# US 2019/0377425 A1 · Predicting text input based on user demographic information and context information

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

- Number: US 2019/0377425 A1
- Document ID: US20190377425A1
- Status: Published application
- Kind: A1
- Application number: 16/545,198
- Filed: 2019-08-20
- Published: 2019-12-12
- Earliest claimed: 2016-02-29
- Assignees: Samsung Electronics Co., Ltd.
- Applicants: Samsung Electronics Co., Ltd.
- Inventors: Won-ho RYU; Hee-jun SONG
- Web page: https://patentgrep.com/patent/US20190377425A1

## CPC

- G06F 3/0237: {using prediction or retrieval techniques}
- G06F 3/018: {Input/output arrangements for oriental characters}
- 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 40/274: Converting codes to words; Guess-ahead of partial word inputs
- G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30)
- G06F 40/129: Handling non-Latin characters, e.g. kana-to-kanji conversion
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

An approach, performed by a device, for recommending at least one word to be input through a keyboard is provided. The approach displays the keyboard to be used to input at least one character or text on the device. The approach selects at least one language model. The approach recommends the at least one word related to at least one character or text inputted on the keyboard, based on the at least one inputted character or text and the at least one selected language model, in which the at least one selected language model comprises at least one of a language model based on demographic properties of a user of the device, a language model based on text input histories of the user of the device, and a language model based on a context in which the keyboard is executed.

## Claims

### Claim 1

A method of recommending at least one word to be input through a keyboard, the method, being performed by a device and comprising:
displaying the keyboard to be used to input at least one character or text on the device;
obtaining application category information of a first application on which the virtual keyboard is executed;
selecting a context language model for inputted or selected text in a second application based on the application category information; and
recommending the at least one word related to at least one character or text inputted on the keyboard, based on the at least one inputted character or text and the selected context language model,
wherein the first application belongs to the same application category as the second application.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
selecting at least one of a demographic language model based on demographic properties of a user of the device or a user input language model based on text input histories of the user of the device; and
recommending the at least one word related to at least one character or text inputted on the keyboard, based on the at least one inputted character or text and the at least one selected language model,

### Claim 3 (depends on 2)

The method of claim 2, wherein the demographic properties of the user of the device comprise at least one of a gender, an age, a regional dialect, an occupation, a hometown, a religion, and one or more interests of the user.

### Claim 4 (depends on 2)

The method of claim 2, wherein the context language model is based on the context in which the virtual keyboard is executed, and the context in which the keyboard is executed comprises at least one of information about a time when the keyboard is executed and information about a place where the keyboard is executed.

### Claim 5 (depends on 2)

The method of claim 2, wherein the recommending comprises recommending, from among words included in the at least one selected language model, a word that includes the at least one inputted text and has been inputted before by the user a predetermined number of times.

### Claim 6 (depends on 5)

The method of claim 5, wherein the demographic properties of the user of the device are estimated based on text input histories of the user of the device.

### Claim 7 (depends on 6)

The method of claim 6, wherein the demographic properties of the user of the device are estimated based on additional information about the user.

### Claim 8 (depends on 2)

The method of claim 2, further comprising:
requesting a server to transmit a language model; and
receiving from the server the requested language model.

### Claim 9 (depends on 8)

The method of claim 8, further comprising:
transmitting user information to the server; and
receiving a language model updated based on the transmitted user information, from the server.

### Claim 10 (depends on 2)

The method of claim 2, wherein the recommending further comprises determining a priority of the at least one recommended word.

### Claim 11

An apparatus for recommending at least one word to be input through a keyboard, the apparatus comprising at least one processor, the at least one processor is configured to:
display the keyboard to input at least one character or text on the device,
obtain application category information of a first application on which the virtual keyboard is executed,
select a context language model for inputted or selected text in a second application based on the application category information, and
recommend the at least one word related to at least one character or text inputted on the keyboard, based on the at least one inputted character or text and the selected context language model,
wherein the first application belongs to the same application category as the second application.

### Claim 12 (depends on 11)

The apparatus of claim 11, the at least one processor is configured to select at least one of a demographic language model based on demographic properties of a user of the device or a user input language model based on text input histories of the user of the device and recommend the at least one word related to at least one character or text inputted on the keyboard, based on the at least one inputted character or text and the at least one selected language model,

### Claim 13 (depends on 12)

The apparatus of claim 12, wherein the demographic properties of the user of the device comprise at least one of a gender, an age, a regional dialect, an occupation, a hometown, a religion, and one or more interests of the user.

### Claim 14 (depends on 12)

The apparatus of claim 12, wherein the context language model is based on the context in which the virtual keyboard is executed, and the context in which the keyboard is executed comprises at least one of information about a time when the keyboard is executed and information about a place where the keyboard is executed.

### Claim 15 (depends on 12)

The apparatus of claim 12, wherein the at least one processor is configured to recommend, from among words included in the at least one selected language model, a word that includes the at least one inputted text and has been inputted before by the user a predetermined number of times.

### Claim 16 (depends on 12)

The apparatus of claim 12, wherein the at least one processor is configured to receive demographic properties of the user of the device.

### Claim 17 (depends on 12)

The apparatus of claim 12, wherein the at least one processor is further configured to estimate the demographic properties of the user of the device.

### Claim 18 (depends on 17)

The apparatus of claim 17, wherein the demographic properties of the user of the device are estimated based on text input histories of the user of the device.

### Claim 19 (depends on 17)

The apparatus of claim 17, wherein the at least one processor is further configured to determine a priority of the at least one recommended word.

### Claim 20 (depends on 1)

A non-transitory computer-readable recording medium having recorded thereon a computer program for executing the method of claim 1.
