Patents by Inventor Manjunath Ramachandra

Manjunath Ramachandra has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 11030815
    Abstract: The invention relates generally to Virtual Reality (VR) and more particularly to method and system for rendering VR content. The method includes identifying user interaction with at least one object within a VR environment. The method further includes training a deep learning feature extraction model to identify predetermined and undetermined interactions in the VR environment. The deep learning feature extraction model is trained based on a plurality of scene images and associated applied templates that are provided to the deep learning feature extraction model. Each of the applied templates identifies at least one spurious object and at least one object of interest in an associated scene image. The method includes classifying the user interaction as one of a predetermined interaction and an undetermined interaction based on the deep learning feature extraction model. The method further includes rendering a VR content in response to the user interaction being classified.
    Type: Grant
    Filed: October 22, 2019
    Date of Patent: June 8, 2021
    Assignee: Wipro Limited
    Inventors: Manjunath Ramachandra Iyer, Sethuraman Ulaganathan
  • Publication number: 20210165954
    Abstract: This disclosure relates to method and system for providing user-specific explanations for an output generated by an Artificial Neural Network (ANN) model. The method may include receiving a training dataset, and identifying one or more relevant features from the training dataset. The method may further include distributing the one or more relevant features into a plurality of groups. The plurality of groups may correspond to a plurality of levels of domain knowledge of users. The method may further include generating a plurality of vocabularies of explanations for an output generated by the ANN model for the training dataset corresponding to the plurality of groups, using the one or more relevant features.
    Type: Application
    Filed: January 14, 2020
    Publication date: June 3, 2021
    Inventors: Manjunath Ramachandra IYER, Chandrashekar Bangalore Nagaraj
  • Patent number: 11025501
    Abstract: Disclosed subject matter relates to field of Internet of Things (IoT) that performs a method and system for providing seamless connectivity in an IoT network. A router deployment system receives input data from input sources, comprising at least one of wireless routers and IoT devices, connected in an IoT network. Further, the router deployment system may predict intensity of data traffic at each wireless router based on the input data and may estimate a need for relocating at least one portable router based on intensity of data traffic at each wireless router. Thereafter, the router deployment system may relocate the at least one portable router to a target location for providing seamless connectivity in the IoT network. The present disclosure reduces load on wireless routers and waiting time for transmitting data via wireless routers by dynamically deploying portable routers for providing necessary bandwidth and accessibility, as per requirement.
    Type: Grant
    Filed: March 30, 2020
    Date of Patent: June 1, 2021
    Assignee: Wipro Limited
    Inventor: Manjunath Ramachandra Iyer
  • Patent number: 11017006
    Abstract: The present disclosure relates to a method and a system for generating sentiment-based summaries for a user review. In an embodiment, a text analyzer receives a block of text indicating a user review. The text analyzer may generate one or more vectors for the plurality of words. Further, a relation is identified among the one or more vectors. A model is trained to identify a relation among the one or more vectors. Using the relation between the one or more vectors, a sentiment associated with the block of text is determined. Thereafter, one or more keywords from the block of text contributing to the determined sentiment is are identified and are classified into categories according to the sentiment contributed by the one or more words. Thereafter, the summary is generated for each category using the corresponding one or more words.
    Type: Grant
    Filed: March 19, 2019
    Date of Patent: May 25, 2021
    Assignee: Wipro Limited
    Inventors: Arindam Chatterjee, Manjunath Ramachandra Iyer, Vinutha Bangalore Narayanamurthy
  • Publication number: 20210150339
    Abstract: A technique is provided for minimizing impact of a faulty node associated with an artificial network. The technique includes detecting a faulty node associated with the artificial neural network. The faulty node causes a faulty path in the artificial neural network. Further, a plurality of alternate paths are identified to reroute the faulty path. Based on the identified plurality of alternate paths, the faulty path is rerouted by assigning one or more weights associated with the faulty node to one or more nodes associated with the plurality of alternate paths.
