Patents by Inventor Andrew Smith Lewis
Andrew Smith Lewis 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: 11776417Abstract: A method for predictively updating one or more user parameters associated with a user of a learning system includes predicting, based on the one or more user parameters, a predicted activity of the user, receiving an actual activity of the user, comparing the predicted activity to the actual activity, and updating the one or more user parameters in response to determining that the predicted activity does not match the actual activity. The method may further include scheduling one or more learning interactions based on the one or more updated learning parameters, where the scheduling includes selecting at least one of a timing of the one or more learning interactions or a type of the one or more learning interactions.Type: GrantFiled: July 14, 2021Date of Patent: October 3, 2023Assignee: CEREGO JAPAN KABUSHIKI KAISHAInventors: Iain M. Harlow, Andrew Smith Lewis, Paul T. Mumma
-
Patent number: 11721230Abstract: Learning systems and methods of the present disclosure include generating a text document based on a digital file, tokenizing the text document, generating a semantic model based on the tokenized text document using an unsupervised machine learning algorithm, assigning a plurality of passage scores to a corresponding plurality of passages of the tokenized text document, selecting one or more candidate knowledge items from the tokenized text document based on the plurality of passage scores, filtering the one or more candidate knowledge items based on user data, generating one or more structured learning assets based on the one or more filtered candidate knowledge items, generating an interaction based at least on the one or more structured learning assets, and transmitting the interaction to a user device. Each passage score is assigned based on a relationship between a corresponding passage and the semantic model.Type: GrantFiled: April 20, 2022Date of Patent: August 8, 2023Assignee: CEREGO JAPAN KABUSHIKI KAISHAInventors: Andrew Smith Lewis, Paul Mumma, Alex Volkovitsky, Iain Harlow, Kyle Stewart
-
Patent number: 11487804Abstract: A method for generating a set of concepts related to a target concept includes accessing a set of candidate concepts, embedding the target concept and the set of candidate concepts in a semantic vector space, selecting one or more intermediate concepts from the set of candidate concepts in response to determining whether each embedded candidate concept in the set of embedded candidate concepts satisfies a predetermined relationship with the embedded target concept, and filtering the one or more intermediate concepts to yield the set of concepts related to the target concept. The method may further include generating a multiple-choice question in which the target concept corresponds to a correct answer choice and the set of concepts related to the target concept correspond to distractors.Type: GrantFiled: April 20, 2022Date of Patent: November 1, 2022Assignee: CEREGO JAPAN KABUSHIKI KAISHAInventors: Michael A. Yen, Iain M. Harlow, Andrew Smith Lewis, Paul T. Mumma
-
Publication number: 20220245184Abstract: A method for generating a set of concepts related to a target concept includes accessing a set of candidate concepts, embedding the target concept and the set of candidate concepts in a semantic vector space, selecting one or more intermediate concepts from the set of candidate concepts in response to determining whether each embedded candidate concept in the set of embedded candidate concepts satisfies a predetermined relationship with the embedded target concept, and filtering the one or more intermediate concepts to yield the set of concepts related to the target concept. The method may further include generating a multiple-choice question in which the target concept corresponds to a correct answer choice and the set of concepts related to the target concept correspond to distractors.Type: ApplicationFiled: April 20, 2022Publication date: August 4, 2022Inventors: Michael A. YEN, Iain M. HARLOW, Andrew SMITH LEWIS, Paul T. MUMMA
-
Publication number: 20220246052Abstract: Learning systems and methods of the present disclosure include generating a text document based on a digital file, tokenizing the text document, generating a semantic model based on the tokenized text document using an unsupervised machine learning algorithm, assigning a plurality of passage scores to a corresponding plurality of passages of the tokenized text document, selecting one or more candidate knowledge items from the tokenized text document based on the plurality of passage scores, filtering the one or more candidate knowledge items based on user data, generating one or more structured learning assets based on the one or more filtered candidate knowledge items, generating an interaction based at least on the one or more structured learning assets, and transmitting the interaction to a user device. Each passage score is assigned based on a relationship between a corresponding passage and the semantic model.Type: ApplicationFiled: April 20, 2022Publication date: August 4, 2022Inventors: Andrew SMITH LEWIS, Paul MUMMA, Alex VOLKOVITSKY, Iain HARLOW, Kyle STEWART
