Automatic mapping of records without configuration information
A method, a computer system, and a computer program product for mapping operational records to a topology graph. Embodiments of the present invention may include generating an event frequent pattern using operational records. Embodiments of the present invention may include integrating topology-based event frequent patterns. Embodiments of the present invention may include mapping the operational records with an embedding engine. Embodiments of the present invention may include predicting incident events. Embodiments of the present invention may include receiving labeled patterns to the embedding engine for an active learning cycle.
1. A method comprising:
generating an event frequent pattern using operational records retrieved from a historical database of operational records, wherein the event frequent pattern is generated using local neighborhood information;
integrating topology-based event frequent patterns into a word embedding model;
automatically mapping the operational records with a word embedding engine;
predicting incident events; and
receiving labeled patterns to the embedding engine for an active learning cycle.
2. The method of claim 1 , wherein the event frequent patterns are generated from a same node.
3. The method of claim 1 , wherein the event frequent patterns are generated from cross nodes.
4. The method of claim 1 , wherein the operational records do not contain configuration information.
5. The method of claim 1 , wherein the embedding engine uses a topology-based association embedding engine to map the event frequent patterns from an event embedding and a node embedding to train a model.
6. A computer system comprising:
one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage media, and program instructions stored on at least one of the one or more computer-readable tangible storage media for execution by at least one of the one or more processors via at least one of the one or more computer-readable memories, wherein the computer system is capable of performing a method comprising:
generating an event frequent pattern using operational records retrieved from a historical database of operational records, wherein the event frequent pattern is generated using local neighborhood information;
integrating topology-based event frequent patterns into a word embedding model;
automatically mapping the operational records with a word embedding engine;
predicting incident events; and
receiving labeled patterns to the embedding engine for an active learning cycle.
7. The computer system of claim 6 , wherein the event frequent patterns are generated from a same node.
8. The computer system of claim 6 , wherein the event frequent patterns are generated from cross nodes.
9. The computer system of claim 6 , wherein the operational records do not contain configuration information.
10. The computer system of claim 6 , wherein the embedding engine uses a topology-based association embedding engine to map the event frequent patterns from an event embedding and a node embedding to train a model.
11. A computer program product comprising:
one or more computer-readable tangible storage media and program instructions stored on at least one of the one or more computer-readable tangible storage media, the program instructions executable by a processor to cause the processor to perform a method comprising:
generating an event frequent pattern using operational records retrieved from a historical database of operational records, wherein the event frequent pattern is generated using local neighborhood information;
integrating topology-based event frequent patterns into a word embedding model;
automatically mapping the operational records with a word embedding engine;
predicting incident events; and
receiving labeled patterns to the embedding engine for an active learning cycle.
12. The computer program product of claim 11 , wherein the event frequent patterns are generated from a same node.
13. The computer program product of claim 11 , wherein the event frequent patterns are generated from cross nodes.
14. The computer program product of claim 11 , wherein the operational records do not contain configuration information.
15. The computer program product of claim 11 , wherein the embedding engine uses a topology-based association embedding engine to map the event frequent patterns from an event embedding and a node embedding to train a model.