    Type: Application
    Filed: January 2, 2020
    Publication date: May 20, 2021
    Inventor: Manjunath Ramachandra IYER
  • Patent number: 11010180
    Abstract: The present disclosure discloses method and guidance providing system for providing real-time guidance to users during troubleshooting of devices. The guidance providing system receives user input indicating troubleshooting actions on device, by user, where user input comprises textual input and non-textual input, identifies object in device associated with troubleshooting actions and state of user while performing troubleshooting actions, from non-textual input. The object identified from non-textual input is mapped with textual input to obtain mapped user input. Consistency of mapped user input is verified based on conversation information and domain specific content associated with device. Sequence of instructions corresponding to mapped user input, based on state of user and one or more similar troubleshooting actions, may be extracted from knowledge database.
    Type: Grant
    Filed: July 17, 2018
    Date of Patent: May 18, 2021
    Assignee: Wipro Limited
    Inventors: Manjunath Ramachandra Iyer, Meenakshi Sundaram Murugeshan
  • Patent number: 11003915
    Abstract: This disclosure relates to a method and system for summarizing multimedia content. The method may include receiving multimedia content. The method may further include identifying one or more primary objects, wherein identifying the primary objects comprises identifying one or more actions associated with the primary objects and one or more interactions between the primary objects and one or more secondary objects. The primary objects are associated with one or more parameters. The method may further include determining at least one primary object of interest from the primary objects by selectively prioritizing the parameters. The method may further include summarizing the multimedia content based on the primary object of interest, actions associated with the primary object of interest, interactions between the primary object of interest and the secondary objects, and interactions between the secondary objects and one or more tertiary objects.
    Type: Grant
    Filed: March 29, 2019
    Date of Patent: May 11, 2021
    Assignee: Wipro Limited
    Inventor: Manjunath Ramachandra Iyer
  • Patent number: 10990761
    Abstract: The present disclosure discloses method and a content rendering system for providing multimodal content to selective users during visual presentation. The method includes identifying plurality of users attending visual presentation based on login and user details provided during registering to visual presentation. One or more keywords is determined in visual presentation associated with one or more auxiliary content based on narration by a presenter. The one or more auxiliary content corresponding to each of the one or more keywords is retrieved. The method includes identifying one or more users from plurality of users allowed to receive one or more auxiliary content based on user details and predefined auxiliary mapping details. The one or more auxiliary content is combined with corresponding one or more keywords in visual presentation. Thereafter, combined auxiliary content along with the visual presentation is provided to users in respective user devices.
    Type: Grant
    Filed: March 15, 2019
    Date of Patent: April 27, 2021
    Assignee: Wipro Limited
    Inventor: Manjunath Ramachandra Iyer
  • Patent number: 10990579
    Abstract: The present disclosure discloses a method and system for providing response to a user input. The system receives a user input, processes the user input by finding equivalents of the user input and dividing each of the user input and the equivalents into a frame. One or more keywords are generated for each of the one or more frames. Further, each of the one or more frames are classified into one or more domains present in a knowledge graph. Then, one or more objects are determined in each of the corresponding one or more domains based on the corresponding one or more keywords. Further, a processing means is determined for each of the one or more objects based on the metadata of the corresponding one or more objects. The processing means is processed by the system for providing response to the user input.
    Type: Grant
    Filed: January 18, 2018
    Date of Patent: April 27, 2021
    Assignee: Wipro Limited
    Inventors: Manjunath Ramachandra Iyer, Suyog Trivedi, Gopichand Agnihotram
  • Patent number: 10990602
    Abstract: The present disclosure relates to a method and a system for generating optimized response to user input. The system may receive a user input indicative of a data required by the user. The system identifies one or more keywords based on the user input. The system determines user expertise level based on search graphs generated using the one or more keywords. The system retrieves a plurality of responses relevant to the data based on the one or more keywords. The system assigns a value to each of the plurality of responses based on the user expertise level. The system identifies a base response in one or more responses having the value greater than a threshold value. Finally, the system collates content of the one or more responses excluding the base response with content of the base response, in a pre-defined sequential order, for generating the optimized response to user input.
