# US 2025/0139364 A1 · Device and method for providing recommended words for character input

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0139364 A1
- Document ID: US20250139364A1
- Status: Published application
- Kind: A1
- Application number: 19/010,326
- Filed: 2025-01-06
- Published: 2025-05-01
- Earliest claimed: 2016-10-21
- Assignees: Samsung Electronics Co., Ltd.
- Applicants: Samsung Electronics Co., Ltd.
- Inventors: Hee-jun SONG; Jung-wook KIM
- Web page: https://patentgrep.com/patent/US20250139364A1

## CPC

- G06F 40/274: Converting codes to words; Guess-ahead of partial word inputs
- G06F 40/163: Handling of whitespace
- G06F 40/268: Morphological analysis
- G06F 40/279: Recognition of textual entities
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A device and method for providing recommended words for at least one input character are provided. The method includes: receiving an input for inputting at least character and recommending one or more extended words including the at least one character by applying the input at least one character to an artificial intelligence (AI) model. An input that selects one of the recommended word is received, and whether a space is located next to the selected extended word is predicted. The selected extended word and the space on a character input window is displayed based on the predicting that the space is located next to the selected extended word, and at least one word to be located next to the space is recommended.

## Claims

### Claim 1

A device comprising:
a display;
a memory configured to store instructions; and
at least one processor comprising processing circuitry configured to execute the instructions stored in the memory, the at least one processor configured to:
receive an input for inputting at least one character,
recommend one or more extended words including the at least one character by applying the at least one character to an artificial intelligence (AI) model,
receive an input that selects one of the recommended one or more extended words,
predict whether a space is located next to the selected extended word,
display the selected extended word and the space on a character input window, based on a prediction that the space is located next to the selected extended word, and
recommend at least one word to be located next to the space.

### Claim 2 (depends on 1)

The device of claim 1, wherein the at least one processor is further configured to recommend a plurality of extended words including the selected word based on a characteristic for inputting characters.

### Claim 3 (depends on 2)

The device of claim 2, wherein the at least one processor is further configured to:
receive an input that selects one of the recommended plurality of extended words,
recommend at least one other extended word including the selected extended word in response to receiving the input for selecting one of the recommended plurality of extended words.

### Claim 4 (depends on 3)

The device of claim 3, wherein the at least one processor is further configured to:
recommend the at least one other extended word including the selected extended word or other extended words not including the selected extended word,
based on the predicting whether the space is located next to the selected extended word.

### Claim 5 (depends on 4)

The device of claim 4, wherein the other extended words not including the selected extended word are determined based on at least one extended word pre-displayed, the selected extended word, and the space.

### Claim 6 (depends on 1)

The device of claim 1, wherein the recommended one or more extended words are determined based on a use frequency with respect to each of the one or more extended words.

### Claim 7 (depends on 1)

The device of claim 1, wherein the at least one processor is further configured to:
display the at least one word outside the character input window, and
differently display the at least one word to indicate whether extended words to be recommended for each of the at least one word exist.

### Claim 8 (depends on 1)

The device of claim 1, wherein the AI model is configured to be trained using at least one of: information regarding characters or pieces of speech data input in past,
statistical data regarding a common use frequency for each word, or information regarding a word selected from among the one or more words recommended by the device.

### Claim 9 (depends on 1)

The device of claim 1, wherein the at least one processor is further configured to:
predict whether the space is located next to the selected extended word by using a neural network.

### Claim 10 (depends on 1)

The device of claim 1, wherein the at least one processor is further configured to:
recommend the at least one word to be located next to the space by applying the selected extended word to a neural network.

### Claim 11 (depends on 10)

The device of claim 10, wherein the neural network outputs a probability distribution of the at least one word to be located next to the space and a probability distribution of a space to be located next to the at least one word, when the selected extended word is input.

### Claim 12

A method by which a device provides recommended words for at least one input character, the method comprising:
receiving an input for inputting at least one character;
recommending one or more extended words including the at least one character by applying the input at least one character to an artificial intelligence (AI) model;
receiving an input that selects one of the recommended word;
predicting whether a space is located next to the selected extended word;
displaying the selected extended word and the space on a character input window, based on the predicting that the space is located next to the selected extended word; and
recommending at least one word to be located next to the space.

### Claim 13 (depends on 12)

The method of claim 12, further comprising recommending a plurality of extended words including the selected word based on a characteristic for inputting characters.

### Claim 14 (depends on 13)

The method of claim 13, wherein the recommending of the plurality of extended words comprises:
receiving an input that selects one of the recommended plurality of extended words; and
recommending at least one other extended word including the selected extended word in response to receiving the input for selecting one of the recommended plurality of extended words.

### Claim 15 (depends on 14)

The method of claim 14, wherein the recommending of the at least one other extended word comprises:
recommending the at least one other extended word including the selected extended word or other extended words not including the selected extended word,
based on the predicting whether the space is located next to the selected extended word.

### Claim 16 (depends on 15)

The method of claim 15, wherein the other extended words not including the selected extended word are determined based on at least one extended word pre-displayed, the selected extended word, and the space.

### Claim 17 (depends on 12)

The method in claim 12, wherein the recommended one or more extended words are determined based on a use frequency with respect to each of the one or more extended words.

### Claim 18 (depends on 12)

The method of claim 12, wherein the recommending of the at least one word comprises:
displaying the at least one word outside the character input window; and
differently displaying the at least one word to indicate whether extended words to be recommended for each of the at least one word exist.

### Claim 19 (depends on 12)

The method of claim 12, wherein the AI model is trained using at least one of: information regarding characters or pieces of speech data input in past, statistical data regarding a common use frequency for each word, or information regarding a word selected from among the one or more words recommended by the device.

### Claim 20

A computer program product comprising a non-transitory computer-readable recording medium having recorded thereon at least one instruction set which when executed causes at least one process comprising processing circuitry to:
receive an input for inputting at least one character,
recommend one or more extended words including the at least one character by applying the at least one character to an artificial intelligence (AI) model,
receive an input that selects one of the recommended one or more extended words,
predict whether a space is located next to the selected extended word,
display the selected extended word and the space on a character input window, based on a prediction that the space is located next to the selected extended word, and
recommend at least one word to be located next to the space.
