US 12,405,976 B2
Method and system for generating training data for classifying intents in a conversational system
Joy Mustafi, Bangalore (IN); Geet Tapan Telang, Bangalore (IN); Thiruvengadam Samon, Bangalore (IN); and Kingshuk Banerjee, Bangalore (IN)
Assigned to HITACHI, LTD., Tokyo (JP)
Filed by HITACHI, LTD., Tokyo (JP)
Filed on Dec. 7, 2022, as Appl. No. 18/062,632.
Claims priority of application No. 202141058729 (IN), filed on Dec. 16, 2021.
Prior Publication US 2023/0195765 A1, Jun. 22, 2023
Int. Cl. G06F 16/3329 (2025.01); G06F 40/30 (2020.01); G06F 40/40 (2020.01)
CPC G06F 16/3329 (2019.01) [G06F 40/30 (2020.01); G06F 40/40 (2020.01)] 10 Claims
OG exemplary drawing
 
1. A method for providing natural language response to a user for a query using a conversational system (1041), the method comprising:
receiving, by a conversational system (1041), a query in a natural language from a user;
classifying, by the conversational system (1041), an intent associated with the query by using a classification model associated with the conversational system (1041), wherein the classification model is trained by using a method for generating training data for classifying intents in a conversational system (1041), the generating method comprising:
receiving, by a training data generation system (101), structured databases schema, wherein the structured databases schema comprise information related to an enterprise;
creating, by the generation system (101), at least one of one or more Structured Query Language (SQL) and not only SQL (NoSQL) queries based on the structured databases schema by using predefined rules;
converting, by the generation system (101), at least one of the one or more SQL and NoSQL queries into respective one or more natural language queries using a Deep Learning Neural Network (DNN) model, wherein the DNN model is trained using a first knowledge corpus (210) of a specific natural language;
creating, by the generation system (101), a second knowledge corpus based on the one or more natural language queries and the first knowledge corpus (210) using semantic analysis methodology; and
generating, by the generation system (101), training data for intents associated with each of the one or more natural language queries using the second knowledge corpus, wherein the training data is provided to one or more classification models for classifying an intent in the conversational system (1041);
mapping, by the conversational system (1041), the query with at least one of, one or more SQL and NoSQL queries prestored in a database using the classified intent; and
providing, by the conversational system (1041), a natural language response to the user from the database based on the mapped at least one of the one or more SQL and NoSQL queries.