Encoding and decoding troubleshooting actions with machine learning to predict repair solutions
A method includes obtaining information regarding a given asset to be repaired, providing the information regarding the given asset to an encoder of a deep learning model, and receiving, from a decoder of the deep learning model, a recommendation for a troubleshooting action to be performed on the given asset. The method also includes performing the recommended troubleshooting action on the given asset, determining whether the recommended troubleshooting action results in a successful repair of the given asset and, responsive to determining that the recommended troubleshooting action does not result in a successful repair of the given asset, augmenting the information regarding the given asset based at least in part on an output vocabulary of the decoder corresponding to the recommended troubleshooting action. The method further includes repeating the providing, receiving, performing and determining steps utilizing the augmented information regarding the given asset.
1. A method comprising steps of:
obtaining information regarding a given asset to be repaired;
providing the information regarding the given asset to an encoder of a deep learning model;
receiving, from a decoder of the deep learning model, a recommendation for a troubleshooting action to be performed on the given asset;
performing the recommended troubleshooting action on the given asset;
determining whether the recommended troubleshooting action results in a successful repair of the given asset;
responsive to determining that the recommended troubleshooting action does not result in a successful repair of the given asset, augmenting the information regarding the given asset based at least in part on an output vocabulary of the decoder corresponding to the recommended troubleshooting action; and
repeating the providing, receiving, performing and determining steps utilizing the augmented information regarding the given asset;
wherein the method is performed by at least one processing device comprising a processor coupled to a memory.
2. The method of claim 1 wherein the information regarding the given asset to be repaired comprises one or more symptom sets, a given one of the one or more symptom sets comprising an identifier of the given asset, a description of the given asset, and a description of at least one error encountered on the given asset.
3. The method of claim 2 , wherein the information regarding the given asset to be repaired further comprises result information regarding the success or failure of one or more troubleshooting actions previously performed on the given asset.
4. The method of claim 2 wherein the information regarding the given asset comprises two or more symptom sets, and wherein iterations of the providing, receiving, performing and determining steps are run separately for each of the two or more symptom sets by utilizing information corresponding to a single one of the two or more symptom sets in each iteration of the providing step.
5. The method of claim 1 wherein augmenting the information regarding the given asset based at least in part on the output vocabulary of the decoder corresponding to the recommended troubleshooting action comprises adding a negation of the output vocabulary of the decoder corresponding to the recommended troubleshooting action to the information regarding the given asset that is provided to the encoder of the deep learning model in a subsequent iteration of the providing step.
6. The method of claim 1 wherein the deep learning model comprises a sequence-to-sequence machine learning model.
7. The method of claim 6 wherein providing the information regarding the given asset to the encoder of the deep learning model comprises performing character-level input of the information regarding the given asset.
8. The method of claim 7 wherein augmenting the information regarding the given asset based at least in part on the output vocabulary of the decoder corresponding to the recommended troubleshooting action comprises modifying the character-level input of the information regarding the given asset to add a set of characters comprising a negation of the output vocabulary of the decoder corresponding to the recommended troubleshooting action.
9. The method of claim 6 wherein providing the information regarding the given asset to the encoder of the deep learning model comprises performing word-level input of the information regarding the given asset.
10. The method of claim 9 wherein augmenting the information regarding the given asset based at least in part on the output vocabulary of the decoder corresponding to the recommended troubleshooting action comprises modifying the word-level input of the information regarding the given asset to comprise negations of words in the output vocabulary of the decoder corresponding to the recommended troubleshooting action.
11. The method of claim 1 further comprising training the deep learning model utilizing information from one or more repair log entries for the given asset, historical repair logs for a plurality of other assets, and one or more technical support forums.
12. The method of claim 1 wherein the troubleshooting action comprises a diagnostic action.
13. The method of claim 1 wherein the troubleshooting action comprises a repair action.
14. The method of claim 13 wherein the given asset comprises a computing device, and wherein the repair action comprises modifying at least one of: one or more software components of the computing device; and one or more hardware components of the computing device.
15. 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 perform steps of:
obtaining information regarding a given asset to be repaired;
providing the information regarding the given asset to an encoder of a deep learning model;
receiving, from a decoder of the deep learning model, a recommendation for a troubleshooting action to be performed on the given asset;
performing the recommended troubleshooting action on the given asset;
determining whether the recommended troubleshooting action results in a successful repair of the given asset;
responsive to determining that the recommended troubleshooting action does not result in a successful repair of the given asset, augmenting the information regarding the given asset based at least in part on an output vocabulary of the decoder corresponding to the recommended troubleshooting action; and
repeating the providing, receiving, performing and determining steps utilizing the augmented information regarding the given asset.
16. The computer program product of claim 15 wherein the information regarding the given asset to be repaired comprises:
one or more symptom sets, a given one of the one or more symptom sets comprising an identifier of the given asset, a description of the given asset, and a description of at least one error encountered on the given asset; and
result information regarding the success or failure of one or more diagnostic and repair actions previously performed on the given asset.
17. The computer program product of claim 15 wherein augmenting the information regarding the given asset based at least in part on the output vocabulary of the decoder corresponding to the recommended troubleshooting action comprises adding a negation of the output vocabulary of the decoder corresponding to the recommended troubleshooting action to the information regarding the given asset that is provided to the encoder of the deep learning model in a subsequent iteration of the providing step.
18. An apparatus comprising:
at least one processing device comprising a processor coupled to a memory;
the at least one processing device being configured to perform steps of:
obtaining information regarding a given asset to be repaired;
providing the information regarding the given asset to an encoder of a deep learning model;
receiving, from a decoder of the deep learning model, a recommendation for a troubleshooting action to be performed on the given asset;
performing the recommended troubleshooting action on the given asset;
determining whether the recommended troubleshooting action results in a successful repair of the given asset;
responsive to determining that the recommended troubleshooting action does not result in a successful repair of the given asset, augmenting the information regarding the given asset based at least in part on an output vocabulary of the decoder corresponding to the recommended troubleshooting action; and
repeating the providing, receiving, performing and determining steps utilizing the augmented information regarding the given asset.
19. The apparatus of claim 18 wherein the information regarding the given asset to be repaired comprises:
one or more symptom sets, a given one of the one or more symptom sets comprising an identifier of the given asset, a description of the given asset, and a description of at least one error encountered on the given asset; and
result information regarding the success or failure of one or more diagnostic and repair actions previously performed on the given asset.
20. The apparatus of claim 18 wherein augmenting the information regarding the given asset based at least in part on the output vocabulary of the decoder corresponding to the recommended troubleshooting action comprises adding a negation of the output vocabulary of the decoder corresponding to the recommended troubleshooting action to the information regarding the given asset that is provided to the encoder of the deep learning model in a subsequent iteration of the providing step.