    Type: Grant
    Filed: July 31, 2018
    Date of Patent: April 27, 2021
    Assignee: Wipro Limited
    Inventors: Vinutha Bangalore Narayanamurthy, Manjunath Ramachandra Iyer
  • Patent number: 10984279
    Abstract: A method and system for machine translation of text is disclosed. The method includes processing an image comprising a text to generate a pattern associated with the text based on a trained Convolution Neural Network (CNN). The method further includes mapping the pattern to a word in a mapping table and at least one text attribute, based on a classifier network. The method further includes initiating an Optical Character Recognition (OCR) conversion for the pattern, when at least one of the mapping between at least one of the pattern and at least one word in the mapping table and the mapping between the pattern and the at least one text attribute is below a predefined threshold. The method further includes performing incremental learning for the trained CNN and the classifier network based on the OCR conversion.
    Type: Grant
    Filed: August 16, 2019
    Date of Patent: April 20, 2021
    Assignee: Wipro Limited
    Inventor: Manjunath Ramachandra Iyer
  • Publication number: 20210097894
    Abstract: A method and a system of selective encryption of a test dataset is disclosed. In an embodiment, the method may include determining a relevancy grade associated with each of a plurality of datapoints within a test dataset by comparing the test dataset with a common heat map, wherein the common heat map is generated using a plurality of training datasets. The method may further include calculating, based on the relevancy grade, an encryption level associated with each of the plurality of datapoints. The method may further include selectively encrypting at least one datapoint from the plurality of datapoints based on the encryption level associated with each of the plurality of datapoints. The at least one data point is rendered to a user after being decrypted.
    Type: Application
    Filed: December 4, 2019
    Publication date: April 1, 2021
    Inventors: Manjunath Ramachandra IYER, Sibsambhu KAR, Vinutha Bangalore NARAYANAMURTHY
  • Publication number: 20210097294
    Abstract: The present disclosure relate to effectively determining spatial and temporal features for extracting low-level and high-level features from image frames of a multimedia content. A plurality of image frames are received from an imaging unit. Spatial filters are applied on each image frame to generate a first set of activation maps which provide spatial features in the image frames. Further, a temporal filter is applied on the plurality of image frames at a plurality of levels to generate one or more second set of activation maps corresponding to each level for determining temporal features in the image frames. Thereafter, the spatial feature from each image and temporal feature of the plurality of image frames from each level is extracted, which represent low-level and high-level spatial and temporal features.
    Type: Application
    Filed: November 26, 2019
    Publication date: April 1, 2021
    Inventors: Vinutha B. NARAYANMURTHY, Sibsambhu KAR, Manjunath Ramachandra IYER
  • Publication number: 20210074064
    Abstract: A method and system for rendering Virtual Reality (VR) content is disclosed. The method may include identifying user interaction with at least one object within a VR environment. The method may further include training a deep learning feature extraction model to identify predetermined and undetermined interactions in the VR environment. The deep learning feature extraction model is trained based on a plurality of scene images and associated applied templates that are provided to the deep learning feature extraction model. Each of the applied templates identifies at least one spurious object and at least one object of interest in an associated scene image. The method may include classifying the user interaction as one of a predetermined interaction and an undetermined interaction based on the deep learning feature extraction model. The method may further include rendering a VR content in response to the user interaction being classified.
    Type: Application
    Filed: October 22, 2019
    Publication date: March 11, 2021
    Inventors: Manjunath Ramachandra Iyer, Sethuraman Ulaganathan
  • Patent number: 10936586
    Abstract: Disclosed herein is method and system for providing domain-specific response to user query. The user query is split into one or more sub-queries and domain of each of the sub-queries is determined based on domain-specific keywords present in each of the sub-queries. One or more responses to each of the sub-queries is retrieved from corresponding Domain-specific Query Handlers (DQHs). Finally, each of the one or more responses are collated for providing the domain-specific query to the user. In an embodiment, the DQHs are hierarchically arranged based on their importance and relevance to the user query. Further, the resources are allocated to each of the DQHs based on their hierarchy, thereby optimally distributing the resources among the DQHs. In an embodiment, the method of present disclosure ensures completeness/sufficiency in the response, before collating the one or more responses and providing the domain-specific response to the user.
