Adaptive collection of telemetry data
An information handling system includes a memory and a processor. The memory stores telemetry data, telemetry collection rules, and persona classifications for the information handling system. The processor collects first telemetry data for the information handling system based on first telemetry collection rules. The first telemetry collection rules are set based on a first persona classification for the information handling system. The processor determines whether user behaviors change from behaviors associated with the first persona classification. In response to an amount of change in the user behaviors being above a threshold amount, the processor changes a classification of the information handling system from the first persona classification to a second persona classification. In response to the classification of the information handling system being the second persona classification, the processor collects second telemetry data for the information handling system based on second telemetry collection rules of the second persona classification.
1. An information handling system comprising:
a memory to store first and second telemetry data, telemetry collection rules including first and second sets of telemetry collection rules, and persona classifications; and
a processor to communicate with the memory, the processor to:
collect the first telemetry data for the information handling system based on the first set of telemetry collection rules, wherein the first set of telemetry collection rules are set based on a first persona classification for the information handling system;
determine whether user behaviors change from behaviors associated with the first persona classification;
in response to an amount of change in the user behaviors being above a threshold amount, change a classification of the information handling system from the first persona classification to a second persona classification; and
in response to the classification of the information handling system being the second persona classification, collect the second telemetry data for the information handling system based on the second set of telemetry collection rules of the second persona classification.
2. The information handling system of claim 1 , wherein the processor further to:
identify one or more usage profiles associated with the information handling system;
determine a persona type of an end user of the information handling system; and
determine the second persona classification based on the identified personas usage profiles and the persona type of the end user.
3. The information handling system of claim 2 , wherein each of the usage profiles is mapped to a different major consumption pattern of the information handling system.
4. The information handling system of claim 2 , wherein the processor further to:
determine a degree of association between the first persona classification and a cluster of usage profiles associated with the information handling system;
assign a weight to the degree of association, wherein a higher weight is assigned to a closer degree of association; and
determine an amount of time between retraining of a machine learning model based on the weight of the degree of association, wherein the amount of time increases in proportion to an increase of the weight of the degree of association.
5. The information handling system of claim 4 , wherein the machine learning model determines the second persona classification.
6. The information handling system of claim 4 , wherein prior to the determination of whether user behaviors change from behaviors associated with the first persona classification, the processor further determines whether a particular amount of time has expired, wherein the particular amount of time is associated with the degree of association.
7. The information handling system of claim 1 , wherein the first telemetry data is collected for a first set of attributes and the second telemetry data is collected for a second set of attributes.
8. The information handling system of claim 1 , wherein the first persona classification is determined based on usages and behaviors of an individual utilizing the information handling system.
9. A method comprising:
collecting, by a processor of an information handling system, first telemetry data for the information handling system based on first telemetry collection rules, wherein the first telemetry collection rules are set based on a first persona classification for the information handling system;
determining whether user behaviors change from behaviors associated with the first persona classification;
in response to an amount of change in the user behaviors being above a threshold amount, changing a classification of the information handling system from the first persona classification to a second persona classification; and
in response to the classification of the information handling system being the second persona classification, collecting second telemetry data for the information handling system based on second telemetry collection rules of the second persona classification.
10. The method of claim 9 , further comprising:
identifying one or more usage profiles associated with the information handling system;
determining a persona type of an end user of the information handling system; and
determining the second persona classification based on the identified usage profiles and the persona type of the end user.
11. The method of claim 10 , wherein each of the usage profiles is mapped to a different major consumption pattern of the information handling system.
12. The method of claim 10 , further comprising:
determining a degree of association between the first persona classification and a cluster of usage profiles associated with the information handling system;
assigning a weight to the degree of association, wherein a higher weight is assigned to a closer degree of association; and
determining an amount of time between retraining of a machine learning model based on the weight of the degree of association, wherein the amount of time increases in proportion to an increase of the weight of the degree of association.
13. The method of claim 12 , further comprising:
determining, by the machine learning model, the second persona classification.
14. The method of claim 12 , wherein prior to the determining of whether user behaviors change from behaviors associated with the first persona classification, the method further comprises:
determining whether a particular amount of time has expired, wherein the particular amount of time is associated with the degree of association.
15. The method of claim 9 , wherein the first telemetry data is collected for a first set of attributes and the second telemetry data is collected for a second set of attributes.
16. The method of claim 9 , wherein the first persona classification is determined based on usages and behaviors of an individual utilizing the information handling system.
17. A method comprising:
collecting telemetry for personas from multiple information handling systems;
determining one or more new metrics for the telemetry for the personas;
based on the determined new metrics, re-classifying one or more personas;
providing the re-classified personas to each of the information handling systems;
collecting, by a processor of a first information handling system of the information handling systems, first telemetry data for the first information handling system based on first telemetry collection rules, wherein the first telemetry collection rules are set based on a first persona classification for the first information handling system;
determining whether user behaviors change from behaviors associated with the first persona classification;
in response to an amount of change in the user behaviors being above a threshold amount, changing a classification of the first information handling system from the first persona classification to a second persona classification; and
in response to the classification of the information handling systems being the second persona classification, collecting second telemetry data for the information handling system based on second telemetry collection rules of the second persona classification.
18. The method of claim 17 , further comprising:
identifying one or more usage profiles associated with the first information handling system;
determining a persona type of an end user of the first information handling system; and
determining the second persona classification based on the identified usage profiles and the persona type of the end user.
19. The method of claim 18 , further comprising:
determining a degree of association between the first persona classification and a cluster of usage profiles associated with the first information handling system;
assigning a weight to the degree of association, wherein a higher weight is assigned to a closer degree of association; and
determining an amount of time between retraining of a machine learning model based on the weight of the degree of association, wherein the amount of time increases in proportion to an increase of the weight of the degree of association.
20. The method of claim 17 , wherein the first telemetry data is collected for a first set of attributes and the second telemetry data is collected for a second set of attributes.