# US 2019/0173917 A1 · Systems and methods for serving module

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

- Number: US 2019/0173917 A1
- Document ID: US20190173917A1
- Status: Published application
- Kind: A1
- Application number: 15/829,737
- Filed: 2017-12-01
- Published: 2019-06-06
- Earliest claimed: 2017-12-01
- Assignees: KnowBe4, Inc.
- Applicants: KnowBe4, Inc.
- Inventors: Eric Sites
- Web page: https://patentgrep.com/patent/US20190173917A1

## CPC

- G06V 10/82: using neural networks
- G06F 18/23: Clustering techniques
- G06F 18/24: Classification techniques
- G06F 21/552: {involving long-term monitoring or reporting}
- G06F 21/577: {Assessing vulnerabilities and evaluating computer system security}
- G06N 3/0499: Feedforward networks
- G06N 3/082: modifying the architecture, e.g. adding, deleting or silencing nodes or connections
- G06N 3/09: Supervised learning
- G06V 10/762: using clustering, e.g. of similar faces in social networks
- H04L 63/1433: {Vulnerability analysis}
- H04L 63/1483: {service impersonation, e.g. phishing, pharming or web spoofing (detection of rogue wireless access points H04W12/12)}
- H04L 67/535: {Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34)}
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

Systems and methods are described for selecting a model for a simulated phishing campaign for a user based on classifying a user into a cluster of a plurality of clusters. A campaign controller may initiate a simulated phishing campaign for a user. In some examples, while initiating the simulated phishing campaign the campaign controller identifies a plurality of attributes of the user and/or a plurality of attributes of a company of the user, and sends the plurality of attributes to a serving module of the campaign controller. The serving module receives historical information on activity associated with the user during previous simulated phishing campaigns. The serving module uses the historical information as input into one or more clustering models and using the model, classifies the user into a cluster which contains users that are responsive to one or more specific models.

## Claims

### Claim 1

A method comprising:
(a) initiating, by a campaign controller, a simulated phishing campaign for a user of a plurality of users;
(b) receiving, by a serving module logic, a simulated phishing campaign history of the user, the simulated phishing campaign history comprising information on activity associated with the user during one or more previous simulated phishing campaigns;
(c) classifying, by the serving module logic using the simulated phishing campaign history as input into one or more clustering models for clustering a plurality of users into at least one of a plurality of clusters identified as output from the one or more clustering models, the user into a cluster of the plurality of clusters, each cluster of the plurality of clusters identifying the plurality of users that are responsive to a specific one or more simulated phishing campaign models of the plurality of simulated phishing campaign models for executing the simulated phishing campaign;
(d) determining, by the serving module logic based at least on the cluster of the user, a simulated phishing campaign model from the plurality of simulated phishing campaign models for the simulated phishing campaign; and
(e) executing, by the campaign controller responsive to the serving module, the simulated phishing campaign using the simulated phishing campaign model.

### Claim 2 (depends on 1)

The method of claim 1, wherein (a) further comprises identifying, by the campaign controller, a plurality of attributes of the user.

### Claim 3 (depends on 2)

The method of claim 2, wherein (b) further comprises receiving, by the serving module logic, the plurality of attributes of the user.

### Claim 4 (depends on 3)

The method of claim 3, wherein (c) further comprises classifying, by the serving module logic using the simulated phishing campaign history and the plurality of attributes of the user as input into the one or more clustering models, the user into the cluster.

### Claim 5 (depends on 1)

The method of claim 1, wherein (a) further comprises identifying, by the campaign controller, a plurality of attributes of a company of the user.

### Claim 6 (depends on 5)

The method of claim 5, wherein (b) further comprises receiving, by the serving module logic, the plurality of attributes of the company of the user.

### Claim 7 (depends on 6)

The method of claim 6, wherein (c) further comprises classifying, by the serving module logic using the simulated phishing campaign history and the plurality of attributes of the company of the user as input into the one or more clustering models, the user into the cluster.

### Claim 8 (depends on 1)

The method of claim 1, wherein (d) further comprises determining, by the serving module logic based at least on the classification, a template from a plurality of templates.

### Claim 9 (depends on 1)

The method of claim 1, wherein (d) further comprises determining, by the serving module logic based at least on the classification, one of a frequency and timing for the simulated phishing campaign.

### Claim 10 (depends on 1)

The method of claim 1, wherein (d) further comprises receiving, by the campaign controller, data from the serving module to use by the campaign controller in executing the simulated phishing campaign.

