Patents by Inventor Lovekesh Vig

Lovekesh Vig 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).

  • Publication number: 20220284215
    Abstract: This disclosure relates to a method and system for extracting information from images of one or more templatized documents. A knowledge graph with a fixed schema based on background knowledge is used to capture spatial and semantic relationships of entities present in scanned document. An adaptive lattice-based approach based on formal concepts analysis (FCA) is used to determine a similarity metric that utilizes both spatial and semantic information to determine if the structure of the scanned document image adheres to any of the known document templates, If known document template whose structure is closely matching the structure of the scanned document is detected, then an inductive rule learning based approach is used to learn symbolic rules to extract information present in scanned document image. If a new document template is detected, then any future scanned document images belonging to new document template are automatically processed using the learnt rules.
    Type: Application
    Filed: May 27, 2021
    Publication date: September 8, 2022
    Applicant: Tata Consultancy Services Limited
    Inventors: Mouli RASTOGI, Syed Afshan ALI, Mrinal RAWAT, Lovekesh VIG, Puneet AGARWAL, Gautam SHROFF, Ashwin SRINIVASAN
  • Patent number: 11429837
    Abstract: Anomaly detection from time series is one of the key components in automated monitoring of one or more entities. Domain-driven sensor selection for anomaly detection is restricted by knowledge of important sensors to capture only a certain set of anomalies from the entire set of possible anomalies. Hence, existing anomaly detection approaches are not very effective for multi-dimensional time series. Embodiments of the present disclosure depict sparse neural network for anomaly detection in multi-dimensional time series (MDTS) corresponding to a plurality of parameters of entities. A reduced-dimensional time series is obtained from the MDTS via an at least one feedforward layer by using a dimensionality reduction model. The dimensionality reduction model and recurrent neural network (RNN) encoder-decoder model are simultaneously learned to obtain a multi-layered sparse neural network. A plurality of error vectors corresponding to at least one time instance of the MDTS is computed to obtain an anomaly score.
    Type: Grant
    Filed: March 14, 2019
    Date of Patent: August 30, 2022
    Assignee: TATA CONSULTANCY SERVICES LIMITED
    Inventors: Pankaj Malhotra, Narendhar Gugulothu, Lovekesh Vig, Gautam Shroff
  • Publication number: 20220222956
    Abstract: This disclosure relates generally to intelligent visual reasoning over graphical illustrations using a MAC unit. Prior arts use visual attention to map particular words in a question to specific areas in an image to memorize the corresponding answers, thereby resulting in a limited capability to answer questions of a specific type. The present disclosure incorporates the MAC unit to enable reasoning capabilities and accordingly attend to an area in the image to find the answer. The present disclosure therefore allows generalizing over a possible set of questions with varying complexities so that an unseen question can also be answered correctly based on the reasoning methods that it has learned. The system and method of the present disclosure can be used for understanding of visual information when processing documents like business reports, research papers, consensus reports etc. containing charts and reduce the time spent in manual analysis.
    Type: Application
    Filed: May 28, 2020
    Publication date: July 14, 2022
    Applicant: Tata Consultancy Services Limited
    Inventors: MONIKA SHARMA, ARINDAM CHOWDHURY, LOVEKESH VIG, SHIKHA GUPTA
  • Publication number: 20220215683
    Abstract: Keypoint extraction is done for extracting keypoints from images of documents. Based on different keypoint extraction approaches used by existing keypoint extraction mechanisms, number of keypoints extracted and related parameters vary. Disclosed herein is a method and system for keypoint extraction from images of one or more documents. In this method, a reference image and a test image of a document are collected as input. During the keypoint extraction, based on types of characters present in words extracted from the document images, a plurality of words are extracted. Further, all connected components in each of the extracted words are identified. Further, it is decided whether keypoints are to be searched in a first component or in a last component of all the identified connected components, and accordingly searches and extracts at least four of the keypoints from the test image and the corresponding four keypoints from the reference image.
