Abstract: A computer-implemented method and system for enrichment of responses in a multimodal conversation environment are disclosed. A Question Answer (QA) engine, such as a reinforcement document transformer exploits a document template structure or layout, adapts the information extraction using a domain ontology, stores the enriched contents in a hierarchical form, and learns context and query patterns based on the intent and utterances of one or more queries. The region of enriched content for preparing a response to a given query is expanded or collapsed by navigating upwards or downwards in the hierarchy. The QA engine returns the most relevant answer with the proper context for one or more questions. The responses are provided to the user in one or more modalities.

Abstract: A system and method of recognizing data in a table area from unstructured data includes a computer network, one or more processors communicatively coupled with the computer network, a storage location, and a graph-theoretic engine that receives an input stream of unstructured data associated. A table area is recognized from unstructured data, through one or more computer processors, from an input stream of unstructured data received over a computer network. One or more table headers associated with the detected one or more table areas are recognized. Further, one or more column delimiters associated with each column of the detected one or more table areas are determined. One or more tabular data associated with the detected one or more table areas are extracted. The extracted tabular data is mapped to one or more target schema to store onto a relational database.

Abstract: A computer implemented a method and system for enrichment of OCR extracted data is disclosed comprising of accepting a set of extraction criteria and a set of configuration parameters by a data extraction engine. The data extraction engine captures data satisfying an extraction criteria using the configuration parameters and adapts the captured data using a set of domain specific rules and a set of OCR error patterns. A learning engine generates learning data models using the adapted data and the configuration parameters and the system dynamically updates the extraction criteria using the generated learning data models. The extraction criteria comprise one or more extraction templates wherein an extraction template includes one of a regular expression, geometric markers, anchor text markers and a combination thereof.

Abstract: A system and method of recognizing data in a table area from unstructured data includes a computer network, one or more processors communicatively coupled with the computer network, a storage location, and a graph-theoretic engine that receives an input stream of unstructured data associated. A table area is recognized from unstructured data, through one or more computer processors, from an input stream of unstructured data received over a computer network. One or more table headers associated with the detected one or more table areas are recognized. Further, one or more column delimiters associated with each column of the detected one or more table areas are determined. One or more tabular data associated with the detected one or more table areas are extracted. The extracted tabular data is mapped to one or more target schema to store onto a relational database.

Abstract: A computer implemented a method and system for enrichment of OCR extracted data is disclosed comprising of accepting a set of extraction criteria and a set of configuration parameters by a data extraction engine. The data extraction engine captures data satisfying an extraction criteria using the configuration parameters and adapts the captured data using a set of domain specific rules and a set of OCR error patterns. A learning engine generates learning data models using the adapted data and the configuration parameters and the system dynamically updates the extraction criteria using the generated learning data models. The extraction criteria comprise one or more extraction templates wherein an extraction template includes one of a regular expression, geometric markers, anchor text markers and a combination thereof.

Abstract: The present disclosure describes a method of sentiment oriented slang for opinion mining. With increasing use of internet, many users can submit their review comments directly to the companies which can be automatically processed and summarized with critical issues from time to time and help the company get real time feedback from its customers. The method comprises, receiving at least one document comprising a plurality of sentiment oriented slang. The next step of the method comprises identifying the plurality of sentiment oriented slang in the at least one document. Further, a polarity score of each of a slang word identified is determined and sentiment information is displayed on an output device as an output.

Abstract: A method and system masks sensitive fields on a cheque image based one or more access privileges assigned to a user. The method involves receiving a cheque image at a cheque masking engine. A cheque template from one or more cheque templates is selected based on metadata associated with the cheque image. One or more zones of sensitive information associated with the cheque image are identified based on the one or more access privileges assigned to the user and a comparison with the selected cheque template. One or more characters are extracted from the one or more zones of sensitive information. The extracted one or more characters are aliased based on an aliasing rule. Another cheque image is generated by overlaying the one or more zones of sensitive information with the aliased one or more characters.

