IP Library Granted Patent US 11,973,784
Granted Patent B1
US 11,973,784 · App. 18/154,684 · Granted Apr 30, 2024

Natural language interface for an anomaly detection framework

Inventors: Úlfar Erlingsson (Palo Alto, CA); Jay Parikh (Redwood City, CA); Yijou Chen (Cupertino, CA)
Assignee: LACEWORK, INC.
H04L63/1425G06F9/455G06F9/545G06F16/2456G06F16/9024G06F16/9038G06F16/9535G06F16/9537G06F21/57H04L43/045H04L43/06H04L63/10H04L67/306H04L67/535
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 11,973,784
App. No.
18/154,684
Granted
Apr 30, 2024
Kind
B1
Abstract

A natural language interface for an anomaly detection framework, including: receiving a natural language input associated with a cloud deployment; generating a query corresponding to the natural language input by disambiguating at least a portion of the natural language input based on data describing activity associated with an anomaly detection framework monitoring the cloud deployment; and providing, based on a response to the query, a response to the natural language input.

Claims (46)

1. A method of providing a natural language interface for an anomaly detection framework, the method comprising:

receiving a natural language input associated with a cloud deployment that is being monitored by an anomaly detection framework;

generating a query corresponding to the natural language input by disambiguating at least a portion of the natural language input based on data describing activity associated with the cloud deployment, wherein the data describing activity associated with the cloud deployment comprises data describing a state of one or more assets of the cloud deployment; and

providing, based on a response to the query, a response to the natural language input.

2. The method of claim 1 , wherein generating a query corresponding to the natural language input further comprises disambiguating at least a portion of the natural language input based on data describing activity associated with the anomaly detection framework.

3. The method of claim 1 , wherein the cloud deployment is associated with a customer and wherein disambiguating the natural language input is further based on data associated with another cloud deployment of another customer.

4. The method of claim 1 , wherein the data describing activity associated with the cloud deployment comprises one or more queries provided by a domain expert.

5. The method of claim 1 , wherein the data describing activity associated with the cloud deployment comprises one or more user interactions with a user interface of the anomaly detection framework.

6. The method of claim 1 , wherein the data describing activity associated with the cloud deployment comprises data describing one or more anomalies identified by the anomaly detection framework.

7. The method of claim 1 , wherein the data describing activity associated with the cloud deployment comprises one or more user-provided clarifications corresponding to one or more previously received natural language inputs.

8. The method of claim 1 , further comprising:

providing a request for clarification associated with the natural language input; and

wherein disambiguating the natural language input is further based on a response to the request for clarification.

9. The method of claim 1 , further comprising storing data associating the natural language input with one or more criteria for generating the query.

10. The method of claim 1 , further comprising:

providing a request for confirmation to use, for generating the query, an alternative to the natural language input; and

in response to receiving a confirmation:

generating the query based on the alternative instead of the natural language input; and

providing, instead of the response to the natural language input, based on the query, a response to the alternative.

11. The method of claim 1 , further comprising:

training at least one model based on data describing historical activity associated with the anomaly detection framework; and

wherein generating the query comprises providing, as input to the at least one model, the natural language input.

12. The method of claim 11 , wherein training the model is further based on data describing one or more previously received natural language inputs and one or more corresponding generated queries.

13. A computer program product for a natural language interface for an anomaly detection framework, the computer program product disposed on a non-transitory computer readable medium, the computer program product including computer program instructions configurable to carry out the steps of:

receiving a natural language input associated with a cloud deployment;

generating a query corresponding to the natural language input by disambiguating at least a portion of the natural language input based on data describing activity associated with an anomaly detection framework monitoring the cloud deployment, wherein the data describing activity associated with the cloud deployment comprises data describing one or more anomalies identified by the anomaly detection framework; and

providing, based on a response to the query, a response to the natural language input.

14. The computer program product of claim 13 , wherein the cloud deployment is associated with a customer and wherein disambiguating the at least a portion of the natural language input is further based on data associated with another cloud deployment of another customer.

15. The computer program product of claim 13 , wherein the data describing activity associated with the anomaly detection framework monitoring the cloud deployment comprises one or more queries provided by a domain expert.

16. The computer program product of claim 13 , wherein the data describing activity associated with the anomaly detection framework monitoring the cloud deployment comprises one or more user interactions with a user interface for monitoring the cloud deployment.

17. The computer program product of claim 13 , wherein the data describing activity associated with the anomaly detection framework monitoring the cloud deployment comprises data describing a state of one or more assets of the cloud deployment.

18. The computer program product of claim 13 , wherein the data describing activity associated with the anomaly detection framework monitoring the cloud deployment comprises one or more user-provided clarifications corresponding to one or more previously received natural language inputs.

19. The computer program product of claim 13 , wherein the steps further comprise:

providing a request for clarification associated with the natural language input; and

wherein disambiguating the at least a portion of the natural language input is further based on a response to the request for clarification.

20. The computer program product of claim 13 , wherein the steps further comprise storing data associating the natural language input with one or more criteria for generating the query.

21. The computer program product of claim 13 , wherein the natural language input is received via a command line interface.

22. The computer program product of claim 13 , wherein the steps further comprise:

providing a request for confirmation to use an alternative to the natural language input instead of the natural language input for generating the query; and

in response to receiving a confirmation:

generating the query based on the alternative instead of the natural language input; and

provide, instead of the response to the natural language input, based on the query, a response to the alternative.

23. The computer program product of claim 13 , wherein the steps further comprise:

training at least one model based on data describing historical activity associated with the anomaly detection framework; and

wherein generating the query comprises providing, as input to the at least one model, the natural language input.

24. The computer program product of claim 23 , wherein training the at least one model is further based on data describing one or more previously received natural language inputs and one or more corresponding generated queries.

Assignments (2)
MERGER Recorded Oct 7, 2024
From: LACEWORK, INC.
To: FORTINET, INC.
Reel/Frame 069113/0745 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 13, 2023
From: ERLINGSSON, ÚLFAR; PARIKH, JAY; CHEN, YIJOU
To: LACEWORK, INC.
Reel/Frame 062376/0316 →