    Type: Application
    Filed: September 6, 2020
    Publication date: July 7, 2022
    Applicant: Tata Consultancy Services Limited
    Inventors: Kushagra MAHAJAN, Monika SHARMA, Lovekesh VIG
  • Patent number: 11379717
    Abstract: Traditional systems and methods have implemented hand-crafted feature extraction from varying length time series that results in complexity and requires domain knowledge. Building classification models requires large labeled data and is computationally expensive. Embodiments of the present disclosure implement learning models for classification tasks in multi-dimensional time series by performing feature extraction from entity's parameters via unsupervised encoder and build a non-temporal linear classifier model. A fixed-dimensional feature vector is outputted using a pre-trained unsupervised encoder, which acts as off-the shelf feature extractor. Extracted features are concatenated to learn a non-temporal linear classification model and weight is assigned to each extracted feature during learning which helps to determine relevant parameters for each class. Mapping from parameters to target class is considered while constraining the linear model to use only subset of large number of features.
    Type: Grant
    Filed: March 25, 2019
    Date of Patent: July 5, 2022
    Assignee: Tata Consultancy Services Limited
    Inventors: Pankaj Malhotra, Priyanka Gupta, Lovekesh Vig, Gautam Shroff
  • Patent number: 11373090
    Abstract: In automated assistant systems, a deep-learning model in form of a long short-term memory (LSTM) classifier is used for mapping questions to classes, with each class having a manually curated answer. A team of experts manually create the training data used to train this classifier. Relying on human curation often results in such linguistic training biases creeping into training data, since every individual has a specific style of writing natural language and uses some words in specific context only. Deep models end up learning these biases, instead of the core concept words of the target classes. In order to correct these biases, meaningful sentences are automatically generated using a generative model, and then used for training a classification model. For example, a variational autoencoder (VAE) is used as the generative model for generating novel sentences and a language model (LM) is utilized for selecting sentences based on likelihood.
    Type: Grant
    Filed: September 18, 2018
    Date of Patent: June 28, 2022
    Assignee: Tata Consultancy Services Limited
    Inventors: Puneet Agarwal, Mayur Patidar, Lovekesh Vig, Gautam Shroff
  • Publication number: 20220188899
    Abstract: This disclosure relates generally to method and system for handling popularity bias in item recommendations. In an embodiment the method includes initializing an item embedding look-up matrix corresponding to items in a sequence of item-clicks with respect to a training data. L2 norm is applied to the item embedding look-up matrix to learn a normalized item embeddings. Using a neural network, a session embeddings corresponding to the sequences of item-clicks is modeled and L2 norm is applied to the session embeddings to obtain a normalized session embeddings. Relevance scores corresponding to each of the plurality of items arc obtained based on similarity between the normalized item embeddings and the normalized session embeddings. A multi-dimensional probability vector corresponding to the relevance scores for the items to be clicked in the sequence is obtained. A list of the items ordered based on the multi-dimensional probability vector is provided as recommendation.
    Type: Application
    Filed: August 25, 2020
    Publication date: June 16, 2022
    Applicant: Tata Consultancy Services Limited
    Inventors: PANKAJ MALHOTRA, PRIYANKA GUPTA, DIKSHA GARG, LOVEKESH VIG, GAUTAM SHROFF
  • Publication number: 20220156607
    Abstract: Session-based Recommendation (SR) is the task of recommending the next item based on previously recorded user interactions. However, most existing approaches for SR either rely on costly online interactions with real users (model-free approaches) or rely on potentially biased rule-based or data-driven user-behavior models (model-based approaches) for learning. This disclosure relates to a system and method for selecting session-based recommendation policies using historical recommendations and user feedback. Herein, the learning of recommendation policies given offline or batch data from old recommendation policies based on a Distributional Reinforcement Learning (DRL) based recommender system in the offline or batch-constrained setting without requiring access to a user-behavior model or real-interactions with the users.
