US 12,425,449 B2
Logical language model prompts for fraud detection
Constantin D. Cernat, Bucharest (RO); and Ovidiu M. Craciun, Bucharest (RO)
Assigned to Bitdefender IPR Management Ltd., Nicosia (CY)
Filed by Bitdefender IPR Management Ltd., Nicosia (CY)
Filed on Apr. 30, 2024, as Appl. No. 18/650,312.
Application 18/650,312 is a continuation of application No. 18/650,276, filed on Apr. 30, 2024.
Claims priority of provisional application 63/612,405, filed on Dec. 20, 2023.
Prior Publication US 2025/0211615 A1, Jun. 26, 2025
Int. Cl. H04L 9/40 (2022.01); G06F 40/284 (2020.01); G06F 40/40 (2020.01)
CPC H04L 63/1483 (2013.01) [G06F 40/284 (2020.01); G06F 40/40 (2020.01); H04L 63/1416 (2013.01); H04L 63/1425 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A computer system comprising at least one hardware processor configured to analyze a target text formulated in a natural language, wherein analyzing the target text comprises executing a prompt manager communicatively coupled to a generative language module (GLM), wherein:
the GLM is configured to:
receive from the prompt manager a language model (LM) prompt formulated in the natural language, and
in response, output to the prompt manager a predicted token comprising a continuation of the received LM prompt; and
the prompt manager is configured to:
receive a logical prompt, the logical prompt including the target text and a code snippet comprising computer code for updating the LM prompt,
formulate the LM prompt according to the logical prompt, the LM prompt instructing the GLM to perform a text analysis task according to the target text and in response, to output a flag token,
in response to receiving the predicted token, initiate an execution of the code snippet to produce an updated LM prompt,
transmit the updated LM prompt to the GLM, and
formulate a reply message comprising a result of analyzing the target text, the reply message formulated according to an output of the GLM in response to the updated LM prompt.