IP Library › Granted Patent US 12,632,366
Granted Patent B2
US 12,632,366 · App. 18/646,089 · Granted May 19, 2026

Accelerated event generation for supervised learning

Inventors: Erik P. Smith (Douglas, MA); Edward Henry (Jurupa Valley, CA); Gajanan S Natu (Cary, NC); Sumanta SK Kashyapi (Worcester, MA); David Carl Sydow (Merrimack, NH)
Assignee: Dell Products L.P.
G06F11/3684
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,632,366
App. No.
18/646,089
Granted
May 19, 2026
Kind
B2
Abstract

A method for generating testing information for prediction model training includes: identifying, by an automated event generation and data labeling (AEGDL) manager, a test case initiation event; in response to the identification: selecting a first test case of a plurality of test cases; identifying a first test configuration cluster (TCC) of a plurality of TCCs based on the test case; performing the first test case in the TCC; generating testing information based on the performing of the first test case in the TCC; and providing the testing information to prediction models for model training.

Claims (53)

1 . A method for generating testing information, comprising:

identifying, by an automated event generation and data labeling (AEGDL) manager, a test case initiation event;

in response to the identification:

selecting a first test case of a plurality of test cases;

identifying a first test configuration cluster (TCC) of a plurality of TCCs based on the test case;

performing the first test case in the TCC;

generating testing information based on the performing of the first test case in the TCC; and

providing the testing information to prediction models for model training; and

initiating telemetry collection associated with the first test case to generate telemetry information;

confirming test configuration cluster configuration is in a required state based on the test case;

performing a first iteration of iterations of the first test case; and

resetting the first test configuration cluster.

2 . The method of claim 1 , wherein:

the first TCC comprises a first configuration of compute devices, network devices, and storage devices; and

a second TCC of the plurality of TCCs comprises a second configuration of compute devices, network devices, and storage devices.

3 . The method of claim 2 , wherein the first TCC further comprises at least one testing device that performs at least a portion of the first test case.

4 . The method of claim 1 , wherein:

the first test case comprises a first error scenario associated with the first TCC; and

a second test case of the plurality of test cases comprises a second error scenario associated with the first TCC.

5 . The method of claim 4 , wherein the testing information comprises:

telemetry information associated with the first TCC generated during the performance of the first test case; and

a label specifying the first error scenario.

6 . The method of claim 5 , wherein generating the testing information based on the performing of the first test case in the TCC comprises labeling the telemetry information with the label to enable prediction model training.

7 . The method of claim 1 , wherein performing the first test case in the TCC comprises: making a first determination that additional test iterations are required; and in response to the first determination:

performing a second iteration of iterations of the first test case.

8 . The method of claim 1 , wherein identifying the first TCC comprises comparing TCC configuration information associated with the first TCC with test case parameters associated with the first test case.

9 . The method of claim 8 , wherein the test case parameters further specify:

the iterations;

the configuration information; and

the required state.

10 . The method of claim 1 , wherein the AEGDL manager executes in an on-premises environment comprising the plurality of TCCs.

11 . The method of claim 1 , wherein the AEGDL manager executes in a cloud environment operatively connected to the plurality of TCCs.

12 . A system for generating testing information, comprising:

a processor;

memory storing computer executable instructions when executed by the processor to:

identifying, by an automated event generation and data labeling (AEGDL) manager, a test case initiation event;

in response to the identification:

selecting a first test case of a plurality of test cases;

identifying a first test configuration cluster (TCC) of a plurality of TCCs based on the test case;

performing the first test case in the TCC, wherein performing the first test case in the TCC comprises:

initiating telemetry collection associated with the first test case to generate telemetry information;

confirming test configuration cluster configuration is in a required state based on the test case;

performing a first iteration of iterations of the first test case; and resetting the first test configuration cluster; generating testing information based on the performing of the first test case in the TCC; and

providing the testing information to prediction models for model training.

13 . The system of claim 12 , wherein: the first TCC comprises a first configuration of devices; and a second TCC of the plurality of TCCs comprises a second configuration of devices.

14 . The system of claim 13 , wherein the first configuration of devices comprises compute devices, network devices, and storage devices.

15 . The system of claim 13 , wherein the first TCC further comprises at least one testing device that performs at least a portion of the first test case.

16 . The system of claim 12 , wherein: the first test case comprises a first error scenario associated with the first TCC; and a second test case of the plurality of test cases comprises a second error scenario associated with the first TCC.

17 . The system of claim 16 , wherein the testing information comprises:

telemetry information associated with the first TCC generated during the performance of the first test case; and

a label specifying the first error scenario.

18 . The system of claim 17 , wherein generating the testing information based on the performing of the first test case in the TCC comprises labeling the telemetry information with the label to enable prediction model training.

19 . The system of claim 12 , wherein performing the first test case in the TCC comprises: making a first determination that additional test iterations are required; and in response to the first determination: performing a second iteration of iterations of the first test case.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 26, 2024
From: SMITH, ERIK P.; HENRY, EDWARD; NATU, GAJANAN S; KASHYAPI, SUMANTA SK; SYDOW, DAVID CARL
To: DELL PRODUCTS L.P.
Reel/Frame 067242/0249 →
Continuity (1)
Related Publication 20250335337A1 · Oct 30, 2025
References Cited (11)
US 1572451A · Taylor · 1926 [cited by examiner]
US 8874477B2 · Hoffberg · 2014 [cited by examiner]
US 8930758B2 · Budnik · 2015 [cited by examiner]
US 10073763B1 · Raman · 2018 [cited by examiner]
US 10839415B2 · Fleming · 2020 [cited by examiner]
US 11416609B1 · Hencinski · 2022 [cited by examiner]
US 11640163B1 · Nguyen · 2023 [cited by examiner]
US 12271423B1 · Veron Vialard · 2025 [cited by examiner]
Cheng et al, “Test-Case Prioritization for Configuration Testing”, ACM, pp. 1-15 (Year: 2021). [cited by examiner]
Yoo et al, “Clustering Test Cases to Achieve Effective & Scalable Prioritisation Incorporating Expert Knowledge”, ACM, pp. 1-12 (Year: 2009). [cited by examiner]
Bilal et al, “Finding the Right Cloud Configuration for Analytics Clusters”, ACM, pp. 1-16 (Year: 2020). [cited by examiner]