# US 2025/0168068 A1 · Systems and methods for identifying confidence measures of network rules

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

- Number: US 2025/0168068 A1
- Document ID: US20250168068A1
- Status: Published application
- Kind: A1
- Application number: 18/612,884
- Filed: 2024-03-21
- Published: 2025-05-22
- Earliest claimed: 2023-11-20
- Assignees: Aetna Inc.
- Applicants: Aetna Inc.
- Inventors: Andrew Hinton; Salil Jain; Christopher Durand
- Web page: https://patentgrep.com/patent/US20250168068A1

## CPC

- H04L 63/0263: {Rule management}
- H04L 41/0823: characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability (for optimising operational conditions of wireless networks H04W24/02)
- H04L 43/062: related to network traffic
- H04L 45/42: Centralised routing
- H04L 45/74: Address processing for routing
- H04L 47/12: Avoiding congestion; Recovering from congestion
- H04L 47/781: {Centralised allocation of resources}
- H04L 47/801: {Real time traffic}
- H04L 61/301: Name conversion
- H04L 63/0236: {Filtering by address, protocol, port number or service, e.g. IP-address or URL}
- H04L 63/1425: {Traffic logging, e.g. anomaly detection}
- H04L 63/20: {for managing network security; network security policies in general (filtering policies H04L63/0227)}
- H04L 2101/618: Details of network addresses
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

In some instances, a method for generating network traffic rules for a cloud environment is provided. The method comprises: converting a plurality of internet protocol (IP) addresses from a plurality of network traffic rules into a plurality of integer pair representations of the IP addresses; determining a plurality of similarity values based on the plurality of integer pair representations of the IP addresses and a similarity algorithm; determining stability of one or more of the plurality of network traffic rules based on the plurality of similarity values and one or more thresholds; and applying the one or more of the plurality of network traffic rules that are determined to be stable.

## Claims

### Claim 1

A method for generating network traffic rules for a cloud environment, comprising:
converting a plurality of internet protocol (IP) addresses from a plurality of network traffic rules into a plurality of integer pair representations of the IP addresses;
determining a plurality of similarity values based on the plurality of integer pair representations of the IP addresses and a similarity algorithm;
determining stability of one or more of the plurality of network traffic rules based on the plurality of similarity values and one or more thresholds; and
applying the one or more of the plurality of network traffic rules that are determined to be stable.

### Claim 2 (depends on 1)

The method of claim 1, wherein each of the plurality of IP addresses comprises four octets, and wherein converting the plurality of IP addresses into the plurality of integer pair representations of the IP addresses comprises:
converting each of the four octets of the plurality of IP addresses into a plurality of binary representations;
converting the plurality of binary representations into numerical representations; and
obtaining the plurality of integer pair representations of the IP addresses based on the numerical representations.

### Claim 3 (depends on 2)

The method of claim 2, further comprising:
determining a plurality of vectors of binary values based on the plurality of integer pair representations, and wherein determining the plurality of similarity values is based on the vector of binary values.

### Claim 4 (depends on 3)

The method of claim 3, wherein the plurality of network traffic rules is associated with a particular time period, and wherein each of the plurality of vectors of binary values is associated with a single day from the particular time period.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
determining a plurality of vectors of binary values based on the plurality of integer pair representations, and wherein determining the plurality of similarity values comprises:
comparing, using the similarity algorithm, each of the plurality of vectors of binary values with each other; and
determining the plurality of similarity values based on the comparison.

### Claim 6 (depends on 5)

The method of claim 5, wherein comparing each of the plurality of vectors of binary values using the similarity algorithm comprises:
determining an overlap of values between a first vector of binary value and a second vector of binary value;
determining an aggregation of the first vector of binary value and the second vector of binary value; and
determining a similarity value for the first vector of binary value and the second vector of binary value based on the overlap of values and the aggregation.

### Claim 7 (depends on 5)

The method of claim 5, wherein comparing each of the plurality of vectors of binary values using the similarity algorithm is based on using a normalized dot product.

### Claim 8 (depends on 5)

The method of claim 5, wherein determining the plurality of similarity values comprises populating an array data structure, wherein each entry of the array data structure is associated with a similarity value from the plurality of similarity values.

