Patents by Inventor Scott Hellman
Scott Hellman 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: 11875706Abstract: Systems and methods for automated custom training of a scoring model are disclosed herein. The method include: receiving a plurality of responses received from a plurality of students in response to providing of a prompt; identifying an evaluation model relevant to the provided prompt, which evaluation model can be a machine learning model trained to output a score relevant to at least portions of a response; generating a training indicator that provides a graphical depiction of the degree to which the identified evaluation model is trained; determining a training status of the model; receiving at least one evaluation input when the model is identified as insufficiently trained; updating training of the evaluation model based on the at least one received evaluation input; and controlling the training indicator to reflect the degree to which the evaluation model is trained subsequent to the updating of the training of the evaluation model.Type: GrantFiled: February 20, 2019Date of Patent: January 16, 2024Assignee: PEARSON EDUCATION, INC.Inventors: Alok Baikadi, Scott Hellman, Jill Budden, Stephen Hopkins, Kyle Habermehl, Peter Foltz, Lee Becker, Mark Rosenstein
-
Patent number: 11817014Abstract: Systems and methods for automated custom training of a scoring model are disclosed herein. The method include: receiving a plurality of responses received from a plurality of students in response to providing of a prompt; identifying an evaluation model relevant to the provided prompt, which evaluation model can be a machine learning model trained to output a score relevant to at least portions of a response; generating a training indicator that provides a graphical depiction of the degree to which the identified evaluation model is trained; determining a training status of the model; receiving at least one evaluation input when the model is identified as insufficiently trained; updating training of the evaluation model based on the at least one received evaluation input; and controlling the training indicator to reflect the degree to which the evaluation model is trained subsequent to the updating of the training of the evaluation model.Type: GrantFiled: February 20, 2019Date of Patent: November 14, 2023Assignee: PEARSON EDUCATION, INC.Inventors: Lee Becker, William Murray, Peter Foltz, Mark Rosenstein, Alok Baikadi, Scott Hellman, Kyle Habermehl, Jill Budden, Stephen Hopkins, Andrew Gorman
-
Patent number: 11741849Abstract: Systems and methods for automated custom training of a scoring model are disclosed herein. The method include: receiving a plurality of responses received from a plurality of students in response to providing of a prompt; identifying an evaluation model relevant to the provided prompt, which evaluation model can be a machine learning model trained to output a score relevant to at least portions of a response; generating a training indicator that provides a graphical depiction of the degree to which the identified evaluation model is trained; determining a training status of the model; receiving at least one evaluation input when the model is identified as insufficiently trained; updating training of the evaluation model based on the at least one received evaluation input; and controlling the training indicator to reflect the degree to which the evaluation model is trained subsequent to the updating of the training of the evaluation model.Type: GrantFiled: February 20, 2019Date of Patent: August 29, 2023Assignee: PEARSON EDUCATION, INC.Inventors: Scott Hellman, William Murray, Kyle Habermehl, Alok Baikadi, Jill Budden, Andrew Gorman, Mark Rosenstein, Lee Becker, Stephen Hopkins, Peter Foltz
-
Patent number: 11651239Abstract: Systems and methods for content aggregation creation are disclosed herein. The system can include memory having a content database and an aggregation database. The system can include a user device having a first network interface and a first I/O subsystem. The system can include a server that can: provide content to the user device via a first electrical signal; receive a selection of a portion of the provided content from the user device via a second electrical signal; automatically extract sentences from the selected portion of the provided content via a natural language processor; automatically generate a parse tree for one of the automatically extracted sentences; identify noun phrases from the part of speech tags within the parse tree; place content associated with one of the noun phrase in a content aggregation; and output the content aggregation to the user device.Type: GrantFiled: May 13, 2019Date of Patent: May 16, 2023Assignee: PEARSON EDUCATION, INC.Inventors: Sean York, Tim Stewart, David Strong, Scott Hellman, William Murray
-
Patent number: 11475245Abstract: Systems and methods for automated custom training of a scoring model are disclosed herein. The method include: receiving a plurality of responses received from a plurality of students in response to providing of a prompt; identifying an evaluation model relevant to the provided prompt, which evaluation model can be a machine learning model trained to output a score relevant to at least portions of a response; generating a training indicator that provides a graphical depiction of the degree to which the identified evaluation model is trained; determining a training status of the model; receiving at least one evaluation input when the model is identified as insufficiently trained; updating training of the evaluation model based on the at least one received evaluation input; and controlling the training indicator to reflect the degree to which the evaluation model is trained subsequent to the updating of the training of the evaluation model.Type: GrantFiled: February 20, 2019Date of Patent: October 18, 2022Assignee: PEARSON EDUCATION, INC.Inventors: Peter Foltz, Mark Rosenstein, Alok Baikadi, Lee Becker, Stephen Hopkins, Jill Budden, Luis M. Oros, Kyle Habermehl, Scott Hellman, William Murray, Andrew Gorman