    Type: Application
    Filed: March 8, 2021
    Publication date: May 19, 2022
    Applicant: Tata Consultancy Services Limited
    Inventors: Diksha Garg, Pankaj Malhotra, Priyanka Gupta, Lovekesh Vig, Gautam Shroff
  • Patent number: 11294946
    Abstract: This disclosure relates generally to methods and systems for generating a textual summary from a tabular data. During the textual summary generation using conventional end-to-end neural network-based techniques, a numeric data present in the tables is encoded via textual embeddings. However, the textual embeddings cannot reliably encode information about numeric concepts and relationships. The methods and systems generate the textual summary from the tabular data, by incorporating rank information for different records present in the tabular data. Then, a two-stage encoder-decoder network is used to learn correlations between the rank information and the probability of including the records based on the rank information, to obtain the textual summary generation model. The textual summary generation model identifies the content selection having the records present in the tables to be included in the textual summary and generates the textual summary from the identified content selection.
    Type: Grant
    Filed: May 13, 2021
    Date of Patent: April 5, 2022
    Assignee: TATA CONSULTANCY SERVICES LIMITED
    Inventors: Mrinal Rawat, Lovekesh Vig, Amit Sangroya, Gautam Shroff
  • Publication number: 20220093249
    Abstract: In presence of high-cardinality treatment variables, number of counterfactual outcomes to be estimated is much larger than number of factual observations, rendering the problem to be ill-posed. Furthermore, lack of information regarding the confounders among large number of covariates pose challenges in handling confounding bias. Essential is to find lower-dimensional manifold where an equivalent problem of causal inference can be posed, and counterfactual outcomes can be computed.
    Type: Application
    Filed: July 13, 2021
    Publication date: March 24, 2022
    Applicant: Tata Consultancy Services Limited
    Inventors: ANKIT SHARMA, GARIMA GUPTA, RANJITHA PRASAD, ARNAB CHATTERJEE, LOVEKESH VIG, GAUTAM SHROFF
  • Publication number: 20220036166
    Abstract: This disclosure relates to optimizing an operation of an equipment by a neural network based optimizer is provided. The method include receiving, information associated with at least one equipment instance (j) as an input at a predefined sequence of timestamps; training, a plurality of simulation models for each equipment instance to obtain a function (fj); processing, the external input parameters (et) to obtain a fixed-dimensional vector and passed as an input to obtain an vector (it); generating, a modified (it) from the output vector (it) based on a domain constraint value; computing, a reward (rt) based on (i) the function (fj), (ii) the modified (it), (iii) the external input parameters (et), and (iv) a reward function (Rj); and iteratively performing the steps of processing, generating, and computing reward (rt) for a series of subsequent equipment instances after expiry of the predefined sequence of timestamps associated with a first equipment instance.
    Type: Application
    Filed: November 28, 2019
    Publication date: February 3, 2022
    Applicant: Tata Consultancy Services Limited
    Inventors: Vishnu TANKASALA VEPARALA, Solomon Pushparaj MANUELRAJ, Ankit BANSAL, Pankaj MALHOTRA, Lovekesh VIG, Gautam SHROFF, Venkataramana RUNKANA, Sivakumar SUBRAMANIAN, Aditya PAREEK, Vishnu Swaroopji MASAMPALLY, Nishit RAJ
  • Publication number: 20210406603
    Abstract: Several applications capture data from sensors resulting in multi-sensor time series. Existing neural networks-based approaches for such multi-sensor/multivariate time series modeling assume fixed input-dimension/number of sensors. Such approaches can struggle in practical setting where different instances of same device/equipment come with different combinations of installed sensors. In the present disclosure, neural network models are trained from such multi-sensor time series having varying input dimensionality, owing to availability/installation of different sensors subset at each source of time series. Neural network (NN) architecture is provided for zero-shot transfer learning allowing robust inference for multivariate time series with previously unseen combination of available dimensions/sensors at test time.
