# US 2022/0036418 A1 · Design of services using ai/ml to select virtual network functions and vendors for supplying the virtual network functions

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

- Number: US 2022/0036418 A1
- Document ID: US20220036418A1
- Status: Published application
- Kind: A1
- Application number: 16/941,623
- Filed: 2020-07-29
- Published: 2022-02-03
- Earliest claimed: 2020-07-29
- Assignees: EMC IP Holding Company LLC
- Applicants: EMC IP Holding Company LLC
- Inventors: Sathish Kumar Bikumala; Vasile Radoaca; Deepak NagarajeGowda
- Web page: https://patentgrep.com/patent/US20220036418A1

## CPC

- G06N 3/088: Non-supervised learning, e.g. competitive learning
- G06N 20/00: Machine learning
- G06N 3/0499: Feedforward networks
- G06N 3/09: Supervised learning
- G06N 3/092: Reinforcement learning
- H04L 41/145: {involving simulating, designing, planning or modelling of a network}
- H04L 41/5041: characterised by the time relationship between creation and deployment of a service
- G06N 3/045: Combinations of networks
- H04L 41/16: using machine learning or artificial intelligence
- 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

The disclosed systems and methods are directed to a computer-implemented method for use in designing a service. In at least one embodiment, a method includes designing a service with one or more generic virtual network functions (VNFs), where the generic VNFs are defined independent of vendor sourcing information. One or more trained machine learning (ML) models are used to identify VNFs available from VNF vendors that may source one or more VNFs similar to the generic VNFs. The service is implemented using VNFs provided by one or more VNF vendors, where the VNFs provided by the one or more VNF vendors have network functionality generating similar to the one or generic VNFs.

## Claims

### Claim 1

A computer-implemented method for use in designing a service, the method comprising:
designing a service with one or more generic virtual network functions (VNFs), wherein the generic VNFs are defined independent of vendor sourcing information;
using one or more trained machine learning (ML) models to identify VNFs available from VNF vendors that may source one or more VNFs similar to the generic VNFs; and
implementing the Service using VNFs provided by one or more VNF vendors, wherein the VNFs provided by the one or more VNF vendors have network functionality that is generally similar to the one or generic VNFs.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein
the one or more trained ML models include an ML quality model configured to assess a quality of VNFs provided by vendors.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, wherein the method further comprises:
executing an unsupervised learning operation using raw data relating to past performance of vendors providing VNFs;
clustering and classifying data provided from the unsupervised learning operation to generate a set of training data; and
using the set of training data to train the ML quality model.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein
the one or more trained ML models include an ML similarity scoring model configured to identify a degree of similarity between one or more of the generic VNFs and one or more VNFs available from the vendors.

### Claim 5 (depends on 4)

The computer-implemented method of claim 4, wherein
the ML similarity scoring model is trained using data derived from VNF images, VNF descriptions, and taxonomy data available from the vendors; and
wherein training the ML similarity scoring model further includes feature selection and engineering of features derived from the VNF images, VNF descriptions, and taxonomy data.

### Claim 6 (depends on 5)

The computer-implement method of claim 5, wherein
the data derived from feature selection and feature engineering are subject to localities sensitive hashing to train the ML similarity scoring model.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein
the one or more trained machine learning (ML) models provide VNF and vendor information including one or more VNF vendors, the VNFs available from VNF vendors that may source VNFs similar to the generic VNFs, VNF vendor quality metrics, similarity scores comparing vendors sourced VNFs with generic VNFs, and/or taxonomy data for VNFs provided by vendors, and wherein the VNF and vendor information is stored in a smart VNF catalog.

### Claim 8

A computer system comprising:
one or more information handling systems, wherein the one or more information handling systems include:
a processor;
a data bus coupled to the processor; and
a non-transitory, computer-readable storage medium embodying computer program code, the non-transitory, computer-readable storage medium being coupled to the data bus;
wherein the computer program code included in one or more of the information handling systems is executable by the processor of the information handling system so that the information handling system, alone or in combination with other information handling systems, executes operations comprising:
designing a service with one or more generic virtual network functions (VNFs), wherein the generic VNFs are defined independent of vendor sourcing information;
using one or more trained machine learning (ML) models to identify VNFs available from VNF vendors that may source one or more VNFs similar to the generic VNFs; and
implementing the Service using VNFs provided by one or more VNF vendors, wherein the VNFs provided by the one or more VNF vendors have network functionality that is generally similar to the one or generic VNFs.

