# US 2020/0394362 A1 · Apparatus and method for providing sentence based on user input

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

- Number: US 2020/0394362 A1
- Document ID: US20200394362A1
- Status: Published application
- Kind: A1
- Application number: 17/006,930
- Filed: 2020-08-31
- Published: 2020-12-17
- Earliest claimed: 2016-11-29
- Assignees: Samsung Electronics Co., Ltd.
- Applicants: Samsung Electronics Co., Ltd.
- Inventors: Ji-yeon LEE; Ji-hyun RHO; Won-ho RYU
- Web page: https://patentgrep.com/patent/US20200394362A1

## CPC

- G06F 40/274: Converting codes to words; Guess-ahead of partial word inputs
- G06F 3/0237: {using prediction or retrieval techniques}
- G06F 3/0482: Interaction with lists of selectable items, e.g. menus
- G06F 3/04842: Selection of displayed objects or displayed text elements (G06F3/0482 takes precedence)
- G06F 3/04886: by partitioning the display area of the touch-screen or the surface of the digitising tablet into independently controllable areas, e.g. virtual keyboards or menus
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Disclosed are an apparatus and/or method for providing a sentence based on a user input. When a sentence corresponding to a shorthand word input from a user is generated and provided to the user, a sentence most suitable for a current context is provided to the user by further considering context information. At least a portion of the method for providing a sentence based on a user input may be performed using a rule-based model and/or an artificial intelligence model learned according to at least one of neural network or deep learning algorithms. The rule-based model and/or artificial intelligence model may provide a sentence most suitable for a current context to the user by using the input shorthand word and the context information as input values.

## Claims

### Claim at position 1

1-20. (canceled)

### Claim 21

An apparatus for providing a sentence based on a user input, the apparatus comprising:
a touch screen;
a memory configured to store computer-executable instructions; and
at least one processor configured to execute the computer-executable instructions to:
obtain, via the touch screen, an input word by a user;
obtain context information associated with a context of chat contents input before the input word is input;
generate a prediction of a sentence corresponding to the input word based on the input word and the context information associated with the context of the chat contents input before the input word is input;
provide the sentence corresponding to the input word to the user; and
replace the input word with the sentence corresponding to the input word and control the touch screen to display the sentence corresponding to the input word according to a selection of the user.

### Claim 22 (depends on 21)

The apparatus of claim 21, wherein, when the sentence corresponding to the input word comprises a plurality of sentences, the touch screen is further configured to provide a sentence that is from among the plurality of sentences and corresponds to the input word to the user based on priority indicating an optimal sentence with which the input word is to be replaced.

### Claim 23 (depends on 21)

The apparatus of claim 21, wherein the touch screen is configured, when a selectable expression is included in the sentence corresponding to the shorthand word, to provide a user interface through which the selectable expression can be selected.

### Claim 24 (depends on 21)

The apparatus of claim 21, wherein the at least one processor is further configured to generate the sentence corresponding to the input word by applying the input word and the context information of the user to a data recognition model learned using an artificial intelligence algorithm.

### Claim 25 (depends on 24)

The apparatus of claim 24, wherein the data recognition model is stored in an external server and/or received from the server in response to a request of the apparatus.

### Claim 26 (depends on 21)

The apparatus of claim 21, wherein the context information comprises information related to a counterpart of the user, and
the at least one processor is further configured to generate the sentence corresponding to the input word based on the input word and a relationship between the counterpart and the user.

### Claim 27 (depends on 21)

The apparatus of claim 21, wherein the context information comprises a type of an application through which the input word is input, and
the at least one processor is further configured to generate the sentence corresponding to the input word based on the input word and a characteristic and/or function of the application.

### Claim 28 (depends on 21)

The apparatus of claim 21, wherein the context information comprises a user input pattern detected from a past user input history, and
the at least one processor is further configured to generate the sentence corresponding to the input word based on the input word and the user input pattern.

### Claim 29 (depends on 21)

The apparatus of claim 21, wherein the at least one processor is further configured to learn a correlation between the input word and the sentence based on the sentence corresponding to the input word according to the selection of the user.

### Claim 30

A method of providing a sentence based on a user input, the method being implemented in a computer and comprising:
obtaining an input word by a user;
obtaining context information associated with a context of chat contents input before the input word is input;
generating a prediction of a sentence corresponding to the input word based on the input word and the context information associated with the context of the chat contents input before the input word is input;
providing the sentence corresponding to the input word to the user; and
replacing the input word with the sentence corresponding to the input word and displaying the sentence corresponding to the shorthand word according to a selection of the user.

### Claim 31 (depends on 30)

The method of claim 30, wherein the providing comprises providing, when the sentence corresponding to the input word comprises a plurality of sentences, a sentence that is from among the plurality of sentences and corresponds to the input word to the user based on priority indicating an optimal sentence with which the input word is to be replaced.

### Claim 31 (depends on 30)

The method of claim 30, wherein the providing comprises providing, to the user, a sentence corresponding to the input word, which is generated from a data recognition model learned using an artificial intelligence algorithm by using the input word and the context information of the user as input values of the learned data recognition model.

### Claim 32 (depends on 30)

The method of claim 30, wherein the providing comprises providing, when a selectable expression is included in the sentence corresponding to the input word, a user interface through which the selectable expression can be selected.

### Claim 34 (depends on 30)

A non-transitory computer-readable recording medium having recorded thereon a program for executing, in a computer, the method of claim 30.
