IP Library › Granted Patent US 12,430,375

Granted Patent B2

US 12,430,375 · App. 18/225,033 · Granted Sep 30, 2025

Method for adaptive conversation state management with filtering operators applied dynamically as part of a conversational interface

Inventors: Sashikumar Venkataraman (Andover, MA); Ahmed Nizam Mohaideen Pathurudeen (Kovilpatti, IN); K China Srinivasulu Reddy (Marathalli, IN); Mangesh Dattatray Pujari (Navi Mumbai, IN); Soumyadip Majumder (West Bengal, IN); Rakesh Barve (Bangalore, IN); Murali Aravamudan (Andover, MA)

Assignee: Adeia Guides Inc.

G06F16/3349 G06F16/24535 G06F16/907 G06F16/9535

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 12,430,375
App. No.: 18/225,033
Granted: Sep 30, 2025
Kind: B2

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

A system and method of processing a search request is provided. Identification of a desired content item is based on comparing a topic of the search request to previous user input. The method includes providing access to a set of content items with metadata that describes the corresponding content items and providing information about previous searches. The method further includes receiving a present input from the user and determining a relatedness measure between the information about the previous searches and an element of the present input. If the relatedness measure is high, the method also includes selecting a subset of content items based on comparing the present input and information about the previous searches with the metadata that describes the subset of content items. Otherwise, the method includes selecting a subset of content items based on comparing the present input with the metadata that describes the subset of content items.

Claims (99)

1. A computer-implemented method including a hardware processor, the method comprising:

receiving a first speech input via a user interface;

storing the first speech input in a conversation space data structure, wherein the conversation space data structure comprises spoken entities;

selecting a first set of content items based on the first speech input;

generating identifiers for output for the first set of content items;

receiving a second speech input via the user interface;

storing the second speech input in the conversation space data structure;

selecting a second set of content items by filtering the first set of content items based on the second speech input;

generating identifiers for output for the second set of content items;

receiving a third speech input via the user interface;

storing the third speech input in the conversation space data structure;

determining that the second speech input and the third speech input are mutually exclusive;

in response to determining that the second speech input and the third speech input are mutually exclusive:

removing the second speech input from the conversation space data structure;

selecting a third set of content items by filtering the first set of content items based on the third speech input; and

generating identifiers for output for the third set of content items.

2. The method of claim 1 , wherein the first speech input is received via the user interface as part of a conversation between a user and a system that displays the user interface;

wherein the second speech input is received via the user interface as part of the conversation between the user and the system that displays the user interface; and

wherein the third speech input is received via the user interface as part of the conversation between the user and the system that displays the user interface.

3. The method of claim 1 , wherein:

the determining that the second speech input and the third speech input are mutually exclusive comprises determining that filtering the second set of content items by the third speech input results in an empty set.

4. The method of claim 1 , wherein:

the determining that the second speech input and the third speech input are mutually exclusive comprises comparing the second speech input and the third speech input.

5. The method of claim 1 , further comprising:

generating for output a request to display the second speech input via the user interface; and

wherein the second speech input is received via the user interface in response to the request to display the second speech input.

6. The method of claim 1 , further comprising:

generating for output a request to display the third speech input via the user interface; and

wherein the third speech input is received via the user interface in response to the request to displays the third speech input.

7. The method of claim 1 , wherein the selecting the first set of content items is further based on user history.

8. The method of claim 1 , wherein the selecting of the second set of content items is further based on user history associated with the first set of content items.

9. The method of claim 1 , wherein the selecting the first set of content items is further based at least in part on a relationship graph that identifies relationships between a plurality of terms, wherein each content item of the first set of content items corresponds to a respective node of the relationship graph.

10. The method of claim 1 , wherein the selecting the second set of content items is further based at least in part on a relationship graph that identifies relationships between a plurality of terms, wherein each content item of the second set of content items corresponds to a respective node of the relationship graph.

11. A system including a hardware processing, the system comprising:

input/output circuitry configured to:

receive a first speech input via a user interface; and

control circuitry configured to:

store the first speech input in a conversation space data structure, wherein the conversation space data structure comprises spoken entities;

select a first set of content items based on the first speech input;

wherein the input/output circuitry is further configured to:

generate identifiers for output for the first set of content items; and

receive a second speech input via the user interface;

wherein the control circuitry is further configured to:

store the second speech input in the conversation space data structure;

select a second set of content items by filtering the first set of content items based on the second speech input;

wherein the input/output circuitry is further configured to:

generate identifiers for output for the second set of content items; and

receive a third speech input via the user interface;

wherein the control circuitry is further configured to:

store the third speech input in the conversation space data structure;

determine that the second speech input and the third speech input are mutually exclusive;

in response to determining that the second speech input and the third speech input are mutually exclusive:

remove the second speech input from the conversation space data structure; and

select a third set of content items by filtering the first set of content items based on the third speech input; and

wherein the input/output circuitry is further configured to:

generate identifiers for output for the third set of content items.

12. The system of claim 11 , wherein the input/output circuitry is further configured to:

receive the first speech input via the user interface as part of a conversation between a user and a system that displays the user interface;

receive the second speech input via the user interface as part of the conversation between the user and the system that displays the user interface; and

receive the third speech input via the user interface as part of the conversation between the user and the system that displays the user interface.

13. The system of claim 11 , wherein the control circuitry is further configured to determine that the second speech input and the third speech input are mutually exclusive by:

determining that filtering the second set of content items by the third speech input results in an empty set.

14. The system of claim 11 , wherein the control circuitry is further configured to determine that the second speech input and the third speech input are mutually exclusive by:

comparing the second speech input and the third speech input.

15. The system of claim 11 , wherein the input/output circuitry is further configured to:

generate for output a request to display the second speech input via the user interface; and

wherein the second speech input is received via the user interface in response to the request to display the second speech input.

16. The system of claim 11 , wherein the input/output circuitry is further configured to:

generate for output a request to display the third speech input via the user interface; and

wherein the third speech input is received via the user interface in response to the request to display the third speech input.

17. The system of claim 11 , wherein the control circuitry is further configured to select the first set of content items further based on user history.

18. The system of claim 11 , wherein the control circuitry is further configured to select the first set of content items further based on user history associated with the first set of content items.

19. A non-transitory computer readable medium comprising:

instructions that when executed by control circuitry cause input/output circuitry to:

receive a first speech input via a user interface;

instructions that when executed by the control circuitry cause the control circuitry to:

store the first speech input in a conversation space data structure, wherein the conversation space data structure comprises spoken entities;

select a first set of content items based on the first speech input;

further instructions that when executed by the control circuitry cause the input/output circuitry to:

generate identifiers for output for the first set of content items; and

receive a second speech input via the user interface;

further instructions that when executed by the control circuitry cause the control circuitry to: