| CPC G06Q 10/06393 (2013.01) [G06F 40/30 (2020.01)] | 20 Claims |
|
1. A computer-implemented method for automatically managing one or more applications in one or more environments using an artificial intelligence (AI) driven autonomic application management framework, the computer-implemented method comprising:
obtaining, by one or more hardware processors, one or more items of data from at least one of: one or more electronic devices associated with one or more users and one or more databases, wherein the one or more data comprise information associated with one or more service level agreements (SLAs) corresponding to the one or more applications in the one or more environments, and wherein the one or more service level agreements (SLAs) associated with the one or more applications comprise one or more natural language texts;
determining, by the one or more hardware processors, one or more semantics and structure of the one or more natural language texts associated with the one or more service level agreements (SLAs) based on analysis of the one or more natural language texts associated with the one or more service level agreements (SLAs), using a first artificial intelligence (AI) model;
extracting, by the one or more hardware processors, one or more service level objectives (SLOs) and associated metrics corresponding to one or more services specified in the one or more service level agreements (SLAs) based on the determined one or more semantics and structure of the one or more natural language texts associated with the one or more service level agreements (SLAs), using the first artificial intelligence (AI) model;
obtaining, by the one or more hardware processors, one or more first real-time data comprising one or more actual performance levels, and one or more service level indictors (SLIs), of the one or more services associated with the one or more applications, from one or more monitoring platforms;
determining, by the one or more hardware processors, whether the one or more actual performance levels of the one or more services associated with the one or more applications, are compliant with one or more expected performance levels by comparing the one or more actual performance levels with one or more pre-defined key performance indicators (KPIs) and one or more pre-defined goals of the one or more services defined in at least one of: the service level agreements (SLAs) and the service level objectives (SLOs), using the first artificial intelligence (AI) model,
wherein the first artificial intelligence (AI) model is trained with one or more pre-defined rules and criteria to assess the one or more pre-defined key performance indicators (KPIs) and one or more pre-defined goals defined in at least one of: the service level agreements (SLAs) and the service level objectives (SLOs);
automatically updating, by the one or more hardware processors, the one or more service level objectives (SLOs) and associated metrics corresponding to the one or more services specified in the one or more service level agreements (SLAs), based on deviations of the one or more actual performance levels of the one or more services from the one or more expected performance levels, using the first artificial intelligence (AI) model;
fine-tuning, by the one or more hardware processors, the trained first artificial intelligence (AI) model with the determined one or more semantics and structure of the one or more natural language texts specific to the one or more service level objectives (SLOs) and associated metrics, using one or more techniques comprising at least one of: few shots learning, chain of thoughts, tree of thoughts, ReACT trajectories, symbolic reasoning, self-consistency, automatic reasoning, and tool use, wherein the fine-tuned first artificial intelligence (AI) model comprises a Linguistic Latent Attribute model (LLAMA 2), and wherein the LLAMA 2 is collection of pre-trained and fine-tuned generative test models;
generating by the one or more hardware processors, the one or more actions, to be applied to the one or more environments, based on at least one of: current state of the one or more service level objectives (SLOs) and probabilities of meeting the one or more service level objectives (SLOs), by at least one of: learning, planning procedures, and resembling actor-critic updates for Partial Observable Markov Decision Processes (POMDPs), wherein the Augmented Deep Active learning for text and Planning Trajectories (ADAPT) agent with the Partial Observable Markov Decision Processes (POMDPs) is configured to monitor the one or more services for adjusting one or more governance principles in the one or more environments, wherein the ADAPT agent is further configured to establish a framework to enable self-correction and self-reinforcement;
generating, by the one or more hardware processors, one or more insights associated with the one or more actions, to be applied to one or more corresponding services, to be performed to automatically manage the one or more applications based on the automatic updates on the one or more service level objectives (SLOs) and associated metrics corresponding to the one or more services specified in the one or more service level agreements (SLAs), using the first artificial intelligence (AI) model; and
providing, by the one or more hardware processors, information associated with the one or more actions, to be applied to the one or more corresponding services to automatically manage the one or more applications, to the one or more environments.
|