Framework for anomaly detection and resolution prediction
A method comprises collecting operational data for one or more devices and identifying one or more anomalies associated with the one or more devices based at least in part on the collected operational data. At least a portion of the collected operational data corresponding to the identified one or more anomalies is analyzed, and a probability of automatic resolution for respective ones of the identified one or more anomalies is determined based at least in part on the analysis. The identifying, the analyzing and the determining are performed using one or more machine learning models.
1. An apparatus comprising:
at least one processing platform comprising a plurality of processing devices;
said at least one processing platform being configured:
to receive operational data for one or more devices, wherein the operational data identifies one or more anomalies associated with the one or more devices;
to open one or more data streams corresponding to the one or more anomalies based at least in part on the operational data;
to analyze at least a portion of the operational data corresponding to the one or more anomalies;
to determine, using one or more machine learning models, probabilities of automatic resolution for respective ones of the one or more anomalies based at least in part on the analysis;
to generate one or more support requests for at least a subset of the one or more anomalies based at least in part on the determined probabilities;
to determine that at least one anomaly of the one or more anomalies has been resolved; and
to close a portion of the one or more data streams corresponding to the at least one anomaly.
2. The apparatus of claim 1 wherein the operational data comprises state data and telemetry data for the one or more devices.
3. The apparatus of claim 2 wherein the operational data is received at predetermined intervals.
4. The apparatus of claim 1 wherein the operational data is collected and transmitted from a client environment to an enterprise environment.
5. The apparatus of claim 4 wherein:
the operational data comprises state data and telemetry data for the one or more devices; and
said at least one processing platform is further configured:
to compress at least a portion of the telemetry data in the client environment;
to receive the compressed telemetry data in the enterprise environment; and
to decompress the compressed telemetry data in the enterprise environment.
6. The apparatus of claim 4 wherein said at least one processing platform is further configured to receive from the client environment an instruction to close the portion of the one or more data streams corresponding to the at least one anomaly.
7. The apparatus of claim 4 wherein said at least one processing platform is further configured to receive a timestamp of the resolution of the at least one anomaly from the client environment.
8. The apparatus of claim 4 wherein said at least one processing platform is further configured:
to receive from the client environment an instruction to open the one or more data streams; and
to listen for the instruction in the enterprise environment.
9. The apparatus of claim 4 wherein said at least one processing platform is further configured to receive from the client environment respective timestamps corresponding to when the one or more anomalies were identified.
10. The apparatus of claim 1 wherein said at least one processing platform is further configured to compute a confidence score for respective ones of the determined probabilities.
11. The apparatus of claim 10 wherein said at least one processing platform is further configured to generate a flag indicating an automatic resolution based on values of at least one of the respective ones of the determined probabilities and respective ones of the confidence scores.
12. The apparatus of claim 1 wherein said at least one processing platform is further configured:
to determine whether the at least one anomaly has been resolved automatically; and
to train the one or more machine learning models with data indicating whether the at least one anomaly was resolved automatically.
13. The apparatus of claim 1 wherein said at least one processing platform is further configured to train the one or more machine learning models with data indicating whether a plurality of anomalies were resolved automatically.
14. A method comprising:
receiving operational data for one or more devices, wherein the operational data identifies one or more anomalies associated with the one or more devices;
opening one or more data streams corresponding to the one or more anomalies based at least in part on the operational data;
analyzing at least a portion of the operational data corresponding to the one or more anomalies;
determining, using one or more machine learning models, probabilities of automatic resolution for respective ones of the one or more anomalies based at least in part on the analysis;
generating one or more support requests for at least a subset of the one or more anomalies based at least in part on the determined probabilities;
determining that at least one anomaly of the one or more anomalies has been resolved; and
closing a portion of the one or more data streams corresponding to the at least one anomaly;
wherein the method is performed by at least one processing platform comprising at least one processing device comprising a processor coupled to a memory.
15. The method of claim 14 wherein the operational data is collected and transmitted from a client environment to an enterprise environment.
16. The method of claim 15 further comprising
receiving from the client environment an instruction to close the portion of the one or more data streams corresponding to the at least one anomaly.
17. 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 platform causes said at least one processing platform:
to receive operational data for one or more devices, wherein the operational data identifies one or more anomalies associated with the one or more devices;
to open one or more data streams corresponding to the one or more anomalies based at least in part on the operational data;
to analyze at least a portion of the operational data corresponding to the one or more anomalies;
to determine, using one or more machine learning models, probabilities of automatic resolution for respective ones of the one or more anomalies based at least in part on the analysis;
to generate one or more support requests for at least a subset of the one or more anomalies based at least in part on the determined probabilities;
to determine that at least one anomaly of the one or more anomalies has been resolved; and
to close a portion of the one or more data streams corresponding to the at least one anomaly.
18. The computer program product according to claim 17 wherein the operational data is collected and transmitted from a client environment to an enterprise environment.
19. The computer program product according to claim 18 wherein the program code further causes said at least one processing platform to receive from the client environment an instruction to close the portion of the one or more data streams corresponding to the at least one anomaly.
20. The computer program product according to claim 17 wherein said at least one processing platform is further configured:
to determine whether the at least one anomaly has been resolved automatically; and
to train the one or more machine learning models with data indicating whether the at least one anomaly was resolved automatically.