Tata Consultancy Services Limited

Souvik Barat

Vinay Vasant Kulkarni

Prasenjit Das

Vinay Kulkarni

Sankaranarayanan Viswanathan

Hardik Meisheri

Harshad Khadilkar

Vinita Baniwal

Prashant Kumar

Kaustav Bhattacharya

Monika Gajrani

Generally, in complex systems such as business organizations and supply chain networks, decisions making and control are challenging due to dynamic environment thereof. The embodiments herein provide method and system that uses reinforcement learning (RL) for exploring policies and deciding control actions, and actor-based modelling and simulation for performing accurate long-term rollouts of the policies, in order to optimize operation of the complex systems. In an embodiment, a method for actor based simulation of complex system includes modeling, actors of the complex system using an actor abstraction, where actors includes RL agents embodied in each subsystem of the complex system, and executes micro-level interactions amongst the subsystems. An emergent macro-behavior of the complex system is simulated by the using the RL agents based on the micro-level interactions. Optimal decisions pertaining to actions of the RL agents are learnt based on the emergent macro-behavior of the complex subsystem.

System and method for actor based simulation of complex system using reinforcement learning

The present invention provides a computationally efficient system for developing configurable, extensible business application product lines using model-driven techniques. The invention enables to create a common business application with a set of pre-defined variants, selection of a suitable variant from the pre-defined set, and composition of the common application with the selected variant into a purpose-specific business application and also provides for modeling of commonality and variability thus leading to a single specification. The invention provides model-based solution to address extensibility and configurability of both structural and behavioral aspects in a functionality dimension of database intensive business application and it supports configuration process at three different stages of application development (i.e. design time, installation time and run time) of database intensive business application. The invention reduces the cost as well as computational time for creating new business applications, and leads to effective maintenance and smooth evolution.

Computationally efficient system for developing configurable, extensible business application product lines using model-driven techniques

The present invention provides a system and method for developing a set of business process definitions sharing the common business intent as a business process family using model-driven techniques. The present invention minimizes on development time and resources thus leading to a cost effective system and method for developing business process families. The invention enables to create a business process family which can be easily configured to behave as a specific business process thus meeting the needs of a set of apriori known situations. The invention supports configuration process at different stages (i.e. design time, and run time) of the business process application and also support extension of the configuration structure at different stages (i.e. design time, and run time). The invention enables to create a business process family which can be easily extended to meet the needs of an as yet unseen situation.

Efficient system for realizing business process families using model-driven techniques

Growing community of inventors

Pune, India

Souvik Barat