### Claim 11 (depends on 10)

The method of claim 10, wherein the data comprises one or more of the following: back off time to use between simulated phishing communications, detail pages for a template for the model, wording to be used in simulated phishing communications.

### Claim 12 (depends on 1)

The method of claim 1, further comprising receiving, by the serving module logic, a response from the user to a simulated phishing communication, determining a next action to perform for the user based at least on the response and providing the next action to the campaign controller.

### Claim 13 (depends on 1)

The method of claim 1, further comprising receiving, by the serving module logic, a response from the user to a simulated phishing communication, changing one of an order, a type or content of a next simulated phishing communication in a template based at least on the response and providing the next action to the campaign controller.

### Claim 14 (depends on 1)

The method of claim 1, wherein (e) further comprises managing, by the serving module logic, the simulated phishing campaign model loaded in memory by the serving module.

### Claim 15 (depends on 1)

The method of claim 1, wherein (e) further comprising communicating, by the serving module logic, to the campaign controller information on executing the simulated phishing campaign to the user based at least on the simulated phishing campaign model.

### Claim 16

A system comprising:
a campaign controller, executable on one or more processors, coupled to memory and configured to initiate a simulated phishing campaign for a user;
a serving module logic, executable on the one or more processors and configured to receive a simulated phishing campaign history of the user, the simulated phishing campaign history comprising information on activity associated with the user during one or more previous simulated phishing campaigns;
wherein the serving module logic is configured to:
classify, using the simulated phishing campaign history as input into one or more clustering models for clustering a plurality of users into at least one of a plurality of clusters identified as output from the one or more clustering models, the user into a cluster of the plurality of clusters, each cluster of the plurality of clusters identifying users that are responsive to specific one or more simulated phishing campaign models of the plurality of simulated phishing campaign models for executing the simulated phishing campaign;
determine, based at least on the cluster of the user, a simulated phishing campaign model from the plurality of simulated phishing campaign models for the simulated phishing campaign; and
wherein the campaign controller is configured to execute, responsive to the serving module, the simulated phishing campaign using the simulated phishing campaign model.

### Claim 17 (depends on 16)

The system of claim 16, wherein the campaign controller is further configured to identify a plurality of attributes of the user.

### Claim 18 (depends on 17)

The system of claim 17, wherein the serving module logic is further configured to receive the plurality of attributes of the user.

### Claim 19 (depends on 18)

The system of claim 18, wherein the serving module logic is further configured to classify using the simulated phishing campaign history and the plurality of attributes the user as input into the one or more clustering models, the user into the cluster.

### Claim 20 (depends on 16)

The system of claim 16, wherein the campaign controller is further configured to identify a plurality of attributes of a company of the user.

### Claim 21 (depends on 20)

The system of claim 20, wherein the serving module logic is further configured to receive the plurality of attributes of the company of the user.

### Claim 22 (depends on 21)

The system of claim 21, wherein the serving module logic is further configured to classify, using the simulated phishing campaign history and the plurality of attributes of the company of the user as input into the one or more clustering models, the user into the cluster.

### Claim 23 (depends on 16)

The system of claim 16, wherein the serving module logic is further configured to determine, based at least on the classification, a template from a plurality of templates.

### Claim 24 (depends on 16)

The system of claim 16, wherein the serving module logic is further configured to determine, based at least on the classification, one of a frequency and timing for the simulated phishing campaign.

### Claim 25 (depends on 16)

The system of claim 16, wherein the campaign controller is further configured to receive data from the serving module to use by the campaign controller in executing the simulated phishing campaign.

### Claim 26 (depends on 25)

The system of claim 25, wherein the data comprises one or more of the following: back off time to use between simulated phishing communications, detail pages for a template for the simulated phishing campaign model, wording to be used in simulated phishing communications.

### Claim 27 (depends on 16)

The system of claim 16, wherein the serving module logic is further configured to receive a response from the user to a simulated phishing communication, determine a next action to perform for the user based at least on the response and provide the next action to the campaign controller.

### Claim 28 (depends on 16)

The system of claim 16, wherein the serving module logic is further configured to receive a response from the user to a simulated phishing communication, change one of an order, a type or content of a next simulated phishing communication in a template based at least on the response and provide the next action to the campaign controller.

### Claim 29 (depends on 16)

The system of claim 16, wherein the serving module logic is further configured to manage the simulated phishing campaign model loaded in memory by the serving module.

### Claim 30 (depends on 16)

The system of claim 16, wherein the serving module logic is further configured to communicate to the campaign controller information on executing the simulated phishing campaign to the user based at least on the simulated phishing campaign model.
