# US 12,120,004 B2 · Methods and apparatus to determine main pages from network traffic

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

- Number: US 12,120,004 B2
- Document ID: US12120004B2
- Status: Granted
- Kind: B2
- Application number: 18/166,900
- Filed: 2023-02-09
- Published: 2023-06-15
- Granted: 2024-10-15
- Earliest claimed: 2021-06-30
- Assignees: The Nielsen Company (US), LLC
- Applicants: The Nielsen Company (US), LLC
- Inventors: Achilleas Papakostas; Travis Berthelot; Andrey Shapovalov; Jaimin Patel; Brendan Phillips
- Web page: https://patentgrep.com/patent/US12120004B2

## CPC

- H04L 43/04: Processing captured monitoring data, e.g. for logfile generation
- H04L 43/062: related to network traffic
- G06F 16/9566: {URL specific, e.g. using aliases, detecting broken or misspelled links}
- H04L 43/028: by filtering
- H04L 43/045: for graphical visualisation of monitoring data
- H04L 63/0272: {Virtual private networks}
- H04L 41/16: using machine learning or artificial intelligence
- H04L 43/16: Threshold monitoring
- 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)

## Abstract

Methods and apparatus to determine main pages from network traffic are disclosed. A disclosed example non-transitory computer readable medium includes instructions which, when executed, cause at least one processor to determine patterns of uniform resource identifiers (URIs) with corresponding main pages, parse data from network traffic, identify at least one of the main pages from the data based on the patterns, and provide the identified at least one of the main pages for crediting thereof.

## Claims

### Claim 1

An audience measurement computing system comprising:
a media device; and
one or more comprising a first network interface and configured to:
access main pages via the first network interface;
collect, via the first network interface, first network traffic data associated with the access to the main pages;
based on the collected first network data, identify, for each accessed main page, a pattern of requested uniform resource identifiers (URIs) corresponding to response times of the requested URIs:
generate training data comprising the patterns; and
transmit the training data to the media device via the first network interface, wherein the media device comprises a second network interface and is configured to:
collect, via the second network interface, second network traffic data associated with access to at least one of the main pages;
identify a set of URIs from the second network traffic data; and
detect the at least one of the main pages based on a comparison of the set of URIs with the patterns of the training received from the one or more servers.

### Claim 2 (depends on 1)

The audience measurement computing system of claim 1, wherein the one or more servers are configured to identify the pattern based on numbers of occurrences of the requested URIs.

### Claim 3 (depends on 2)

The audience measurement computing system of claim 2, wherein the occurrences are associated with corresponding GET URI functions.

### Claim 4 (depends on 1)

The audience measurement computing system of claim 1, wherein the media device is further configured to discard the set of URIs identified in the second network traffic data from a storage based on a detection of the at least one of the main pages.

### Claim 5 (depends on 1)

The audience measurement computing system of claim 1, wherein collecting the second network traffic data via the second network interface comprises receiving the second network traffic data via the second network interface from a virtual private network (VPN), wherein the VPN is configured to record the second network traffic data.

### Claim 6 (depends on 1)

The audience measurement computing system of claim 1, wherein the media device is further configured to request additional training data when the at least one of the main pages cannot be detected.

### Claim 7 (depends on 1)

The audience measurement computing system of claim 1, wherein detecting the at least one of the main pages comprises detecting the at least one of the main pages based on a ratio of a sum of attempts of the set of URIs to a total number of occurrences of the set of URIs.

### Claim 8 (depends on 1)

The audience measurement computing system of claim 1, wherein detecting the at least one of the main pages comprises detecting the at least one of the main pages based on an order of responses of the set of URIs.

### Claim 9

A non-transitory computer readable medium comprising instructions that, when executed, cause an audience measurement computing system to perform operations comprising:
accessing, by one or more servers and via a first network interface of the one or more servers, main pages:
collecting, by the one or more servers and via the first network interface, first network traffic data associated with the access to the main pages;
based on the collected first network traffic data, identifying by the one or more servers, for each accessed main page, a pattern requested uniform resource identifiers (URIs) corresponding to response times of the requested URIs;
generating, by the one or more servers, training data comprising the patterns;
transmitting, by the one or more servers, the training data to a media device via the first network interface;
collecting, by the media device via a second network interface of the media device, second network traffic data associated with access to at least one of the main pages;
identifying, by th media device, a set of URIs from the second network traffic data; and
detecting, by the media device, the at least one of the main pages based on a comparison of the set of URIs with the patterns of the training dat received from the one or more servers.

