# US 2019/0171966 A1 · Automated application reliability management using adaptable machine learning models > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0171966 A1 - Document ID: US20190171966A1 - Status: Published application - Kind: A1 - Application number: 16/207,089 - Filed: 2018-12-01 - Published: 2019-06-06 - Earliest claimed: 2017-12-01 - Assignees: Appranix, Inc. - Inventors: GOVINDARAJAN RANGASAMY - Web page: https://patentgrep.com/patent/US20190171966A1 ## CPC - G06N 20/00: Machine learning - G06F 11/1464: {for networked environments} - G06F 11/3003: {Monitoring arrangements specially adapted to the computing system or computing system component being monitored} - G06F 11/3006: {where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems (multiprogramming arrangements G06F9/46; allocation of resources G06F9/50)} - G06F 11/3476: {Data logging (G06F11/14, G06F11/2205 take precedence)} - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G06F 11/1451: {by selection of backup contents} - G06F 11/3051: {Monitoring arrangements for monitoring the configuration of the computing system or of the computing system component, e.g. monitoring the presence of processing resources, peripherals, I/O links, software programs (verification or detection of system hardware configuration G06F11/2247)} - G06F 2201/815: Virtual - G06F 2201/84: Using snapshots, i.e. a logical point-in-time copy of the data - H04L 67/10: in which an application is distributed across nodes in the network (software deployment G06F8/60; multiprogramming arrangements G06F9/46) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract Techniques for automated application reliability management using adaptable machine learning models are disclosed. In one example, a computer-implemented method may include identifying cloud components of an application deployed in a cloud service platform, determining relationships between the cloud components of the application and between the cloud components and other applications to generate a plurality of sub-assemblies, determining dependencies among the plurality of sub-assemblies to generate a super-assembly, generating infrastructure as code for application cloud components of the super-assembly and the plurality of sub-assemblies using metadata of the application cloud components, and performing a management operation to create a cloud infrastructure of the application using the generated infrastructure as code and verifying reliability of the created application using an adaptable machine learning model. ## Claims ### Claim 1 A computer-implemented method, comprising: identifying cloud components of an application deployed in a cloud service platform; determining relationships between the cloud components of the application and between the cloud components and other applications in the cloud service platform to generate a plurality of sub-assemblies; determining dependencies among the plurality of sub-assemblies to generate a super-assembly; generating infrastructure as code for application cloud components of the super-assembly and the plurality of sub-assemblies using metadata of the application cloud components; and performing a management operation to create a cloud infrastructure of the application using the generated infrastructure as code and verifying reliability of the created application using an adaptable machine learning model. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, wherein the management operation comprises at least one of: recovery, self-healing, migration, and cloning of the application. ### Claim 3 (depends on 1) The computer-implemented method of claim 1, wherein the cloud components are identified from a staging environment or a production environment of the application's development environment. ### Claim 4 (depends on 3) The computer-implemented method of claim 3, further comprising: receiving log trails associated with the production environment; analysing the log trails associated with the production environment; and training an adaptable machine learning model based on the analysis for detecting the reliability and/or anomalies associated with the application. ### Claim 5 (depends on 4) The computer-implemented method of claim 4, wherein verifying the reliability of the created application comprises: receiving log trails associated with the created application; analysing the log trails associated with the created application using the trained adaptable machine learning model; and detecting the reliability and/or the anomalies associated with the created application based on analysing the log trails associated with the created application. ### Claim 6 (depends on 5) The computer-implemented method of claim 5, further comprising: generating a notification on detecting an anomaly during execution of the created application. