Data collection agent trained for telemetry data collection

Patent metadata

Field	Value
Publication number	US-2022237061-A1
Application number	US-202117157257-A
Country	US
Kind code	A1
Filing date	Jan 25, 2021
Priority date	Jan 25, 2021
Publication date	Jul 28, 2022
Grant date	—

Abstract

An apparatus comprises at least one processing device that is configured to implement a data collection agent and obtain a telemetry data collection specification. The at least one processing device is configured to train the data collection agent based at least in part on the telemetry data collection specification and to obtain an issue description corresponding to a technical support issue associated with a source device of an information processing system. The at least one processing device is configured to generate a telemetry data collection query based at least in part on the obtained issue description using the trained data collection agent and to submit the query to the source device. The at least one processing device is configured to obtain from the source device, telemetry data generated based at least in part on the query and to present the telemetry data to a user via a graphical user interface.

First claim

What is claimed is:

1 . An apparatus comprising:
at least one processing device comprising a processor coupled to memory, the at least one processing device being configured:
to implement a data collection agent;
to obtain a telemetry data collection specification;
to train the data collection agent based at least in part on the telemetry data collection specification;
to obtain an issue description corresponding to a technical support issue associated with a source device of an information processing system;
to generate a telemetry data collection query based at least in part on the obtained issue description using the trained data collection agent;
to submit the query to the source device;
to obtain from the source device, telemetry data generated based at least in part on the query; and
to present the telemetry data to a user via a graphical user interface.

2 . The apparatus of claim 1 wherein the at least one processing device is further configured:
to obtain an input from the user via the graphical user interface, the input comprising at least one action;
to obtain information indicating a result of the at least one action; and
to re-train the data collection agent based at least in part on the obtained information.

3 . The apparatus of claim 2 :
wherein the at least one processing device is further configured:
to store information corresponding to the issue description in the telemetry data collection specification; and
to store at least one of the following in the telemetry data collection specification in conjunction with the information corresponding to the issue description:
information corresponding to the obtained telemetry data;
information corresponding to the at least one action; and
the information indicating the result of the at least one action; and

wherein re-training the data collection agent based at least in part on the obtained information comprises re-training the data collection agent based at least in part on the telemetry data collection specification.

4 . The apparatus of claim 3 :
wherein the data collection specification comprises a plurality of steps, at least a first of the steps corresponding to the telemetry data generated based at least in part on the query generated by the data collection agent and at least a second of the steps corresponding to the at least one action input by the user; wherein the at least one processing device is further configured to determine an influence of each step toward a resolution of the technical support issue; and wherein re-training the data collection agent based at least in part on the telemetry data collection specification comprises re-training the data collection agent based at least in part on the determined influence for each step.

5 . The apparatus of claim 3 :
wherein the re-training of the data collection agent comprises at least one of an offline mode of re-training and an online mode of re-training; wherein the offline mode of re-training comprises utilizing a temporal difference updates model of re-training; and wherein the online mode of re-training comprises utilizing a Monte Carlo updates model of re-training.

6 . The apparatus of claim 1 :
wherein the source device comprises a module that is configured to generate a set of telemetry data corresponding to a plurality of attributes of the source device; and wherein the trained data collection agent is configured to generate the telemetry data collection query such that the telemetry data collection query is configured to request telemetry data corresponding to a specific portion of the plurality of attributes of the source device from the module of the source device, the specific portion being less than the full plurality of attributes.

7 . The apparatus of claim 6 :
wherein the at least one processing device is configured to assign each of the attributes of the plurality of attributes of the source device to a corresponding attribute group of a plurality of attribute groups such that the plurality of attributes is divided among the plurality of attribute groups, the number of attribute groups in the plurality of attribute groups being smaller than the number of attributes in the plurality of attributes; and wherein the specific portion of the plurality of attributes requested by the telemetry data collection query corresponds to the attributes assigned to at least one of the attribute groups.

8 . A method comprising:
implementing a data collection agent; obtaining a telemetry data collection specification; training the data collection agent based at least in part on the telemetry data collection specification; obtaining an issue description corresponding to a technical support issue associated with a source device of an information processing system; generating a telemetry data collection query based at least in part on the obtained issue description using the trained data collection agent; submitting the query to the source device; obtaining from the source device, telemetry data generated based at least in part on the query; and presenting the telemetry data to a user via a graphical user interface; wherein the method is implemented by at least one processing device comprising a processor coupled to memory.

9 . The method of claim 8 wherein the method further comprises:
obtaining an input from the user via the graphical user interface, the input comprising at least one action;
obtaining information indicating a result of the at least one action; and
re-training the data collection agent based at least in part on the obtained information.

10 . The method of claim 9 :
wherein the method further comprises:
storing information corresponding to the issue description in the telemetry data collection specification; and
storing at least one of the following in the telemetry data collection specification in conjunction with the information corresponding to the issue description:
information corresponding to the obtained telemetry data;
information corresponding to the at least one action; and
the information indicating the result of the at least one action; and

wherein re-training the data collection agent based at least in part on the obtained information comprises re-training the data collection agent based at least in part on the telemetry data collection specification.

11 . The method of claim 10 :
wherein the data collection specification comprises a plurality of steps, at least a first of the steps corresponding to the telemetry data generated based at least in part on the query generated by the data collection agent and at least a second of the steps corresponding to the at least one action input by the user; wherein the method further comprises determining an influence of each step toward a resolution of the technical support issue; and wherein re-training the data collection agent based at least in part on the telemetry data collection specification comprises re-training the data collection agent based at least in part on the determined influence for each step.

12 . The method of claim 10 :
wherein the re-training of the data collection agent comprises at least one of an offline mode of re-training and an online mode of re-training; wherein the offline mode of re-training comprises utilizing a temporal difference updates model of re-training; and wherein the online mode of re-training comprises utilizing a Monte Carlo updates model of re-training.

13 . The method of claim 8 :
wherein the source device comprises a module that is configured to generate a set of telemetry data corresponding to a plurality

Assignees

• Dell Products Lp

Inventors

• Sethi Parminder Singh
• Chambers Landon Martin

Classifications

• G06N3/045

  Combinations of networks · CPC title

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06N3/006

  based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] · CPC title

• G06F11/321

  Display for diagnostics, e.g. diagnostic result display, self-test user interface · CPC title

• G06F11/3065

  Monitoring arrangements determined by the means or processing involved in reporting the monitored data (error or fault reporting or logging G06F11/0766) · CPC title