US 11,715,554 B1
System and method for determining a mismatch between a user sentiment and a polarity of a situation using an AI chatbot
Jyotsana Vempati Aggarwal, Bengaluru (IN); Chaitali Sinha, Bengaluru (IN); and Megha Gupta, Bengaluru (IN)
Assigned to Wysa Inc, Boston, MA (US)
Filed by Wysa Inc, Boston, MA (US)
Filed on Jan. 10, 2023, as Appl. No. 18/95,464.
Claims priority of provisional application 63/298,189, filed on Jan. 10, 2022.
Int. Cl. G16H 20/70 (2018.01); G06F 40/20 (2020.01); G06F 40/35 (2020.01)
CPC G16H 20/70 (2018.01) [G06F 40/20 (2020.01); G06F 40/35 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A processor-implemented method for automatically determining a mismatch between a sentiment and a polarity of a life situation using an Artificial Intelligence (AI) model during a conversation with an AI chatbot, comprising:
determining at least one sentiment of the user using a sentiment detecting AI model;
predicting at least one life situation from the conversation between the AI chatbot and the user using an intent recognition AI model, wherein predicting the at least one life situation comprises (i) semantically matching at least one statement of the conversation with at least one representative statement of a life situation using the intent recognition AI model to obtain at least one semantic match, and (ii) assigning a confidence score to the at least one semantic match;
determining (i) a gravity of the at least one life situation as at least one of high, medium or low, and (ii) a polarity of the at least one life situation as at least one of negative, neutral or positive using a life events scale;
comparing the at least one sentiment of the user to the polarity of the at least one life situation when the gravity of the at least one life situation is determined as high, wherein the at least one sentiment of the user and the polarity of the at least one life situation is selected from any of a positive, a neutral or a negative; and
automatically determining the mismatch between the at least one sentiment of the user and the polarity of the at least one life situation of high gravity.