-
Patent number: 11347784Abstract: A method for generating a set of concepts related to a target concept includes accessing a set of candidate concepts, embedding the target concept and the set of candidate concepts in a semantic vector space, selecting one or more intermediate concepts from the set of candidate concepts in response to determining whether each embedded candidate concept in the set of embedded candidate concepts satisfies a predetermined relationship with the embedded target concept, and filtering the one or more intermediate concepts to yield the set of concepts related to the target concept. The method may further include generating a multiple-choice question in which the target concept corresponds to a correct answer choice and the set of concepts related to the target concept correspond to distractors.Type: GrantFiled: December 15, 2021Date of Patent: May 31, 2022Assignee: CEREGO JAPAN KABUSHIKI KAISHAInventors: Michael A. Yen, Iain M. Harlow, Andrew Smith Lewis, Paul T. Mumma
-
Patent number: 11348476Abstract: Learning systems and methods of the present disclosure include generating a text document based on a digital file, tokenizing the text document, generating a semantic model based on the tokenized text document using an unsupervised machine learning algorithm, assigning a plurality of passage scores to a corresponding plurality of passages of the tokenized text document, selecting one or more candidate knowledge items from the tokenized text document based on the plurality of passage scores, filtering the one or more candidate knowledge items based on user data, generating one or more structured learning assets based on the one or more filtered candidate knowledge items, generating an interaction based at least on the one or more structured learning assets, and transmitting the interaction to a user device. Each passage score is assigned based on a relationship between a corresponding passage and the semantic model.Type: GrantFiled: November 23, 2021Date of Patent: May 31, 2022Assignee: CEREGO JAPAN KABUSHIKI KAISHAInventors: Andrew Smith Lewis, Paul Mumma, Alex Volkovitsky, Iain Harlow, Kyle Stewart
-
Publication number: 20220147554Abstract: A method for generating a set of concepts related to a target concept includes accessing a set of candidate concepts, embedding the target concept and the set of candidate concepts in a semantic vector space, selecting one or more intermediate concepts from the set of candidate concepts in response to determining whether each embedded candidate concept in the set of embedded candidate concepts satisfies a predetermined relationship with the embedded target concept, and filtering the one or more intermediate concepts to yield the set of concepts related to the target concept. The method may further include generating a multiple-choice question in which the target concept corresponds to a correct answer choice and the set of concepts related to the target concept correspond to distractors.Type: ApplicationFiled: December 15, 2021Publication date: May 12, 2022Inventors: Michael A. YEN, Iain M. HARLOW, Andrew SMITH LEWIS, Paul T. MUMMA
-
Publication number: 20220084429Abstract: Learning systems and methods of the present disclosure include generating a text document based on a digital file, tokenizing the text document, generating a semantic model based on the tokenized text document using an unsupervised machine learning algorithm, assigning a plurality of passage scores to a corresponding plurality of passages of the tokenized text document, selecting one or more candidate knowledge items from the tokenized text document based on the plurality of passage scores, filtering the one or more candidate knowledge items based on user data, generating one or more structured learning assets based on the one or more filtered candidate knowledge items, generating an interaction based at least on the one or more structured learning assets, and transmitting the interaction to a user device. Each passage score is assigned based on a relationship between a corresponding passage and the semantic model.Type: ApplicationFiled: November 23, 2021Publication date: March 17, 2022Inventors: Andrew SMITH LEWIS, Paul MUMMA, Alex VOLKOVITSKY, Iain HARLOW, Kyle STEWART
-
Patent number: 11238085Abstract: A method for generating a set of concepts related to a target concept includes accessing a set of candidate concepts, embedding the target concept and the set of candidate concepts in a semantic vector space, selecting one or more intermediate concepts from the set of candidate concepts in response to determining whether each embedded candidate concept in the set of embedded candidate concepts satisfies a predetermined relationship with the embedded target concept, and filtering the one or more intermediate concepts to yield the set of concepts related to the target concept. The method may further include generating a multiple-choice question in which the target concept corresponds to a correct answer choice and the set of concepts related to the target concept correspond to distractors.Type: GrantFiled: July 14, 2021Date of Patent: February 1, 2022Assignee: CEREGO JAPAN KABUSHIKI KAISHAInventors: Michael A. Yen, Iain M. Harlow, Andrew Smith Lewis, Paul T. Mumma
