IP Library Granted Patent US 12694061
Granted Patent B2
US 12694061 · App. 18/312,387 · Granted Jul 28, 2026

Computer-implemented methods, systems comprising computer-readable media, and electronic devices for narrative representation of a network computing environment

Inventors: John N. Laliberte (Oakton, VA); Andrew Davis (Doylestown, PA)
Assignee: Clear Vector, Inc.
G06F16/9024G06F3/0481G06F3/04842G06F9/54G06F16/258G06F16/285G06F16/288G06F16/3344G06F40/134G06N20/00H04L41/0813H04L43/045H04L63/08H04L63/0884H04L63/101H04L63/102H04L63/126H04L63/1408H04L63/1425H04L63/168
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 12694061
App. No.
18/312,387
Granted
Jul 28, 2026
Kind
B2
Abstract

A computer-implemented method for feedback-driven narrative-structure representation of a network computing environment. The method may include: monitoring the network computing environment; obtaining, via the monitoring, data relating to an action performed in the network computing environment; generating an initial natural language narrative describing the action; exposing or providing a representation of the initial natural language narrative to an individual user; receiving input from the individual user in response to the initial natural language narrative; based at least in part on the input, generating a revised natural language narrative relating to the action; and exposing or providing a representation of the revised natural language narrative to the individual user.

Claims (44)

1 . Non-transitory computer-readable storage media having computer-executable instructions stored thereon for feedback-driven narrative-structured representation of a network computing environment, wherein when executed by at least one processor the computer-executable instructions cause the at least one processor to:

monitor the network computing environment;

obtain, via the monitoring, data relating to an action performed by a first entity on a second entity in the network computing environment, the action including one or more of: a creation operation, a deletion operation, a read operation, a write operation, a backup operation, a transmission, a login attempt, execution of a computer-readable instruction, creation of an entity in the network computing environment, removal of an entity from the network computing environment, application of a restriction to an entity in the network computing environment, or application of a permission to an entity in the network computing environment;

generate an initial natural language narrative describing the action;

expose or provide a representation of the initial natural language narrative to an individual user;

receive input from the individual user in response to the initial natural language narrative;

based at least in part on the input, generate a revised natural language narrative relating to the action; and

expose or provide a representation of the revised natural language narrative to the individual user.

2 . The non-transitory computer-readable storage media of claim 1 , wherein generating the revised natural language narrative includes-

generating a notification based at least in part on the input, the notification prompting a supervisory or trusted user to select from a plurality of options,

receiving a selection from the supervisory or trusted user from among the plurality of options,

the revised natural language narrative being generated based at least in part on the selection from the supervisory or trusted user.

3 . The non-transitory computer-readable storage media of claim 2 , wherein the notification includes an explanatory natural language narrative describing or including all or part of the initial natural language narrative and the input from the individual user.

4 . The non-transitory computer-readable storage media of claim 2 , wherein the plurality of options includes one or more of the following: (i) attach a new or different enabled action program to the revised natural language narrative; (ii) generate the revised natural language narrative based on a different preference set than an initial preference set used to generate the initial natural language narrative; (iii) generate the revised natural language narrative based on an explanatory language processing rule configured to include one or more facts in the revised natural language narrative regarding criteria met by the action causing the action to be categorized as an event of interest; (iv) generate the revised natural language narrative by expanding or abstracting a fact type represented in the initial natural language narrative; and (v) generate the revised natural language narrative by changing an identity-, time- or entity-slice of a graph database model on which the initial natural language narrative was based.

5 . The non-transitory computer-readable storage media of claim 1 , wherein generating the revised natural language narrative includes performing one or more of the following based on the input: (i) attaching a new or different enabled action program to the revised natural language narrative; (ii) implementing a different preference set than an initial preference set used to generate the initial natural language narrative; (iii) implementing an explanatory language processing rule configured to include one or more facts in the revised natural language narrative regarding criteria met by the action causing the action to be categorized as an event of interest; (iv) expanding or abstracting a fact type represented in the initial natural language narrative; and (v) changing an identity-, time- or entity-slice of a graph database model on which the initial natural language narrative was based.

6 . The non-transitory computer-readable storage media of claim 1 , wherein-

the input from the individual user includes selecting a toggle link for navigating up or down abstraction levels.

