US 11,783,133 B2
Supervised machine learning for automated assistants
Prem Kumar Sivasankar, Concord, NC (US); Vamsi Pola, Concord, NC (US); Francis McGovern, Wrentham, MA (US); Charles Gregory Starnes, Clover, SC (US); Zsa-Zsa Porter, Mint Hill, NC (US); Tasneem Hajara, Hillsborough, NJ (US); Jennifer Adelhardt, Waxhaw, NC (US); Daniel J. Gibbons, Mooresville, NC (US); Scott Blandford, Hopewell, NJ (US); Michael Ilfeld, Charlotte, NC (US); Peter Tsahalis, Colts Neck, NJ (US); Justin Meyer, Indian Trail, NC (US); James Titus, Garland, TX (US); Alysce Balbuena, Mount Holly, NC (US); Mehul Shah, Mumbai (IN); Jeffrey Scola, Charlotte, NC (US); Heather H. Gordon, Asheville, NC (US); Claudette Grose, Concord, NC (US); Reena T. Khatwani, Bridgewater, NJ (US); Reetu Sharma, Mumbai (IN); and Lisa R. Weil, Sudbury, MA (US)
Assigned to Teachers Insurance and Annuity Association of America, New York, NY (US)
Filed by Teachers Insurance and Annuity Association of America, New York, NY (US)
Filed on Jul. 8, 2020, as Appl. No. 16/923,795.
Claims priority of application No. 202041021738 (IN), filed on May 23, 2020.
Prior Publication US 2021/0365834 A1, Nov. 25, 2021
Int. Cl. G06N 20/00 (2019.01); G06F 40/30 (2020.01); G06F 40/35 (2020.01); G06F 18/22 (2023.01); G06F 18/24 (2023.01); G06F 18/21 (2023.01)
CPC G06F 40/30 (2020.01) [G06F 18/217 (2023.01); G06F 18/22 (2023.01); G06F 18/24 (2023.01); G06F 40/35 (2020.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving, by a computer system, an automated assistant transcript comprising a plurality of records, wherein each record of the plurality of records comprises a query, a classification of the query, an intent associated with the query, and a responsive action associated with the intent;
receiving, via a graphical user interface (GUI), a user input indicating an approval of a new automated assistant transcript record;
comparing the new automated assistant transcript record to one or more records of the plurality of records;
detecting a conflict of the new automated assistant transcript record with an existing record of the plurality of records;
displaying, via the GUI, a notification of the conflict;
responsive to receiving, via the GUI, a user input modifying one or more fields of the new automated assistant transcript record, appending the new automated assistant transcript record to the automated assistant transcript; and
utilizing the automated assistant transcript for training a first set of classification models, a second set of classification models, and a third set of classification models, wherein each classification model of the first set of classification models is employed to determine a degree of association of an input query with a topic of a predefined set of topics, wherein each classification model of the second set of classification models is employed to determine a degree of association of the input query with a subtopic of a predefined set of subtopics associated with a specified topic, and wherein each classification model of the third set of classification models is employed to determine a degree of association of the input query with an intent of a predefined set of intents associated with the specified topic and a specified subtopic.