IP Library Granted Patent US 12,282,740
Granted Patent B2
US 12,282,740 · App. 17/978,103 · Granted Apr 22, 2025

Distributed computing architecture for intent matching

Inventors: Connor Isaac Brinton (Holly Springs, NC); Victor The Vong (Dublin, CA)
Assignee: Zoom Communications, Inc.
G06F40/30G06F40/216G06F40/295H04M3/5234
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 12,282,740
App. No.
17/978,103
Granted
Apr 22, 2025
Kind
B2
Abstract

A server transmits a query received from a user device to multiple deployment engines, each deployment engine being associated with an intent. The server receives, from each of a subset of the multiple deployment engines, a score representing a likelihood that the query matches to the associated intent. The server transmits, to the user device, a message comprising representations of intents for which the score is within a predefined range.

Claims (34)

1. A method, comprising:

transmitting a query received from a user device to multiple deployment engines, each deployment engine being associated with an intent and the multiple deployment engines being controlled by a controller engine that accesses a data repository of intents and generates a deployment engine for at least one intent from the data repository;

receiving, from each of a subset of the multiple deployment engines, a score representing a likelihood that the query matches to the intent; and

transmitting, to the user device, a message comprising representations of intents for which the score is within a predefined range.

2. The method of claim 1 , the message being a single message aggregating the intents for which the score is within the predefined range.

3. The method of claim 1 , the score being within the predefined range comprising the score exceeding a predefined threshold value.

4. The method of claim 1 , the multiple deployment engines comprising global deployment engines associated with global intents and entity-specific deployment engines associated with specific intents for an entity.

5. The method of claim 1 , comprising:

receiving the query at a contact center server and from the user device.

6. The method of claim 1 , further comprising:

assigning, by the controller engine, multiple computing nodes to the multiple deployment engines based on computations being processed by the multiple deployment engines, each computing node representing a set of computational resources.

7. The method of claim 1 , the message comprising representations of fewer than a preset threshold number of intents.

8. A non-transitory computer readable medium storing instructions operable to cause one or more processors to perform operations comprising:

transmitting a query received from a user device to multiple deployment engines, each deployment engine being associated with an intent and the multiple deployment engines being controlled by a controller engine that accesses a data repository of intents and generates a deployment engine for at least one intent from the data repository;

receiving, from each of a subset of the multiple deployment engines, a score representing a likelihood that the query matches to the intent; and

transmitting, to the user device, a message comprising representations of intents for which the score is within a predefined range.

9. The non-transitory computer readable medium of claim 8 , the message being a single message aggregating the representations of the intents.

10. The non-transitory computer readable medium of claim 8 , the score being within the predefined range comprising the score being below a predefined threshold value.

11. The non-transitory computer readable medium of claim 8 , the multiple deployment engines comprising at least one global deployment engine associated with global intents and at least one entity-specific deployment engine associated with specific intents for an entity.

12. The non-transitory computer readable medium of claim 8 , the operations further comprising:

receiving the query at a contact center server.

13. The non-transitory computer readable medium of claim 8 , wherein the controller engine assigns multiple computing nodes to the multiple deployment engines, each computing node representing a set of computational resources, the controller engine assigning at least one computing node to at least one deployment engine based on computations being processed by the at least one deployment engine.

14. The non-transitory computer readable medium of claim 8 , the message comprising representations of at most n intents, n being a preset positive integer.

15. An apparatus comprising:

a memory; and

a processor configured to execute instructions stored in the memory to:

transmit a query received from a user device to multiple deployment engines, each deployment engine being associated with an intent and the multiple deployment engines being controlled by a controller engine that accesses a data repository of intents and generates a deployment engine for at least one intent from the data repository;

receive, from each of a subset of the multiple deployment engines, a score representing a likelihood that the query matches to the intent; and

transmit, to the user device, a message comprising representations of intents for which the score is within a predefined range.

16. The apparatus of claim 15 , the message being a single message aggregating the representations of the intents for which the score is within the predefined range.

17. The apparatus of claim 15 , the multiple deployment engines comprising at least one of a global deployment engine associated with a global intent or an entity-specific deployment engine associated with a specific intent for an entity.

18. The apparatus of claim 15 , the score being within the predefined range comprising the score exceeding a predefined threshold value.

19. The apparatus of claim 15 , the query being received at a contact center server and from the user device.

20. The apparatus of claim 15 , the message comprising representations of fewer than a preset threshold number of intents.

Assignments (2)
CHANGE OF NAME Recorded Jan 7, 2025
From: ZOOM VIDEO COMMUNICATIONS, INC.
To: ZOOM COMMUNICATIONS, INC.
Reel/Frame 069839/0593 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 2, 2022
From: BRINTON, CONNOR ISAAC; VONG, VICTOR THE
To: ZOOM VIDEO COMMUNICATIONS, INC.
Reel/Frame 061630/0060 →
Continuity (1)
Related Publication 20240143930A1 · May 2, 2024
References Cited (16)
US 10791158B2 · Buchanan · 2020 [cited by examiner]
US 11061700B2 · Jernigan et al. · 2021 [cited by applicant]
US 20130332438A1 · Li · 2013 [cited by examiner]
US 20180157721A1 · Khaitan · 2018 [cited by examiner]
US 20180365026A1 · Jernigan · 2018 [cited by examiner]
US 20190102078A1 · Bhatt · 2019 [cited by examiner]
US 20190108836A1 · Kato · 2019 [cited by examiner]
US 20210035572A1 · D'Amato · 2021 [cited by examiner]
US 20210083994A1 · Pan · 2021 [cited by examiner]
US 20210174783A1 · Wieman · 2021 [cited by examiner]
US 20230033887A1 · Luthra · 2023 [cited by examiner]
US 20230199118A1 · Koneru · 2023 [cited by examiner]
International Search Report and Written Opinion mailed on Dec. 15, 2023 in corresponding PCT Application No. PCT/US2023/034552. [cited by applicant]
Configure the Aggregation Layer, Kubernetes, https://kubernetes.io/docs/tasks/extend-kubernetes/configure-aggregation-layer/, Jul. 21, 2022, 6 pages. [cited by applicant]
Controllers, Kubernetes, https://kubernetes.io/docs/concepts/architecture/controller/, Jun. 14, 2021, 3 pages. [cited by applicant]
Kubernetes API Aggregation Layer, Kubernetes, https://kubernetes.io/docs/concepts/extend-kubernetes/api-extension/apiserver-aggregation/, Oct. 8, 2022, 1 page. [cited by applicant]