公开(公告)号：US20220284215A1

公开(公告)日：2022-09-08

申请号：US17332021

申请日：2021-05-27

Applicant: Tata Consultancy Services Limited

Inventor： Mouli RASTOGI ,  Syed Afshan ALI ,  Mrinal RAWAT ,  Lovekesh VIG ,  Puneet AGARWAL ,  Gautam SHROFF ,  Ashwin SRINIVASAN

IPC: G06K9/00 ,  G06F16/93 ,  G06F16/901 ,  G06K9/62 ,  G06K9/40 ,  G06K9/46

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.

公开(公告)号：US20220036166A1

公开(公告)日：2022-02-03

申请号：US17309432

申请日：2019-11-28

Applicant: Tata Consultancy Services Limited

Inventor： 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

IPC: G06N3/063 ,  G06N3/10

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.

公开(公告)号：US20210103812A1

公开(公告)日：2021-04-08

申请号：US17005155

申请日：2020-08-27

Applicant: Tata Consultancy Services Limited

Inventor： Pankaj MALHOTRA ,  Jyoti NARWARIYA ,  Lovekesh VIG ,  Gautam SHROFF

IPC: G06N3/08 ,  G06F16/28

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.

公开(公告)号：US20200175304A1

公开(公告)日：2020-06-04

申请号：US16353570

申请日：2019-03-14

Applicant: Tata Consultancy Services Limited

Inventor： Lovekesh VIG ,  Gautam SHROFF ,  Arindam CHOWDHURY ,  Rohit RAHUL ,  Gunjan SEHGAL ,  Vishwanath DORESWAMY ,  Monika SHARMA ,  Ashwin SRINIVASAN

IPC: G06K9/46 ,  G06F17/27 ,  G06T5/00 ,  G06K9/00 ,  G06K9/62 ,  G06F16/2452 ,  G06F16/2455 ,  G06F16/28 ,  G06N3/08

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.

公开(公告)号：US20200090056A1

公开(公告)日：2020-03-19

申请号：US16361778

申请日：2019-03-22

Applicant: Tata Consultancy Services Limited

Inventor： Rekha SINGHAL ,  Gautam SHROFF ,  Vartika TEWARI ,  Sanket KADARKAR ,  Siddharth VERMA ,  Sharod Roy CHOUDHURY ,  Lovekesh VIG ,  Rupinder VIRK

IPC: G06N5/04 ,  G06N20/20 ,  G06F16/901 ,  G06F16/908 ,  G06N3/04 ,  G06K9/62

Abstract: Business to Consumer (B2C) systems face a challenge of engaging users since offers are created using static rules generated using clustering on large transactional data generated over a period of time. Moreover, the offer creation and assignment engine is disjoint to the transactional system which led to significant gap between history used to create offers and current activity of users. Systems and methods of the present disclosure provide a meta-model based configurable auto-tunable recommendation model generated by ensembling optimized machine learning and deep learning models to predict a user's likelihood to take an offer and deployed in real time. Furthermore, the offer given to the user is based on a current context derived from the user's recent behavior that makes the offer relevant and increases probability of conversion of the offer to a sale. The system achieves low recommendation latency and scalable high throughput by virtue of the architecture used.

公开(公告)号：US20200020061A1

公开(公告)日：2020-01-16

申请号：US16510748

申请日：2019-07-12

Applicant: Tata Consultancy Services Limited

Inventor： Vishal SUNDER ,  Lovekesh VIG ,  Arnab CHATTERJEE ,  Gautam SHROFF

IPC: G06Q50/18 ,  G06N5/04

Abstract: This disclosure relates generally to method and system for performing negotiation task using reinforcement learning agents. Performing negotiation on a task is a complex decision making process and to arrive at consensus on contents of a negotiation task is often expensive and time consuming due to the negotiation terms and the negotiation parties involved. The proposed technique trains reinforcement learning agents such as negotiating agent and an opposition agent. These agents are capable of performing the negotiation task on a plurality of clauses to agree on common terms between the agents involved. The system provides modelling of a selector agent on a plurality of behavioral models of a negotiating agent and the opposition agent to negotiate against each other and provides a reward signal based on the performance. This selector agent emulate human behavior provides scalability on selecting an optimal contract proposal during the performance of the negotiation task.

公开(公告)号：US20180260396A1

公开(公告)日：2018-09-13

申请号：US15920094

申请日：2018-03-13

Applicant: Tata Consultancy Services Limited

Inventor： Karamjit SINGH ,  Garima GUPTA ,  Gautam SHROFF ,  Puneet AGARWAL

IPC: G06F17/30 ,  G06N7/00 ,  G06N99/00

CPC classification number: G06F16/24578 ,  G06F16/215 ,  G06F16/2246 ,  G06N7/005 ,  G06N10/00

Abstract: This disclosure relates generally to data processing, and more particularly to a system and a method for mapping heterogeneous data sources. For a product being sold globally, there might be one global database listing characteristics of the product, and from various System and method for mapping attributes of entities are disclosed. In an embodiment, the system uses a combination of Supervised Bayesian Model (SBM) and an Unsupervised Textual Similarity (UTS) model for data analysis. A weighted ensemble of the SBM and the UTS is used, wherein the ensemble is weighted based on a confidence measure. The system, by performing data processing, identifies data match between different data sources (a local databases and a corresponding global database) being compared, and based on matching data found, performs mapping between the local databases and the global database.

公开(公告)号：US20150019513A1

公开(公告)日：2015-01-15

申请号：US14328172

申请日：2014-07-10

Applicant: TATA CONSULTANCY SERVICES LIMITED

Inventor： Lipika DEY ,  Ishan VERMA ,  Arpit KHURDIYA ,  Diwakar MAHAJAN ,  Gautam SHROFF

IPC: G06F17/30

CPC classification number: G06F17/30613 ,  G06F17/30156 ,  G06Q10/10

Abstract: The present subject matter relates to analysis of time-series data based on world events derived from unstructured content. According to one embodiment, a method comprises obtaining event information corresponding to at least one world event from unstructured content obtained from a plurality of data sources. The event information includes at least time of occurrence of the world event, time of termination of the world event, and at least one entity associated with the world event. Further, the method comprises retrieving time-series data pertaining to the entity associated with the world event from a time-series data repository. Based on the event information and the time-series data, the world event is aligned and correlated with at least one time-series event to identify at least one pattern indicative of cause-effect relationship amongst the world event and the time-series event.

Abstract translation: 本主题涉及基于从非结构化内容导出的世界事件的时间序列数据的分析。 根据一个实施例，一种方法包括从从多个数据源获得的非结构化内容获得对应于至少一个世界事件的事件信息。 事件信息至少包括世界事件的发生时间，世界事件终止的时间，以及与世界事件相关联的至少一个实体。 此外，该方法包括从时间序列数据库中检索与世界事件相关联的实体有关的时间序列数据。 基于事件信息和时间序列数据，世界事件被对准并与至少一个时间序列事件相关联，以识别指示世界事件与时间序列事件之间的因果关系的至少一个模式。