Method and apparatus for recommending word

Patent metadata

Field	Value
Publication number	US-11556708-B2
Application number	US-202017099831-A
Country	US
Kind code	B2
Filing date	Nov 17, 2020
Priority date	May 16, 2017
Publication date	Jan 17, 2023
Grant date	Jan 17, 2023

Abstract

Provided is a device including a memory storing information about sequences of a plurality of registered words; an input unit comprising input circuitry configured to receive an input of a text comprising a first eojeol not belonging to the plurality of registered words, wherein, in the first eojeol, a first word is attached to a first registered word that belongs to the plurality of registered words; and a controller configured to detect the first registered word from the first eojeol, to determine a predicted eojeol to be input after the text, based on the information about the sequences of the plurality of registered words and the detected first registered word and to control a display to display the predicted eojeol.

First claim

What is claimed is:

1. A device comprising:
a display; and
at least one processor configured to:
obtain information about sequences about a plurality of registered words,
receive a user input including a text comprising a first portion and a second portion,
determine whether the text is included in the plurality of registered words,
when the text is not included in the plurality of registered words, detect the first portion corresponding to at least one word of the plurality of registered words, and determine at least one first predicted word to be input in succession to the text via the neural network based on the information about the sequences about the plurality of registered words and the first portion,
when the text is included in the plurality of registered words, determine at least one second predicted word to be input in succession to the text via the neural network based on the information about the sequences about the plurality of registered words and the text,
modify and refine parameters of the neural network so that, when the sequences about the plurality of registered words detected from the second portion of the text is input as an input value to the neural network, a next word is output as an output value from the neural network,
control the display to display menu user interface (UI) for receiving a user input for selecting a predicted word from among the at least one the first predicted word or the at least one second predicted word predicted via the neural network, and
input the predicted word selected by the user input received through the menu UI in succession to the text.

2. The device of claim 1 , the at least one processor is further configured to:
detect the first portion corresponding to the at least one word of the plurality of registered words by applying a plurality of filters corresponding to the plurality of registered words to a plurality of syllables forming the text.

3. The non-transitory computer-readable recording medium of claim 2 , wherein the method further comprises:
detecting the first portion corresponding to the at least one word of the plurality of registered words by applying a plurality of filters corresponding to the plurality of registered words to a plurality of syllables forming the text.

4. The device of claim 1 , the at least one processor is further configured to:
update at least one of the plurality of registered words or the information about sequences about a plurality of registered words.

5. The device of claim 1 , wherein the information about sequences about the plurality of registered words comprises probability information about the sequences about the plurality of registered words.

6. The device of claim 1 , wherein the text comprising the first portion includes at least one of a first text obtained via a user interface, a second text obtained via voice recognition, or a third text obtained via machine translation.

7. The device of claim 1 , wherein the at least one of the plurality of registered words or the information about sequences about a plurality of registered words is updated based on the selected word.

8. The method of claim 1 , wherein the at least one first predicted word or at least one the second predicted word are determined based on a morpheme comprised of the text.

9. A method performed by a device, the method comprising:
obtaining information about sequences about a plurality of registered words;
receiving a user input including a text comprising a first portion and a second portion;
determining whether the text is included in the plurality of registered words;
when the text is not included in the plurality of registered words, detecting the first portion corresponding to at least one word of the plurality of registered words, and determining at least one first predicted word to be input in succession to the text via the neural network based on the information about the sequences about the plurality of registered words and the first portion;
when the text is included in the plurality of registered words, determining at least one second predicted word to be input in succession to the text via the neural network based on the information about the sequences about the plurality of registered words and the text;
modifying and refining parameters of the neural network so that, when the sequences about the plurality of registered words detected from the second portion of the text is input as an input value to the neural network, a next word is output as an output value from the neural network;
displaying menu user interface (UI) for receiving a user input selecting a predicted word from among the at least one first predicted word or the at least one second predicted word predicted via the neural network; and
inputting the predicted word selected by the user input received through the menu UI in succession to the text.

10. The method of claim 9 , wherein the method further comprises:
detecting the first portion corresponding to the at least one word of the plurality of registered words by applying a plurality of filters corresponding to the plurality of registered words to a plurality of syllables forming the text.

11. The device of claim 9 , wherein the method further comprises:
update at least one of the plurality of registered words or the information about sequences about a plurality of registered words.

12. The method of claim 9 , wherein the information about sequences about the plurality of registered words comprises probability information about the sequences about the plurality of registered words.

13. The method of claim 9 , wherein the text comprising the first portion includes at least one of a first text obtained via a user interface, a second text obtained via voice recognition, or a third text obtained via machine translation.

14. The method of claim 9 , wherein the at least one of the plurality of registered words or the information about sequences about a plurality of registered words is updated based on the selected word.

15. The method of claim 9 , wherein the at least one first predicted word or the at least one second predicted word are determined based on a morpheme comprised of the text.

16. A non-transitory computer-readable recording medium having recorded thereon a program for executing, on a computer, a method comprising:
obtaining information about sequences about a plurality of registered words;
receiving a user input including a text comprising a first portion and a second portion;
determining whether the text is included in the plurality of registered words;
when the text is not included in the plurality of registered words, detecting the first portion corresponding to at least one word of the plurality of registered words, and determining at least one first predicted word to be input in succession to the text via the neural network based on the information about the sequences about the plurality of registered words and the first portion;
when the text is included in the plurality of registered words, determining at least one second predicted word to be input in succession to the text via the neural network based on the information about the sequences about the plurality of registered words and the text;
modifying and refining parameters of the neural network so that, when the sequences about the plurality of registered words detected from the second portion of the text is input as an input value to the neural network, a next word is output as an output value from the neural network;
displaying menu user interface (UI) for receiving a user input selecting a pre

Assignees

• Samsung Electronics Co Ltd

Inventors

• Lee Hae-Jun
• Yu Seung-Hak

Classifications

• G06F40/268

  Morphological analysis · CPC title

• G06F40/284

  Lexical analysis, e.g. tokenisation or collocates · CPC title

• G06F40/216

  using statistical methods · CPC title

• G06F40/274 Primary

  Converting codes to words; Guess-ahead of partial word inputs · CPC title

• G06F3/0237 Primary

  using prediction or retrieval techniques · CPC title