US 12,437,163 B2
System and method for identifying a user intent in a code-mixed utterance of a user
Marykutty Michael, Thiruvananthapuram (IN); Boby Chaitanya Villari, Bengaluru (IN); and Vijayalakshmi Iyer, Bengaluru (IN)
Assigned to US Technology International Private Limited, (IN)
Filed by US Technology International Private Limited, Thiruvananthapuram (IN)
Filed on Jan. 17, 2024, as Appl. No. 18/415,068.
Claims priority of application No. 202341020581 (IN), filed on Mar. 23, 2023.
Prior Publication US 2024/0320450 A1, Sep. 26, 2024
Int. Cl. G06F 40/58 (2020.01); G06F 40/284 (2020.01); H04L 51/02 (2022.01)
CPC G06F 40/58 (2020.01) [G06F 40/284 (2020.01); H04L 51/02 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A method for identifying a user intent in a code-mixed utterance of a user, the method comprising:
receiving the code-mixed utterance from the user for performing one or more actions via a chatbot, wherein the code-mixed utterance corresponds to one or more commands provided by the user to the chatbot in two or more source languages;
segmenting the received code-mixed utterance into a set of tokens by using an Artificial Intelligence (AI)-based Language Translator Network (LTN);
obtaining contextual information and contextual representations associated with the received code-mixed utterance based on the set of tokens by using the AI-based LTN;
generating a fixed dimensional representation for each token of the set of tokens based on the obtained contextual information and the obtained contextual representations by using the AI-based LTN;
generating a set of vocabulary probabilities for the fixed dimensional representation associated with each token of the set of tokens by using the AI-based LTN, wherein each vocabulary probability of the set of vocabulary probabilities corresponds to probabilities associated with the vocabulary of a target language;
translating the code-mixed utterances to a translation text in the target language based on the generated set of vocabulary probabilities by using the AI-based LTN; and
identifying the user intent in the translation text by using an AI-based Intent Detection Network (IDN).