The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Nov. 17, 2020

Filed:

Jun. 08, 2017
Applicant:

Microsoft Technology Licensing, Llc, Redmond, WA (US);

Inventors:

Ying Wang, Bellevue, WA (US);

Qi Yao, Bellevue, WA (US);

Maria Alexandropoulou, Kirkland, WA (US);

Konstantinos Aisopos, Kirkland, WA (US);

Di Li, Beijing, CN;

Oussama Elachqar, Seattle, WA (US);

Emmanouil Koukoumidis, Kirkland, WA (US);

Assignee:
Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G06F 16/00 (2019.01); G06F 7/00 (2006.01); G06F 16/2457 (2019.01); G10L 25/63 (2013.01); G06N 3/00 (2006.01); G06N 20/00 (2019.01); G06F 16/242 (2019.01); G06F 16/9535 (2019.01); G06N 20/20 (2019.01); G10L 15/22 (2006.01); G06K 9/62 (2006.01); G06F 16/332 (2019.01); G06K 9/46 (2006.01); G06F 40/30 (2020.01); G06K 9/00 (2006.01);
U.S. Cl.
CPC ...
G06F 16/24575 (2019.01); G06F 16/243 (2019.01); G06F 16/24578 (2019.01); G06F 16/3329 (2019.01); G06F 16/9535 (2019.01); G06F 40/30 (2020.01); G06K 9/46 (2013.01); G06K 9/6267 (2013.01); G06N 3/006 (2013.01); G06N 20/00 (2019.01); G06N 20/20 (2019.01); G10L 15/22 (2013.01); G10L 25/63 (2013.01); G06K 9/00302 (2013.01); G06K 9/00885 (2013.01); G10L 2015/227 (2013.01);
Abstract

A system provides emotionally and intellectually relevant responses to user queries received by a chatbot instantiated by a computing device. The system also receives user data associated with the user query. The user query is communicated to a first supervised machine learning model to obtain a first plurality of ranked responses. The system also communicates the received user data to a second supervised machine learning model to obtain a first plurality of emotions associated with the user data. The system then determines determine a second plurality of emotions for the first plurality of responses and re-ranks the first plurality of responses based on a comparison of the first plurality of emotions and the second plurality of emotions. The system then selects a response to the user query from the re-ranked responses and outputs the selected response using the chatbot instantiated by the computing device.


Find Patent Forward Citations

Loading…