Granted Patent B2

US 12,494,196 · App. 18/325,600 · Granted Dec 9, 2025

Inventors: Indermeet Singh Gandhi (San Jose, CA); Jerome Henry (Pittsboro, NC)

Assignee: CISCO TECHNOLOGY, INC.

G10L15/197G10L15/04G10L15/22

Abstract

Claims (79)

1 . A computer-implemented method comprising:

capturing audio from an online meeting;

while the online meeting is occurring, identifying words being spoken by a participant during the online meeting from the audio;

determining one or more suggested next words or phrases to be spoken by the participant based on the words being spoken by the participant and one or more scores associated with previous words spoken by the participant, wherein the previous words and the one or more scores associated with the previous words are stored in a profile associated with the participant;

generating, for display on a user device being used by the participant to participate in the online meeting, the words being spoken by the participant and the one or more suggested next words or phrases;

identifying a next word or phrase spoken by the participant;

updating a score associated with the next word or phrase when the next word or phrase is a suggested next word or phrase of the one or more suggested next words or phrases; and

storing an indication of the next word or phrase and the score associated with the next word or phrase in the profile associated with the participant.

2 . The computer-implemented method of claim 1 , wherein determining the one or more suggested next words or phrases to be spoken comprises:

dividing the words being spoken by the participant into tokens;

analyzing the tokens to predict next tokens; and

determining the one or more suggested next words or phrases based on the next tokens.

3 . The computer-implemented method of claim 1 , wherein generating for display the one or more suggested next words or phrases comprises:

determining a probability score for each predicted next word or phrase of the one or more suggested next words or phrases; and

generating for display a suggested next word or phrase with a highest probability score first.

4 . The computer-implemented method of claim 3 , further comprising:

generating for display the one or more suggested next words or phrases in different colors based on the probability score for each suggested next word or phrase.

5 . The computer-implemented method of claim 1 , wherein determining the one or more suggested next words or phrases comprises:

identifying information from content associated with the online meeting; and

determining the one or more suggested next words or phrases based on the information.

6 . The computer-implemented method of claim 1 , wherein determining the one or more suggested next words or phrases comprises:

identifying an enterprise or organization associated with the participant or the online meeting;

identifying words spoken by participants associated with the enterprise or organization; and

determining the one or more suggested next words or phrases based on the words spoken by the participants associated with the enterprise or organization.

7 . The computer-implemented method of claim 1 , further comprising:

assigning a new score to the next word or phrase when the next word or phrase is not a suggested next word or phrase of the one or more suggested next words or phrases.

8 . The computer-implemented method of claim 1 , wherein generating for display the one or more suggested next words or phrases comprises:

determining a probability score for each predicted next word or phrase of the one or more suggested next words or phrases; and

generating for display the one or more suggested next words or phrases with a probability score above a threshold score.

9 . An apparatus comprising:

a memory;

a network interface configured to enable network communication; and

a processor, wherein the processor is configured to perform operations comprising:

capturing audio from an online meeting;

while the online meeting is occurring, identifying words being spoken by a participant during the online meeting from the audio;

determining one or more suggested next words or phrases to be spoken by the participant based on the words being spoken by the participant and one or more scores associated with previous words spoken by the participant, wherein the previous words and the one or more scores associated with the previous words are stored in a profile associated with the participant;

generating for display on a user device being used by the participant to participate in the online meeting the words being spoken by the participant and the one or more suggested next words or phrases;

identifying a next word or phrase spoken by the participant;

updating a score associated with the next word or phrase when the next word or phrase is a suggested next word or phrase of the one or more suggested next words or phrases; and

storing an indication of the next word or phrase and the score associated with the next word or phrase in the profile associated with the participant.

10 . The apparatus of claim 9 , wherein, wherein determining the one or more suggested next words or phrases to be spoken, the processor is configured to perform operations comprising:

dividing the words being spoken by the participant into tokens;

analyzing the tokens to predict next tokens; and

determining the one or more suggested next words or phrases based on the next tokens.

11 . The apparatus of claim 9 , wherein, when generating for display the one or more suggested next words or phrases, the processor is further configured to perform operations comprising:

determining a probability score for each predicted next word or phrase of the one or more suggested next words or phrases; and

generating for display a suggested next word or phrase with a highest probability score first.

12 . The apparatus of claim 11 , wherein the processor is further configured to perform operations comprising:

generating for display the one or more suggested next words or phrases in different colors based on the probability score for each suggested next word or phrase.

13 . The apparatus of claim 9 , wherein, when determining the one or more suggested next words or phrases, the processor is further configured to perform operations comprising:

identifying information from content associated with the online meeting; and

determining the one or more suggested next words or phrases based on the information.

14 . The apparatus of claim 9 , wherein, when determining the one or more suggested next words or phrases, the processor is further configured to perform operations comprising:

identifying an enterprise or organization associated with the participant or the online meeting;

identifying words spoken by participants associated with the enterprise or organization; and

determining the one or more suggested next words or phrases based on the words spoken by the participants associated with the enterprise or organization.

15 . The apparatus of claim 9 , wherein the processor is further configured to perform operations comprising:

assigning a new score to the next word or phrase when the next word or phrase is not a suggested next word or phrase of the one or more suggested next words or phrases.

16 . The apparatus of claim 9 , wherein, when generating for display the one or more suggested next words or phrases, the processor is further configured to perform operations comprising:

determining a probability score for each predicted next word or phrase of the one or more suggested next words or phrases; and

generating for display the one or more suggested next words or phrases with a probability score above a threshold score.

17 . One or more non-transitory computer readable storage media encoded with instructions that, when executed by a processor, cause the processor to execute a method comprising:

capturing audio from an online meeting;

while the online meeting is occurring, identifying words being spoken by a participant during the online meeting from the audio;

determining one or more suggested next words or phrases to be spoken by the participant based on the words being spoken by the participant and one or more scores associated with previous words spoken by the participant, wherein the previous words and the one or more scores associated with the previous words are stored in a profile associated with the participant;

generating for display on a user device being used by the participant to participate in the online meeting the words being spoken by the participant and the one or more suggested next words or phrases;

identifying a next word or phrase spoken by the participant;

updating a score associated with the next word or phrase when the next word or phrase is a suggested next word or phrase of the one or more suggested next words or phrases; and

storing an indication of the next word or phrase and the score associated with the next word or phrase in the profile associated with the participant.

18 . The one or more non-transitory computer readable storage media of claim 17 , wherein determining the one or more suggested next words or phrases to be spoken comprises:

dividing the words being spoken by the participant into tokens;

analyzing the tokens to predict next tokens; and

determining the one or more suggested next words or phrases based on the next tokens.

19 . The one or more non-transitory computer readable storage media of claim 17 , wherein generating for display the one or more suggested next words or phrases comprises:

determining a probability score for each predicted next word or phrase of the one or more suggested next words or phrases; and

generating for display a suggested next word or phrase with a highest probability score first.

20 . The one or more non-transitory computer readable storage media of claim 17 , wherein generating for display the one or more suggested next words or phrases comprises:

determining a probability score for each predicted next word or phrase of the one or more suggested next words or phrases; and

generating for display the one or more suggested next words or phrases with a probability score above a threshold score.

Assignments (1)

Continuity (1)

References Cited (30)