### Claim 10 (depends on 9)

The non-transitory computer readable medium of claim 9, wherein
identifying the pattern comprises identifying the pattern based on numbers of occurrences of the requested URIs.

### Claim 11 (depends on 10)

The non-transitory computer readable medium a of claim 10, wherein the occurrences are associated with corresponding GET URI functions.

### Claim 12 (depends on 9)

The non-transitory computer readable medium of claim 9, the operations further comprising
discarding, by the media device, the set of URIs identified in the second network traffic data from a storage based on a detection of the at least one of the main pages.

### Claim 13 (depends on 9)

The non-transitory computer readable medium of claim 9, wherein collecting the second network traffic data via the second network interface comprises receiving the second network traffic data via the second network interface from a virtual private network (VPN), wherein the VPN is configured to record the second network traffic data.

### Claim 14 (depends on 9)

The non-transitory computer readable medium of claim 9, the operations further comprising:
requesting, by the media device, additional training data when the at least one of the main pages cannot be identified.

### Claim 15 (depends on 9)

The non-transitory computer readable medium of claim 9, wherein detecting the at least one of the main pages comprises detecting the at least one of the main pages based on a ratio of a sum of attempts of the set of URIs with to a total number of occurrences of the set of URIs.

### Claim 16 (depends on 9)

The non-transitory computer readable medium of claim 9, wherein detecting the at least one of the main pages comprises detecting the at least one of the main pages based on an order of responses of the set of URIs.

### Claim 17 (depends on 9)

The non-transitory computer readable medium of claim 9, wherein identifying the patterns comprises identifying the patterns using a machine learning model.

### Claim 18

A method performed by an audience measurement computing system comprising one or more servers and a media device, the method comprising:
accessing, by the one more servers and via a first network interface of the one or more servers, main pages:
collecting, by the one or more servers and via the first network interface, first network traffic data associated with the access to the main pages;
based on the collected first network traffic data, identifying, by the one or more servers, for each accessed main page, a pattern of requested uniform resource identifiers (URIs) corresponding to response times of the requested URIs:
generating, by the one or more servers, training data comprising the patterns;
transmitting, by the one or more servers, the training data to the media device via the first network interface;
collecting, by the media device via a second network interface of the media device, second network traffic data associated with access to at least one of the main pages;
identifying, by the media device, a set of URIs from the second network traffic data; and
detecting, by the media device, the at least one of the main pages based on a comparison of the set of URIs with the patterns of the training data received from the one or more servers.

### Claim 19 (depends on 18)

The method of claim 18, wherein identifying the pattern comprises identifying the pattern based on numbers of occurrences of the requested URIs.

### Claim 20 (depends on 19)

The method of claim 19, wherein the occurrences are associated with corresponding GET URI functions.

### Claim 21 (depends on 18)

The method of claim 18, further comprising:
discarding, by the media device, the set of URIs identified in the second network traffic data from a storage based on a detection of the at least one of the main pages.

### Claim 22 (depends on 18)

The method of claim 18, wherein collecting the second network traffic data via the second network interface comprises receiving the second network traffic data via the second network interface from a virtual private network (VPN), wherein the VPN is configured to record the second network traffic data.

### Claim 23 (depends on 18)

The method of claim 18, further comprising:
requesting, by the media device, additional training data when the at least one of the main pages cannot be identified.

### Claim 24 (depends on 18)

The method of claim 18, wherein detecting the at least one of the main pages comprises detecting the at least one of the main pages based on a ratio of a sum of attempts of set of URIs to a total number of occurrences of the set of URIs.

### Claim 25 (depends on 18)

The method of claim 18, wherein detecting the at least one of the main pages comprises detecting the at least one of the main pages based on an order of responses of the set of URIs.