Cognitive computer diagnostics and problem resolution
AssigneeInternational Business Machines Corporation
InventorsShubhadip Ray, Andrew S. Christiansen, Norbert Herman, Avik Sanyal
Life of this patent
Estimating the term…
Abstract
Disclosed embodiments provide techniques for automated technical support based on cognitive capabilities and preferences of a user. A user profile is obtained which includes a skill level assessment. A solution path includes one or more potential solutions for a problem. One or more solutions in the solution path are presented to a user as a potential remedy for a technical problem, based on the cognitive capabilities and preferences of a user.
Claims20
A computer implemented method for device technical support for a user, comprising:
- determining a user cluster corresponding to the user;
- detecting a device problem on an electronic device corresponding to the user;
- determining, using a machine learning algorithm, a solution path for the device problem, wherein the solution path has a plurality of solutions that are based on the device problem and the user cluster and that are queued on the solution path sorted from simplest to most complex;
- providing instructions corresponding to the solution path to the user;
- determining a solution path success result;
- recording the solution path success result;
- and
- inputting the results are into the machine learning algorithm to further train the machine learning algorithm whether the solutions in the solution path work for the user cluster.
An electronic computing device comprising:
- a processor;
- a memory coupled to the processor, the memory containing instructions, that when executed by the processor, perform the steps of:
- determining a user cluster corresponding to a user;
- detecting a device problem on an electronic device corresponding to the user;
- determining, using a machine learning algorithm, a solution path for the device problem, wherein the solution path has a plurality of solutions that are based on the device problem and the user cluster and that are queued on the solution path sorted from simplest to most complex a solution path for the device problem, wherein the solution path is based on the device problem and the user cluster;
- providing instructions corresponding to the solution path to the user;
- determining a solution path success result;
- recording the solution path success result;
- and
- inputting the results are into the machine learning algorithm to further train the machine learning algorithm whether the solutions in the solution path work for the user cluster.
A computer program product for an electronic computing device comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the electronic computing device to:
- determine a user cluster corresponding to a user;
- detect a device problem on an electronic device corresponding to the user;
- determine, using a machine learning algorithm, a solution path for the device problem, wherein the solution path has a plurality of solutions that are based on the device problem and the user cluster and that are queued on the solution path sorted from simplest to most complex;
- provide instructions corresponding to the solution path to the user;
- determine a solution path success result;
- record the solution path success result;
- and
- input the results are into the machine learning algorithm to further train the machine learning algorithm whether the solutions in the solution path work for the user cluster.
Dependencies are inferred from the claim text.