US 12,254,015 B1
Systems and methods for relational database insight extraction and visualization
Gaurav Kumar, Karnataka (IN); Kanak Dahake, Maharashtra (IN); Chakkarapani Vijayakumar, Chennai (IN); Saurabh Mohanty, Los Gatos, CA (US); and Joseph David Voyles, Louisville, KY (US)
Assigned to PwC Product Sales LLC, New York, NY (US)
Filed by PwC Product Sales LLC, New York, NY (US)
Filed on Mar. 29, 2024, as Appl. No. 18/622,411.
Int. Cl. G06F 16/242 (2019.01); G06F 16/2457 (2019.01); G06F 16/248 (2019.01)
CPC G06F 16/24575 (2019.01) [G06F 16/243 (2019.01); G06F 16/248 (2019.01)] 23 Claims
OG exemplary drawing
 
22. A method for processing relational database data using a generative artificial intelligence (AI) language model, the method performed by a system comprising memory and one or more processors, the method comprising:
receiving relational database data;
generating, based on the relational database data, schema data in text string format;
receiving a user query input;
generating and providing a first prompt to a generative AI language model, wherein the first prompt is generated based on the user query input and based on the schema data;
receiving, from the generative AI language model, in response to the first prompt, an indication of a first subset of the database data that is identified as relevant to the user query;
generating and providing a second prompt to the generative AI language model, wherein the second prompt is generated based on the user query input and based on the identified first subset of the database data; and
receiving, from the generative AI language model, in response to the second prompt, an output comprising insight data generated based on the user query input and based on the identified first subset of the database data.