Granted Patent B2

US 12,367,874 · App. 17/309,993 · Granted Jul 22, 2025

Inventors: Katsutoshi Kanamori (Tokyo, JP); Masato Nishio (Tokyo, JP)

Assignee: SONY GROUP CORPORATION

G10L15/22G10L15/06G10L15/10

Abstract

Claims (63)

1. An information processing apparatus, comprising:

a central processing unit (CPU) configured to:

receive a first utterance of a user;

recognize a situation associated with the user based on the first utterance of the user, wherein the recognized situation includes at least an intention analysis result of the first utterance of the user;

control a conversation with the user based on the recognized situation;

acquire one or more knowledge elements, from a first knowledge set of a plurality of knowledge sets, based on the recognized situation, wherein

the first knowledge set of the plurality of knowledge sets is based on a usage priority associated with the first knowledge set, and

the usage priority is set by the user based on a knowledge domain associated with the first knowledge set;

determine a type of utterance template of a plurality of types of utterance templates based on the intention analysis result of the first utterance of the user;

acquire an utterance template based on the determined type of utterance template;

determine contents of a second utterance based on the one or more knowledge elements and the utterance template; and

output the second utterance to the user.

2. The information processing apparatus according to claim 1 , wherein

the one or more knowledge elements include at least a first vocabulary, and

the first vocabulary corresponds to the knowledge domain of a plurality of knowledge domains.

3. The information processing apparatus according to claim 2 , wherein the first knowledge set of the plurality of knowledge sets contains a first description of the one or more knowledge elements and a second description of a relation between the one or more knowledge elements.

4. The information processing apparatus according to claim 3 , further comprising:

a memory configured to store the plurality of knowledge sets.

5. The information processing apparatus according to claim 1 ,

wherein the CPU is further configured to add one or more knowledge sets to the plurality of knowledge sets, based on an operation by the user.

6. The information processing apparatus according to claim 5 , wherein the CPU is further configured to download the plurality of knowledge sets from a server.

7. The information processing apparatus according to claim 1 ,

wherein the plurality of knowledge sets is based on a user input.

8. The information processing apparatus according to claim 1 ,

wherein the recognized situation includes at least a conversation history of the user, and

the CPU is further configured to acquire, from the first knowledge set, the one or more knowledge elements related to a second vocabulary included in the conversation history.

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

apply the one or more knowledge elements to the acquired utterance template.

10. The information processing apparatus according to claim 1 , wherein the recognized situation further includes at least one of an object recognition result, an environment recognition result, or location information.

11. The information processing apparatus according to claim 1 , wherein

the one or more knowledge elements are used in a specific period for the second utterance by a smaller number of times than a first threshold.

12. The information processing apparatus according to claim 1 , wherein the utterance template is used for a smaller number of times than a second threshold during a specific period.

13. The information processing apparatus according to claim 1 , wherein

the plurality of knowledge sets include a second knowledge set regarding an advertisement, and

the CPU is further configured to:

acquire the one or more knowledge elements from at least one of the second knowledge set or one or more advertisement-related words included in a conversation history of the user.

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

determine first contents of a third utterance based on a third vocabulary included in the first utterance of the user; and

recommend to the user, based on the third utterance, addition of a third knowledge set to the plurality of knowledge sets, wherein the third knowledge set is related to the third vocabulary.

15. The information processing apparatus according to claim 1 , further comprising:

a speaker configured to output a voice that corresponds to the contents of the second utterance.

16. An information processing method, comprising:

receiving a first utterance of a user;

recognizing a situation associated with the user based on the first utterance of the user, wherein the recognized situation includes at least an intention analysis result of the first utterance of the user;

controlling a conversation with the user based on the recognized situation;

acquiring one or more knowledge elements from a first knowledge set of a plurality of knowledge sets, based on the recognized situation, wherein

the first knowledge set of the plurality of knowledge sets is based on a usage priority associated with the first knowledge set, and

the usage priority is set by the user based on a knowledge domain associated with the first knowledge set;

determining a type of utterance template of a plurality of types of utterance templates based on the intention analysis result of the first utterance of the user;

acquiring an utterance template based on the determined type of utterance template;

determining contents of a second utterance based on the one or more knowledge elements and the utterance template; and

outputting the second utterance to the user.

17. 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:

receiving a first utterance of a user;

recognizing a situation associated with the user based on the first utterance of the user, wherein the recognized situation includes at least an intention analysis result of the first utterance of the user;

controlling a conversation with the user based on the recognized situation;

acquiring one or more knowledge elements from a first knowledge set of a plurality of knowledge sets, based on the recognized situation, wherein

the first knowledge set of the plurality of knowledge sets is based on a usage priority associated with the first knowledge set, and

the usage priority is set by the user based on a knowledge domain associated with the first knowledge set;

determining a type of utterance template of a plurality of types of utterance templates based on the intention analysis result of the first utterance of the user;

acquiring an utterance template based on the determined type of utterance template;

determining contents of a second utterance based on the one or more knowledge elements and the utterance template; and

outputting the second utterance to the user.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (19)