# US 12,225,388 B1 · Machine learning-based system, method, and computer program for making a 5G private network deployment recommendation > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,225,388 B1 - Document ID: US12225388B1 - Status: Granted - Kind: B1 - Application number: 17/410,894 - Filed: 2021-08-24 - Granted: 2025-02-11 - Earliest claimed: 2021-08-24 - Assignees: Amdocs Development Limited - Applicants: Amdocs Development Limited - Inventors: Jean-marc Eric Ohayon; Gil Mazurik - Web page: https://patentgrep.com/patent/US12225388B1 ## CPC - H04W 16/18: Network planning tools - G06N 5/04: Inference or reasoning models - H04W 16/14: Spectrum sharing arrangements {between different networks} - H04W 24/02: Arrangements for optimising operational condition - H04W 48/18: Selecting a network or a communication service - H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract As described herein, a system, method, and computer program are provided for making a 5G private network deployment recommendation using machine learning. A plurality of parameter values associated with an enterprise for which a 5G private network is to be deployed are obtained. A machine learning model is used to infer, for the enterprise, an optimal deployment scenario for the 5G private network among a plurality of available deployment scenarios, based on the plurality of parameter values. An indication of the optimal deployment scenario is output as a recommendation for deploying the for the 5G private network for the enterprise. ## Claims ### Claim 1 A non-transitory computer-readable media storing computer instructions which when executed by one or more processors of a device cause the device to: obtain input that defines a plurality of parameter values associated with an enterprise for which a 5G private network is to be deployed, wherein the plurality of parameter values include at least: characteristics of the enterprise, quality of service requirements for the 5G private network, and capabilities of the 5G private network; process the plurality of parameter values by a machine learning model to infer, for the enterprise, an optimal deployment scenario for the 5G private network, wherein the optimal deployment scenario is selected by the machine learning model from among a plurality of available deployment scenarios that are existing deployment configurations for use in implementing 5G private networks; output an indication of the optimal deployment scenario as a recommendation for deploying the 5G private network for the enterprise; select a network service from a catalog of network services that is configured to deploy the optimal deployment scenario; and initiate the network service to deploy the optimal deployment scenario for the enterprise. ### Claim 2 (depends on 1) The non-transitory computer-readable media of claim 1, wherein the plurality of parameter values further include: security requirements for the 5G private network, number of devices to be connected to the 5G private network, budget for the 5G private network, and budget for maintenance of the 5G private network. ### Claim 3 (depends on 1) The non-transitory computer-readable media of claim 1, wherein the characteristics of the enterprise includes: size of the enterprise, and market within which the enterprise operates. ### Claim 4 (depends on 1) The non-transitory computer-readable media of claim 1, wherein the quality of service requirements include: reliability requirements, connection speed requirements, and latency requirements. ### Claim 5 (depends on 1) The non-transitory computer-readable media of claim 1, wherein the input is provided in a user interface of an application by one or more representatives of the enterprise. ### Claim 6 (depends on 1) The non-transitory computer-readable media of claim 1, wherein the input is provided in a user interface of an application by a sales agent in communication with one or more representatives of the enterprise. ### Claim 7 (depends on 1) The non-transitory computer-readable media of claim 1, wherein the machine learning model is generated by training a machine learning algorithm using training data that includes previous deployment scenarios used for enterprises with corresponding parameter values. ### Claim 8 (depends on 1) The non-transitory computer-readable media of claim 1, wherein the plurality of available deployment scenarios include a physically-isolated 5G private network. ### Claim 9 (depends on 8) The non-transitory computer-readable media of claim 8, wherein the physically-isolated 5G private network is independent of a mobile operator's public 5G network and wherein components of the 5G private network are deployed within a premise of the enterprise and are private and dedicated to the enterprise. ### Claim 10 (depends on 1) The non-transitory computer-readable media of claim 1, wherein the plurality of available deployment scenarios include radio access network (RAN) sharing between a private network and a public network. ### Claim 11 (depends on 8) The non-transitory computer-readable media of claim 8, wherein the RAN sharing between the private network and the public network includes: deploying components of the 5G private network within a premise of the enterprise, wherein only 5G base stations are shared between the private network and the public network and remaining components of the 5G private network are private and dedicated to the enterprise. ### Claim 12 (depends on 1) The non-transitory computer-readable media of claim 1, wherein the plurality of available deployment scenarios include RAN and control plane sharing between a private network and a public network. ### Claim 13 (depends on 8) The non-transitory computer-readable media of claim 8, wherein the RAN and control plane sharing between the private network and the public network includes: deploying a first subset of components of the 5G private network within a premise of the enterprise that are private and dedicated to the enterprise, and deploying a second subset of components of the 5G private network within the premise of the enterprise that are shared between the private network and the public network, deploying a third subset of components of the 5G private network in a mobile operator's public 5G network, wherein the first subset of components are physically separated between the private network and the public network, wherein the second subset of components and the third subset of components are logically separated between the private network and the public network. ### Claim 14 (depends on 1) The non-transitory computer-readable media of claim 1, wherein the plurality of available deployment scenarios include end to end network slicing including RAN and core sharing between a private network and a public network. ### Claim 15 (depends on 8) The non-transitory computer-readable media of claim 8, wherein the end to end network slicing including RAN and core sharing between a private network and a public network includes: deploying only 5G base stations within a premise of the enterprise, deploying at least two other components of the 5G private network in a mobile operator's public 5G network, wherein components of the 5G private network are logically separated between the private network and the public network. ### Claim 16 (depends on 1) The non-transitory computer-readable media of claim 1, wherein the plurality of available deployment scenarios include: a physically-isolated 5G private network, radio access network (RAN) sharing between a private network and a public network, RAN and control plane sharing between a private network and a public network, and end to end network slicing including RAN and core sharing between a private network and a public network. ### Claim 17 (depends on 1) The non-transitory computer-readable media of claim 1, wherein the plurality of available deployment scenarios are associated with different resource requirements and different prices. ### Claim 18 A method, comprising: at a computer system: obtaining input that defines a plurality of parameter values associated with an enterprise for which a 5G private network is to be deployed, wherein the plurality of parameter values include at least: characteristics of the enterprise, quality of service requirements for the 5G private network, and capabilities of the 5G private network; processing the plurality of parameter values by a machine learning model to infer, for the enterprise, an optimal deployment scenario for the 5G private network, wherein the optimal deployment scenario is selected by the machine learning model from among a plurality of available deployment scenarios that are existing deployment configurations for use in implementing 5G private networks; outputting an indication of the optimal deployment scenario as a recommendation for deploying the 5G private network for the enterprise; selecting a network service from a catalog of network services that is configured to deploy the optimal deployment scenario; and initiating the network service to deploy the optimal deployment scenario for the enterprise. ### Claim 19 A system, comprising: a non-transitory memory storing instructions; and one or more processors in communication with the non-transitory memory that execute the instructions to: obtain input that defines a plurality of parameter values associated with an enterprise for which a 5G private network is to be deployed, wherein the plurality of parameter values include at least: characteristics of the enterprise, quality of service requirements for the 5G private network, and capabilities of the 5G private network; process the plurality of parameter values by a machine learning model to infer, for the enterprise, an optimal deployment scenario for the 5G private network, wherein the optimal deployment scenario is selected by the machine learning model from among a plurality of available deployment scenarios that are existing deployment configurations for use in implementing 5G private networks; output an indication of the optimal deployment scenario as a recommendation for deploying the 5G private network for the enterprise; select a network service from a catalog of network services that is configured to deploy the optimal deployment scenario; and initiate the network service to deploy the optimal deployment scenario for the enterprise.