IP Library › Granted Patent US 12,536,367
Granted Patent B2
US 12,536,367 · App. 18/203,617 · Granted Jan 27, 2026

Using artificial intelligence to generate customized summaries of conversations

Inventor: Warren Benedetto (Foothill Ranch, CA)
Assignee: Sony Interactive Entertainment Inc.
G06F40/166G10L15/1815G10L15/22H04L51/046H04L51/216G10L2015/088
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 12,536,367
App. No.
18/203,617
Granted
Jan 27, 2026
Kind
B2
Abstract

A method includes receiving text corresponding to a conversation between two or more people, receiving information for use in customizing a summary of the conversation that is to be generated, and generating the summary of the conversation that is customized according to the received information. The summary of the conversation is generated by feeding the received text and the received information into an artificial intelligence model that uses the received text and the received information as inputs. A system includes a network interface and a processor-based system configured to receive text corresponding to a conversation between two or more people, receive information for use in customizing a summary of the conversation that is to be generated, and generate the summary of the conversation that is customized according to the received information.

Claims (91)

1 . A method, comprising:

receiving an indication that a conversation between two or more people on an online platform is occurring;

in response to receiving the indication, accessing customization information for use in summarizing the conversation;

receiving text corresponding to the conversation;

providing the received text and the customization information into an artificial intelligence model that uses the received text and the customization information as inputs;

obtaining, as output from the artificial intelligence model, an initial summary of the conversation; and

periodically during the conversation, generating an updated summary of the conversation, including:

receiving additional text corresponding to the conversation;

providing the additional text and the customization information into the artificial intelligence model;

obtaining, as output from the artificial intelligence model, the updated summary of the conversation; and

providing the updated summary of the conversation to a device.

2 . The method of claim 1 , wherein the accessed customization information is specific to a profile of a particular user comprising (i) one person of the two or more people attending the conversation or (ii) a person that was scheduled to attend the conversation and is not attending the conversation.

3 . The method of claim 2 , wherein the customization information comprises one or more keywords, and the initial summary and the updated summary are generated based at least in part on the one or more keywords.

4 . The method of claim 2 , wherein the customization information is derived from the profile of the particular user, the customization information including a level of experience of the particular user relative to a subject matter of the conversation.

5 . The method of claim 2 , wherein the customization information is derived from the profile of the particular user, the customization information including at least one of an occupation or organizational role of the particular user.

6 . The method of claim 1 , wherein the customization information indicates a level of detail to be included in the initial summary and the updated summary.

7 . The method of claim 1 , wherein the customization information comprises a request for the initial summary and the updated summary of the conversation to include one or more of the following:

one or more portions of verbatim text from the received text;

a highlight reel;

a summary of all topics discussed during the conversation between two or more people;

a chronology of topics discussed during the conversation between two or more people; or

attribution to appropriate people.

8 . The method of claim 1 , wherein summarizing the conversation is responsive to receiving a request to summarize the conversation.

9 . The method of claim 2 , wherein the device is associated with the particular user.

10 . The method of claim 2 , wherein:

summarizing the conversation is responsive to receiving a request from the particular user to summarize the conversation via an option provided by the online platform.

11 . The method of claim 2 , further comprising:

receiving an indication that a person scheduled to attend the conversation between two or more people is not attending the conversation,

wherein:

the summarizing the conversation is responsive to the indication, and

the profile of the particular user is associated with the person that was scheduled to attend the conversation and is not attending the conversation.

12 . The method of claim 1 , wherein the device is associated with a person who is not attending the conversation between two or more people.

13 . The method of claim 1 , wherein generating the updated summary of the conversation further periodically during the conversation comprises:

receiving updated customization information;

providing the additional text and the updated customization information into the artificial intelligence model;

obtaining, as output from the artificial intelligence model, the updated summary of the conversation; and

providing the updated summary of the conversation to the device.

14 . The method of claim 13 , wherein:

the accessed customization information is derived from a profile of a particular user, and

the updated customization information is received as user input from the particular user.

15 . The method of claim 13 , wherein the updated customization information specifies a request for a greater level of detail; and

the updated summary of the conversation includes a greater level of detail than the initial summary of the conversation.

16 . The method of claim 13 , wherein the updated customization information specifies a request for a lesser level of detail; and

the updated summary of the conversation includes a lesser level of detail than the initial summary of the conversation.

17 . The method of claim 1 , wherein:

the customization information specifies a frequency at which the conversation is to be summarized, and

periodically generating the updated summary of the conversation during the conversation is performed at the specified frequency.

18 . A non-transitory computer readable storage medium storing one or more computer programs configured to cause a processor-based system to execute steps comprising:

receiving an indication that a conversation between two or more people on an online platform is occurring;

in response to receiving the indication, accessing customization information for use in summarizing the conversation;

receiving text corresponding to the conversation;

providing the received text and the customization information into an artificial intelligence model that uses the received text and the customization information as inputs;

obtaining, as output from the artificial intelligence model, an initial summary of the conversation; and

periodically during the conversation, generating an updated summary of the conversation, including:

receiving additional text corresponding to the conversation;

providing the additional text and the customization information into the artificial intelligence model;

obtaining, as output from the artificial intelligence model, the updated summary of the conversation; and

providing the updated summary of the conversation to a device.