    Type: Grant
    Filed: January 18, 2018
    Date of Patent: March 2, 2021
    Assignee: Wipro Limited
    Inventor: Manjunath Ramachandra Iyer
  • Patent number: 10917375
    Abstract: A method of managing messages in a communication device is disclosed. The method includes receiving messages through a communication device. Critical messages may be determined by identification of one or more critical content in the one or more messages and analyzed based on the context and content associated with the critical messages. A priority for each of the critical messages may be generated by assigning vocabulary weight to the critical content and a context weight to the critical message. The critical messages may be queued based on their respective priorities. Dynamic allocation of resources by adjusting at least one of buffer, and packet delay associated with the communication device based on the priority of the one or more messages in the queue is done. The one or more messages in the communication device may be managed based on the queuing and the dynamic allocation of resources.
    Type: Grant
    Filed: March 29, 2019
    Date of Patent: February 9, 2021
    Assignee: Wipro Limited
    Inventor: Manjunath Ramachandra Iyer
  • Patent number: 10901494
    Abstract: This technology relates to virtual assistance including a method and system for providing gesture-based interaction with a virtual product from a remote location. A virtual assistance system identifies in real-time, direct or personified user actions performed by a user on the virtual product from images and videos. Further, user actions are mapped with predefined user actions related to virtual product to determine values associated with predefined qualifiers and predefined consequences associated with the mapped predefined user actions. Furthermore, pre-stored images and pre-stored videos corresponding to the mapped predefined user actions, values associated with the predefined qualifiers and the predefined consequences, and detected active objects are extracted.
    Type: Grant
    Filed: March 28, 2017
    Date of Patent: January 26, 2021
    Assignee: Wipro Limited
    Inventors: Manjunath Ramachandra, Jijith Nadumuri Ravi
  • Patent number: 10885119
    Abstract: Disclosed herein is method and system for processing multimodal user queries. The method comprises determining availability of one or more responses to each of one or more sub-queries, wherein the one or more sub-queries are formed by splitting the multimodal user queries. The method detects requirement of an expert to provide the one or more responses upon determining at least one of unavailability of the one or more responses by the response generation system or based predefined conditions. Thereafter, a summarized content is generated by summarizing context of the one or more sub-queries and historical conversation data associated with the one or more sub-queries. Based on the summarized content, the one or more sub-queries are reformulated. Finally, the one or more responses received, from the expert, for the reformulated one or more sub-queries are collated provided as the one or more responses for the multimodal user queries.
    Type: Grant
    Filed: January 18, 2018
    Date of Patent: January 5, 2021
    Assignee: Wipro Limited
    Inventor: Manjunath Ramachandra Iyer
  • Publication number: 20200410283
    Abstract: A method and system of multi-modality classification using augmented data is disclosed. The method includes generating a pattern for each of a plurality of augmented data associated with each of a plurality of object classes, based on at least one modality associated with each of the plurality of objects classes using a Long Term Short Memory (LSTM) classifier and a Layer-wise Relevance Propagation (LRP). The method further includes classifying an input image into a first object class of the plurality of object classes based on one or more objects within the input image using a Convolution Neural Network (CNN). The method further includes re-classifying the input image into one of the first object class or a second object class of the plurality of object classes when the accuracy of classification by the CNN into the first object class is below a matching threshold.
    Type: Application
    Filed: August 14, 2019
    Publication date: December 31, 2020
    Inventors: Manjunath Ramachandra Iyer, Sethuraman Ulaganathan
  • Publication number: 20200412664
    Abstract: The present disclosure provides a method and a system for triggering of Internet of things (IoT) devices. The system comprising a processor causes the processor to receive a change in output of first IoT device from a plurality of IoT devices, wherein the plurality of IoT devices are connected to each other, determine one or more connectivity paths between the plurality of IoT devices including the first IoT device based on stored connectivity paths between the plurality of IoT devices in a database, select one of the determined one or more connectivity paths between the plurality of IoT devices, wherein the selecting is based on similarity of metadata of each of the plurality of IoT devices in each of the one or more connectivity paths and trigger one or more IoT devices of the plurality of IoT devices in the selected connectivity path.
    Type: Application
    Filed: August 21, 2019
    Publication date: December 31, 2020
    Inventor: Manjunath Ramachandra