-
Patent number: 11449762Abstract: Systems and methods for automated custom training of a scoring model are disclosed herein. The method include: receiving a plurality of responses received from a plurality of students in response to providing of a prompt; identifying an evaluation model relevant to the provided prompt, which evaluation model can be a machine learning model trained to output a score relevant to at least portions of a response; generating a training indicator that provides a graphical depiction of the degree to which the identified evaluation model is trained; determining a training status of the model; receiving at least one evaluation input when the model is identified as insufficiently trained; updating training of the evaluation model based on the at least one received evaluation input; and controlling the training indicator to reflect the degree to which the evaluation model is trained subsequent to the updating of the training of the evaluation model.Type: GrantFiled: August 19, 2019Date of Patent: September 20, 2022Assignee: PEARSON EDUCATION, INC.Inventors: Mark Rosenstein, Kyle Habermehl, Scott Hellman, Alok Baikadi, Peter Foltz, Lee Becker, Luis M. Oros, Jill Budden, Marcia Derr
-
Patent number: 11443140Abstract: Systems and methods for automated custom training of a scoring model are disclosed herein. The method include: receiving a plurality of responses received from a plurality of students in response to providing of a prompt; identifying an evaluation model relevant to the provided prompt, which evaluation model can be a machine learning model trained to output a score relevant to at least portions of a response; generating a training indicator that provides a graphical depiction of the degree to which the identified evaluation model is trained; determining a training status of the model; receiving at least one evaluation input when the model is identified as insufficiently trained; updating training of the evaluation model based on the at least one received evaluation input; and controlling the training indicator to reflect the degree to which the evaluation model is trained subsequent to the updating of the training of the evaluation model.Type: GrantFiled: February 20, 2019Date of Patent: September 13, 2022Assignee: PEARSON EDUCATION, INC.Inventors: Scott Hellman, Lee Becker, Samuel Downs, Alok Baikadi, William Murray, Kyle Habermehl, Peter Foltz, Mark Rosenstein
-
Publication number: 20220013023Abstract: The disclosed embodiments include a method to predict annotation spans without requiring any labeled annotation data. The approach is to consider AES as a Multiple Instance Learning (MIL) task. The disclosed embodiments show that such models can both predict content scores and localize content by leveraging their sentence-level score predictions. This capability arises despite never having access to annotation training data. Implications are discussed for improving formative feedback and explainable AES models.Type: ApplicationFiled: July 13, 2021Publication date: January 13, 2022Inventors: Scott HELLMAN, Peter W. FOLTZ, Lee BECKER, William R. MURRAY
-
Patent number: 11126924Abstract: Systems and methods for content aggregation creation are disclosed herein. The system can include memory having a content database and an aggregation database. The system can include a user device having a first network interface and a first I/O subsystem. The system can include a server that can: provide content to the user device via a first electrical signal; receive a selection of a portion of the provided content from the user device via a second electrical signal; automatically extract sentences from the selected portion of the provided content via a natural language processor; automatically generate a parse tree for one of the automatically extracted sentences; identify noun phrases from the part of speech tags within the parse tree; place content associated with one of the noun phrase in a content aggregation; and output the content aggregation to the user device.Type: GrantFiled: July 23, 2019Date of Patent: September 21, 2021Assignee: PEARSON EDUCATION, INC.Inventors: Sean York, Tim Stewart, David Strong, Scott Hellman, William Murray
-
Patent number: 11068043Abstract: Systems and methods for virtual reality interaction evaluation are disclosed herein. The system can include a memory including: an interaction sub-database containing information relating to user interactions with at least one virtual asset in a virtual environment, and a content library database containing a plurality of virtual assets and information relating to those virtual assets. The system can include at least one server that can determine user engagement with at least one of the plurality of virtual assets, receive data indicative of an interaction with at least one of the plurality of virtual assets, and determine an interaction type of the interaction associated with the received data. The server can perform a speech capture and analysis process, perform a manipulation process, generate an evaluation of the user interactions with the at least one of the plurality of virtual assets, and deliver the generated evaluation.Type: GrantFiled: June 29, 2018Date of Patent: July 20, 2021Assignee: PEARSON EDUCATION, INC.Inventors: David Strong, Scott Hellman, Johann Larusson, Jake Noble, Timothy J. Stewart, Alex Nickel, Luis Oros, Quinn Lathrop, Daniel Tonks, Peter Foltz
-