    Type: Application
    Filed: February 22, 2021
    Publication date: December 30, 2021
    Applicant: Tata Consultancy Services Limited
    Inventors: Jyoti NARWARIYA, Pankaj Malhotra, Vibhor Gupta, Vishnu Tankasala Veparala, Lovekesh Vig, Gautam Shroff
  • Publication number: 20210357443
    Abstract: This disclosure relates generally to methods and systems for generating a textual summary from a tabular data. During the textual summary generation using conventional end-to-end neural network-based techniques, a numeric data present in the tables is encoded via textual embeddings. However, the textual embeddings cannot reliably encode information about numeric concepts and relationships. The methods and systems generate the textual summary from the tabular data, by incorporating rank information for different records present in the tabular data. Then, a two-stage encoder-decoder network is used to learn correlations between the rank information and the probability of including the records based on the rank information, to obtain the textual summary generation model. The textual summary generation model identifies the content selection having the records present in the tables to be included in the textual summary and generates the textual summary from the identified content selection.
    Type: Application
    Filed: May 13, 2021
    Publication date: November 18, 2021
    Applicant: Tata Consultancy Services Limited
    Inventors: Mrinal RAWAT, Lovekesh VIG, Amit SANGROYA, Gautam SHROFF
  • Publication number: 20210326727
    Abstract: Causality is a crucial paradigm in several domains where observational data is available. Primary goal of Causal Inference (CI) is to uncover cause-effect relationship between entities. Conventional methods face challenges in providing an accurate CI framework due to cofounding and selection bias in multiple treatment scenario. The present disclosure computes a Propensity Score (PS) from a received CI data for the plurality of subjects under test for a treatment. A Generalized Propensity Score (GPS) is computed for a plurality of treatments corresponding to the plurality of subjects by using the PS. Further, a plurality of task batches are created using the GPS and given as input to the DNN for training. Errors in factual data and in balancing representation of the DNN are rectified using a novel loss function. The trained DNN is further used for predicting the counter factual treatment response corresponding to the factual treatment data.
    Type: Application
    Filed: March 2, 2021
    Publication date: October 21, 2021
    Applicant: Tata Consultancy Services Limited
    Inventors: Garima GUPTA, Ankit SHARMA, Ranjitha PRASAD, Arnab CHATTERJEE, Lovekesh VIG, Gautam SHROFF
  • Patent number: 11023686
    Abstract: Conversational systems are required to be capable of handling more sophisticated interactions than providing factual answers only. Such interactions are handled by resolving abstract anaphoric references in conversational systems which includes antecedent fact references and posterior fact references. The present disclosure resolves abstract anaphoric references in conversational systems using hierarchically stacked neural networks. In the present disclosure, a deep hierarchical maxpool network based model is used to obtain a representation of each utterance received from users and a representation of one or more generated sequences of utterances. The obtained representations are further used to identify contextual dependencies with in the one or more generated sequences which helps in resolving abstract anaphoric references in conversational systems.
    Type: Grant
    Filed: July 9, 2019
    Date of Patent: June 1, 2021
    Assignee: TATA CONSULTANCY SERVICES LIMITED
    Inventors: Puneet Agarwal, Prerna Khurana, Gautam Shroff, Lovekesh Vig
  • Publication number: 20210103812
    Abstract: Neural networks can be used for time series data classification. However, in a K-shot scenario in which sufficient training data is unavailable to train the neural network, the neural network may not produce desired results. Disclosed herein are a method and system for training a neural network for time series data classification. In this method, by processing a plurality of task specific data, a system generates a set of updated parameters, which is further used to train a neural network (network) till a triplet loss is below a threshold. The network is trained on a diverse set of few-shot tasks sampled from various domains (e.g. healthcare, activity recognition, and so on) such that it can solve a target task from another domain using only a small number of training samples from the target task.
