daniel Louis KLEIN