US 12,443,635 B1
Systems and methods for automated prompt generation for intelligent alerting in condition monitoring using contextual language models and retrieval-augmented generation
Mark A. Wolff, Cary, NC (US)
Assigned to SAS INSTITUTE INC., Cary, NC (US)
Filed by SAS Institute Inc., Cary, NC (US)
Filed on Jun. 5, 2025, as Appl. No. 19/229,708.
Claims priority of provisional application 63/704,226, filed on Oct. 7, 2024.
Int. Cl. G06F 16/3329 (2025.01); G06F 16/334 (2025.01)
CPC G06F 16/3329 (2019.01) [G06F 16/334 (2019.01)] 30 Claims
OG exemplary drawing
 
1. A computer-program product comprising a non-transitory machine-readable storage medium storing computer instructions that, when executed by one or more processors, perform operations comprising:
receiving a machine-generated alert indicating a data outlier for a physical asset;
obtaining, from a computer database, a dataset comprising observed data for the physical asset within a predefined temporal window of the machine-generated alert;
generating, via a description generator, a contextual description of the data outlier based at least on the observed data for the physical asset;
in response to generating the contextual description of the data outlier, searching an embedding-based knowledgebase that comprises a plurality of embedding representations corresponding to a plurality of reference artifacts for the physical asset, wherein searching the embedding-based knowledgebase includes:
computing, via an embedding model, an embedding representation of the contextual description generated for the data outlier, and
detecting a subset of embedding representations of the plurality of embedding representations within a similarity threshold of the embedding representation of the contextual description;
obtaining, from the computer database, a subset of the plurality of reference artifacts that correspond to the subset of embedding representations; and
generating, via a large language model, a resolution suggestion for resolving the data outlier based at least on the subset of reference artifacts obtained from the computer database.