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, wherein the cloud infrastructure of the application is created in a cloud region different from the cloud service platform. ### Claim 8 (depends on 1) The computer-implemented method of claim 1, wherein the metadata associated with the application components of the super-assembly and the plurality of sub-assemblies comprises information selected from the group consisting of a processor, memory, storage, private IPs, elastic network Interfaces, elastic storage service types, encryption and encryption key management key IDs, security groups, routing table configurations, virtual private cloud resources, virtual private cloud peering, elastic load balancer configurations, auto-scaling groups, subnets, domain naming service configurations, object storage buckets and configurations, tags associated with resources running in a cloud region, Network Address Translation (NAT) Gateways, and Network Access Control lists. ### Claim 9 (depends on 1) The computer-implemented method of claim 1, wherein the relationships between the cloud components and between the cloud components and other applications comprise information related to one or more virtual machines deployed in the cloud, a storage, networks, security groups, virtual private gateways, elastic load balancers, Dynamic Host Configuration Protocol configurations, NAT Gateways, subnet configurations, internet gateways and/or route tables within a virtual private cloud. ### Claim 10 (depends on 1) The computer-implemented method of claim 1, wherein the dependencies among the sub-assemblies comprise connectivity information between cloud components of the sub-assemblies. ### Claim 11 (depends on 1) The computer-implemented method of claim 1, wherein the applications are running on virtual machines or containers. ### Claim 12 A system comprising: a management node connected to one or more cloud service platforms via a network, wherein the management node comprises an adaptive site reliability automation unit residing in memory and executable by a processor to: identify cloud components of an application deployed in a cloud service platform; determine relationships between the cloud components of the application and between the cloud components and other applications to generate a plurality of sub-assemblies; determine dependencies among the plurality of sub-assemblies to generate a super-assembly; generate infrastructure as code for application cloud components of the super-assembly and the plurality of sub-assemblies using metadata of the application cloud components; and perform a management operation to create a cloud infrastructure of the application using the generated infrastructure as code and verifying the reliability of the created application using an adaptable machine learning model. ### Claim 13 (depends on 12) The system of claim 12, wherein the wherein the management operation comprises at least one of: recovery, self-healing, migration, and cloning of the application. ### Claim 14 (depends on 12) The system of claim 12 further comprises an artificial intelligence app recovery and verification component to: receive log trails associated with a production environment of the application's development environment; analyse the log trails associated with the production environment; and training an adaptable machine learning model based on the analysis for detecting the reliability and/or anomalies associated with the application. ### Claim 15 (depends on 14) The system of claim 14 wherein the artificial intelligence app recovery and verification component is further configured to: receive log trails associated with the created application; analyse the log trails associated with the created application using the trained adaptable machine learning model; and detect the reliability and/or the anomalies associated with the created application based on analysing the log trails associated with the created application. ### Claim 16 (depends on 12) The system of claim 12, further comprises a timeline-based creation/recovery/rollback component to: create the cloud infrastructure of the application in a cloud region different from the cloud service platform. ### Claim 17 A non-transitory machine-readable medium storing instructions executable by a processing resource to: identify cloud components of an application deployed in a cloud service platform; determine relationships between the cloud components of the application and between the cloud components and other applications to generate a plurality of sub-assemblies; determine dependencies among the plurality of sub-assemblies to generate a super-assembly; generate infrastructure as code for application cloud components of the super-assembly and the plurality of sub-assemblies using metadata of the application cloud components; and perform a management operation to create a cloud infrastructure of the application using the generated infrastructure as code and verifying the reliability of the created application using an adaptable machine learning model. ### Claim 18 (depends on 17) The non-transitory machine-readable medium of claim 17, wherein the management operation comprises at least one of: recovery, self-healing, migration, and cloning of the application. ### Claim 19 (depends on 17) The non-transitory machine-readable medium of claim 17, further comprising instructions to: receive log trails associated with a production environment of the application's development environment; analyse the log trails associated with the production environment; and train an adaptable machine learning model based on the analysis for detecting the reliability and/or anomalies associated with the application. ### Claim 20 (depends on 19) The non-transitory machine-readable medium of claim 19, further comprising instructions to: receive log trails associated with the created application; analyse the log trails associated with the created application using the trained adaptable machine learning model; and detect the reliability and/or the anomalies associated with the created application based on analysing the log trails associated with the created application.