IP Library Granted Patent US 10,050,868
Granted Patent B2
US 10,050,868 · App. 14/807,782 · Granted Aug 14, 2018

Multimodal help agent for network administrator

Inventors: Phillip A. Porras (Cupertino, CA); Jeffrey Klaben (San Jose, CA); Patrick D. Lincoln (Woodside, CA); Nicholas Chapin (Mountain View, CA)
Assignee: SRI International
H04L45/22G06F3/0484H04L41/12H04L41/14H04L41/22H04L63/1416H04L63/1491G06F8/34G06F2203/0381
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 10,050,868
App. No.
14/807,782
Filed
Jul 23, 2015
Granted
Aug 14, 2018
Kind
B2
Art Unit
2498
USPC
726/1
Abstract

Network management technology as disclosed herein generates and dynamically updates an intuitive, interactive visualization of a computer network in live operation. The network management technology interprets human user interactions, such as gestures, conversational natural language dialog, and combinations of gestures and natural language dialog, as network directives. The technology can implement the network directives to, for example, facilitate analysis of network activity or to respond to network security events.

Claims (28)

1. A system comprising, embodied in one or more non-transitory machine accessible storage media, instructions configured to cause one or more computing devices to:

generate an interactive visualization of a computer network, the interactive visualization comprising a plurality of graphical elements arranged to depict the operation of the network;

receive unstructured conversational spoken natural language input in relation to at least one of the graphical elements of the interactive visualization;

interpret a combination of inputs comprising at least non-verbal data relating to the interactive visualization and the unstructured conversational spoken natural language input as a structured network directive relating to one or more components of the network; and

convert the structured network directive to a set of instructions executable by one or more devices of the network.

2. The system of claim 1 , comprising instructions configured to identify a network event on the network at least in part by algorithmically correlating network activity data indicative of data flows on the network with one or more of: network infection data generated by one or more network analytics systems, network role data, network topology data, and network policy data, and interpret the combination of inputs comprising at least the non-speech input and the natural language input as a network security directive relating to the identified network event.

3. The system of claim 2 , comprising instructions configured to interpret the combination of inputs as a command relating to one or more nodes and/or data flows involved in the network event.

4. The system of claim 2 , comprising instructions configured to interpret the combination of inputs as a query relating to the identified network event.

5. The system of claim 2 , comprising instructions configured to display a view of the interactive visualization of the network and manipulate the view of the visualization in response to the combination of inputs comprising at least the non-speech input and the conversational natural language input.

6. The system of claim 2 , comprising instructions configured to interpret the combination of inputs comprising at least the non-speech input and the conversational natural language input as a command to: redirect one or more data flows on the network, quarantine one or more nodes of the network, divert one or more network flows away from a node, divert one or more network flows to a node, or reconfigure a switching device on the computer network.

7. The system of claim 1 , comprising instructions configured to use a current view of the interactive visualization to interpret the conversational natural language input.

8. The system of claim 1 , comprising instructions configured to use a model to interpret the unstructured conversational natural language input.

9. The system of claim 1 , comprising instructions configured to use a model to interpret the non-verbal data.

10. The system of claim 1 , wherein the interactive visualization comprises a plurality of different icon-like graphical elements representing different types of devices on the network.

11. The system of claim 1 , wherein the interactive visualization comprises a plurality of different graphical elements representing different types of network threats on the network.

12. The system of claim 1 , wherein the interactive visualization comprises an animated representation of a network flow.

13. The system of claim 1 , wherein the interactive visualization comprises an animated representation of a direction of a network flow.

14. The system of claim 1 , wherein the interactive visualization comprises an animated representation of a duration of a network connection.

15. The system of claim 1 , wherein the non-verbal data comprises gaze-based interaction data.

16. The system of claim 1 , wherein the non-verbal data comprises touch-based interaction data.

17. The system of claim 1 , wherein the non-verbal data comprises motion-based interaction data.

18. The system of claim 1 , wherein the non-verbal data comprises gesture-based interaction data.

19. The system of claim 1 , comprising instructions configured to manipulate a three-dimensional view of the interactive visualization in response to the network directive.

20. A method, comprising:

generating an interactive visualization of a computer network, the interactive visualization comprising a plurality of graphical elements arranged to depict the operation of the network;

receiving unstructured conversational spoken natural language input in relation to at least one of the graphical elements of the interactive visualization;

interpreting a combination of inputs comprising at least non-verbal data relating to the interactive visualization and the unstructured conversational spoken natural language input as a structured network directive relating to one or more components of the network;

converting the structured network directive to a set of instructions executable by one or more devices of the network, wherein the method is performed by one or more computing devices.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 17, 2016
From: PORRAS, PHILLIP A.; KLAHEN, JEFFREY; LINCOLN, PATRICK D.; CHAPIN, NICHOLAS
To: SRI INTERNATIONAL
Reel/Frame 037749/0226 →
Continuity (3)
Provisional Application 62108175 · Jan 27, 2015
Provisional Application 62104517 · Jan 16, 2015
Related Publication 20160219078A1 · Jul 28, 2016
Cited By (2)
US 12,388,719 US 12,683,876