# US 2021/0084008 A1 · Fully qualified domain name (fqdn) determination

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

- Number: US 2021/0084008 A1
- Document ID: US20210084008A1
- Status: Published application
- Kind: A1
- Application number: 17/010,472
- Filed: 2020-09-02
- Published: 2021-03-18
- Earliest claimed: 2019-09-04
- Assignees: Cujo LLC
- Applicants: Cujo LLC
- Inventors: Leonid Kuperman; Santeri Kangas
- Web page: https://patentgrep.com/patent/US20210084008A1

## CPC

- H04L 61/3015: Name registration, generation or assignment
- H04L 63/04: {for providing a confidential data exchange among entities communicating through data packet networks}
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/00: Machine learning
- H04L 61/4511: using domain name system [DNS]
- H04L 63/1408: {by monitoring network traffic (monitoring network traffic per se H04L43/00)}
- H04L 61/5007: Internet protocol [IP] addresses
- H04L 67/02: based on web technology, e.g. hypertext transfer protocol [HTTP]
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Fully qualified domain name determination is disclosed. A queue of fully qualified domain names (FQDN) is created using a predetermined amount of network domains. Each FQDN is crawled from a plurality of collection agents of a computer network. For each FQDN, data comprising an Internet Protocol (IP) address of the FQDN, IP addresses for resources loaded for the FQDN and load times of the resources loaded for the FQDN are extracted. A correlation model is generated based on the data. An FQDN being accessed by one or more computer devices of the computer network is determined by using the correlation model.

## Claims

### Claim 1

A method comprising:
creating a queue of fully qualified domain names (FQDN) using a predetermined amount of network domains;
crawling each FQDN from a plurality of collection agents of a computer network;
extracting, for each FQDN, data comprising an Internet Protocol (IP) address of the FQDN, IP addresses for resources loaded for the FQDN and load times of the resources loaded for the FQDN;
generating a correlation model based on the data; and
determining an FQDN being accessed by one or more computer devices of the computer network by using the correlation model.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the plurality of collection agents of the computer network reside in multiple physical locations globally.

### Claim 3 (depends on 1)

The method according to claim 1, wherein the plurality of collection agents of the computer network are configured to use a plurality of web browser software technologies to extract the data related to each FQDN.

### Claim 4 (depends on 3)

The method according to claim 3, further comprising storing data of the web browser software technologies used by the plurality of collection agents and a location of each collection agent, and the step of generating the correlation model is further based on the data of the web browser software technologies used by the plurality of collection agents and the location of each collection agent.

### Claim 5 (depends on 1)

The method according to claim 1, further comprising providing the data to a central database.

### Claim 6 (depends on 1)

The method according to claim 1, wherein generating the correlation model further comprises:
determining a main uniform resource locator (URL) being requested for each IP address based on the load times of the resources loaded for each FQDN;
determining all possible FQDNs mapped to each IP address determined as the main URL; and
using a statistical model or a machine learning model to determine a closest correlation between possible FQDNs and the main URL based on the IP addresses for the resources loaded and the load times of the resources for each possible FQDN.

### Claim 7 (depends on 1)

The method according to claim 1, further comprising extracting geolocation data of the one or more computer devices, and the step of generating the correlation model is further based on the geolocation data of the one or more computer devices.

### Claim 8 (depends on 1)

The method according to claim 1, wherein generating the correlation model further comprises analyzing an order of the resources loaded for the FQDN based on the load times of the resources loaded for the FQDN.

### Claim 9 (depends on 1)

The method according to claim 1, further comprising extracting, for each FQDN, data relating to a number of downloaded bytes of the resources loaded, and using the number of downloaded bytes for generating the correlation model, wherein determining the FQDN being accessed is further based on analyzing the number of downloaded bytes.

### Claim 10 (depends on 1)

The method according to claim 1, wherein the data further comprises data of a number of webpage loads, a number of downloaded bytes for each webpage load, and an order of the webpage loads.

### Claim 11 (depends on 1)

The method according to claim 1, further comprising: testing accuracy of the correlation model by comparing an FQDN determined by using a server name indication (SNI) information of the FQDN being accessed with the FQDN determined by using the correlation model; and adjusting the correlation model based on the testing.

### Claim 12 (depends on 1)

The method according to claim 1, further comprising taking further action to protect the one or more computer devices from a possible security threat caused by the FQDN being accessed by the one or more computer devices.

### Claim 13 (depends on 12)

The method according to claim 12, wherein taking further action to protect the one or more computer devices comprises one or more of: blocking or preventing access to the FQDN determined by using the correlation model, providing security, parental control, or privacy protection measures based on the FQDN determined by using the correlation model.

### Claim 14

An apparatus in a computer network system comprising:
one or more processors; and
a non-transitory computer-readable medium comprising stored program code, the program code comprising computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to:
create a queue of fully qualified domain names (FQDN) using a predetermined amount of network domains;
crawl each FQDN from a plurality of collection agents of a computer network;
extract, for each FQDN, data comprising an Internet Protocol (IP) address of the FQDN, IP addresses for resources loaded for the FQDN and load times of the resources loaded for the FQDN;
generate a correlation model based on the data; and
determine an FQDN being accessed by one or more computer devices of the computer network by using the correlation model.

### Claim 15 (depends on 14)

The apparatus according to claim 14, wherein the plurality of collection agents of the computer network reside in multiple physical location globally and are configured to use a plurality of web browser software technologies to extract the data related to each FQDN.

### Claim 16 (depends on 14)

The apparatus according to claim 14, wherein the instructions further cause the one or more processors to: determine a main uniform resource locator (URL) being requested for each IP address based on the load times of the resources loaded for each FQDN; determine all possible FQDNs mapped to each IP address determined as the main URL; and use a statistical model or a machine learning model to determine a closest correlation between the possible FQDNs and the main URL based on the IP addresses for the resources loaded and the load times of the resources for each possible FQDN.

### Claim 17 (depends on 14)

The apparatus according to claim 14, wherein the data further comprises one or more of: data of a number of webpage loads, a number of downloaded bytes for each webpage load, an order of the webpage loads, and geolocation data of the one or more computer devices.

### Claim 18 (depends on 14)

The apparatus according to claim 14, wherein the instructions further cause the one or more processors to extract, for each FQDN, data relating to a number of downloaded bytes of the resources loaded, and to use the number of downloaded bytes for generating the correlation model, and wherein determining the FQDN being accessed is further based on analyzing the number of downloaded bytes.

### Claim 19 (depends on 14)

The apparatus according to claim 14, wherein the instructions further cause the one or more processors to: test accuracy of the correlation model by comparing an FQDN determined using a server name indication (SNI) information with the FQDN determined on the basis of the generated correlation model; and to adjust the correlation model based on the testing.

### Claim 20

A non-transitory computer-readable medium comprising stored program code, the program code comprised of computer-executable instructions that, when executed by a processor, cause the processor to:
create a queue of fully qualified domain names (FQDN) using a predetermined amount of network domains;
crawl each FQDN from a plurality of collection agents of a computer network;
extract, for each FQDN, data comprising an Internet Protocol (IP) address of the FQDN, IP addresses for resources loaded for the FQDN and load times of the resources loaded for the FQDN;
generate a correlation model based on the data; and
determine an FQDN being accessed by one or more computer devices of the computer network by using the correlation model.