19 . The non-transitory computer readable storage medium of claim 18 , wherein the customization information is specific to a profile of a particular user comprising (i) one person of the two or more people attending the conversation or (ii) a person that was scheduled to attend the conversation and is not attending the conversation.

20 . The non-transitory computer readable storage medium of claim 19 , wherein:

summarizing the conversation is responsive to receiving a request from the particular user to summarize the conversation via an option provided by the online platform.

21 . The non-transitory computer readable storage medium of claim 19 , wherein the one or more computer programs are further configured to cause the processor-based system to execute steps comprising:

receiving an indication that a person scheduled to attend the conversation between two or more people is not attending the conversation,

wherein:

the summarizing the conversation is responsive to the indication, and

the profile of the particular user is associated with the person that was scheduled to attend the conversation and is not attending the conversation.

22 . A system, comprising:

a display;

a network interface; and

a processor-based system coupled to the display and the network interface and configured to execute steps comprising:

receiving an indication that a conversation between two or more people on an online platform is occurring;

in response to receiving the indication, accessing customization information for use in summarizing the conversation;

receiving text corresponding to the conversation;

providing the received text and the customization information into an artificial intelligence model that uses the received text and the customization information as inputs;

obtaining, as output from the artificial intelligence model, an initial summary of the conversation; and

periodically during the conversation, generating an updated summary of the conversation, including:

receiving additional text corresponding to the conversation;

providing the additional text and the customization information into the artificial intelligence model;

obtaining, as output from the artificial intelligence model, the updated summary of the conversation; and

providing the updated summary of the conversation to a device.

23 . The system of claim 22 , wherein the processor-based system is further configured to execute steps comprising:

converting audio corresponding to the conversation between two or more people into the received text and the additional text.

24 . The system of claim 22 , wherein the processor-based system is further configured to execute steps comprising:

running the online platform, the online platform comprising a communication platform application;

wherein summarizing the conversation is performed in response to an indication generated by the communication platform application.

25 . The system of claim 22 , wherein the processor-based system is further configured to execute steps comprising:

establishing a user interface on the display;

wherein the customization information is received in response to interaction with the user interface.

26 . The system of claim 22 , wherein the processor-based system is further configured to execute steps comprising:

establishing a user interface on the display;

wherein summarizing the conversation is performed in response to interaction with the user interface.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 31, 2023
From: BENEDETTO, WARREN
To: SONY INTERACTIVE ENTERTAINMENT INC.
Reel/Frame 063811/0437 →
Continuity (1)
Related Publication 20240403540A1 · Dec 5, 2024
References Cited (26)
US 10529336B1 · Matthews et al. · 2020 [cited by applicant]
US 10977258B1 · Liu · 2021 [cited by examiner]
US 11822885B1 · Sundararaman et al. · 2023 [cited by applicant]
US 20080300872A1 · Basu · 2008 [cited by applicant]
US 20150117662A1 · Kulavik et al. · 2015 [cited by applicant]
US 20180192141A1 · Akumiah et al. · 2018 [cited by applicant]
US 20180349502A1 · Maycock · 2018 [cited by applicant]
US 20190028362A1 · Kim et al. · 2019 [cited by applicant]
US 20190164539A1 · Schmidt et al. · 2019 [cited by applicant]
US 20190327362A1 · Herrin · 2019 [cited by applicant]
US 20200311122A1 · Ramamurthy · 2020 [cited by examiner]
US 20210158458A1 · Waldrop · 2021 [cited by examiner]
US 20220115033A1 · Huffman et al. · 2022 [cited by applicant]
US 20220407900A1 · Gawande · 2022 [cited by examiner]
US 20230305682A1 · Faulkner · 2023 [cited by examiner]
US 20240079025A1 · Hamlin et al. · 2024 [cited by applicant]
US 20240223825A1 · Wolowiec et al. · 2024 [cited by applicant]
US 20240297863A1 · Lovitt · 2024 [cited by examiner]
US 20240314093A1 · Mehta · 2024 [cited by examiner]
Patent Cooperation Treaty; Notification of Transmittal of the International Search Report and the Written Opinion of the International Searching Authority issued in PCT Application No. PCT/US2024/030532, mailed Aug. 7, … [cited by applicant]
Patent Cooperation Treaty; International Search Report issued in PCT Application No. PCT/US2024/030532, mailed Aug. 7, 2024; 2 pages. [cited by applicant]
Patent Cooperation Treaty; Written Opinion of the International Searching Authority issued in PCT Application No. PCT/US2024/030532, mailed Aug. 7, 2024; 13 pages. [cited by applicant]
Wikipedia; “Generative pre-trained transformer”; https://en.wikipedia.org/wiki/Generative_pre-trained_transformer; the first GPT was introduced in 2018; pp. 1-12. [cited by applicant]
Wikipedia; “ChatGPT”; https://en.wikipedia.org/wiki/ChatGPT; initial release on Nov. 30, 2022; pp. 1-48. [cited by applicant]
Wikipedia; “OpenAI”; https://en.wikipedia.org/wiki/OpenAI; founded Dec. 11, 2015; pp. 1-47. [cited by applicant]
Wikipedia; “Large language model”; https://en.wikipedia.org/wiki/Large_language_model; printed on Jul. 24, 2024; pp. 1-27. [cited by applicant]