# US 2023/0412471 A1 · Edge-based artificial intelligence enablement

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

- Number: US 2023/0412471 A1
- Document ID: US20230412471A1
- Status: Published application
- Kind: A1
- Application number: 18/241,605
- Filed: 2023-09-01
- Published: 2023-12-21
- Earliest claimed: 2021-02-22
- Assignees: CenturyLink Intellectual Property LLC
- Applicants: CenturyLink Intellectual Property LLC
- Inventors: Ronald A. Lewis; Alison Grayson; Carlos Santiago
- Web page: https://patentgrep.com/patent/US20230412471A1

## CPC

- H04L 41/16: using machine learning or artificial intelligence
- H04L 67/10: in which an application is distributed across nodes in the network (software deployment G06F8/60; multiprogramming arrangements G06F9/46)
- H04L 41/145: {involving simulating, designing, planning or modelling of a network}
- H04L 67/56: Provisioning of proxy services (store-and-forward switching systems in data switching networks H04L12/54)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

An edge computing telecommunications network is provided for efficiently generating and updating computing models for use at distributed devices connected to different edge compute sites of the network. A network orchestration system may track devices connected to the network and the edge compute sites to which they are connected. The devices may comprise limited computing power and may include sensors or other data collection mechanisms. Raw data may be provided from connected devices to one or more edge compute sites. Edge compute sites may be instructed, e.g., by the network orchestration system, whether to replicate the raw data, modify the data to make it ready for consumption by a computing model, replicate the modified data, refine the computing model, replicate the refined computing model, and/or share some or all of the raw data, modified data, and/or refined computing model with other edge computing sites and/or connected devices.

## Claims

### Claim 1

A method, comprising:
receiving, at a first edge compute site of a telecommunications network, raw data from a first device over a first access network;
determining, by the first edge compute site, that the raw data needs to be modified for consumption by a first model;
modifying the raw data to generate modified data;
modifying the first model using the modified data to generate a modified first model;
sending the modified first model to at least one device connected to the first edge compute site; and
using the modified first model to automatically affect operation of at least one of the first edge compute site or the at least one device.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
receiving, by the first edge compute site, second modified data related to a second model, from a second edge compute site.

### Claim 3 (depends on 2)

The method of claim 2, further comprising:
modifying the second model at the first edge compute site; and
providing, by the first edge compute site, the modified second model to the second device.

### Claim 4 (depends on 2)

The method of claim 2, further comprising:
evaluating the second modified data to determine a security value for the second modified data;
based on determining the security value, determining, by the first compute site, whether to provide the second modified data to the second device.

### Claim 5 (depends on 2)

The method of claim 2, further comprising:
providing the second modified data by the first edge compute site to the second device over the first access network.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
receiving, from a network orchestration system at the first edge compute site, instructions to provide the modified data to a second edge compute site and the modified first model to the second device.

### Claim 7 (depends on 6)

The method of claim 6, further comprising:
receiving updated instructions from the network orchestration system at the first edge compute site to no longer provide updates to modified data or the modified first model to the second edge compute site.

### Claim 8 (depends on 6)

The method of claim 6, further comprising:
receiving, from the network orchestration system at the first edge compute site, instructions to provide the raw data to a third edge compute site but not provide the raw data to the second edge compute site.

### Claim 9 (depends on 1)

The method of claim 1, wherein modifying the raw data comprises extracting feature pairs from the raw data.

### Claim 10 (depends on 9)

The method of claim 9, wherein modifying the raw data to generate the modified data comprises generating first modified data by extracting a first set of feature pairs from the raw data for use in the first model and generating second modified data by extracting a second set of feature pairs from the raw data for use in a second model, the method further comprising:
using the first modified data to modify the first model at the first edge compute site; and
sending the second modified data to a second edge compute site.

### Claim 11

A system, comprising:
at least one processor;
memory, operatively connected to the at least one processor and storing instructions that, when executed by the at least one processor, cause the system to perform a method, the method comprising:
receiving, at a first edge compute site of a telecommunications network, raw data from a first device over a first access network;
determining, by the first edge compute site, that the raw data needs to be modified for consumption by a first model;
modifying the raw data to generate modified data;
modifying the first model using the modified data to generate a modified first model;
sending the modified first model to at least one device connected to the first edge compute site; and
using the modified first model to automatically affect operation of at least one of the first edge compute site or the at least one device.

### Claim 12 (depends on 11)

The system of claim 11, wherein the method further comprises:
receiving, by the first edge compute site, second modified data related to a second model, from a second edge compute site.

### Claim 13 (depends on 12)

The system of claim 12, wherein the method further comprises:
modifying the second model at the first edge compute site; and
providing, by the first edge compute site, the modified second model to the second device.

### Claim 14 (depends on 12)

The system of claim 12, wherein the method further comprises:
evaluating the second modified data to determine a security value for the second modified data;
based on determining the security value, determining, by the first compute site, whether to provide the second modified data to the second device.

### Claim 15 (depends on 12)

The system of claim 12, wherein the method further comprises:
providing the second modified data by the first edge compute site to the second device over the first access network.

### Claim 16 (depends on 12)

The system of claim 12, wherein the method further comprises:
receiving, from a network orchestration system at the first edge compute site, instructions to provide the modified data to the second edge compute site and the modified first model to the second device.

### Claim 17 (depends on 16)

The system of claim 16, wherein the method further comprises:
receiving updated instructions from the network orchestration system at the first edge compute site to no longer provide updates to modified data or the modified first model to the second edge compute site.

### Claim 18 (depends on 16)

The system of claim 16, wherein the method further comprises:
receiving, from the network orchestration system at the first edge compute site, instructions to provide the raw data to a third edge compute site but not provide the raw data to the second edge compute site.

### Claim 19 (depends on 11)

The system of claim 11, wherein modifying the raw data comprises extracting feature pairs from the raw data, wherein modifying the raw data to generate the modified data comprises generating first modified data by extracting a first set of feature pairs from the raw data for use in the first model and generating second modified data by extracting a second set of feature pairs from the raw data for use in a second model, and wherein the method further comprises:
using the first modified data to modify the first model at the first edge compute site; and
sending the second modified data to a second edge compute site.
