Granted Patent B2

US 12,749,479 · App. 18/395,775 · Granted Sep 29, 2026

Inventor: Kazuhiko Kogami (Kanagawa, JP)

Assignee: RICOH COMPANY, LTD.

G10L15/08G06F3/0484G08B21/24G10L15/22G10L2015/088

Abstract

Claims (49)

1 . A communication support system, comprising:

circuitry configured to:

manage a plurality of keywords;

control a display to display an operation screen including a setting field for setting any of the plurality of keywords;

acquire audio of one or more participants in a communication;

determine, by analyzing the audio, whether or not each of the plurality of keywords is made in the communication;

determine, using a pre-trained machine learning model trained in advance, a predetermined time in accordance with the keywords or a number of keywords, wherein

the predetermined time is before a scheduled end time of the communication, and

a different predetermined time is determined for each keyword of the plurality of keywords; and

in a case that the circuitry determines that a keyword of the plurality of keywords has not been made in the communication, notify a participant of the one or more participants at the respective predetermined time determined for the keyword that the keyword has not been made in the communication.

2 . The communication support system of claim 1 , wherein the circuitry is further configured to notify the one or more participants that the keyword has not been made in the communication.

3 . The communication support system of claim 1 , wherein

the communication is made during a meeting between the one or more participants, and

the circuitry is further configured to:

acquire the audio each participant of the one or more participants in the meeting; and

notify the participant that the keyword has not been made during the meeting.

4 . The communication support system of claim 1 , wherein the circuitry is further configured to notify the participant regarding the plurality of keywords in a case that a predetermined operation is received on the operation screen.

5 . The communication support system of claim 1 , wherein the circuitry is further configured to:

convert the audio into text; and

notify the participant regarding the keyword before the communication ends in a case that the text does not include the keyword.

6 . The communication support system of claim 1 , wherein the circuitry is further configured to:

interpret a suggested keyword of the audio by analyzing the audio; and

notify the participant of a reminder regarding the suggested keyword before an end of the communication in a case that the audio does not include the suggested keyword.

7 . The communication support system of claim 1 , further comprising:

a memory, wherein

the circuitry manages the plurality of keywords by storing the one or more keywords in the memory.

8 . The communication support system of claim 7 , wherein the circuitry is further configured to store the audio in the memory in association with the plurality of keywords.

9 . The communication support system of claim 1 , wherein to notify the participant, the circuitry is configured to control the display to display the keyword.

10 . The communication support system of claim 1 , wherein the circuitry is configured to notify each participant of the one or more participants of the keyword in the case that the circuitry determines that the keyword has not been made in the communication.

11 . The communication support system of claim 1 , wherein the circuitry is further configured to receive the plurality of keywords prior to start of the communication.

12 . The communication support system of claim 11 , wherein the circuitry receives the plurality of keywords from a participant of the one or more participants.

13 . A communication support method, comprising:

managing a plurality of keywords;

controlling a display to display an operation screen including a setting field for setting any of the plurality of keywords;

acquiring audio of one or more participants in a communication;

determining, by analyzing the audio, whether or not each of the plurality of keywords is made in the communication;

determining, using a pre-trained machine learning model trained in advance, a predetermined time in accordance with the keywords or a number of keywords, wherein

the predetermined time is before a scheduled end time of the communication, and

a different predetermined time is determined for each keyword of the plurality of keywords; and

in a case that the determining indicates that a keyword of the plurality of keywords has not been made in the communication, notifying a participant of the one or more participants at the respective predetermined time determined for the keyword that the keyword has not been made in the communication.

14 . A non-transitory computer readable medium storing computer executable instructions which, when executed by circuitry of a communication support system, cause the communication support system to perform a process comprising:

managing a plurality of keywords;

controlling a display to display an operation screen including a setting field for setting any of the plurality of keywords;

acquiring audio of one or more participants in a communication;

determining, by analyzing the audio, whether or not each of the plurality of keywords is made in the communication;

determining, using a pre-trained machine learning model trained in advance, a predetermined time in accordance with the keywords or a number of keywords, wherein

the predetermined time is before a scheduled end time of the communication, and

a different predetermined time is determined for each keyword of the plurality of keywords; and

in a case that the determining indicates that a keyword of the plurality of keywords has not been made in the communication, notifying a participant of the one or more participants at the respective predetermined time determined for the keyword that the keyword has not been made in the communication.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (11)