Interaction apparatus and method

• US 10,319,378 B2
• Filed: 09/06/2016
• Issued: 06/11/2019
• Est. Priority Date: 06/27/2014
• Status: Expired due to Fees

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Ichimura, Yumi
• Primary Examiner(s): Chawan, Vijay B
• Application Number:
  US15/257,203
• Publication Number:
  US 20170040019A1
• Time in Patent Office: 1,008 Days
• Field of Search: 704 9, 704257, 704243, 704251, 704254, 704255, 7042701, 707999005, 707706, 707769, 707803, 707999003, 707999006, 707999009, 7079991
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/0635 updating or merging of old and new templates; Mean values; Weighting
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/221 Announcement of recognition results
• CPC Class Codes: G10L 25/54 for retrieval

Abstract

According to one embodiment, an interaction apparatus includes an interaction apparatus includes a storage, a first extractor, a retriever, a generator, a second extractor and a register. The storage stores a problem and at least one solution for solving the problem. The first extractor extracts a target problem which is an expression regarded as the problem, from a first speech. The generator generates a first speech-prompting sentence prompting the user to make a speech including the target solution if the storage stores no target solution or if the user rejects the target solution. The second extractor extracts the target solution from a second speech which is a response of the user relating to the first speech-prompting sentence. The register registers, on the storage, the target problem and the target solution.

Claims

1. An interaction apparatus, comprising:

a storage that stores a problem and at least one solution for solving the problem, in association with each other;

a first extractor that extracts a target problem which is an expression regarded as the problem, from a first speech of a user;

a retriever that retrieves, from the storage, a target solution which is a solution corresponding to the target problem;

a generator that generates a first speech-prompting sentence if the storage stores no target solution or if the user rejects the target solution, the first speech-prompting sentence prompting the user to make a speech including the target solution;

a second extractor that extracts the target solution from a second speech which is a response of the user relating to the first speech-prompting sentence; and

a register that registers, on the storage, the target problem and the target solution in association with each other.

2. The apparatus according to claim 1, wherein the generator changes the first speech-prompting sentence in accordance with an expression of the first speech.

3. The apparatus according to claim 1, wherein the retriever acquires, as the target solution, a solution associated with a related problem if the related problem exists in the storage, the related problem relating to the target problem.

4. The apparatus according to claim 1, wherein the second extractor extracts, from the second speech, a noun phrase which is a subject or object and a verb which is a predicate, and acquires, as the target solution, an expression combined the noun phrase and the verb.

5. The apparatus according to claim 1, wherein

if the second speech fails to include a noun which is different from the noun included in the first speech and which is not a formal noun, the generator generates a second speech-prompting sentence prompting the user to make a speech including a solution that uses an expression different from the second speech;

and

the second extractor extracts the target solution from a third speech which a response of the user relating to the second speech-prompting sentence.

6. The apparatus according to claim 1, wherein

if a noun phrase which is a subject or object in the second speech is not included in a keyword list, the generator generates a second speech-prompting sentence prompting the user to make a speech including a solution that uses an expression different from the second speech;

and

the second extractor extracts the target solution from a third speech which a response of the user with respect to the second speech-prompting sentence.

7. The apparatus according to claim 5, wherein

the second extractor extracts, from the second speech, a first noun phrase that is a subject or object and a verb that is the predicate and extracts, from the third speech, a second noun phrase different from the first noun phrase, and acquires, as the target solution, an expression combined the second noun phrase and the verb.

8. An interaction method, comprising:

storing, in a storage, a problem and at least one solution for solving the problem, in association with each other;

extracting a target problem which is an expression regarded as the problem, from a first speech of a user;

retrieving, from the storage, a target solution which is a solution corresponding to the target problem;

generating a first speech-prompting sentence if the storage stores no target solution or if the user rejects the target solution, the first speech-prompting sentence prompting the user to make a speech including the target solution;

extracting the target solution from a second speech which is a response of the user relating to the first speech-prompting sentence; and

registering, on the storage, the target problem and the target solution in association with each other.

9. The method according to claim 8, further comprising changing the first speech-prompting sentence in accordance with an expression of the first speech.

10. The method according to claim 8, wherein the retrieving the target solution acquires, as the target solution, a solution associated with a related problem if the related problem exists in the storage, the related problem relating to the target problem.

11. The method according to claim 8, wherein the extracting the target solution extracts, from the second speech, a noun phrase which is a subject or object and a verb which is a predicate, and acquires, as the target solution, an expression combined the noun phrase and the verb.

12. The method according to claim 8, wherein

if the second speech fails to include a noun which is different from the noun included in the first speech and which is not a formal noun, the generating the first speech-prompting sentence generates a second speech-prompting sentence prompting the user to make a speech including a solution that uses an expression different from the second speech;

and

the extracting the target solution extracts the target solution from a third speech which a response of the user relating to the second speech-prompting sentence.

13. The method according to claim 8, wherein

if a noun phrase which is a subject or object in the second speech is not included in a keyword list, the generating the first speech-prompting sentence generates a second speech-prompting sentence prompting the user to make a speech including a solution that uses an expression different from the second speech;

and

the extracting the target solution extracts the target solution from a third speech which a response of the user with respect to the second speech-prompting sentence.

14. The method according to claim 12, wherein

the extracting the target solution extracts, from the second speech, a first noun phrase that is a subject or object and a verb that is the predicate and extracts, from the third speech, a second noun phrase different from the first noun phrase, and acquires, as the target solution, an expression combined the second noun phrase and the verb.

15. A non-transitory computer readable medium including computer executable instructions, wherein the instructions, when executed by a processor, cause the processor to perform a method comprising:

storing, in a storage, a problem and at least one solution for solving the problem, in association with each other;

extracting a target problem which is an expression regarded as the problem, from a first speech of a user;

retrieving, from the storage, a target solution which is a solution corresponding to the target problem;

generating a first speech-prompting sentence if the storage stores no target solution or if the user rejects the target solution, the first speech-prompting sentence prompting the user to make a speech including the target solution;

extracting the target solution from a second speech which is a response of the user relating to the first speech-prompting sentence; and

registering, on the storage, the target problem and the target solution in association with each other.

16. The medium according to claim 15, further comprising changing the first speech-prompting sentence in accordance with an expression of the first speech.

17. The medium according to claim 15, wherein the retrieving the target solution acquires, as the target solution, a solution associated with a related problem if the related problem exists in the storage, the related problem relating to the target problem.

18. The medium according to claim 15, wherein the extracting the target solution extracts, from the second speech, a noun phrase which is a subject or object and a verb which is a predicate, and acquires, as the target solution, an expression combined the noun phrase and the verb.

19. The medium according to claim 15, wherein

if the second speech fails to include a noun which is different from the noun included in the first speech and which is not a formal noun, the generating the first speech-prompting sentence generates a second speech-prompting sentence prompting the user to make a speech including a solution that uses an expression different from the second speech;

and

the extracting the target solution extracts the target solution from a third speech which a response of the user relating to the second speech-prompting sentence.

20. The medium according to claim 15, wherein

if a noun phrase which is a subject or object in the second speech is not included in a keyword list, the generating the first speech-prompting sentence generates a second speech-prompting sentence prompting the user to make a speech including a solution that uses an expression different from the second speech;

and

the extracting the target solution extracts the target solution from a third speech which a response of the user with respect to the second speech-prompting sentence.