Apparatus and method for providing personal assistant service based on automatic translation

1. An apparatus for providing a personal assistant service based on automatic translation, the apparatus comprising:

an input section configured to receive a command of a user;

a memory in which a program for providing a personal assistant service according to the command of the user is stored; and

a processor configured to execute the program,

wherein the processor updates at least one of a speech recognition model, an automatic interpretation model, and an automatic translation model on the basis of an intention of the command of the user using a recognition result of the command of the user and provides the personal assistant service on the basis of an automatic translation call,

wherein the processor acquires the personalization-based information using at least one of an address book, a note, and a search history in a smart terminal,

wherein the processor collects information on at least one of a product, a service, and an address through a website or a social network service (SNS) and structures the collected information into a database (DB) to acquire the information based on specialized online data,

wherein the processor acquires personalization-based information, information based on specialized online data, and information based on general online data and updates at least one of the speech recognition model, the automatic interpretation model, and the automatic translation model with the acquired information, and

wherein the processor prepares an empty slot in a search network and updates the at least one of the models by filling the empty slot with a corresponding word or sentence when information determined as a speech recognition candidate is acquired.

2. The apparatus of claim 1 , wherein the processor executes a natural language understanding (NLU) module according to the command of the user to analyze the command of the user.

3. The apparatus of claim 2 , wherein the processor determines whether the command of the user is a command based on speech recognition or a command of a text input, transfers the command to the NLU module without any change when the command of the user is the command of the text input, and transfers a speech recognition result to the NLU module when the command of the user is the command based on the speech recognition.

4. The apparatus of claim 1 , wherein, when an automatic interpretation support server is in operation, the processor acquires one-to-one translation data from the automatic interpretation support server, and

when the automatic interpretation support server is not in operation, the processor acquires translation data with regard to a source language and a target language by utilizing a one-to-one translation dictionary search or an automatic interpreter.

5. The apparatus of claim 1 , wherein, when the information based on the specialized online data is not provided in target language text, the processor acquires the information in source language text and acquires the information in target language text using an automatic interpretation support server, a translation dictionary, and an automatic interpreter.

6. The apparatus of claim 1 , wherein the processor interprets a keyword related to the intention of the user into a target language and performs a web search in the target language using the interpreted keyword as an input keyword to structure found text into a database.

7. A method of providing a personal assistant service based on automatic translation, the method comprising:

(a) receiving a command of a user;

(b) updating at least one of a speech recognition model, an automatic interpretation model, and an automatic translation model on the basis of an intention of the command of the user using a recognition result of the command of the user; and

(c) providing a personal assistant service using an automatic translation call,

wherein the operation (b) comprises:

acquiring the personalization-based information using at least one of an address book, a note, and a search history in a smart terminal;

acquiring the information based on specialized online data by collecting information on at least one of a product, a service, and an address through a website or a social network service (SNS) to structure the collected information into a database;

interpreting a keyword related to the intention of the user into a target language and performing a web search in the target language using the interpreted keyword as an input keyword to structure found text into a database;

updating at least one of the speech recognition model, the automatic interpretation model, and the automatic translation model using personalization-based information, information based on specialized online data, and information based on general online data;

preparing an empty slot in advance for a word or a sentence to be recognized in a search network; and

updating the at least one of the models by filling the empty slot with a corresponding word or sentence when information determined as a speech recognition candidate is acquired.

8. The method of claim 7 , wherein, when a command of a text input is received as the command of the user in the operation (a), the operation (b) comprises transferring the command to a natural language understanding (NLU) module without any change, and

when a command based on speech recognition is received as the command of the user, the operation (b) comprises transferring a speech recognition result to the NLU module.

9. The method of claim 7 , wherein the operation (b) further comprises acquiring translation data using an automatic interpretation support server, a translation dictionary searcher, and an automatic interpreter.