Granted Patent B2

US 12,505,282 · App. 18/410,621 · Granted Dec 23, 2025

Inventors: Luke Percival de Oliveira (San Francisco, CA); Alfredo Láinez Rodrigo (Madrid, ES)

Assignee: Twilio Inc.

G06F40/166G06F40/284G06N3/04G06N3/08H04M3/5183

Abstract

Claims (54)

1 . A method comprising:

training a machine-learning model to output a word to be added to a summary of text, the machine-learning model being trained to output the word based on the text and on the summary of the text;

by one or more processors, accessing the text;

inputting, by the one or more processors, the text and the summary of the text into the machine-learning model trained to output the word to be added to the inputted summary of the text based on the inputted text and on the inputted summary to which the outputted word is to be added; and

adding, by the one or more processors, the outputted word to the summary of the text.

2 . The method of claim 1 , wherein:

the summary is a running summary of the accessed text; and

the machine-learning model is trained to output the word to be included in the running summary of the accessed text.

3 . The method of claim 1 , further comprising:

initializing the summary by causing the summary to be empty.

4 . The method of claim 1 , wherein:

the accessed text represents a turn in a conversation that includes multiple turns.

5 . The method of claim 1 , further comprising:

causing presentation of at least a portion of the summary with the added word.

6 . The method of claim 1 , wherein:

the machine-learning model is trained to estimate the word based on the inputted text and on the inputted summary of the text and to output the estimated word in response to the inputting of the text and the summary of the text.

7 . The method of claim 1 , wherein:

the machine-learning model is trained based on multiple conversations and multiple summaries, each of the multiple conversations being summarized by a corresponding summary among multiple summaries.

8 . A system comprising:

one or more processors; and

one or more computer-readable media storing instructions that, when executed by the one or more processors, cause the system to perform operations comprising:

training a machine-learning model to output a word to be added to a summary of text, the machine-learning model being trained to output the word based on the text and on the summary of the text;

accessing the text;

inputting the text and the summary of the text into the machine-learning model trained to output the word to be added to the inputted summary of the text based on the inputted text and on the inputted summary to which the outputted word is to be added; and

adding the outputted word to the summary of the text.

9 . The system of claim 8 , wherein:

the summary is a running summary of the accessed text; and

the machine-learning model is trained to output the word to be included in the running summary of the accessed text.

10 . The system of claim 8 , wherein the operations further comprise:

initializing the summary by causing the summary to be empty.

11 . The system of claim 8 , wherein:

the accessed text represents a turn in a conversation that includes multiple turns.

12 . The system of claim 8 , wherein the operations further comprise:

causing presentation of at least a portion of the summary with the added word.

13 . The system of claim 8 , wherein:

the machine-learning model is trained to estimate the word based on the inputted text and on the inputted summary of the text and to output the estimated word in response to the inputting of the text and the summary of the text.

14 . The system of claim 8 , wherein:

the machine-learning model is trained based on multiple conversations and multiple summaries, each of the multiple conversations being summarized by a corresponding summary among multiple summaries.

15 . A non-transitory machine-readable medium storing instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:

training a machine-learning model to output a word to be added to a summary of text, the machine-learning model being trained to output the word based on the text and on the summary of the text;

accessing the text;

inputting the text and the summary of the text into the machine-learning model trained to output the word to be added to the inputted summary of the text based on the inputted text and on the inputted summary to which the outputted word is to be added; and

adding the outputted word to the summary of the text.

16 . The non-transitory machine-readable medium of claim 15 , wherein:

the summary is a running summary of the accessed text; and

the machine-learning model is trained to output the word to be included in the running summary of the accessed text.

17 . The non-transitory machine-readable medium of claim 15 , wherein the operations further comprise:

initializing the summary by causing the summary to be empty.

18 . The non-transitory machine-readable medium of claim 15 , wherein:

the accessed text represents a turn in a conversation that includes multiple turns.

19 . The non-transitory machine-readable medium of claim 15 , wherein the operations further comprise:

causing presentation of at least a portion of the summary with the added word.

20 . The non-transitory machine-readable medium of claim 15 , wherein:

the machine-learning model is trained to estimate the word based on the inputted text and on the inputted summary of the text and to output the estimated word in response to the inputting of the text and the summary of the text.

Assignments (1)

Continuity (4)

References Cited (175)