    Type: Application
    Filed: August 27, 2020
    Publication date: April 8, 2021
    Applicant: Tata Consultancy Services Limited
    Inventors: Pankaj MALHOTRA, Jyoti NARWARIYA, Lovekesh VIG, Gautam SHROFF
  • Patent number: 10970531
    Abstract: This disclosure relates to digitization of industrial inspection sheets. Digital scanning of paper based inspection sheets is a common process in factory settings. The paper based scans have data pertaining to millions of faults detected over several decades of inspection. The technical challenge ranges from image preprocessing and layout analysis to word and graphic item recognition. This disclosure provides a visual pipeline that works in the presence of both static and dynamic background in the scans, variability in machine template diagrams, unstructured shape of graphical objects to be identified and variability in the strokes of handwritten text. The pipeline incorporates a capsule and spatial transformer network based classifier for accurate text reading and a customized Connectionist Text Proposal Network (CTPN) for text detection in addition to hybrid techniques for arrow detection and dialogue cloud removal.
    Type: Grant
    Filed: February 25, 2019
    Date of Patent: April 6, 2021
    Assignee: Tata Consultancy Services Limited
    Inventors: Rohit Rahul, Arindam Chowdhury, Lovekesh Vig, . Animesh, Samarth Mittal
  • Patent number: 10936897
    Abstract: Various methods are using SQL based data extraction for extracting relevant information from images. These are rule based methods of generating SQL-Query from NL, if any new English sentences are to be handled then manual intervention is required. Further becomes difficult for non-technical user. A system and method for extracting relevant from the images using a conversational interface and database querying have been provided. The system eliminates noisy effects, identifying the type of documents and detect various entities for diagrams. Further a schema is designed which allows an easy to understand abstraction of the entities detected by the deep vision models and the relationships between them. Relevant information and fields can then be extracted from the document by writing SQL queries on top of the relationship tables. A natural language based interface is added so that a non-technical user, specifying the queries in natural language, can fetch the information effortlessly.
    Type: Grant
    Filed: March 14, 2019
    Date of Patent: March 2, 2021
    Assignee: TATA CONSULTANCY SERVICES LIMITED
    Inventors: Lovekesh Vig, Gautam Shroff, Arindam Chowdhury, Rohit Rahul, Gunjan Sehgal, Vishwanath Doreswamy, Monika Sharma, Ashwin Srinivasan
  • Patent number: 10853640
    Abstract: This disclosure relates generally to document processing, and more particularly to extracting information from hand-marked industrial inspection sheets. In an embodiment, the system performs localization of text as well as arrows in the inspection sheet, and identifies text that matches each arrow. Further by identifying machine zone each arrow is pointing to, the system assigns corresponding text to the appropriate machine zone; thus facilitating digitization of the inspection sheets.
    Type: Grant
    Filed: March 28, 2018
    Date of Patent: December 1, 2020
    Assignee: Tata Consultancy Services Limited
    Inventors: Gaurav Gupta, Swati, Monika Sharma, Lovekesh Vig
  • Patent number: 10839246
    Abstract: The present disclosure provides systems and methods for end-to-end handwritten text recognition using neural networks. Most existing hybrid architectures involve high memory consumption and large number of computations to convert an offline handwritten text into a machine readable text with respective variations in conversion accuracy. The method combine a deep Convolutional Neural Network (CNN) with a RNN (Recurrent Neural Network) based encoder unit and decoder unit to map a handwritten text image to a sequence of characters corresponding to text present in the scanned handwritten text input image. The deep CNN is used to extract features from handwritten text image whereas the RNN based encoder unit and decoder unit is used to generate converted text as a set of characters. The disclosed method requires less memory consumption and less number of computations with better conversion accuracy over the existing hybrid architectures.
    Type: Grant
    Filed: July 10, 2019
    Date of Patent: November 17, 2020
    Assignee: Tata Consultancy Services Limited
    Inventors: Arindam Chowdhury, Lovekesh Vig