US 12,242,473 B2
Graph-based Natural Language Processing (NLP) for querying, analyzing, and visualizing complex data structures
Mark Naufel, Scottsdale, AZ (US)
Assigned to Arizona Board of Regents on Behalf of Arizona State University, Scottsdale, AZ (US)
Filed by Arizona Board of Regents on Behalf of Arizona State University, Scottsdale, AZ (US)
Filed on Apr. 24, 2024, as Appl. No. 18/644,776.
Claims priority of provisional application 63/461,860, filed on Apr. 25, 2023.
Prior Publication US 2024/0362208 A1, Oct. 31, 2024
Int. Cl. G06F 7/00 (2006.01); G06F 16/242 (2019.01); G06N 20/00 (2019.01)
CPC G06F 16/243 (2019.01) [G06N 20/00 (2019.01)] 23 Claims
OG exemplary drawing
 
1. A system comprising:
processing circuitry;
non-transitory computer readable media storing instructions that, when executed by the processing circuitry, configure the processing circuitry to:
execute an AI language model;
specify data for training the AI language model available from one or more original data sources;
migrate the data specified for training the AI language model from the one or more original data sources into a graph database by exposing the one or more original data sources to the AI language model and performing at least the following data migration operations:
determine, via the AI language model, a data structure for the graph database;
generate, via the AI language model, an executable query script having self-written code to extract the data from the one or more original data sources exposed to the AI language model as extracted data;
execute the executable query script to extract the extracted data from the one or more original data sources;
generate, via the AI language model, an executable load script having self-written code to load the extracted data extracted from the one or more original data sources into the data structure of the graph database as new nodes and new relationships with directionality between the new nodes and having metadata parameters within the new nodes describing the extracted data loaded into the graph database;
execute the executable load script to load the extracted data extracted from the one or more original data sources into the graph database as loaded data;
condense the loaded data stored within the graph database into a condensed data structure representing a full architecture of the loaded data in a natural language format by performing at least the following data condensing operations:
query the graph database to obtain information on the new nodes, the new relationships, and the metadata parameters within the graph database;
provide as input to the AI language model, the information on the new nodes, the new relationships, and the metadata parameters; and
responsive to providing as input to the AI language model, the information on the new nodes, the new relationships, and the metadata parameters, generate as output from the AI language model, the condensed data structure;
receive a question as user-input in natural human language;
execute the AI language model to determine a user-intent from the user-input;
execute the AI language model to generate a structured data query contextualized against the condensed data structure based on the determined user-intent;
execute the structured data query against the graph database; and
return output in a structured format to a user-device having originated the user-input.