LINGUISTIC MODEL DATABASE FOR LINGUISTIC RECOGNITION, LINGUISTIC RECOGNITION DEVICE AND LINGUISTIC RECOGNITION METHOD, AND LINGUISTIC RECOGNITION SYSTEM

• US 20170229118A1
• Filed: 04/28/2017
• Published: 08/10/2017
• Est. Priority Date: 03/21/2013
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: CHO, Kyung-sun, CHOI, Young-Il
• Granted Patent: US 10,217,455 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 3/0481 based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
• CPC Class Codes: G06F 40/171 by use of digital ink
• CPC Class Codes: G06F 40/263 Language identification
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/18 using natural language modelling
• 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 2015/227 of the speaker; Human-factor methodology

Abstract

A method of building a database for a linguistic recognition device is provided The method includes storing common linguistic model data configured to infer a word or a sentence from a character acquired by recognizing a language input by a user in a storage section of a linguistic recognition device, collecting recognition-related information related to the user after storing the common linguistic data, and analyzing the collected recognition-related information to be stored as individual linguistic model data.

Claims

1. A linguistic recognition device, the device comprising:

a user language input section through which a user inputs a language;

a character recognition unit configured to recognize a character from the language input through the user language input section;

a database; and

a word recognition unit configured to stochastically infer a word or a sentence based on common linguistic model data and individual linguistic model data stored in a storage section from the character recognized by the character recognition unit,

wherein the database comprises;

the common linguistic model data configured to stochastically infer the word or the sentence from the character acquired by recognizing the language input by the user, and

the individual linguistic model data configured to stochastically infer an individual use word or an individual use sentence related to the user by collecting recognition-related information transmitted through one or more client devices used by the user after storing the common linguistic data and analyzing the collected recognition-related information, and

wherein the word recognition unit is further configured to;

extract the individual use word excluded from the common linguistic model data, and

store the extracted individual use word as the individual linguistic model data.

2. The linguistic recognition device according to claim 1, wherein the individual linguistic model data is acquired by at least one of analyzing an individual unique language pattern, by analyzing a user member group language pattern, and by analyzing a real-time word on the World Wide Web.

3. The linguistic recognition device according to claim 1, further comprising:

a communication section which communicates with a cloud server.

4. The linguistic recognition device according to claim 1, wherein the user language input section comprises at least one of a voice input microphone and a character input interface.

5. The linguistic recognition device according to claim 3, wherein the recognition-related information is collected for a predetermined period of time through one or more client devices used by the user and transmitted to the cloud server through the communication section.

6. A linguistic recognition method, the method comprising:

building a database;

receiving a language input by a user;

recognizing a character from the input language; and

recognizing a word by stochastically inferring the word or a sentence based on stored common linguistic model data and individual linguistic model data from the recognized character,

wherein the database comprises;

the common linguistic model data configured to stochastically infer the word or the sentence from the character acquired by recognizing a language input by the user, and

the individual linguistic model data configured to stochastically infer an individual use word or an individual use sentence related to the user by collecting recognition-related information through one or more client devices used by the user after storing the common linguistic data and analyzing the collected recognition-related information, and

wherein the individual use word is excluded from the common linguistic model data.

7. The method of claim 6, wherein the individual linguistic model data is acquired by at least one of analyzing an individual unique language pattern, analyzing user member group language pattern, and analyzing a real-time word on the World Wide Web.