AI-powered macros to process complex NLP queries across domains
Techniques for AI-powered macros to process complex natural language processing (NLP) across domains are disclosed. In some embodiments, a system, a process, and/or a computer program product for AI-powered macros to process complex NLP across domains includes processing a natural language query; performing a cross-domain search to generate a search result using a plurality of data source domains using a resource query language (RQL) and a Large Language Model (LLM); and outputting the search result.
1 . A system, comprising:
a processor configured to:
process a natural language query;
perform a cross-domain search to generate a search result using a plurality of data source domains using a resource query language (RQL) and a Large Language Model (LLM), comprising to:
generate a structured JSON representation related to the natural language query;
search, based on a generic asset query associated with the structured JSON representation, a vulnerability database to obtain a set of vulnerabilities; and
perform, based a ranked set of RQLs covering a set of asset types, a search to generate the search result, wherein the set of asset types relate to information retrieved from the information retrieval, wherein the ranked set of RQLs relates to the set of vulnerabilities, wherein the ranked set of RQLs includes a plurality of RQLs; and
output the search result; and
a memory coupled to the processor and configured to provide the processor with instructions.
2 . The system of claim 1 , wherein performing the cross-domain search to generate the search result using the plurality of data source domains further includes using a planner, executor, and aggregator to collect distinct results from each of the plurality of data source domains.
3 . The system of claim 1 , wherein performing the cross-domain search to generate the search result using the plurality of data source domains further includes using a planner, executor, and aggregator to collect distinct results from each of the plurality of data source domains and further using an application programming interface (API).
4 . The system of claim 1 , wherein the plurality of data source domains includes a configuration data set, an Identity and Asset Management (IAM) data set, and a vulnerability data set.
5 . The system of claim 1 , wherein the RQL is generated for RQL for multi-domain security applications.
6 . The system of claim 1 , wherein the LLM is trained for performing automated entity extraction for multi-domain security applications.
7 . The system of claim 1 , wherein the processor is further configured to:
generate an output graph of assets in response to the natural language query.
8 . The system of claim 1 , wherein the processor is further configured to:
execute the ranked set of RQLs in a ranked order and aggregate results for the search result.
9 . A method, comprising:
processing a natural language query;
performing a cross-domain search to generate a search result using a plurality of data source domains using a resource query language (RQL) and a Large Language Model (LLM); (LLM), comprising:
generating a structured JSON representation related to the natural language query;
searching, based on a generic asset query associated with the structured JSON representation, a vulnerability database to obtain a set of vulnerabilities; and
performing, based a ranked set of RQLs covering a set of asset types, a search to generate the search result, wherein the set of asset types relate to information retrieved from the information retrieval, wherein the ranked set of ROLs relates to the set of vulnerabilities, wherein the ranked set of RQLs includes a plurality of RQLs; and
outputting the search result.
10 . The method of claim 9 , wherein performing the cross-domain search to generate the search result using the plurality of data source domains further includes using a planner, executor, and aggregator to collect distinct results from each of the plurality of data source domains.
11 . The method of claim 9 , wherein performing the cross-domain search to generate the search result using the plurality of data source domains further includes using a planner, executor, and aggregator to collect distinct results from each of the plurality of data source domains and further using an application programming interface (API).
12 . The method of claim 9 , wherein the plurality of data source domains includes a configuration data set, an Identity and Asset Management (IAM) data set, and a vulnerability data set.
13 . The method of claim 9 , further comprising:
generating an output graph of assets in response to the natural language query.
14 . The method of claim 9 , further comprising:
executing the ranked set of RQLs in a ranked order and aggregating results for the search result.
15 . A computer program product embodied in a non-transitory computer readable medium and comprising computer instructions for:
processing a natural language query;
performing a cross-domain search to generate a search result using a plurality of data source domains using a resource query language (RQL) and a Large Language Model; (LLM), comprising:
generating a structured JSON representation related to the natural language query;
searching, based on a generic asset query associated with the structured JSON representation, a vulnerability database to obtain a set of vulnerabilities; and
performing, based a ranked set of RQLs covering a set of asset types, a search to generate the search result, wherein the set of asset types relate to information retrieved from the information retrieval, wherein the ranked set of ROLs relates to the set of vulnerabilities, wherein the ranked set of RQLs includes a plurality of RQLs; and
outputting the search result.
16 . The computer program product of claim 15 , wherein performing the cross-domain search to generate the search result using the plurality of data source domains further includes using a planner, executor, and aggregator to collect distinct results from each of the plurality of data source domains.
17 . The computer program product of claim 15 , wherein performing the cross-domain search to generate the search result using the plurality of data source domains further includes using a planner, executor, and aggregator to collect distinct results from each of the plurality of data source domains and further using an application programming interface (API).
18 . The computer program product of claim 15 , wherein the plurality of data source domains includes a configuration data set, an Identity and Asset Management (IAM) data set, and a vulnerability data set.
19 . The computer program product of claim 15 , further comprising computer instructions for:
generating an output graph of assets in response to the natural language query.
20 . The computer program product of claim 15 , further comprising computer instructions for:
executing the ranked set of RQLs in a ranked order and aggregating results for the search result.