# US 12,009,994 B2 · Utilizing machine learning to reduce cloud instances in a cloud computing environment > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,009,994 B2 - Document ID: US12009994B2 - Status: Granted - Kind: B2 - Application number: 18/305,427 - Filed: 2023-04-24 - Published: 2023-08-10 - Granted: 2024-06-11 - Earliest claimed: 2018-06-07 - Assignees: Capital One Services, LLC - Applicants: Capital One Services, LLC - Inventors: Sunil Narang; Abhishek Kumar Singh; Nazia Sarang; Vikas Vijay - Web page: https://patentgrep.com/patent/US12009994B2 ## CPC - H04L 41/16: using machine learning or artificial intelligence - G06F 18/23: Clustering techniques - G06N 20/00: Machine learning - G06V 10/762: using clustering, e.g. of similar faces in social networks - H04L 41/0654: using network fault recovery (ring fault isolation or reconfiguration in loop networks without recovery actions by a network management system H04L12/437) - H04L 41/0803: Configuration setting - H04L 41/40: using virtualisation of network functions or resources, e.g. SDN or NFV entities - H04L 67/1001: for accessing one among a plurality of replicated servers - H04L 41/5012: {determining service availability, e.g. which services are available at a certain point in time} - H04L 41/5096: {wherein the managed service relates to distributed or central networked applications} - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A device receives, from a cloud computing environment, cloud instance information associated with cloud instances in the cloud computing environment, and processes the cloud instance information, with a machine learning model, to determine containers for one or more of the cloud instances and whether cloud instances should be removed from the cloud computing environment. The device causes a first subset of the cloud instances to be removed from the cloud computing environment, based on determining which of the cloud instances should be removed, and causes the containers to be created for a second subset of the cloud instances based on determining the containers. The device receives, from the cloud computing environment, cloud container information associated with the containers created in the cloud computing environment, and causes one or more of the containers to be scaled based on the cloud container information. ## Claims ### Claim 1 A method, comprising: generating, by a device, a cloud container based on similarities between a plurality of cloud instances, wherein the similarities are determined based on analyzing the plurality of cloud instances with a machine learning model; receiving, by the device, cloud container information associated with the cloud container indicating utilization of first computing resources used to implement the cloud container; receiving, by the device, cloud instance information associated with one or more cloud instances, of the plurality of cloud instances, executing within the cloud container, wherein the cloud instance information indicates utilization of second computing resources used to implement the one or more cloud instances; scaling, by the device and based on at least one of the cloud container information or the cloud instance information, the cloud container; and monitoring, by the device and after scaling the cloud container, the cloud container to determine whether additional scaling is to be performed. ### Claim 2 (depends on 1) The method of claim 1, further comprising: determining a recent cloud instance image associated with a cloud instance of the one or more cloud instances; and implementing the recent cloud instance image periodically. ### Claim 3 (depends on 1) The method of claim 1, further comprising: receiving information indicating that the cloud container failed; and restarting, based on receiving the information indicating that the cloud container failed, the cloud container. ### Claim 4 (depends on 1) The method of claim 1, further comprising: receiving information indicating that the cloud container failed; and creating, based on receiving the information indicating that the cloud container failed, a new cloud container. ### Claim 5 (depends on 1) The method of claim 1, wherein the cloud container information is received periodically. ### Claim 6 (depends on 1) The method of claim 1, further comprising: providing information indicating one or more alerts associated with the cloud container. ### Claim 7 (depends on 1) The method of claim 1, further comprising: performing, based on directing traffic among the plurality of cloud instances, load balancing of the cloud container. ### Claim 8 A device, comprising: one or more memories; and one or more processors, coupled to the one or more memories, configured to: generate a container based on similarities between a plurality of cloud instances, wherein the similarities are determined based on analyzing the plurality of cloud instances with a machine learning model; receive container information associated with the container indicating utilization of first computing resources used to implement the container; receive cloud instance information associated with one or more cloud instances, of the plurality of cloud instances, executing within the container, wherein the cloud instance information indicates utilization of second computing resources used to implement the one or more cloud instances; scale, based on at least one of the container information or the cloud instance information, the container; and monitor, after scaling the container, the container to determine whether additional scaling is to be performed. ### Claim 9 (depends on 8) The device of claim 8, wherein the one or more processors are further configured to: determine a recent cloud instance image associated with a cloud instance of the one or more cloud instances; and implement the recent cloud instance image periodically. ### Claim 10 (depends on 8) The device of claim 8, wherein the one or more processors are further configured to: receive information indicating that the container failed; and restart, based on receiving the information indicating that the container failed, the container. ### Claim 11 (depends on 8) The device of claim 8, wherein the one or more processors are further configured to: receive information indicating that the container failed; and create, based on receiving the information indicating that the container failed, a new container. ### Claim 12 (depends on 8) The device of claim 8, wherein the container information is received periodically. ### Claim 13 (depends on 8) The device of claim 8, wherein the one or more processors are further configured to: provide information indicating one or more alerts associated with the container. ### Claim 14 (depends on 8) The device of claim 8, wherein the one or more processors are further configured to: perform, based on directing traffic among the plurality of cloud instances, load balancing of the container. ### Claim 15 A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising: one or more instructions that, when executed by one or more processors of a device, cause the device to: generate a container based on similarities between a plurality of cloud instances, wherein the similarities are determined based on analyzing the plurality of cloud instances with a machine learning model; receive container information associated with the container indicating utilization of first computing resources used to implement the container; receive cloud instance information associated with one or more cloud instances, of the plurality of cloud instances, executing within the container, wherein the cloud instance information indicates utilization of second computing resources used to implement the one or more cloud instances; scale, based on at least one of the container information or the cloud instance information, the container; and monitor, after scaling the container, the container to determine whether additional scaling is to be performed. ### Claim 16 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the one or more instructions further cause the device to: determine a recent cloud instance image associated with a cloud instance of the one or more cloud instances; and implement the recent cloud instance image periodically. ### Claim 17 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the one or more instructions further cause the device to: receive information indicating that the container failed; and restart, based on receiving the information indicating that the container failed, the container. ### Claim 18 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the one or more instructions further cause the device to: receive information indicating that the container failed; and create, based on receiving the information indicating that the container failed, a new container. ### Claim 19 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the one or more instructions further cause the device to: provide information indicating one or more alerts associated with the container. ### Claim 20 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the one or more instructions further cause the device to: perform, based on directing traffic among the plurality of cloud instances, load balancing of the container.