# US 2017/0257452 A1 · Systems and methods for data caching in a communications network

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

- Number: US 2017/0257452 A1
- Document ID: US20170257452A1
- Status: Published application
- Kind: A1
- Application number: 15/059,013
- Filed: 2016-03-02
- Published: 2017-09-07
- Earliest claimed: 2016-03-02
- Assignees: Huawei Technologies Canada Co., Ltd.
- Inventors: William August HOILES; Omid NAMVAR GHAREHSHIRAN; Vikram KRISHNAMURTHY; Ngoc-Dung DAO
- Web page: https://patentgrep.com/patent/US20170257452A1

## CPC

- H04L 67/568: Storing data temporarily at an intermediate stage, e.g. caching
- G06F 12/0813: with a network or matrix configuration
- G06N 3/0499: Feedforward networks
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06F 2212/1032: Reliability improvement, data loss prevention, degraded operation etc
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method for managing a cache memory network is disclosed. The method comprises estimating the popularity of a piece of data content according to an extreme learning machine, and managing the cache memory network according to the estimated popularity of the piece of data content. Estimation may be performed upon a request for the piece of data content, and may be accordingly cashed into an appropriate cache memory device upon estimation of its popularity.

## Claims

### Claim 1

A method for managing a cache memory network comprising:
estimating the popularity of a piece of data content according to operation of an extreme learning machine; and
managing the cache memory network according to the estimated popularity of the piece of data content.

### Claim 2 (depends on 1)

The method of claim 1 wherein the cache memory network comprises a first register for indexing relatively popular data content, wherein when the piece of data content is estimated to be popular, managing the cache memory comprises moving a reference to the piece of data content to the first register.

### Claim 3 (depends on 1)

The method of claim 1 wherein the cache memory network comprises a second register for indexing relatively unpopular data content, wherein when the piece of data content is estimated to be unpopular, managing the cache memory comprises providing a reference to the piece of data content to the second register.

### Claim 4 (depends on 1)

The method of claim 1 wherein the cache memory network comprises a third register for indexing data content in the cache memory network, wherein when the piece of data content is estimated to be unpopular, managing the cache memory comprises deleting a reference to the piece of data content from the third register.

### Claim 5 (depends on 1)

The method of claim 1 wherein the cache memory network comprises a first cache location relatively farther from a user device, and a second cache location relatively closer to the user device, wherein when the piece of data content is estimated to be popular, managing the cache memory comprises caching the piece of data content in the second cache location.

### Claim 6 (depends on 1)

The method of claim 1 wherein the cache memory network comprises a first cache location relatively farther from a user device, and a second cache location relatively closer to the user device, wherein when the piece of data content is estimated to be unpopular, managing the cache memory comprises caching the piece of data content in the first cache location.

### Claim 7 (depends on 1)

The method of claim 1 wherein the piece of data content is stored within a cache location of the cache memory network, wherein when the piece of data content is estimated to be unpopular, managing the cache memory comprises deleting the piece of data content from the cache location.

### Claim 8 (depends on 1)

The method of claim 1 wherein operation of the extreme learning machine comprises the steps of:
collecting metadata associated with piece of data content;
computing the collected metadata;
selecting one or more features from the computed metadata; and
training the extreme learning machine according to selected one or more features,
wherein the popularity of a piece of data content is estimated according to the trained extreme learning machine.

### Claim 9 (depends on 8)

The method of claim 8 wherein the step of selecting one or more features is performed according to a feature selection algorithm.

### Claim 10 (depends on 9)

The method of claim 9 wherein the feature selection algorithm comprises a sequential wrapper feature selection algorithm, or a stochastic gradient algorithm.

### Claim 11 (depends on 1)

The method of claim 1 wherein the popularity of the piece of data content is estimated in response to a request for the piece of data content from a user device.

### Claim 12

A management device for managing a cache memory network, the management device comprising:
a processor;
an output interface coupled to the processor, the output interface for communicatively coupling to the cache memory network; and
a memory coupled to the processor and having stored thereon machine readable code which when executed by the processor estimates the popularity of a piece of data content according to operation of an extreme learning machine, and manages the cache memory network according to the estimated popularity of the piece of data content through the output interface.

### Claim 13 (depends on 12)

The management device of claim 12 further comprising a first register for indexing relatively popular data content, wherein when the piece of data content is estimated to be popular, the management device provides a reference to the piece of data content to the first register.

### Claim 14 (depends on 12)

The management device of claim 12 further comprising a second register for indexing relatively unpopular data content, wherein when the piece of data content is estimated to be unpopular, the management device provides a reference to the piece of data content to the second register.

### Claim 15 (depends on 12)

The management device of claim 12 further comprising a third register for indexing data content in the cache memory network, wherein when the piece of data content is estimated to be unpopular, the management device deletes a reference to the piece of data content from the third register.

### Claim 16 (depends on 12)

The management device of claim 12, wherein when the piece of data content is estimated to be popular, the management device is configured to cache the piece of data content in a second cache location of the cache memory network that is relatively closer to a user device than a first cache location of the cache memory network.

### Claim 17 (depends on 12)

The management device of claim 12, wherein when the piece of data content is estimated to be unpopular, the management device is configured to cache the piece of data content in a first cache location of the cache memory network that is relatively farther from a user device than a second cache location of the cache memory network.

### Claim 18 (depends on 12)

The management device of claim 12, wherein when the piece of data content is estimated to be unpopular, the management device is configured to delete the piece of data content from the cache memory network.

### Claim 19 (depends on 12)

The management device of claim 12 wherein operation of the extreme learning machine comprises the steps of:
collecting metadata associated with piece of data content;
computing the collected metadata;
selecting one or more features from the computed metadata; and
training the extreme learning machine according to selected one or more features,
wherein the popularity of the piece of data content is estimated according to the trained extreme learning machine.

### Claim 20

A computer readable memory having recorded thereon statements and instructions for execution by a computer, the statements and instructions comprising:
estimating the popularity of a piece of data content according to operation of an extreme learning machine; and
managing a cache memory network according to the estimated popularity of the piece of data content.