-
Patent number: 11217110Abstract: Learning systems and methods of the present disclosure include generating a text document based on a digital file, tokenizing the text document, generating a semantic model based on the tokenized text document using an unsupervised machine learning algorithm, assigning a plurality of passage scores to a corresponding plurality of passages of the tokenized text document, selecting one or more candidate knowledge items from the tokenized text document based on the plurality of passage scores, filtering the one or more candidate knowledge items based on user data, generating one or more structured learning assets based on the one or more filtered candidate knowledge items, generating an interaction based at least on the one or more structured learning assets, and transmitting the interaction to a user device. Each passage score is assigned based on a relationship between a corresponding passage and the semantic model.Type: GrantFiled: June 17, 2021Date of Patent: January 4, 2022Assignee: CEREGO JAPAN KABUSHIKI KAISHAInventors: Andrew Smith Lewis, Paul Mumma, Alex Volkovitsky, Iain Harlow, Kyle Stewart
-
Publication number: 20210342381Abstract: A method for generating a set of concepts related to a target concept includes accessing a set of candidate concepts, embedding the target concept and the set of candidate concepts in a semantic vector space, selecting one or more intermediate concepts from the set of candidate concepts in response to determining whether each embedded candidate concept in the set of embedded candidate concepts satisfies a predetermined relationship with the embedded target concept, and filtering the one or more intermediate concepts to yield the set of concepts related to the target concept. The method may further include generating a multiple-choice question in which the target concept corresponds to a correct answer choice and the set of concepts related to the target concept correspond to distractors.Type: ApplicationFiled: July 14, 2021Publication date: November 4, 2021Inventors: Michael A. YEN, Iain M. HARLOW, Andrew SMITH LEWIS, Paul T. MUMMA
-
Publication number: 20210343176Abstract: A method for predictively updating one or more user parameters associated with a user of a learning system includes predicting, based on the one or more user parameters, a predicted activity of the user, receiving an actual activity of the user, comparing the predicted activity to the actual activity, and updating the one or more user parameters in response to determining that the predicted activity does not match the actual activity. The method may further include scheduling one or more learning interactions based on the one or more updated learning parameters, where the scheduling includes selecting at least one of a timing of the one or more learning interactions or a type of the one or more learning interactions.Type: ApplicationFiled: July 14, 2021Publication date: November 4, 2021Inventors: Iain M. HARLOW, Andrew SMITH LEWIS, Paul T. MUMMA
-
Patent number: 11158204Abstract: A method for predictively updating one or more user parameters associated with a user of a learning system includes predicting, based on the one or more user parameters, a predicted activity of the user, receiving an actual activity of the user, comparing the predicted activity to the actual activity, and updating the one or more user parameters in response to determining that the predicted activity does not match the actual activity. The method may further include scheduling one or more learning interactions based on the one or more updated learning parameters, where the scheduling includes selecting at least one of a timing of the one or more learning interactions or a type of the one or more learning interactions.Type: GrantFiled: May 11, 2018Date of Patent: October 26, 2021Assignee: CEREGO JAPAN KABUSHIKI KAISHAInventors: Iain M. Harlow, Andrew Smith Lewis, Paul T. Mumma
-
Publication number: 20210312826Abstract: Learning systems and methods of the present disclosure include generating a text document based on a digital file, tokenizing the text document, generating a semantic model based on the tokenized text document using an unsupervised machine learning algorithm, assigning a plurality of passage scores to a corresponding plurality of passages of the tokenized text document, selecting one or more candidate knowledge items from the tokenized text document based on the plurality of passage scores, filtering the one or more candidate knowledge items based on user data, generating one or more structured learning assets based on the one or more filtered candidate knowledge items, generating an interaction based at least on the one or more structured learning assets, and transmitting the interaction to a user device. Each passage score is assigned based on a relationship between a corresponding passage and the semantic model.Type: ApplicationFiled: June 17, 2021Publication date: October 7, 2021Inventors: Andrew SMITH LEWIS, Paul MUMMA, Alex VOLKOVITSKY, Iain HARLOW, Kyle STEWART
-
