IP Library Granted Patent US 11,392,447
Granted Patent B2
US 11,392,447 · App. 17/073,720 · Granted Jul 19, 2022

Fault clustering for remedial action analysis

Inventors: Ezra Spiro (New York, NY); Zachary Imholte (Cincinnati, OH)
Assignee: Palantir Technologies Inc.
G06F11/0793G06F3/04842G06F11/079G06F11/0769G06K9/6218
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 11,392,447
App. No.
17/073,720
Granted
Jul 19, 2022
Kind
B2
Abstract

Systems, methods, and non-transitory computer readable media are provided for facilitating improved analysis of remedial actions for faults. Fault information may be obtained. The fault information may characterize a fault of a device. The fault may be clustered into a fault type based on the fault information. A set of remedial actions taken for the fault type may be identified. A set of remedial effects of the set of remedial actions for the fault type may be determined. A timeline view of the fault type may be generated based on the set of remedial actions and the set of remedial effects. The timeline view may include a visual representation of effectiveness of the set of remedial actions. An interface, through which the timeline view of the fault type is accessible, may be provided.

Claims (55)

1. A system comprising:

one or more processors; and

a memory storing instructions that, when executed by the one or more processors, cause the system to perform:

obtaining fault information, the fault information characterizing a fault of a device;

clustering the fault into a fault type based on the fault information, the clustering comprising:

generating probabilities that the fault matches with respective fault types;

clustering the fault into a fault type having a highest probability; and

in response to the fault information not matching an existing fault type, generating a new fault type and clustering the fault into the new fault type;

identifying a set of remedial actions associated with the fault type;

determining a set of remedial effects of the set of remedial actions for the fault type, wherein the set of remedial effects indicate whether one or more faults of the fault type reoccurred at a specific duration of time following the set of remedial actions;

receiving a selection of a remedial action based on a remedial effect corresponding to the remedial action; and

automatically applying, by the one or more processors, the selected remedial action to resolve the fault of the device.

2. The system of claim 1 , wherein the instructions further cause the system to perform:

determining whether the fault is a chronic fault occurring in the device or a device type corresponding to the device based on a frequency of occurrence of the fault.

3. The system of claim 2 , wherein the instructions further cause the system to perform:

identifying a particular component of the device or the device type affected by the chronic fault.

4. The system of claim 1 , wherein the set of remedial effects includes:

an indication of whether the remedial actions provided a final fix or a temporary fix, determined based on whether one or more faults of the fault type reoccurred within a specific duration of time; and

a percentage of times that the remedial actions provided a final fix or a temporary fix.

5. The system of claim 1 , wherein the instructions further cause the system to perform:

presenting a video or audio media file relating to the fault.

6. The system of claim 5 , wherein the clustering the fault into the fault type having a highest probability is in response to the highest probability satisfying a threshold probability.

7. The system of claim 6 , wherein, in response to the highest probability not satisfying a threshold probability, the system determines that the fault information does not match an existing fault type.

8. A method implemented by a computing system including one or more processors and storage media storing machine-readable instructions, wherein the method is performed using the one or more processors, the method comprising:

obtaining fault information, the fault information characterizing a fault of a device;

clustering the fault into a fault type based on the fault information, the clustering comprising:

generating probabilities that the fault matches with respective fault types;

clustering the fault into a fault type having a highest probability; and

in response to the fault information not matching an existing fault type, generating a new fault type and clustering the fault into the new fault type;

identifying a set of remedial actions associated with the fault type;

determining a set of remedial effects of the set of remedial actions for the fault type, wherein the set of remedial effects indicate whether one or more faults of the fault type reoccurred at a specific duration of time following the set of remedial actions;

receiving a selection of a remedial action based on a remedial effect corresponding to the remedial action; and

automatically applying, by the one or more processors, the selected remedial action to resolve the fault of the device.

9. The method of claim 8 , further comprising:

determining whether the fault is a chronic fault occurring in the device or a device type corresponding to the device based on a frequency of occurrence of the fault.

10. The method of claim 9 , further comprising:

identifying a particular component of the device or the device type affected by the chronic fault.

11. The method of claim 8 , wherein the set of remedial effects includes:

an indication of whether the remedial actions provided a final fix or a temporary fix, determined based on whether one or more faults of the fault type reoccurred within a specific duration of time; and

a percentage of times that the remedial actions provided a final fix or a temporary fix.

12. The method of claim 8 , further comprising:

presenting a video or audio media file relating to the fault.

13. The method of claim 12 , wherein the clustering the fault into the fault type having a highest probability is in response to the highest probability satisfying a threshold probability.

14. The method of claim 13 , further comprising:

in response to the highest probability not satisfying a threshold probability, determining that the fault information does not match an existing fault type.

15. A non-transitory computer readable medium comprising instructions that, when executed, cause one or more processors to perform:

obtaining fault information, the fault information characterizing a fault of a device;

clustering the fault into a fault type based on the fault information, the clustering comprising:

generating probabilities that the fault matches with respective fault types;

clustering the fault into a fault type having a highest probability;

in response to the fault information not matching an existing fault type, generating a new fault type and clustering the fault into the new fault type;

identifying a set of remedial actions associated with the fault type; and

determining a set of remedial effects of the set of remedial actions for the fault type, wherein the set of remedial effects indicate whether one or more faults of the fault type reoccurred at a specific duration of time following the set of remedial actions;

receiving a selection of a remedial action based on a remedial effect corresponding to the remedial action; and

automatically applying, by the one or more processors, the selected remedial action to resolve the fault of the device.

Assignments (2)
SECURITY INTEREST Recorded Jul 3, 2022
From: PALANTIR TECHNOLOGIES INC.
To: WELLS FARGO BANK, N.A.
Reel/Frame 060572/0506 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 19, 2020
From: SPIRO, EZRA; IMHOLTE, ZACHARY
To: PALANTIR TECHNOLOGIES INC.
Reel/Frame 054099/0738 →
Continuity (2)
Continuation 16115081 · Aug 28, 2018
Related Publication 20210034454A1 · Feb 4, 2021
Cited By (1)
US 12,536,597