# US 2015/0091893 A1 · User modeling method based on usage history of smart device and apparatus using the same

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

- Number: US 2015/0091893 A1
- Document ID: US20150091893A1
- Status: Published application
- Kind: A1
- Application number: 14/230,736
- Filed: 2014-03-31
- Published: 2015-04-02
- Earliest claimed: 2013-09-30
- Assignees: Electronics and Telecommunications Research Institute
- Applicants: Electronics and Telecommunications Research Institute
- Inventors: Jae Hui PARK
- Web page: https://patentgrep.com/patent/US20150091893A1

## CPC

- G06Q 30/02: Marketing; Price estimation or determination; Fundraising
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

Disclosed is a method that performs a user modeling operation based on usage history data of a specific function which is provided or executed by a user terminal, and enables the user modeling result to be applied to various services. The method matches a user with a specific class, based on usage history data of various functions collected by a user terminal, and provides a user-based service suitable for the specific class.

## Claims

### Claim 1

A usage history-based user modeling apparatus for generating a user model based on a function provided or executed in a user terminal, the usage history-based user modeling apparatus comprising:
a data collecting unit configured to collect usage history data including number of executions, an execution time, and an execution position for each of a plurality of functions which are executed in the user terminal;
a data analyzing unit configured to quantify the usage history data in a predefined form; and
a user modeling unit configured to convert number of executions of one of the plurality of functions, which are executed in the user terminal, into a three-dimensional (3D) vector shape based on an execution time and an execution position.

### Claim 2 (depends on 1)

The usage history-based user modeling apparatus of claim 1, further comprising a storage unit configured to store the usage history data, the 3D vector shape, and the predefined form.

### Claim 3 (depends on 1)

The usage history-based user modeling apparatus of claim 1, further comprising a user selection input unit configured to receive an input for selecting a function, which is to be monitored, from among the plurality of functions which are executed in the user terminal.

### Claim 4 (depends on 3)

The usage history-based user modeling apparatus of claim 3, wherein usage history data of only functions selected through the user selection input unit are collected and quantified, and the quantified usage history data are converted into 3D vector shapes.

### Claim 5 (depends on 4)

The usage history-based user modeling apparatus of claim 4, wherein the user modeling unit defines, as a characteristic model of a user, a set of the 3D vector shapes for the selected functions.

### Claim 6 (depends on 1)

The usage history-based user modeling apparatus of claim 1, wherein the predefined form is determined by using a statistical model, such as an average or a variance, or a computing data distribution model such as an information entropy or mutual information.

### Claim 7

A usage history-based user modeling method of generating a user model based on a function provided or executed in a user terminal, the usage history-based user modeling method comprising:
receiving an input for selecting a function, which is to be monitored, from among a plurality of functions which are executed in the user terminal;
collecting usage history data including number of executions, an execution time, and an execution position for each of the selected functions;
quantifying the usage history data in a predefined form; and
converting number of executions of one of the selected functions into a three-dimensional (3D) vector shape based on an execution time and an execution position.

### Claim 8 (depends on 7)

The usage history-based user modeling method of claim 7, wherein the collecting of usage history data comprise collecting data of number of executions of the selected functions in real time, and collecting data of an execution time and an execution position at certain intervals.

### Claim 9 (depends on 7)

The usage history-based user modeling method of claim 7, wherein the converting comprises defining, as a characteristic model of a user, a set of the 3D vector shapes for the selected functions.