### Claim 9 (depends on 1)

The method of claim 1, wherein determining stability of one or more of the plurality of network traffic rules comprises:
determining a temporal stability similarity vector based on the plurality of similarity values;
determining a temporal stability metric based on the temporal stability similarity vector; and
determining the stability of the one or more of the plurality of network traffic rules based on comparing the temporal stability metric to the one or more thresholds.

### Claim 10 (depends on 9)

The method of claim 9, wherein determining the temporal stability metric is based on applying a linear regression model to the temporal stability similarity vector.

### Claim 11 (depends on 9)

The method of claim 9, wherein determining the temporal stability metric is based on using one or more machine learning algorithms and the temporal stability similarity vector.

### Claim 12 (depends on 1)

The method of claim 1, wherein determining stability of one or more of the plurality of network traffic rules comprises:
determining a mean weighted degree or a mean strength based on the plurality of similarity values;
determining the stability of the one or more of the plurality of network traffic rules based on comparing the mean weighted degree or the mean strength to the one or more thresholds.

### Claim 13 (depends on 12)

The method of claim 12, wherein the plurality of similarity values are represented as a weighted adjacency matrix, wherein the weighted adjacency matrix comprises a plurality of nodes indicating particular days associated with the plurality of similarity values and a plurality of edges indicating the plurality of similarity values, and wherein the mean strength of the graph indicates a mean normalized dot product between the plurality of nodes.

### Claim 14

An enterprise organization cloud computing platform for generating network traffic rules for a cloud environment, comprising:
one or more processors; and
a non-transitory computer-readable medium having processor-executable instructions stored thereon, wherein the processor-executable instructions, when executed by the one or more processors, facilitate:
converting a plurality of internet protocol (IP) addresses from a plurality of network traffic rules into a plurality of integer pair representations of the IP addresses;
determining a plurality of similarity values based on the plurality of integer pair representations of the IP addresses and a similarity algorithm;
determining stability of one or more of the plurality of network traffic rules based on the plurality of similarity values and one or more thresholds; and
applying the one or more of the plurality of network traffic rules that are determined to be stable.

### Claim 15 (depends on 14)

The enterprise organization cloud computing platform of claim 14, wherein each of the plurality of IP addresses comprises four octets, and wherein converting the plurality of IP addresses into the plurality of integer pair representations of the IP addresses comprises:
converting each of the four octets of the plurality of IP addresses into a plurality of binary representations;
converting the plurality of binary representations into numerical representations; and
obtaining the plurality of integer pair representations of the IP addresses based on the numerical representations.

### Claim 16 (depends on 15)

The enterprise organization cloud computing platform of claim 15, wherein the processor-executable instructions, when executed by the one or more processors, further facilitate:
determining a plurality of vectors of binary values based on the plurality of integer pair representations, and wherein determining the plurality of similarity values is based on the vector of binary values.

### Claim 17 (depends on 16)

The enterprise organization cloud computing platform of claim 16, wherein the plurality of network traffic rules is associated with a particular time period, and wherein each of the plurality of vectors of binary values is associated with a single day from the particular time period.

### Claim 18 (depends on 14)

The enterprise organization cloud computing platform of claim 14, wherein the processor-executable instructions, when executed by the one or more processors, further facilitate:
determining a plurality of vectors of binary values based on the plurality of integer pair representations, and wherein determining the plurality of similarity values comprises:
comparing, using the similarity algorithm, each of the plurality of vectors of binary values with each other; and
determining the plurality of similarity values based on the comparison.

### Claim 19 (depends on 14)

The enterprise organization cloud computing platform of claim 14, wherein comparing each of the plurality of vectors of binary values using the similarity algorithm comprises:
determining an overlap of values between a first vector of binary value and a second vector of binary value;
determining an aggregation of the first vector of binary value and the second vector of binary value; and
determining a similarity value for the first vector of binary value and the second vector of binary value based on the overlap of values and the aggregation.

### Claim 20

A non-transitory computer-readable medium having processor-executable instructions stored thereon, wherein the processor-executable instructions, when executed, facilitate:
converting a plurality of internet protocol (IP) addresses from a plurality of network traffic rules into a plurality of integer pair representations of the IP addresses;
determining a plurality of similarity values based on the plurality of integer pair representations of the IP addresses and a similarity algorithm;
determining stability of one or more of the plurality of network traffic rules based on the plurality of similarity values and one or more thresholds; and
applying the one or more of the plurality of network traffic rules that are determined to be stable.