7 . The non-transitory computer-readable storage media of claim 1 , wherein-

the input from the individual user includes activating an enabled action program link.

8 . The non-transitory computer-readable storage media of claim 1 , wherein generating the initial natural language narrative includes extracting at least some of the data relating to the action from a graph database model representing the network computing environment.

9 . The non-transitory computer-readable storage media of claim 8 , wherein generating the revised natural language narrative includes taking the initial natural language narrative as input to a natural language processing program.

10 . The non-transitory computer-readable storage media of claim 8 , wherein generating the initial natural language narrative includes executing an analyzer, the analyzer being configured to analyze the action and, based on the analysis, extract additional data from the network computing environment and add the additional data to the graph database model.

11 . A computer-implemented method for feedback-driven narrative-structured representation of a network computing environment comprising, via one or more transceivers and/or processors:

monitoring the network computing environment;

obtaining, via the monitoring, data relating to an action performed by a first entity on a second entity in the network computing environment;

generating an initial natural language narrative describing the action, the action including one or more of: a creation operation, a deletion operation, a read operation, a write operation, a backup operation, a transmission, a login attempt, execution of a computer-readable instruction, creation of an entity in the network computing environment, removal of an entity from the network computing environment, application of a restriction to an entity in the network computing environment, or application of a permission to an entity in the network computing environment;

exposing or providing a representation of the initial natural language narrative to an individual user;

receiving input from the individual user in response to the initial natural language narrative;

based at least in part on the input, generating a revised natural language narrative relating to the action; and

exposing or providing a representation of the revised natural language narrative to the individual user.

12 . The computer-implemented method of claim 11 , wherein generating the revised natural language narrative includes-

generating a notification based at least in part on the input, the notification prompting a supervisory or trusted user to select from a plurality of options,

receiving a selection from the supervisory or trusted user from among the plurality of options,

the revised natural language narrative being generated based at least in part on the selection from the supervisory or trusted user.

13 . The computer-implemented method of claim 12 , wherein the notification includes an explanatory natural language narrative describing or including all or part of the initial natural language narrative and the input from the individual user.

14 . The computer-implemented method of claim 12 , wherein the plurality of options includes one or more of the following: (i) attach a new or different enabled action program to the revised natural language narrative; (ii) generate the revised natural language narrative based on a different preference set than an initial preference set used to generate the initial natural language narrative; (iii) generate the revised natural language narrative based on an explanatory language processing rule configured to include one or more facts in the revised natural language narrative regarding criteria met by the action causing the action to be categorized as an event of interest; (iv) generate the revised natural language narrative by expanding or abstracting a fact type represented in the initial natural language narrative; and (v) generate the revised natural language narrative by changing an identity-, time- or entity-slice of a graph database model on which the initial natural language narrative was based.

15 . The computer-implemented method of claim 11 , wherein generating the revised natural language narrative includes performing one or more of the following based on the input: (i) attaching a new or different enabled action program to the revised natural language narrative; (ii) implementing a different preference set than an initial preference set used to generate the initial natural language narrative; (iii) implementing an explanatory language processing rule configured to include one or more facts in the revised natural language narrative regarding criteria met by the action causing the action to be categorized as an event of interest; (iv) expanding or abstracting a fact type represented in the initial natural language narrative; and (v) changing an identity-, time- or entity-slice of a graph database model on which the initial natural language narrative was based.

16 . The computer-implemented method of claim 11 , wherein-

the input from the individual user includes selecting a toggle link for navigating up or down abstraction levels.

17 . The computer-implemented method of claim 11 , wherein-

the input from the individual user includes activating an enabled action program link.

18 . The computer-implemented method of claim 11 , wherein generating the initial natural language narrative includes extracting at least some of the data relating to the action from a graph database model representing the network computing environment.

19 . The computer-implemented method of claim 18 , wherein generating the revised natural language narrative includes taking the initial natural language narrative as input to a natural language processing program.

20 . The computer-implemented method of claim 18 , wherein generating the initial natural language narrative includes executing an analyzer, the analyzer being configured to analyze the action and, based on the analysis, extract additional data from the network computing environment and add the additional data to the graph database model.