Publication number: 20200005157Abstract: Systems and methods for automated custom training of a scoring model are disclosed herein. The method include: receiving a plurality of responses received from a plurality of students in response to providing of a prompt; identifying an evaluation model relevant to the provided prompt, which evaluation model can be a machine learning model trained to output a score relevant to at least portions of a response; generating a training indicator that provides a graphical depiction of the degree to which the identified evaluation model is trained; determining a training status of the model; receiving at least one evaluation input when the model is identified as insufficiently trained; updating training of the evaluation model based on the at least one received evaluation input; and controlling the training indicator to reflect the degree to which the evaluation model is trained subsequent to the updating of the training of the evaluation model.Type: ApplicationFiled: August 19, 2019Publication date: January 2, 2020Inventors: Mark Rosenstein, Kyle Habermehl, Scott Hellman, Alok Baikadi, Peter Foltz, Lee Becker, Luis M. Oros, Jill Budden, Marcia Derr
-
Publication number: 20190347266Abstract: Systems and methods for content aggregation creation are disclosed herein. The system can include memory having a content database and an aggregation database. The system can include a user device having a first network interface and a first I/O subsystem. The system can include a server that can: provide content to the user device via a first electrical signal; receive a selection of a portion of the provided content from the user device via a second electrical signal; automatically extract sentences from the selected portion of the provided content via a natural language processor; automatically generate a parse tree for one of the automatically extracted sentences; identify noun phrases from the part of speech tags within the parse tree; place content associated with one of the noun phrase in a content aggregation; and output the content aggregation to the user device.Type: ApplicationFiled: July 23, 2019Publication date: November 14, 2019Inventors: Sean YORK, Tim STEWART, David STRONG, Scott HELLMAN, William MURRAY
-
Patent number: 10459956Abstract: Systems and methods for content aggregation creation are disclosed herein. The system can include memory having a content database and an aggregation database. The system can include a user device having a first network interface and a first I/O subsystem. The system can include a server that can: provide content to the user device via a first electrical signal; receive a selection of a portion of the provided content from the user device via a second electrical signal; automatically extract sentences from the selected portion of the provided content via a natural language processor; automatically generate a parse tree for one of the automatically extracted sentences; identify noun phrases from the part of speech tags within the parse tree; place content associated with one of the noun phrase in a content aggregation; and output the content aggregation to the user device.Type: GrantFiled: December 14, 2016Date of Patent: October 29, 2019Assignee: PEARSON EDUCATION, INC.Inventors: Sean York, Tim Stewart, David Strong, Scott Hellman, William Murray
-
Publication number: 20190273780Abstract: Systems and methods for content aggregation creation are disclosed herein. The system can include memory having a content database and an aggregation database. The system can include a user device having a first network interface and a first I/O subsystem. The system can include a server that can: provide content to the user device via a first electrical signal; receive a selection of a portion of the provided content from the user device via a second electrical signal; automatically extract sentences from the selected portion of the provided content via a natural language processor; automatically generate a parse tree for one of the automatically extracted sentences; identify noun phrases from the part of speech tags within the parse tree; place content associated with one of the noun phrase in a content aggregation; and output the content aggregation to the user device.Type: ApplicationFiled: May 13, 2019Publication date: September 5, 2019Inventors: Sean YORK, Tim STEWART, David STRONG, Scott HELLMAN, William MURRAY
-
Publication number: 20190259293Abstract: Systems and methods for automated custom training of a scoring model are disclosed herein. The method include: receiving a plurality of responses received from a plurality of students in response to providing of a prompt; identifying an evaluation model relevant to the provided prompt, which evaluation model can be a machine learning model trained to output a score relevant to at least portions of a response; generating a training indicator that provides a graphical depiction of the degree to which the identified evaluation model is trained; determining a training status of the model; receiving at least one evaluation input when the model is identified as insufficiently trained; updating training of the evaluation model based on the at least one received evaluation input; and controlling the training indicator to reflect the degree to which the evaluation model is trained subsequent to the updating of the training of the evaluation model.Type: ApplicationFiled: February 20, 2019Publication date: August 22, 2019Inventors: Scott Hellman, William Murray, Kyle Habermehl, Alok Baikadi, Jill Budden, Andrew Gorman, Mark Rosenstein, Lee Becker, Stephen Hopkins, Peter Foltz
-
