IP Library › Granted Patent US 12688225

Granted Patent B1

US 12688225 · App. 18/297,541 · Granted Jul 21, 2026

Dialogue management system with hierarchical classification and progression

Inventors: Scott Douglas Sandland (Newport Beach, CA); Daniel Paris (San Diego, CA)

Assignee: Cyrano.ai, Inc.

G06F16/353 G06F16/3329 G06F16/3344 G06F16/90332 G06F40/35 G06N3/02 G06N3/08 G06N20/20 G10L15/1822 G10L15/183 G10L15/19 G10L15/22

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 12688225
App. No.: 18/297,541
Granted: Jul 21, 2026
Kind: B1

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

A dialogue management system applies hierarchical classifiers and other natural language processing to dialogue input, and determines whether performance of an action is likely to occur. The dialogue management system may process dialogue input to assess a dialogue participant's current position in various hierarchies or other classification schemes associated with performance of a desired action. The system may then present results of the assessment to another dialogue participant or provide the results to another system. In some embodiments, the dialogue management system may automatically generate responses or questions designed to engage a dialogue participant and cause the participant to progress through the levels of a hierarchy toward performance of a desired action.

Claims (56)

1 . A computer-implemented method comprising:

under control of a computing system comprising one or more computing devices configured to execute specific instructions,

receiving text corresponding to one or more inputs made by a user; and

processing at least a portion of the text in an action hierarchy classifier,

wherein the action hierarchy classifier generates a first plurality of scores,

wherein individual scores of the first plurality of scores correspond to individual levels in an action hierarchy,

wherein individual levels in the action hierarchy correspond to individual phases preceding performance of an action,

wherein the first plurality of scores are generated using a model that maps individual words of the text to individual levels in the action hierarchy;

processing at least a portion of the text in an exchange classifier,

wherein the exchange classifier generates a second plurality of scores, and

wherein individual scores of the second plurality of scores correspond to individual resources of a plurality of resources expected to be exchanged by the user preceding performance of the action;

generating dialogue output based at least partly on the first plurality of scores and the second plurality of scores; and

presenting the dialogue output.

2 . The computer-implemented method of claim 1 , wherein generating the dialogue output comprises using a template and a customization to the template, wherein the customization comprises the text associated with at least one of a particular level of the action hierarchy or a particular resource expected to be exchanged.

3 . The computer-implemented method of claim 2 , further comprising identifying the template based at least partly on a likelihood that processing text, corresponding to a subsequent input of the user, using the action hierarchy classifier will produce a result corresponding to a progression of the user to a higher level of the action hierarchy.

4 . The computer-implemented method of claim 2 , further comprising identifying the template based at least partly on a likelihood that processing text, corresponding to a subsequent input of the user, using the action hierarchy classifier will produce a result corresponding to a satisfaction by the user of a lower level of the action hierarchy.

5 . The computer-implemented method of claim 2 , further comprising identifying the template based at least partly on a likelihood that processing text, corresponding to a subsequent input of the user, using the exchange classifier will produce a result corresponding to a progression of the user to a different resource of the plurality of resources.

6 . The computer-implemented method of claim 1 , wherein presenting the dialogue output comprises presenting the dialogue output to a second user different from the user.

7 . The computer-implemented method of claim 6 , wherein presenting the dialogue output comprises presenting at least one of: profile information about the user, or classification results associated with the user.

8 . A system comprising:

computer-readable memory storing executable instructions; and

one or more processors in communication with the computer-readable memory and programmed by the executable instructions to at least:

receive text corresponding to one or more inputs made by a user; and

process at least a portion of the text in an action hierarchy classifier,

wherein the action hierarchy classifier generates a first plurality of scores,

wherein individual scores of the first plurality of scores correspond to individual levels in an action hierarchy,

wherein individual levels in the action hierarchy correspond to individual phases preceding performance of an action,

wherein the first plurality of scores are generated using a model that maps individual words of the text to individual levels in the action hierarchy;

processing at least a portion of the text in an exchange classifier,

wherein the exchange classifier generates a second plurality of scores, and

wherein individual scores of the second plurality of scores correspond to individual resources of a plurality of resources expected to be exchanged by the user preceding performance of the action;

generate dialogue output based at least partly on the first plurality of scores and the second plurality of scores; and

present the dialogue output.

9 . The system of claim 8 , wherein to generate the dialogue output, the one or more processors are further programmed by the executable instructions to use template and a customization to the template, wherein the customization comprises the text associated with at least one of a particular level of the action hierarchy or a particular resource expected to be exchanged.

10 . The system of claim 9 , wherein the one or more processors are further programmed by the executable instructions to identify the template based at least partly on a likelihood that processing text, corresponding to a subsequent input of the user, using the action hierarchy classifier will produce a result corresponding to a progression of the user to a higher level of the action hierarchy.

11 . The system of claim 9 , wherein the one or more processors are further programmed by the executable instructions to identify the template based at least partly on a likelihood that processing text, corresponding to a subsequent input of the user, using the action hierarchy classifier will produce a result corresponding to a satisfaction by the user of a lower level of the action hierarchy.

12 . The system of claim 9 , wherein the one or more processors are further programmed by the executable instructions to identify the template based at least partly on a likelihood that processing text, corresponding to a subsequent input of the user, using the exchange classifier will produce a result corresponding to a progression of the user to a different resource of the plurality of resources.

13 . The system of claim 8 , wherein the dialogue output is presented to a second user different from the user.

14 . The system of claim 8 , wherein the dialogue output comprises at least one of: profile information about the user, or classification results associated with the user.

15 . A non-transitory computer storage medium storing executable code, wherein the executable code configures a computing system to perform a process comprising: