Systems and methods for prompt-based probe generation
AssigneeServiceNow, Inc.
InventorsYair Aharon Liebkowiz, Robert Bitterfeld, Tal Ben Ari
Life of this patent
Estimating the term…
Abstract
A method including parsing, via a Large Language Model (LLM), a configuration file comprising one or more attributes associated with one or more components of a network, wherein parsing the configuration file comprises generating a probe based on the one or more attributes. The method also includes executing the probe for discovery of one or more attributes associated with the one or more components of the network and updating a resource management database based on the one or more attributes.
Claims20
A method comprising:
- receiving a configuration file and a prompt, wherein the configuration file comprises a plurality of attributes associated with one or more components of a network, and wherein the prompt comprises one or more selected attribute types;
- generating, via a Large Language Model (LLM), a probe by parsing the plurality of attributes in the configuration file to identify one or more attributes corresponding to the one or more selected attribute types, wherein the probe comprises computer-implemented instructions to extract data corresponding to the one or more selected attribute types from the configuration file;
- executing the probe for during a configuration item discovery operation to extract the data corresponding to the one or more attributes from the configuration file;
- and
- updating a resource management database based on the data corresponding to the one or more attributes.
A method, comprising:
- receiving, via an interface, one or more inputs comprising one or more selected attribute types associated with one or more components of a network, a configuration file comprising a plurality of attributes, and a prompt indicative of instructions to identify the one or more selected attribute types;
- generating, via a Large Language Model (LLM), a probe by parsing the plurality of attributes in the configuration file to identify one or more attributes corresponding to the one or more selected attribute types, wherein the probe comprises computer-implemented instructions to extract data corresponding to the one or more selected attribute types from the configuration file;
- recursively applying the LLM to the configuration file based on a validity score, wherein the validity score is based on a correlation between the one or more selected attribute types and the one or more attributes identified by the LLM parsing the configuration file;
- determining that the validity score satisfies a threshold;
- and
- outputting an updated probe in response to the validity score satisfying the threshold, wherein outputting the updated probe comprises outputting the updated probe for display via the interface.
A non-transitory computer-readable storage medium, comprising processor-executable routines that, when executed by a processor, cause the processor to perform operations comprising:
- receiving a configuration file and a prompt, wherein the configuration file comprises a plurality of attributes associated with one or more components of a network, and wherein the prompt comprises one or more selected attribute types;
- generating, via a Large Language Model (LLM), a probe by parsing the plurality of attributes in the configuration file to identify one or more attributes corresponding to the one or more selected attribute types, wherein the probe comprises computer-implemented instructions to extract data corresponding to the one or more selected attribute types from the configuration file;
- executing the probe during a configuration item discovery operation to extract the data corresponding to the one or more attributes from the configuration file;
- and
- updating a resource management database based on the data corresponding to the one or more attributes.
Dependencies are inferred from the claim text.