US 2026/0228426 A1Published application

Machine learning-based generation of solution trees for issues in an information technology infrastructure

AssigneeDell Products L.P.

InventorsAsish Pradhan, Malak Alshawabkeh, Anmol Dubey, Victoria Alexis Young, Sathisha B. Prabhu

Life of this patent

Estimating the term…

Loading patent…

Abstract

An apparatus comprises at least one processing device configured to obtain a natural language description of issues associated with an information technology infrastructure, to process, utilizing a machine learning model, the natural language description and data structures characterizing content of pre-built solution trees for historical issues, and to generate a solution tree for the issues utilizing at least one pre-built solution tree selected based on an output of the machine learning model as a template, the generated solution tree comprising a graphical representation of steps for achieving potential solutions to the issues. The at least one processing device is further configured to associate the generated solution tree with at least a subset of information technology assets of the information technology infrastructure, and to utilize the generated solution tree for diagnosing and remediating the issues on the subset of the information technology assets.

Claims20

Dependent claims

An apparatus comprising:

at least one processing device comprising a processor coupled to a memory;
the at least one processing device being configured:
to obtain a natural language description of one or more issues associated with an information technology infrastructure;
to process, utilizing at least one machine learning model, the natural language description of the one or more issues and at least portions of one or more data structures characterizing content of one or more pre-built solution trees for one or more historical issues;
to select, based at least in part on an output of the at least one machine learning model, at least a portion of at least one of the one or more pre-built solution trees;
to generate a solution tree for the one or more issues utilizing the selected at least a portion of at least one of the one or more pre-built solution trees as a template, the generated solution tree comprising a graphical representation of different potential solutions to the one or more issues and steps for achieving each of the different potential solutions;
to associate the generated solution tree with at least a subset of a plurality of information technology assets of the information technology infrastructure;
and
to utilize the generated solution tree for at least one of diagnosing and remediating instances of the one or more issues encountered on the subset of the plurality of information technology assets of the information technology infrastructure.

6 more elements

A computer program product comprising a non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes the at least one processing device:

to obtain a natural language description of one or more issues associated with an information technology infrastructure;
to process, utilizing at least one machine learning model, the natural language description of the one or more issues and at least portions of one or more data structures characterizing content of one or more pre-built solution trees for one or more historical issues;
to select, based at least in part on an output of the at least one machine learning model, at least a portion of at least one of the one or more pre-built solution trees;
to generate a solution tree for the one or more issues utilizing the selected at least a portion of at least one of the one or more pre-built solution trees as a template, the generated solution tree comprising a graphical representation of different potential solutions to the one or more issues and steps for achieving each of the different potential solutions;
to associate the generated solution tree with at least a subset of a plurality of information technology assets of the information technology infrastructure;
and
to utilize the generated solution tree for at least one of diagnosing and remediating instances of the one or more issues encountered on the subset of the plurality of information technology assets of the information technology infrastructure.

4 more elements

A method comprising:

obtaining a natural language description of one or more issues associated with an information technology infrastructure;
processing, utilizing at least one machine learning model, the natural language description of the one or more issues and at least portions of one or more data structures characterizing content of one or more pre-built solution trees for one or more historical issues;
selecting, based at least in part on an output of the at least one machine learning model, at least a portion of at least one of the one or more pre-built solution trees;
generating a solution tree for the one or more issues utilizing the selected at least a portion of at least one of the one or more pre-built solution trees as a template, the generated solution tree comprising a graphical representation of different potential solutions to the one or more issues and steps for achieving each of the different potential solutions;
associating the generated solution tree with at least a subset of a plurality of information technology assets of the information technology infrastructure;
and
utilizing the generated solution tree for at least one of diagnosing and remediating instances of the one or more issues encountered on the subset of the plurality of information technology assets of the information technology infrastructure;
wherein the method is performed by at least one processing device comprising a processor coupled to a memory.

5 more elements

Dependencies are inferred from the claim text.