Publication number: 20190258900Abstract: Systems and methods for automated custom training of a scoring model are disclosed herein. The method include: receiving a plurality of responses received from a plurality of students in response to providing of a prompt; identifying an evaluation model relevant to the provided prompt, which evaluation model can be a machine learning model trained to output a score relevant to at least portions of a response; generating a training indicator that provides a graphical depiction of the degree to which the identified evaluation model is trained; determining a training status of the model; receiving at least one evaluation input when the model is identified as insufficiently trained; updating training of the evaluation model based on the at least one received evaluation input; and controlling the training indicator to reflect the degree to which the evaluation model is trained subsequent to the updating of the training of the evaluation model.Type: ApplicationFiled: February 20, 2019Publication date: August 22, 2019Inventors: Alok Baikadi, Scott Hellman, Jill Budden, Stephen Hopkins, Kyle Habermehl, Peter Foltz, Lee Becker, Mark Rosenstein
-
Publication number: 20190258903Abstract: Systems and methods for automated custom training of a scoring model are disclosed herein. The method include: receiving a plurality of responses received from a plurality of students in response to providing of a prompt; identifying an evaluation model relevant to the provided prompt, which evaluation model can be a machine learning model trained to output a score relevant to at least portions of a response; generating a training indicator that provides a graphical depiction of the degree to which the identified evaluation model is trained; determining a training status of the model; receiving at least one evaluation input when the model is identified as insufficiently trained; updating training of the evaluation model based on the at least one received evaluation input; and controlling the training indicator to reflect the degree to which the evaluation model is trained subsequent to the updating of the training of the evaluation model.Type: ApplicationFiled: February 20, 2019Publication date: August 22, 2019Inventors: Peter Foltz, Mark Rosenstein, Alok Baikadi, Lee Becker, Stephen Hopkins, Jill Budden, Luis M. Oros, Kyle Habermehl, Scott Hellman, William Murray, Andrew Gorman
-
Publication number: 20190258715Abstract: Systems and methods for automated custom training of a scoring model are disclosed herein. The method include: receiving a plurality of responses received from a plurality of students in response to providing of a prompt; identifying an evaluation model relevant to the provided prompt, which evaluation model can be a machine learning model trained to output a score relevant to at least portions of a response; generating a training indicator that provides a graphical depiction of the degree to which the identified evaluation model is trained; determining a training status of the model; receiving at least one evaluation input when the model is identified as insufficiently trained; updating training of the evaluation model based on the at least one received evaluation input; and controlling the training indicator to reflect the degree to which the evaluation model is trained subsequent to the updating of the training of the evaluation model.Type: ApplicationFiled: February 20, 2019Publication date: August 22, 2019Inventors: Scott Hellman, Lee Becker, Samuel Downs, Alok Baikadi, William Murray, Kyle Habermehl, Peter Foltz, Mark Rosenstein
-
Publication number: 20190258716Abstract: Systems and methods for automated custom training of a scoring model are disclosed herein. The method include: receiving a plurality of responses received from a plurality of students in response to providing of a prompt; identifying an evaluation model relevant to the provided prompt, which evaluation model can be a machine learning model trained to output a score relevant to at least portions of a response; generating a training indicator that provides a graphical depiction of the degree to which the identified evaluation model is trained; determining a training status of the model; receiving at least one evaluation input when the model is identified as insufficiently trained; updating training of the evaluation model based on the at least one received evaluation input; and controlling the training indicator to reflect the degree to which the evaluation model is trained subsequent to the updating of the training of the evaluation model.Type: ApplicationFiled: February 20, 2019Publication date: August 22, 2019Inventors: Lee Becker, William Murray, Peter Foltz, Mark Rosenstein, Alok Baikadi, Scott Hellman, Kyle Habermehl, Jill Budden, Stephen Hopkins, Andrew Gorman
-
Patent number: 10380126Abstract: Systems and methods for content aggregation creation are disclosed herein. The system can include memory having a content database and an aggregation database. The system can include a user device having a first network interface and a first I/O subsystem. The system can include a server that can: provide content to the user device via a first electrical signal; receive a selection of a portion of the provided content from the user device via a second electrical signal; automatically extract sentences from the selected portion of the provided content via a natural language processor; automatically generate a parse tree for one of the automatically extracted sentences; identify noun phrases from the part of speech tags within the parse tree; place content associated with one of the noun phrase in a content aggregation; and output the content aggregation to the user device.Type: GrantFiled: December 13, 2016Date of Patent: August 13, 2019Assignee: PEARSON EDUCATION, INC.Inventors: Sean York, Tim Stewart, David Strong, Scott Hellman, William Murray