### Claim 9 (depends on 8)

The system of claim 8, wherein
the one or more trained ML models include an ML quality model configured to assess a quality of VNFs provided by vendors.

### Claim 10 (depends on 9)

The system of claim 9, wherein the operations further comprise:
executing an unsupervised learning operation using raw data relating to past performance of vendors providing VNFs;
clustering and classifying data provided from the unsupervised learning operation to generate a set of training data; and
using the set of training data to train the ML quality model.

### Claim 11 (depends on 8)

The system of claim 8, wherein
the one or more trained ML models include an ML similarity scoring model configured to identify a degree of similarity between one or more of the generic VNFs and one or more VNFs available from the vendors.

### Claim 12 (depends on 11)

The system of claim 11, wherein
the ML similarity scoring model is trained using data derived from VNF images, VNF descriptions, and taxonomy data available from the vendors; and
wherein training the ML similarity scoring model further includes feature selection and engineering of features derived from the VNF images, VNF descriptions, and taxonomy data.

### Claim 13 (depends on 12)

The system of claim 12, wherein
the data derived from feature selection and feature engineering are subject to localities sensitive hashing to train the ML similarity scoring model.

### Claim 14 (depends on 8)

The system of claim 8, wherein
the one or more trained machine learning (ML) models provide VNF and vendor information including one or more VNF vendors, the VNFs available from VNF vendors that may source VNFs similar to the generic VNFs, VNF vendor quality metrics, similarity scores comparing vendors sourced VNFs with generic VNFs, and/or taxonomy data for VNFs provided by vendors, and wherein the VNF and vendor information is stored in a smart VNF catalog.

### Claim 15

A non-transitory, computer-readable storage medium embodying computer program code, the computer program code comprising computer-executable instructions configured for:
designing a service with one or more generic virtual network functions (VNFs), wherein the generic VNFs are defined independent of vendor sourcing information;
using one or more trained machine learning (ML) models to identify VNFs available from VNF vendors that may source one or more VNFs similar to the generic VNFs; and
implementing the Service using VNFs provided by one or more VNF vendors, wherein the VNFs provided by the one or more VNF vendors have network functionality that is generally similar to the one or generic VNFs.

### Claim 16 (depends on 15)

The non-transitory, computer-readable storage medium of claim 15, wherein
the one or more trained ML models include an ML quality model configured to assess a quality of VNFs provided by vendors.

### Claim 17 (depends on 16)

The non-transitory, computer-readable storage medium of claim 16, wherein the instructions are further configured for:
executing an unsupervised learning operation using raw data relating to past performance of vendors providing VNFs;
clustering and classifying data provided from the unsupervised learning operation to generate a set of training data; and
using the set of training data to train the ML quality model.

### Claim 18 (depends on 15)

The non-transitory, computer-readable storage medium of claim 15, wherein
the one or more trained ML models include an ML similarity scoring model configured to identify a degree of similarity between one or more of the generic VNFs and one or more VNFs available from the vendors.

### Claim 19 (depends on 18)

The non-transitory, computer-readable storage medium of claim 18, wherein
the ML similarity scoring model is trained using data derived from VNF images, VNF descriptions, and taxonomy data available from the vendors; and
wherein training the ML similarity scoring model further includes feature selection and engineering of features derived from the VNF images, VNF descriptions, and taxonomy data.

### Claim 20 (depends on 15)

The non-transitory, computer-readable storage medium of claim 15, wherein
the one or more trained machine learning (ML) models provide VNF and vendor information including one or more VNF vendors, the VNFs available from VNF vendors that may source VNFs similar to the generic VNFs, VNF vendor quality metrics, similarity scores comparing vendors sourced VNFs with generic VNFs, and/or taxonomy data for VNFs provided by vendors, and wherein the VNF and vendor information is stored in a smart VNF catalog.