Granted Patent B2

US 12,260,859 · App. 17/759,095 · Granted Mar 25, 2025

Inventors: Hideki Noma (Tokyo, JP); Katsutoshi Kanamori (Tokyo, JP)

Assignee: SONY GROUP CORPORATION

G10L15/22G10L15/06G10L2015/223

Abstract

Claims (60)

1. An information processing apparatus, comprising:

a central processing unit (CPU) configured to:

acquire sensor information and episode data from an agent apparatus, wherein

each of the sensor information and the episode data is associated with a speaker,

the episode data includes topic information,

the topic information is associated with utterance data of the speaker;

authenticate the speaker based on the sensor information;

control a first interaction with the speaker based on the episode data; and

add a specific episode in the episode data based on the authenticated speaker, wherein the specific episode is associated with the speaker.

2. The information processing apparatus according to claim 1 , wherein the CPU is further configured to:

generate interaction data based on of the episode data and a specific algorithm;

generate an interactive sentence based on the specific algorithm; and

control the first interaction based on the generated interaction data.

3. The information processing apparatus according to claim 2 , wherein

the specific algorithm includes a template,

the template is associated with a classification of the specific episode, and

the CPU is further configured to set specific data of the episode data based on the template.

4. The information processing apparatus according to claim 3 , wherein the topic information satisfies an interaction condition associated with the episode data.

5. The information processing apparatus according to claim 4 , wherein the CPU is further configured to:

acquire the episode data based on the authentication of the speaker and an acquisition condition, wherein the acquisition condition is associated with the episode data;

control a second interaction with the speaker; and

spontaneously output the specific episode based on the second interaction.

6. The information processing apparatus according to claim 5 , wherein the CPU is further configured to:

control a third interaction with the speaker based on

the interaction data different from the specific episode, and

non-acquisition of the episode data.

7. The information processing apparatus according to claim 1 , wherein the CPU is further configured to:

store analysis information that comprises an analysis result, wherein the analysis result is associated with the utterance data;

generate the episode data based on the analysis result; and

store the episode data in association with the speaker.

8. The information processing apparatus according to claim 7 , wherein the CPU is further configured to:

control a second interaction with the speaker based on question data associated with the speaker; and

generate the episode data based on the analysis result of the utterance data, wherein the utterance data corresponds to the question data.

9. The information processing apparatus according to claim 8 , wherein the CPU is further configured to:

acquire related information regarding a past situation of the speaker; and

generate the episode data based on the related information.

10. The information processing apparatus according to claim 9 , wherein the CPU is further configured to:

store common data associated with a plurality of pieces of the episode data; and

generate the episode data based generalized on the common data.

11. An information processing system, comprising:

an agent apparatus configured to receive utterance data of a speaker; and

an information processing apparatus that includes a central processing unit (CPU), wherein the CPU is configured to

acquire sensor information and episode data from the agent apparatus, wherein

each of the sensor information and the episode data is associated with the speaker,

the episode data includes topic information, and

the topic information is associated with the utterance data;

authenticate the speaker based on the sensor information;

control an interaction with the speaker based on the episode data; and

add a specific episode in the episode data based on the authenticated speaker, wherein the specific episode is associated with the speaker.

12. The information processing system according to claim 11 , wherein

the agent apparatus is a movable robot,

the CPU is further configured to control the interaction with the speaker via the agent apparatus.

13. A non-transitory computer-readable medium having stored thereon, computer-executable instructions which, when executed by a computer, cause the computer to execute operations, the operations comprising:

acquiring sensor information and episode data from an agent apparatus, wherein

each of the sensor information and the episode data is associated with a speaker,

the episode data includes topic information,

the topic information is associated with utterance data of the speaker;

authenticating the speaker based on the sensor information;

controlling an interaction with the speaker based on the episode data; and

adding a specific episode in the episode data based on the authenticated speaker, wherein the specific episode is associated with the speaker.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (15)