| CPC G06F 16/3344 (2019.01) [G06F 16/313 (2019.01); G06F 16/3329 (2019.01); G06F 16/338 (2019.01)] | 20 Claims |
|
1. A system comprising:
at least one processor; and
memory storing instructions that, when executed by the at least one processor, cause the system to perform a set of operations, the set of operations comprising:
receiving a natural language (NL) query for retrieving operator metric data, wherein the operator metric data indicate metrics of the system, the operator metric data represent one or more metrics of a plurality of metrics, and a metric of the plurality of metrics comprises a metric definition;
extracting context of the NL query based on a definition database, wherein the definition database comprises the metric definition of a respective metric of the plurality of metrics, and the context comprises at least a part of the metric definition of the metric;
creating a first prompt in natural language based on the NL query and the extracted context for interacting with a first machine learning (ML) model using the natural language;
receiving a first output in the natural language from the first ML model, wherein the first output specifies one or more metrics for query for retrieving at least a part of the operator metric data as an answer to the NL query;
creating a second prompt in the natural language based on the NL query and the first output for interacting with a second ML model using the natural language, wherein the second prompt comprises a request to the second ML model for generating code output;
receiving a second output from the second ML model based on the second prompt, wherein the second output comprises a code query that causes retrieval of metric data of the one or more metrics;
executing the code query, thereby retrieving and generating the metric data of the one or more metrics as the answer responsive to the NL query; and
modifying data traffic based on the generated metric data.
|