# US 12,120,776 B2 · Synchronization of artificial intelligence based microservices > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,120,776 B2 - Document ID: US12120776B2 - Status: Granted - Kind: B2 - Application number: 18/177,368 - Filed: 2023-03-02 - Published: 2023-06-29 - Granted: 2024-10-15 - Earliest claimed: 2021-02-23 - Assignees: AT&T Intellectual Property I, L.P. - Applicants: AT&T Intellectual Property I, L.P. - Inventors: Syed Anwar Aftab; Manoop Talasila; Guy Jacobson; John F. Murray; Mazin E. Gilbert - Web page: https://patentgrep.com/patent/US12120776B2 ## CPC - H04W 88/182: {Network node acting on behalf of an other network entity, e.g. proxy} - H04L 5/0048: {Allocation of pilot signals, i.e. of signals known to the receiver (allocation of control signalling H04L5/0053; use of control signalling H04L5/0091)} - H04W 24/02: Arrangements for optimising operational condition - H04W 24/08: Testing, {supervising or monitoring} using real traffic - H04W 28/0289: {Congestion control (load shedding arrangements in network planning H04W16/08; performing reselection for handling the traffic H04W36/22; wireless traffic scheduling H04W72/12)} - H04W 56/0015: {one node acting as a reference for the others} - H04L 41/083: for increasing network speed - H04W 28/084: among network function virtualisation [NFV] entities; among edge computing entities, e.g. multi-access edge computing - H04W 88/085: {Access point devices with remote components} - H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72) - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract Aspects of the subject disclosure may include, for example, receiving network-related information associated with a first RAN that includes a first RIC, obtaining, from an artificial intelligence (AI) model synchronization system associated with a second RAN, data relating to an AI model deployed by a second RIC of the second RAN, determining, based on the data relating to the AI model and the network-related information associated with the first RAN, that the AI model can be leveraged by the first RAN to improve network performance of the first RAN, performing synchronization with the AI model synchronization system to obtain the AI model, responsive to the determining that the AI model can be leveraged by the first RAN to improve the network performance of the first RAN, and causing the first RIC to deploy the AI model in the first RAN after the performing the synchronization. Other embodiments are disclosed. ## Claims ### Claim 1 A device, comprising: a processing system including a processor, wherein the processing system is associated with a first radio access network (RAN) that includes a first RAN intelligent controller (RIC); and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, the operations comprising: obtaining, from an artificial intelligence (AI) model synchronization system associated with a second RAN, data relating to an AI model deployed by a second RIC of the second RAN, wherein the processing system, the first RAN, and the first RIC are operated by a first network provider, wherein the AI model synchronization system, the second RAN, and the second RIC are operated by a second network provider different from the first network provider, and wherein the processing system is communicatively coupled with the AI model synchronization system to facilitate exchanges of deployed AI models between the first network provider and the second network provider; determining, based on the data relating to the AI model and network-related information associated with the first RAN, that the AI model can be leveraged by the first RAN to improve traffic management of the first RAN, throughput of the first RAN, resource allocation of the first RAN, or a combination thereof; responsive to the determining, receiving the AI model from the AI model synchronization system, wherein the receiving the AI model is in accordance with one or more AI model subscriptions with the AI model synchronization system; and causing the first RIC to deploy the AI model in the first RAN after the receiving the AI model, wherein the first RIC comprises a RIC message router (RMR) message bus, wherein the AI model is configured with a Representational State Transfer (REST) interface, and wherein the AI model is deployed in a container along with an AI microservice adapter that facilitates intra-container function calls for providing protocol conversion between the REST interface and the RMR message bus. ### Claim 2 (depends on 1) The device of claim 1, wherein at least one of the first RAN and the second RAN is a virtualized RAN (vRAN). ### Claim 3 (depends on 1) The device of claim 1, wherein the network-related information includes telemetry data, network performance information, network traffic information, or a combination thereof. ### Claim 4 (depends on 1) The device of claim 1, wherein the data relating to the AI model includes metadata, and wherein the metadata includes telemetry data, network performance information, network traffic information, information regarding performance of the AI model under one or more operating conditions, information regarding performance of the AI model across one or more configurations of the AI model, or a combination thereof. ### Claim 5 (depends on 1) The device of claim 1, wherein the determining comprises comparing the data relating to the AI model and the network-related information associated with the first RAN. ### Claim 6 (depends on 1) The device of claim 1, wherein the receiving the AI model involves utilizing one or more application programming interfaces (APIs). ### Claim 7 (depends on 1) The device of claim 1, wherein the receiving the AI model is conducted over an interface between the processing system and the AI model synchronization system. ### Claim 8 (depends on 1) The device of claim 1, wherein the AI microservice adapter is configured to run as an xApp. ### Claim 9 (depends on 1) The device of claim 1, wherein the AI model and the AI microservice adapter are executed in the container as separate processes. ### Claim 10 (depends on 1) The device of claim 1, wherein the AI microservice adapter is configured to adapt the AI model based on configuration data, and wherein the configuration data includes: information regarding functions relating to an AI microservice; information regarding inputs; information regarding outputs; identification of messages, to detect for on a bus associated with the first RIC, that call or utilize the functions; identification of messages to deliver on the bus relating to the functions; information regarding how messages are to be translated into