# US 12,010,553 B2 · Cloud-based 5G security network architectures with intelligent steering > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,010,553 B2 - Document ID: US12010553B2 - Status: Granted - Kind: B2 - Application number: 17/491,795 - Filed: 2021-10-01 - Published: 2022-09-08 - Granted: 2024-06-11 - Earliest claimed: 2021-03-08 - Assignees: Zscaler, Inc. - Applicants: Zscaler, Inc. - Inventors: Nathan Howe; Kenneth B. Urquhart - Web page: https://patentgrep.com/patent/US12010553B2 ## CPC - H04W 28/0925: {using policies} - H04L 63/0227: {Filtering policies (mail message filtering H04L51/212)} - H04L 63/029: {Firewall traversal, e.g. tunnelling or, creating pinholes} - 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)} - H04W 12/03: Protecting confidentiality, e.g. by encryption - H04W 12/088: using filters or firewalls - H04W 28/12: using signalling between network elements - 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 Cloud-based 5G security, implemented in a Multi-Access Edge Compute (MEC) system, includes steps of receiving a request for a workload from User Equipment (UE); determining a type of traffic for the workflow and querying a machine learning engine based on the traffic type; informing the UE of how the workflow should be accessed; and receiving an updated request for the workflow and steering the traffic based on how the workflow should be steered. The steps can include receiving policy updates from a cloud-based system, related to how workloads should be steered. ## Claims ### Claim 1 A method of cloud-based 5G security, implemented in a Multi-Access Edge Compute (MEC) system, comprising: receiving a request for a workload from User Equipment (UE); determining a type of traffic for the workflow and querying a machine learning engine based on the traffic type; informing the UE of how the workflow should be accessed; and receiving an updated request for the workflow and steering the traffic based on how the workflow should be steered. ### Claim 2 (depends on 1) The method of claim 1, further comprising receiving policy updates from a cloud-based system, related to how workloads should be steered. ### Claim 3 (depends on 1) The method of claim 1, further comprising receiving updates for the machine learning engine based on monitoring in a cloud-based system. ### Claim 4 (depends on 1) The method of claim 1, wherein the MEC is a first MEC in a Radio Access Network (RAN). ### Claim 5 (depends on 1) The method of claim 1, wherein the traffic is encrypted and the steering includes decrypting the traffic for inspection at another MEC closer to a destination. ### Claim 6 (depends on 1) The method of claim 1, wherein the method is implemented in a decision front end that is processed in the MEC and that is part of a cloud-based system including nodes external to the MEC. ### Claim 7 (depends on 1) The method of claim 1, wherein the steering includes decisions about how and where to send traffic based on a topology of data paths through the MEC and other edge compute resources. ### Claim 8 A Multi-Access Edge Compute (MEC) system comprising: one or more servers each including at least one processor and memory storing instructions that, when executed, cause the at least one processor to receive a request for a workload from User Equipment (UE), determine a type of traffic for the workflow and querying a machine learning engine based on the traffic type, inform the UE of how the workflow should be accessed, and receive an updated request for the workflow and steer the traffic based on how the workflow should be steered. ### Claim 9 (depends on 8) The MEC system of claim 8, wherein the instructions, when executed, cause the at least one processor to receive policy updates from a cloud-based system, related to how workloads should be steered. ### Claim 10 (depends on 8) The MEC system of claim 8, wherein the instructions, when executed, cause the at least one processor to receive updates for the machine learning engine based on monitoring in a cloud-based system. ### Claim 11 (depends on 8) The MEC system of claim 8, wherein the MEC is a first MEC in a Radio Access Network (RAN). ### Claim 12 (depends on 8) The MEC system of claim 8, wherein the traffic is encrypted and the steering includes decrypting the traffic for inspection at another MEC closer to a destination. ### Claim 13 (depends on 8) The MEC system of claim 8, wherein the steering includes decisions about how and where to send traffic based on a topology of data paths through the MEC and other edge compute resources. ### Claim 14 A non-transitory computer-readable storage medium having computer-readable code stored thereon for programming a Multi-Access Edge Compute (MEC) system to perform steps of: receiving a request for a workload from User Equipment (UE); determining a type of traffic for the workflow and querying a machine learning engine based on the traffic type; informing the UE of how the workflow should be accessed; and receiving an updated request for the workflow and steering the traffic based on how the workflow should be steered. ### Claim 15 (depends on 14) The non-transitory computer-readable storage medium of claim 14, wherein the steps further include receiving policy updates from a cloud-based system, related to how workloads should be steered. ### Claim 16 (depends on 14) The non-transitory computer-readable storage medium of claim 14, wherein the steps further include receiving updates for the machine learning engine based on monitoring in a cloud-based system. ### Claim 17 (depends on 14) The non-transitory computer-readable storage medium of claim 14, wherein the MEC is a first MEC in a Radio Access Network (RAN). ### Claim 18 (depends on 14) The non-transitory computer-readable storage medium of claim 14, wherein the traffic is encrypted and the steering includes decrypting the traffic for inspection at another MEC closer to a destination. ### Claim 19 (depends on 14) The non-transitory computer-readable storage medium of claim 14, wherein the method is implemented in a decision front end that is processed in the MEC and that is part of a cloud-based system including nodes external to the MEC. ### Claim 20 (depends on 14) The non-transitory computer-readable storage medium of claim 14, wherein the steering includes decisions about how and where to send traffic based on a topology of data paths through the MEC and other edge compute resources.