# US 11,030,252 B2 · Effective extraction of information on time-varying user interest

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

- Number: US 11,030,252 B2
- Document ID: US11030252B2
- Status: Granted
- Kind: B2
- Application number: 16/024,944
- Filed: 2018-07-02
- Published: 2019-01-24
- Granted: 2021-06-08
- Earliest claimed: 2017-07-18
- Assignees: Fujitsu Limited
- Applicants: Fujitsu Limited
- Inventors: Matthieu Parizy; Tatsuya Yamamoto
- Web page: https://patentgrep.com/patent/US11030252B2

## CPC

- G06F 16/90335: {Query processing}
- G06F 16/2477: {Temporal data queries}
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06Q 30/0269: {based on user profile or attribute}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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

An apparatus sets, for a user, a time-width indicating a period of time which precedes a current time and for which a usage history of the user is to be acquired, and extracts an interesting matter of the user from the usage history acquired within the set time-width. The apparatus provides help information obtained based on the extracted interesting matter to the user to acquire a result of an operation that is performed by the user in response to provision of the help information, where the time-width for the user is set based on the acquired result of the operation by the user.

## Claims

### Claim 1

An information extraction apparatus comprising:
a memory; and
a processor coupled to the memory and the processor is configured to:
store a plurality of operations to be performed for a plurality of interesting matters;
set, for a first user among users, a first time-width as a time-width indicating a period of time which precedes a current time and for which a usage history of each of the users is to be acquired;
set a credibility for each of the plurality of operations;
extract a first interesting matter of the first user from the usage history acquired within the set first time-width;
provide help information obtained based on the extracted first interesting matter to the first user to acquire a result of an operation that is performed by the first user in response to provision of the help information; and
calculate an interest group probability by dividing a sum of products of multiplying a total number of the plurality of operations with the credibility for each of the plurality of operations by a number of items in the usage history, wherein
the processor sets the first time-width for the first user, based on the acquired result of the operation by the first user.

### Claim 2 (depends on 1)

The information extraction apparatus of claim 1, wherein the processor is configured to:
in a state where the first time-width is set for the first user, set, for the first user, a second time-width longer than the first time-width, and
set the second time-width as a time-width for which the usage history of the first user is to be subsequently acquired, when a second interesting matter extracted within the second time-width is different from the first interest matter extracted within the first time-width and a result of the operation performed by the first user in response to provision of the help information obtained based on the second interesting matter meets a predetermined condition.

### Claim 3 (depends on 1)

The information extraction apparatus of claim 1, wherein the processor is configured to:
determine, for the first user, a second user among the users whose usage history is similar to the usage history of the first user, and
set, for the first user, a second time-width set for the second user, based on setting information on time-widths set for the respective users.

### Claim 4 (depends on 1)

The information extraction apparatus of claim 1, wherein the processor is configured to:
calculate, based on the usage history, a degree of interest of each of a plurality of interesting matters for the first user, and
provide, as the help information, information obtained based on the degree of interest of each interesting matter to the first user.

### Claim 5

A non-transitory, computer-readable recording medium having stored thein a program for causing a computer to execute a process comprising:
storing a plurality of operations to be performed for a plurality of interesting matters;
setting, for a first user among users, a first time-width as a time-width indicating a period of time which precedes a current time and for which a usage history of each of the users is to be acquired;
setting a credibility for each of the plurality of operations;
extracting a first interesting matter of the first user from the usage history acquired within the set first time-width;
providing help information obtained based on the extracted first interesting matter to the first user to acquire a result of an operation that is performed by the first user in response to provision of the help information, and
calculating an interest group probability by dividing a sum of products of multiplying a total number of the plurality of operations with the credibility for each of the plurality of operations by a number of items in the usage history, wherein
the first time-width for the first user is set based on the acquired result of the operation by the first user.

### Claim 6 (depends on 5)

The non-transitory, computer-readable recording medium of claim 5, the process further comprising:
in a state where the first time-width is set for the first user, setting, for the first user, a second time-width longer than the first time-width; and
setting the second time-width as a time-width for which the usage history of the first user is to be subsequently acquired, when a second interesting matter extracted within the second time-width is different from the first interest matter extracted within the first time-width and a result of the operation performed by the first user in response to provision of the help information obtained based on the second interesting matter meets a predetermined condition.

### Claim 7 (depends on 5)

The non-transitory, computer-readable recording medium of claim 5, the process further comprising:
determining, for the first user, a second user among the users whose usage history is similar to the usage history of the first user; and
setting, for the first user, a second time-width set for the second user, based on setting information on time-widths set for the respective users.

### Claim 8 (depends on 5)

The non-transitory, computer-readable recording medium of claim 5, the process further comprising:
calculating, based on the usage history, a degree of interest of each of a plurality of interesting matters for the first user; and
providing, as the help information, information obtained based on the degree of interest of each interesting matter to the first user.

### Claim 9

A method comprising:
storing a plurality of operations to be performed for a plurality of interesting matters;
setting, for a first user among users, a first time-width as a time-width indicating a period of time which precedes a current time and for which a usage history of each of the users is to be acquired;
setting a credibility for each of the plurality of operations;
extracting a first interesting matter of the first user from the usage history acquired within the set first time-width;
providing help information obtained based on the extracted first interesting matter to the first user to acquire a result of an operation that is performed by the first user in response to provision of the help information, and
calculating an interest group probability by dividing a sum of products of multiplying a total number of the plurality of operations with the credibility for each of the plurality of operations by a number of items in the usage history, wherein
the first time-width for the first user is set based on the acquired result of the operation by the first user.

### Claim 10 (depends on 9)

The method of claim 9, further comprising:
in a state where the first time-width is set for the first user, setting, for the first user, a second time-width longer than the first time-width; and
setting the second time-width as a time-width for which the usage history of the first user is to be subsequently acquired, when a second interesting matter extracted within the second time-width is different from the first interest matter extracted within the first time-width and a result of the operation performed by the first user in response to provision of the help information obtained based on the second interesting matter meets a predetermined condition.

### Claim 11 (depends on 9)

The method of claim 9, further comprising:
determining, for the first user, a second user among the users whose usage history is similar to the usage history of the first user; and
setting, for the first user, a second time-width set for the second user, based on setting information on time-widths set for the respective users.

### Claim 12 (depends on 9)

The method of claim 9, further comprising:
calculating, based on the usage history, a degree of interest of each of a plurality of interesting matters for the first user; and
providing, as the help information, information obtained based on the degree of interest of each interesting matter to the first user.