# US 2015/0178337 A1 · Predictive Service Access

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

- Number: US 2015/0178337 A1
- Document ID: US20150178337A1
- Status: Published application
- Kind: A1
- Application number: 14/379,624
- Filed: 2012-02-22
- Published: 2015-06-25
- Earliest claimed: 2012-02-22
- Assignees: Nokia Corporation
- Inventors: Minna Hellstrom; Mikko Lonnfors; Eki Monni; Istvan Beszteri; Mikko Terho
- Web page: https://patentgrep.com/patent/US20150178337A1

## CPC

- G06F 16/2237: {Vectors, bitmaps or matrices}
- G06F 16/9535: Search customisation based on user profiles and personalisation
- G06F 16/957: Browsing optimisation, e.g. caching or content distillation
- G06N 5/00: Computing arrangements using knowledge-based models
- G06Q 10/10: Office automation; Time management
- G06Q 30/02: Marketing; Price estimation or determination; Fundraising
- 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

The invention relates to predictive browsing. A set of words for use with an experience matrix are formed, wherein the words are descriptive of a context of a system such as a current web page, and wherein said experience matrix comprises sparse vectors associated with words. At least a part of at least one sparse vector of said experience matrix is accessed to form a prediction output, and suggestions of web pages are provided to a user in response to said prediction output.

## Claims

### Claim at position 1

1-59. (canceled)

### Claim 60

A method, comprising:
forming a set of words for use with an experience matrix, wherein the words are descriptive of a context of a system such as a current web page, and wherein said experience matrix comprises sparse vectors associated with words,
accessing at least a part of at least one sparse vector of said experience matrix to form a prediction output, and
providing suggestions of web pages to a user in response to said prediction output.

### Claim 61 (depends on 60)

A method according to claim 60, comprising:
forming an input buffer for collecting words for updating said experience matrix.

### Claim 62 (depends on 60)

A method according to claim 60, comprising:
forming said prediction output based on web browser activity.

### Claim 63 (depends on 60)

A method according to claim 60, comprising:
forming said prediction output based on a page load completion.

### Claim 64 (depends on 60)

A method according to claim 60, comprising:
forming said prediction output in the background.

### Claim 65 (depends on 60)

A method according to claim 60, comprising:
updating said experience matrix based on web browser activity.

### Claim 66 (depends on 60)

A method according to claim 60, comprising:
forming a prediction list comprising images or text of web pages, and
updating said prediction list based on web browser activity.

### Claim 67

An apparatus comprising at least one processor, at least one memory including computer program code for one or more program units, the at least one memory and the computer program code configured to, with the processor, cause the apparatus to perform at least the following:
form a set of words for use with an experience matrix, wherein the words are descriptive of a context of a system such as a current web page, and wherein said experience matrix comprises sparse vectors associated with words,
access at least a part of at least one sparse vector of said experience matrix to form a prediction output, and
provide suggestions of web pages to a user in response to said prediction output.

### Claim 68 (depends on 67)

An apparatus according to claim 67, further comprising computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following:
form an input buffer for collecting words for updating said experience matrix.

### Claim 69 (depends on 67)

An apparatus according to claim 67, further comprising computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following:
form said prediction output based on web browser activity.

### Claim 70 (depends on 67)

An apparatus according to claim 67, further comprising computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following:
form said prediction output based on a page load completion.

### Claim 71 (depends on 67)

An apparatus according to claim 67, further comprising computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following:
form said prediction output in the background.

### Claim 72 (depends on 67)

An apparatus according to claim 67, further comprising computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following:
update said experience matrix based on web browser activity.

### Claim 73 (depends on 67)

An apparatus according to claim 67, further comprising computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following:
form a prediction list comprising images or text of web pages, and
update said prediction list based on web browser activity.

### Claim 74

A computer program product including one or more sequences of one or more instructions which, when executed by one or more processors, cause a system to perform at least the following:
form a set of words for use with an experience matrix, wherein the words are descriptive of a context of a system such as a current web page, and wherein said experience matrix comprises sparse vectors associated with words,
access at least a part of at least one sparse vector of said experience matrix to form a prediction output, and
provide suggestions of web pages to a user in response to said prediction output.

### Claim 75 (depends on 74)

A computer program product according to claim 74, wherein the computer-executable program code portion further comprise program code instructions configured to:
form an input buffer for collecting words for updating said experience matrix.

### Claim 76 (depends on 74)

A computer program product according to claim 74, wherein the computer-executable program code portion further comprise program code instructions configured to:
form said prediction output based on web browser activity.

### Claim 77 (depends on 74)

A computer program product according to claim 74, wherein the computer-executable program code portion further comprise program code instructions configured to:
form said prediction output based on a page load completion.

### Claim 78 (depends on 74)

A computer program product according to claim 74, wherein the computer-executable program code portion further comprise program code instructions configured to:
form said prediction output in the background.

### Claim 79 (depends on 74)

A computer program product according to claim 74, wherein the computer-executable program code portion further comprise program code instructions configured to:
update said experience matrix based on web browser activity.
