# US 2022/0019630 A1 · Method and system for identifying clusters of affiliated web resources

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

- Number: US 2022/0019630 A1
- Document ID: US20220019630A1
- Status: Published application
- Kind: A1
- Application number: 16/937,233
- Filed: 2020-07-23
- Published: 2022-01-20
- Earliest claimed: 2020-07-15
- Assignees: Group-Ib Global Private Limited
- Applicants: Group-Ib Global Private Limited
- Inventors: Ilia ROZHNOV
- Web page: https://patentgrep.com/patent/US20220019630A1

## CPC

- G06F 16/954: Navigation, e.g. using categorised browsing
- H04L 63/1425: {Traffic logging, e.g. anomaly detection}
- G06F 16/9566: {URL specific, e.g. using aliases, detecting broken or misspelled links}
- G06F 16/958: Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
- G06F 17/18: for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)}
- H04L 63/0236: {Filtering by address, protocol, port number or service, e.g. IP-address or URL}
- H04L 63/1483: {service impersonation, e.g. phishing, pharming or web spoofing (detection of rogue wireless access points H04W12/12)}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

A method and a system for determining affiliation of a web resource to a plurality of clusters are provided. The method comprises: at a training stage: detecting a plurality of web resources; retrieving information associated with the plurality of web resources; generating a respective pattern based on the information; grouping the plurality of web resources into the plurality of clusters, based on the respective pattern; at a run-time stage: receiving an indication of a given web resource; retrieving the information about the given web resource; generating a new pattern of the given web resource; analyzing pattern affiliation of the new pattern with a specific one from the plurality of clusters of web resources; calculating an affiliation ratio therewith; in response to the affiliation ratio exceeding a predetermined threshold value, associating the given web resource with the specific one of the plurality of clusters.

## Claims

### Claim 1

A method of determining an affiliation of a web resource to a plurality of clusters of web resources, the method executable by a computing device having at least a processing unit and a memory, the memory storing computer executable instructions, which, when executed, cause the processing unit to execute:
at a training stage:
scanning a communication network to detect a plurality of web resources;
retrieving information associated with the plurality of web resources;
based on the information, for each one of the plurality of web resources, generating a respective pattern;
based on the respective pattern, grouping the plurality of web resources into a plurality of clusters, the grouping being based on a pattern affiliation between the respective patterns;
storing an indication of the plurality of clusters of web resources in the memory;
at a run-time stage:
receiving an indication of an URL to a given web resource;
retrieving the information about the given web resource;
generating a new pattern of the given web resource;
analyzing the pattern affiliation of the new pattern with the patterns associated with the plurality of clusters of the web resources;
calculating an affiliation ratio with a specific one of the plurality of clusters;
in response to the affiliation ratio with the specific one of the plurality of clusters exceeding a predetermined threshold value, associating the given web resource with the specific one of the plurality of clusters;
updating the plurality of clusters stored in the database based on the given web resource.

### Claim 2 (depends on 1)

The method of claim 1, wherein the respective pattern comprises a matrix of distinctive attributes associated with a respective one of the plurality of web resources identified via analyzing the information associated with the plurality of web resources.

### Claim 3 (depends on 2)

The method of claim 2, wherein the distinctive attributes associated with the respective one of the plurality of web resources comprise at least one of:
a size of at least one page block within at least one page associated with the respective one of the plurality of web resources;
a position of the at least one page block within the at least one page;
a title associated with the at least one page block;
region parameters associated with the at least one page;
at least one target domain associated with the at least one page, including at least one of: links placed within the at least one page and transition types associated therewith, the transition types further including at least one of: a direct transition type and a redirect transition type;
contact details;
path patterns to respective structural elements of the at least one page and styles associated therewith; and
names of the structural elements.

### Claim 4 (depends on 2)

The method of claim 2, wherein the information associated with the plurality of web resources includes, for a given web resource, at least one of: an URL of the given web resource; an HTML code associated with the given web resource; a screenshot of at least one web page associated with the given web resource page and a hash value thereof; a date of detecting the given web resource; and domain registration data associated with the given web resource, including: a registration date, a registrar, an owner name and contact details; an IP address; an NS server; a hosting provider; a last activity date.

### Claim 5 (depends on 2)

The method of claim 2, wherein the matrix of distinctive attributes contains at least one distinctive attribute associated with the respective one of the plurality of web resources.

### Claim 6 (depends on 2)

The method of claim 2, wherein each of the distinctive attributes has been selected based on a pre-determined parameter R, the pre-determined parameter being indicative of a maximum threshold value for a degree of distinctiveness of a given distinctive attribute for selection thereof for the respective pattern.

### Claim 7 (depends on 6)

The method of claim 6, wherein the degree of distinctiveness of the given distinctive attribute is determined based on the following inequality:
pi<R,
where p is a number of web resource within the plurality of web resources associated with the given distinctive attribute.

### Claim 8 (depends on 1)

The method of claim 1, wherein the calculating the affiliation ratio further comprises calculating a number of distinctive attributes associated with the given web resource that are similar to those associated with the specific one of the plurality of clusters.

### Claim 9 (depends on 1)

The method of claim 1, wherein the analyzing the pattern affiliation of the new pattern with the patterns associated with the plurality clusters further comprises applying a cross-correlation technique.

### Claim 10

A system for determining an affiliation of a web resource to a plurality of clusters of web resources, the system comprising a computing device, the computing device further comprising:
a processor;
a non-transitory computer-readable medium comprising instructions;
the processor, upon executing the instructions, being configured to:
at a training stage:
scan a communication network to detect a plurality of web resources;
retrieve information associated with the plurality of web resources;
based on the information, for each one of the plurality of web resources, generate a respective pattern;
based on the respective pattern, group the plurality of web resources into the plurality of clusters, the grouping being based on a pattern affiliation between the respective patterns;
store an indication of the plurality of clusters of web resources in the memory;
at a run-time stage:
receive an indication of an URL to a given web resource;
retrieve the information about the given web resource;
generate a new pattern of the given web resource;
analyze the pattern affiliation of the new pattern with the patterns associated with the plurality of clusters of web resources;
calculate an affiliation ratio with a specific one of the plurality of clusters;
in response to the affiliation ratio with the specific one of the plurality of clusters exceeding a predetermined threshold value, associate the given web resource with the specific one of the plurality of clusters;
update the plurality of clusters stored in the database based on the given web resource.
