US 12,190,416 B1
Method and apparatus for contextually intelligent graph generation
Andrei Papancea, New York, NY (US); Vlad Papancea, New York, NY (US); and Peter Szerzo, Berlin (DE)
Assigned to NLX Inc., New York, NY (US)
Filed by NLX Inc., New York, NY (US)
Filed on Aug. 8, 2024, as Appl. No. 18/798,014.
Claims priority of provisional application 63/518,267, filed on Aug. 8, 2023.
Int. Cl. G06F 40/40 (2020.01); G06T 11/20 (2006.01)
CPC G06T 11/206 (2013.01) [G06F 40/40 (2020.01); G06T 2200/24 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving, via a processor, a representation of a first natural language prompt;
sending, via the processor, a representation of the first natural language prompt to a large language model (LLM) configured to identify a first pattern based on the first natural language prompt;
determining, via the processor and based on a graph, a first main inlet associated with the first pattern at the graph, a first success outlet associated with the first pattern at the graph, and a first error outlet associated with the first pattern at the graph;
determining a first modification based on the first main inlet, the first success outlet, and the first error outlet; and
modifying the graph based on the first modification to generate a first modified graph.