Patent number: 11086920Abstract: A method for generating a set of concepts related to a target concept includes accessing a set of candidate concepts, embedding the target concept and the set of candidate concepts in a semantic vector space, selecting one or more intermediate concepts from the set of candidate concepts in response to determining whether each embedded candidate concept in the set of embedded candidate concepts satisfies a predetermined relationship with the embedded target concept, and filtering the one or more intermediate concepts to yield the set of concepts related to the target concept. The method may further include generating a multiple-choice question in which the target concept corresponds to a correct answer choice and the set of concepts related to the target concept correspond to distractors.Type: GrantFiled: May 11, 2018Date of Patent: August 10, 2021Assignee: CEREGO, LLC.Inventors: Michael A. Yen, Iain M. Harlow, Andrew Smith Lewis, Paul T. Mumma
-
Patent number: 11081018Abstract: Learning systems and methods of the present disclosure include generating a text document based on a digital file, tokenizing the text document, generating a semantic model based on the tokenized text document using an unsupervised machine learning algorithm, assigning a plurality of passage scores to a corresponding plurality of passages of the tokenized text document, selecting one or more candidate knowledge items from the tokenized text document based on the plurality of passage scores, filtering the one or more candidate knowledge items based on user data, generating one or more structured learning assets based on the one or more filtered candidate knowledge items, generating an interaction based at least on the one or more structured learning assets, and transmitting the interaction to a user device. Each passage score is assigned based on a relationship between a corresponding passage and the semantic model.Type: GrantFiled: November 11, 2020Date of Patent: August 3, 2021Assignee: CEREGO LLC.Inventors: Andrew Smith Lewis, Paul Mumma, Alex Volkovitsky, Iain Harlow, Kyle Stewart
-
Publication number: 20210158712Abstract: Learning systems and methods of the present disclosure include generating a text document based on a digital file, tokenizing the text document, generating a semantic model based on the tokenized text document using an unsupervised machine learning algorithm, assigning a plurality of passage scores to a corresponding plurality of passages of the tokenized text document, selecting one or more candidate knowledge items from the tokenized text document based on the plurality of passage scores, filtering the one or more candidate knowledge items based on user data, generating one or more structured learning assets based on the one or more filtered candidate knowledge items, generating an interaction based at least on the one or more structured learning assets, and transmitting the interaction to a user device. Each passage score is assigned based on a relationship between a corresponding passage and the semantic model.Type: ApplicationFiled: November 11, 2020Publication date: May 27, 2021Inventors: Andrew SMITH LEWIS, Paul MUMMA, Alex VOLKOVITSKY, Iain HARLOW, Kyle STEWART
-
Patent number: 10861344Abstract: Learning systems and methods of the present disclosure include generating a text document based on a digital file, tokenizing the text document, generating a semantic model based on the tokenized text document using an unsupervised machine learning algorithm, assigning a plurality of passage scores to a corresponding plurality of passages of the tokenized text document, selecting one or more candidate knowledge items from the tokenized text document based on the plurality of passage scores, filtering the one or more candidate knowledge items based on user data, generating one or more structured learning assets based on the one or more filtered candidate knowledge items, generating an interaction based at least on the one or more structured learning assets, and transmitting the interaction to a user device. Each passage score is assigned based on a relationship between a corresponding passage and the semantic model.Type: GrantFiled: December 8, 2017Date of Patent: December 8, 2020Assignee: CEREGO, LLC.Inventors: Andrew Smith Lewis, Paul Mumma, Alex Volkovitsky, Iain Harlow, Kyle Stewart
-
Publication number: 20180373791Abstract: A method for generating a set of concepts related to a target concept includes accessing a set of candidate concepts, embedding the target concept and the set of candidate concepts in a semantic vector space, selecting one or more intermediate concepts from the set of candidate concepts in response to determining whether each embedded candidate concept in the set of embedded candidate concepts satisfies a predetermined relationship with the embedded target concept, and filtering the one or more intermediate concepts to yield the set of concepts related to the target concept. The method may further include generating a multiple-choice question in which the target concept corresponds to a correct answer choice and the set of concepts related to the target concept correspond to distractors.Type: ApplicationFiled: May 11, 2018Publication date: December 27, 2018Inventors: Michael A. YEN, Iain M. HARLOW, Andrew SMITH LEWIS, Paul T. MUMMA