Apparatus and method for generating a guide sentence

• US 9,620,109 B2
• Filed: 02/18/2015
• Issued: 04/11/2017
• Est. Priority Date: 02/25/2014
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Song, In-jee, Chung, Ji-hye
• Primary Examiner(s): Baker, Charlotte M
• Application Number:
  US14/624,815
• Publication Number:
  US 20150243281A1
• Time in Patent Office: 783 Days
• Field of Search: 704251, 704252, 704 9, 701533, 701428
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A server and a guide sentence generating method are provided. The method includes receiving user speech, analyzing the user speech, determining a category of the user speech from among a plurality of categories, storing the user speech in the determined category, determining a usage frequency and a popularity of each of the plurality of categories, selecting a category from among the plurality of categories based on the usage frequency and the popularity, and generating a guide sentence corresponding to the selected category.

Claims

1. A guide sentence generating method implemented by one or more processors, the guide sentence generating method comprising:

receiving speech data corresponding to user speech from an electronic apparatus;

analyzing the speech data, determining a category of the speech data from among a plurality of categories, and storing the analyzed speech data in the determined category;

determining a usage frequency and a global popularity of each of the plurality of categories, wherein the usage frequency comprises a count of speech data of an individual user and the global popularity comprises a count of speech data of a plurality of users;

selecting a category from among the plurality of categories based on the usage frequency and the global popularity;

generating a guide sentence corresponding to the selected category;

transmitting the guide sentence to the electronic apparatus; and

providing the guide sentence to the user in at least one of visual and audio form, so that the user may command the electronic apparatus using the guide sentence.

2. The method of claim 1, wherein the selecting comprises selecting a category whose usage frequency is lowest and global popularity is highest from among the plurality of categories.

3. The method of claim 1, wherein the plurality of categories comprise at least one of a domain category regarding the speech data, a function category of the electronic apparatus that received the speech data, a sentence structure category regarding the speech data, and a keyword category regarding words included in the speech data.

4. The method of claim 1, wherein the plurality of categories comprise complexity information corresponding to sentence length, and

the selecting the category further comprises selecting a category whose global popularity is highest and whose usage frequency and complexity is lowest thereby generating the guide sentence.

5. The method of claim 3, wherein, in response to the sentence structure category being selected, the generating comprises inserting keywords included in the speech data into a sentence structure included in the selected category thereby generating the guide sentence.

6. The method of claim 3, wherein, in response to at least one of the domain category, the function category, and the keyword category being selected, the generating comprises generating the guide sentence based on pre-stored global popularity.

7. The method of claim 1, wherein the plurality of categories have a ranking order comprising a first category and a remainder category, further comprising:

determining a guide sentence cannot be generated corresponding to the first category; and

responsive to determining a guide sentence cannot be generated corresponding to the first category, generating a guide sentence corresponding to the remainder category.

8. The method of claim 1, further comprising providing the guide sentence to the user in at least one of preset intervals or in response to receiving a user command to output the guide sentence.

9. A server, comprising:

a communicator configured to receive speech data corresponding to user speech from an electronic apparatus;

a controller configured to determine a category of the speech data from among a plurality of categories; and

a storage configured to store the speech data in the determined category,

wherein the controller is further configured to determine a usage frequency and a global popularity of each of the plurality of categories, the usage frequency comprising a count of speech data of an individual user and the global popularity comprising a count of speech data of a plurality of users, select a category from among the plurality of categories based on the usage frequency and the global popularity, generate a guide sentence corresponding to the selected category, transmit the guide sentence to the electronic apparatus, and provide the guide sentence to the user in at least one of visual or audio form, so that the user may command the electronic apparatus using the guide sentence.

10. The server of claim 9, wherein the controller is configured to select a category whose usage frequency is lowest and global popularity is highest from among the plurality of categories.

11. The server of claim 9, wherein the plurality of categories comprise at least one of a domain category regarding the speech data, a function category of the electronic apparatus that received the speech data, a sentence structure category of the speech data, and a keyword category regarding words included in the speech data.

12. The server of claim 9, wherein the plurality of categories comprise complexity information corresponding to sentence length, and

the controller is further configured to select a category whose global popularity is highest and whose usage frequency and complexity is lowest thereby generating the guide sentence.

13. The server of claim 11, wherein, in response to the sentence structure category being selected, the controller is configured to insert keywords included in the speech data into a sentence structure included in the selected category thereby generating the guide sentence.

14. The server of claim 11, wherein, in response to at least one of the domain category, the function category, and the keyword category being selected, the controller is configured to generate the guide sentence based on a pre-stored global popularity.

15. An apparatus for generating information for speech recognition, the apparatus comprising:

a storage configured to store a usage frequency of a plurality of vocal commands corresponding to an electronic device;

a controller configured to determine a vocal command from among the plurality of vocal commands and generate information about the vocal command corresponding to the electronic device based on at least one of a user'"'"'s usage frequency of the vocal command, wherein the user'"'"'s usage frequency comprises a count of the vocal command, and a global user usage frequency of the vocal command, wherein the global user usage frequency comprises a count of the vocal command; and

an outputter configured to output the information about the vocal command in at least one of visual or audio form, wherein the information about the vocal command comprises a vocal command for controlling the electronic device.

16. The apparatus of claim 15, wherein the controller is configured to generate information about the vocal command whose user'"'"'s usage frequency is lowest and global user usage frequency is highest.

17. The apparatus of claim 15, wherein the information about the vocal command comprises a guide statement in which keywords previously used by a user are inserted.