calls; information regarding how responses to messages from an AI microservice are to be translated and placed onto the bus; information regarding endpoints of an AI microservice; information regarding a location at which an AI microservice is running; or a combination thereof. ### Claim 11 A non-transitory machine-readable medium, comprising executable instructions that, when executed by a processing system of a first radio access network (RAN) that includes a first RAN intelligent controller (RIC), facilitate performance of operations, the operations comprising: receiving, from an artificial intelligence (AI) model synchronization system associated with a second RAN, data relating to an AI model utilized by a second RIC of the second RAN, wherein the processing system, the first RAN, and the first RIC are operated by a first network provider, wherein the AI model synchronization system, the second RAN, and the second RIC are operated by a second network provider different from the first network provider, and wherein the processing system is communicatively coupled with the AI model synchronization system to facilitate exchanges of deployed AI models between the first network provider and the second network provider; identifying, based on the data relating to the AI model and network-related information associated with the first RAN, that the AI model can be utilized by the first RAN to manage traffic of the first RAN, throughput of the first RAN, resource allocation of the first RAN, or a combination thereof; based on the identifying, obtaining the AI model from the AI model synchronization system, wherein the obtaining the AI model is in accordance with an AI model subscription with the AI model synchronization system; and causing the first RIC to utilize the AI model in the first RAN after the obtaining the AI model, wherein the first RIC comprises a RIC message router (RMR) message bus, wherein the AI model is configured with a Representational State Transfer (REST) interface, and wherein the AI model is deployed in a container along with an AI microservice adapter that facilitates intra-container function calls for providing protocol conversion between the REST interface and the RMR message bus. ### Claim 12 (depends on 11) The non-transitory machine-readable medium of claim 11, wherein at least one of the first RAN and the second RAN is a virtualized RAN (vRAN). ### Claim 13 (depends on 11) The non-transitory machine-readable medium of claim 11, wherein the network-related information includes telemetry data, network performance information, network traffic information, or a combination thereof. ### Claim 14 (depends on 11) The non-transitory machine-readable medium of claim 11, wherein the data relating to the AI model includes metadata, and wherein the metadata includes telemetry data, network performance information, network traffic information, information regarding performance of the AI model under one or more operating conditions, information regarding performance of the AI model across one or more configurations of the AI model, or a combination thereof. ### Claim 15 (depends on 11) The non-transitory machine-readable medium of claim 11, wherein the identifying comprises comparing the data relating to the AI model and the network-related information associated with the first RAN. ### Claim 16 A method, comprising: causing, by a processing system of a first radio access network (RAN) intelligent controller (RIC) of a first RAN including a processor, network-related information associated with the first RAN to be provided to a first artificial intelligence (AI) model synchronization system, wherein providing the network-related information associated with the first RAN to the first AI model synchronization system enables the first AI model synchronization system to obtain, from a second AI model synchronization system associated with a second RAN, data relating to an AI model deployed by a second RIC of the second RAN, determine, based on the data relating to the AI model and the network-related information associated with the first RAN, that the AI model is capable of improving traffic management of the first RAN, throughput of the first RAN, resource allocation of the first RAN, or a combination thereof, and receive the AI model from the second AI model synchronization system in accordance with one or more AI model subscriptions with the second AI model synchronization system, wherein the first AI model synchronization system, the first RAN, and the first RIC are operated by a first network provider, wherein the second AI model synchronization system, the second RAN, and the second RIC are operated by a second network provider different from the first network provider, and wherein the first AI model synchronization system is communicatively coupled with the second AI model synchronization system to facilitate exchanges of deployed AI models between the first network provider and the second network provider; obtaining, by the processing system, the AI model from the first AI model synchronization system responsive to the causing the network-related information associated with the first RAN to be provided to the first AI model synchronization system; and causing, by the processing system, the AI model to be employed in the first RIC responsive to the obtaining the AI model from the first AI model synchronization system, wherein the first RIC comprises a RIC message router (RMR) message bus, wherein the AI model is configured with a Representational State Transfer (REST) interface, and wherein the AI model is deployed in a container along with an AI microservice adapter that facilitates intra-container function calls for providing protocol conversion between the REST interface and the RMR message bus. ### Claim 17 (depends on 16) The method of claim 16, wherein at least one of the first RAN and the second RAN is a virtualized RAN (vRAN). ### Claim 18 (depends on 16) The method of claim 16, wherein the AI model provides one or more RAN-based microservices. ### Claim 19 (depends on 16) The method of claim 16, wherein the one or more AI model subscriptions are associated with one or more application programming interfaces (APIs). ### Claim 20 (depends on 16) The method of claim 16, wherein the data relating to the AI model includes metadata, and wherein the metadata includes telemetry data, network performance information, network traffic information, information regarding performance of the AI model under one or more operating conditions, information regarding performance of the AI model across one or more configurations of the AI model, or a combination thereof.