Linguistic model database for linguistic recognition, linguistic recognition device and linguistic recognition method, and linguistic recognition system
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.
1. A voice recognition device, comprising:
a user input receiver configured to receive a voice input of a first user;
a communicator configured to communicate with an external server, which stores common recognition data of general purpose for a plurality of users and individual recognition data for individual users; and
at least one processor configured to:
determine whether information of the received voice input is included in the common recognition data,
in response to the information of the received voice input being included in the common recognition data, determine a first recognition result of the voice input based on the common recognition data,
in response to the information of the received voice input being not included in the common recognition data, determine a second recognition result of the voice input based on the individual recognition data, and
perform an operation corresponding to the voice input based on one of the first recognition result or the second recognition result according to the determined recognition result, or transmit one of the first recognition result or the second recognition result according to the determined recognition result to a plurality of electronic apparatuses used by the first user such that at least one of the plurality of electronic apparatus performs the operation based on the transmitted recognition result,
wherein the individual recognition data comprises user history information, which has been input in at least one electronic apparatus by the first user or has been transceived from and to another electronic apparatus.
2. The voice recognition device of claim 1 , wherein the at least one processor controls the communicator to transmit the information of the received voice input to the external server and receive the recognition result of voice input determined based on the stored common recognition data or the stored individual recognition data from the external server.
3. The voice recognition device of claim 1 , wherein the individual recognition data is acquired by analyzing at least one of an individual unique language pattern, a user member group language pattern, or a real-time word on the world wide web.
4. The voice recognition device of claim 1 , wherein the external server comprises a cloud server.
5. The voice recognition device of claim 1 , wherein the user input receiver is further configured to receive a character input of the first user.
6. The voice recognition device of claim 4 , wherein the individual recognition data is collected for a predetermined period of time through the plurality of the electronic apparatus used by the first user and transmitted to the cloud server.
7. A voice recognition method, the method comprising:
receiving a voice input of a first user;
communicating with an external server, which stores common recognition data of general purpose for a plurality of users and individual recognition data for individual users;
determining whether information of the received voice input is included in the common recognition data;
in response to the information of the received voice input being included in the common recognition data, determining a first recognition result of the voice input based on the common recognition data;
in response to the information of the received voice input being not included in the common recognition data, determining a second recognition result of the voice input based on the individual recognition data; and
performing an operation corresponding to the voice input based on one of the first recognition result or the second recognition result according to the determined recognition result, or transmitting one of the first recognition result or the second recognition result according to the determined recognition result to a plurality of electronic apparatuses used by the first user such that at least one of the plurality of electronic apparatus performs the operation based on the transmitted recognition result,
wherein the individual recognition data comprises user history information, which has been input in at least one electronic apparatus by the first user or has been transceived from and to another electronic apparatuses.
8. The method of claim 7 , further comprising:
transmitting the information of the received voice input to the external server; and
receiving the recognition result of voice input determined based on the stored common recognition data or the stored individual recognition data from the external server.
9. The method of claim 7 , wherein the individual recognition data is acquired by analyzing at least one of an individual unique language pattern, a user member group language pattern, or a real-time word on the world wide web.