Granted Patent B2

US 12,518,092 · App. 17/502,384 · Granted Jan 6, 2026

Inventors: Jeffry Copps Robert Jose (Tamil Nadu, IN); Ankur Anil Aher (Maharashtra, IN); Reda Harb (Bellevue, WA)

Assignee: Adeia Guides Inc.

G06F40/226G06F3/04817G06F40/30G10L15/26

Abstract

Claims (94)

1 . A method for providing contextual based actions based on a natural language input, the method comprising:

receiving, at a media device, a natural language input;

determining, based at least in part on the natural language input, a first context of the natural language input;

determining, based at least in part on the first context, a first action associated with a first portion of the natural language input and a second action associated with a second portion of the natural language input;

calculating a first priority score of the first action and a second priority score of the second action, wherein the first priority score and the second priority score are calculated based on a vocal tone of the natural language input;

determining that the first action is of higher priority than the second action based on the first priority score being greater than the second priority score;

generating a first visual icon representing the first action;

generating a second visual icon representing the second action;

generating for display on the media device:

a waveform of the natural language input;

the first visual icon representing the first action adjacent to a first segment of the waveform corresponding to the first portion of the natural language input;

the second visual icon representing the second action adjacent to a second segment of the waveform corresponding to the second portion of the natural language input; and

a dynamic action button configured to carry out the first action;

receiving a selection of the second visual icon adjacent to the second segment of the waveform corresponding to the second portion of the natural language input; and

based on receiving the selection of the second visual icon adjacent to the second segment of the waveform corresponding to the second portion of the natural language input, updating the dynamic action button to perform the second action.

2 . The method of claim 1 , further comprising:

providing the user with survey information based on the first action and second action;

receiving survey feedback comprising an indication of user preference of the first action or second action;

associating the indication of user preference of the first action or second action with the first context; and

assigning a weighting to the first context.

3 . The method of claim 1 , further comprising:

providing the action with the lowest priority score to another media device.

4 . The method of claim 1 , further comprising:

providing a text string based on the natural language input, wherein the first context is determined based on the text string.

5 . The method of claim 4 , further comprising:

selecting a plurality of keywords from the text string; and

searching the media device for associated data based on the text string,

wherein the associated data is used in determining the first context of the natural language input.

6 . A media device, comprising a control module, a transceiver module and a network module, configured to:

receive, at a media device, a natural language input;

determine, based at least in part on the natural language input, a first context of the natural language input;

determine, based at least in part on the first context, a first action associated with a first portion of the natural language input and a second action associated with a second portion of the natural language input;

calculate a first priority score of the first action and a second priority score of the second action, wherein the first priority score and the second priority score are calculated based on a vocal tone of the natural language input;

determine that the first action is of higher priority than the second action based on the first priority score being greater than the second priority score;

generate a first visual icon representing the first action;

generate a second visual icon representing the second action

generate for display on the media device:

a waveform of the natural language input;

the first visual icon representing the first action adjacent to a first segment of the waveform corresponding to the first portion of the natural language input;

the second visual icon representing the second action adjacent to a second segment of the waveform corresponding to the second portion of the natural language input; and

a dynamic action button configured to carry out the first action;

receive a selection of the second visual icon adjacent to the second segment of the waveform corresponding to the second portion of the natural language input; and

based on receiving the selection of the second visual icon adjacent to the second segment of the waveform corresponding to the second portion of the natural language input, update the dynamic action button to perform the second action.

7 . The media device of claim 6 , further configured to:

provide the user with survey information based on the first action and second action;

receive survey feedback comprising an indication of user preference of the first action or second action;

associate the indication of user preference of the first action or second action with the first context; and

assign a weighting to the first context.

8 . The media device of claim 6 , further configured to:

provide the action with the lowest priority score to another media device.

9 . The media device of claim 6 , further configured to:

provide a text string based on the natural language input, wherein the first context is determined based on the text string.

10 . The media device of claim 9 , further configured to:

select a plurality of keywords from the text string; and

search the media device for associated data based on the text string,

wherein the associated data is used in determining the first context of the natural language input.

11 . A system for providing contextual based actions based on a natural language input, the system comprising:

means for receiving, at a media device, a natural language input;

means for determining, based at least in part on the natural language input, a first context of the natural language input;

means for determining, based at least in part on the first context, a first action associated with a first portion of the natural language input and a second action associated with a second portion of the natural language input;

means for calculating a first priority score of the first action and a second priority score of the second action, wherein the first priority score and the second priority score are calculated based on a vocal tone of the natural language input;

means for determining that the first action is of higher priority than the second action based on the first priority score being greater than the second priority score;

means for generating a first visual icon representing the first action;

means for generating a second visual icon representing the second action;

means for generating for display on the media device:

a waveform of the natural language input;

the first visual icon representing the first action adjacent to a first segment of the waveform corresponding to the first portion of the natural language input;

the second visual icon representing the second action adjacent to a second segment of the waveform corresponding to the second portion of the natural language input; and

a dynamic action button configured to carry out the first action;

means for receiving a selection of the second visual icon adjacent to the second segment of the waveform corresponding to the second portion of the natural language input; and

based on receiving the selection of the second visual icon adjacent to the second segment of the waveform corresponding to the second portion of the natural language input, means for updating the dynamic action button to perform the second action.

12 . The method of claim 1 , further comprising:

determining a level of urgency associated with the natural language input, wherein the level of urgency is determined based on the vocal tone of the natural language input.

13 . The method of claim 12 , further comprising:

retrieving metadata associated with a previously received natural language input, wherein the level of urgency is based on the retrieved metadata.

14 . The method of claim 1 , wherein the natural language input is a first natural language input, the method further comprising:

receiving a second natural language input;

determining, based on the second natural language input, a second context of the second natural language input;

determining, based on the second context, a third action and a fourth action; and

calculating, based on a keyword database that comprises a list of keywords known to indicate urgency, a third priority score of the third action and a fourth priority score of the fourth action.

15 . The method of claim 1 , further comprising:

storing the action with the lowest priority score in a storage, wherein the stored action can be accessed to be carried out at a later time.

16 . The media device of claim 6 , further configured to:

determine a level of urgency associated with the natural language input, wherein the level of urgency is determined based on the vocal tone of the natural language input.

17 . The media device of claim 16 , further configured to:

retrieve metadata associated with a previously received natural language input, wherein the level of urgency is based on the retrieved metadata.

18 . The method of claim 1 , wherein a first size of the first visual indicator is based the first priority score, and a second size of the second visual indicator is based on the second priority score.

19 . The method of claim 1 , wherein:

the second visual indicator is arranged directly on top of the second segment of the waveform corresponding to the second portion of the natural language input; and

the second visual indicator is arranged directly on top of the second segment of the waveform corresponding to the second portion of the natural language input.

20 . The method of claim 1 , wherein:

the dynamic action button, when configured to perform the first action, is displayed with a first appearance;

the dynamic action button, when configured to perform the second action, is displayed with a second appearance different from the first appearance; and

the dynamic action button is displayed in a same location on a display of the media device when configured to perform both the first action and the second action.

Assignments (3)

Continuity (1)

References Cited (11)

Cited By (1)

US 12,694,046