公开(公告)号：US20200177703A1

公开(公告)日：2020-06-04

申请号：US16698241

申请日：2019-11-27

Applicant: Tata Consultancy Services Limited

Inventor： SATNIK PANDA ,  PRATEEP MISRA ,  SOUMITRA NASKAR

IPC: H04L29/08 ,  H04L12/24 ,  H04L29/06

Abstract: This disclosure relates to a distributed state exchanging model for assets of an organization or entity for an identified task in a domain of interest. The model provides a context aware autonomous Internet of things (IoT) based cognitive edge network, wherein each node is aware of the state of the other nodes based on a subscription. The state information is seamlessly updated and maintained by a certifying node of each group. The nodes are grouped based on associated capability definitions such that at least some of the groups form a hierarchy within the cognitive edge network for completing the identified task. Since the network is context aware, a new sub-task towards completing the identified task is autonomously selected by either groups or by the nodes based on the context thereby obviating a need for centralized scheduling.

公开(公告)号：US20220327336A1

公开(公告)日：2022-10-13

申请号：US17368584

申请日：2021-07-06

Applicant: Tata Consultancy Services Limited

Inventor： Tanushyam Chattopadhyay ,  ABHISEK DAS ,  PRATEEP MISRA ,  SHUBHRANGSHU GHOSH ,  SUVRA DUTTA

IPC: G06K9/62

Abstract: Industries deploy a plethora of sensors that are attached to a system or human being, respectively. Under multi-sensor environment scenarios, there is a need to detect which sensors are behaving similarly within a time span. Sensor values often vary in range of values yet depict similar time series characteristic and sometimes have a phase difference in operation, thus making it impossible to detect such sensor similarity in a large system where the number of input parameters/sensor observations. Systems and methods of the present disclosure determine similar behavioral pattern between time series data obtained from multiple sensors and cluster the sensors. The system implements a pattern recognition-based approach to find the similarity and then applies a Dynamic Programming-based approach to detect similarity in at least two time series data and cluster the sensors and corresponding time series data into specific cluster(s).