Abstract: A method, non-transitory computer readable medium, and anomaly detection computing apparatus that detects one or more of a plurality of symptoms associated with a device when the device is operating in a fault mode. One or more of a plurality of components of the device that are potentially faulty are identified based on the detected symptoms. One or more tests are performed on each of the one or more of the components to confirm that at least a subset of the one or more of the components is faulty. An optimal remedy pattern is determined for the subset of the one or more of the components based at least in part on historical data and cost data obtained from a database, and the optimal remedy pattern is output.

Abstract: The present technique discloses a method and system for committing atomic transaction in NoSQL database by using a transaction manager. The transaction manager is a middle layer between a distributed columnar database and an application accessing the database. The business entity for which data needs to be updated or inserted is identified and concurrency level of that business entity is determined. This concurrency level determines whether all overlapping transaction should be allowed to continue simultaneously or only the transaction which started first should be allowed to continue at a time. The update of business entity data starts from bottom of hierarchical physical tables or from child tables. If any of the child table transaction is unsuccessful then transaction manager aborts transaction at parent level or business entity level. However, if child table transactions are successful then transaction manager commits the transaction at business entity level.

Abstract: A method and a system for registering multi-modal brain images includes registering two or more full volumes of brain images based on a projection based reference image. The registration is based on sharing of mass in a predetermined direction such as axial, sagittal and coronal direction. After the registration of two or more brain images, a two or more partial volumes in a region of interest is registered through a modified mutual information. The modified mutual information may be a factor of an overlap rate and a weight assigned to it.

Abstract: A method and/or system for identity relationship determination among enterprise data entities to extend master data management is disclosed. The method involves extracting the data from the one or more data sources, thereafter grouping the extracted data into one or more groups based on one or more predefined criteria, then computing a plurality of relationship scores by using one or more soft matching techniques, thereafter creating one or more clusters based on the computed relationship scores, then again calculating a plurality of relationship scores among the clusters, and finally, determining the identity relationships by comparing the plurality of relationship scores generated among clusters with a predefined score.

Abstract: A method, non-transitory computer readable medium, and device for clustering a network includes obtaining information regarding a network including relationship information for a plurality of nodes of the network. A weight value for each of a plurality of directly connected pairs of the plurality of nodes is determined, wherein the directly connected pair are identified based on the relationship information. At least one topology score is generated for each of the plurality of nodes. A plurality of clusters is generated using the topology scores and one of the plurality of nodes as a seed node for each of the clusters. At least the seed node used to generate at least a subset of the plurality of clusters is output.

Abstract: Embodiments of the present invention relate to an inventory management method and system. The present invention addresses the foregoing need of an inventory management system through which all size and shape of components can tracked before and after an assembly process in a manufacturing facility. The invention address the challenges faced by store keeping clerks in locating the position of excess components returned from assembly floor, which are taken in excess but not being utilized during assembly process. Since basic spare parts which are smaller in size but taken in large quantity from store room due to their frequent usage, excess components needs to be kept back in store keeping units for effective inventory management.

Abstract: Systems and methods for multi-dimensional object detection are described. Embodiments disclose receiving image frames, extracting image components in the image frame, identifying line segments in the extracted components, grouping the line segments into groups, based at least in part on one or more similarities between the slope associated with a line segment and the spatial proximity between the line segments, and merging each of the one or more identified line segments in a selected group into a single line segment. Embodiments additionally disclose detecting the position of one or more objects in the image frame by identifying objects in the image frame, producing a second version of the image frame, applying at least one image classifier to the image frame and the second version of the image frame, and identifying coordinates associated with at least one target object. Some embodiments additionally couple lane and object detection with alert generation.

Abstract: A method and system masks sensitive fields on a cheque image based one or more access privileges assigned to a user. The method involves receiving a cheque image at a cheque masking engine. A cheque template from one or more cheque templates is selected based on metadata associated with the cheque image. One or more zones of sensitive information associated with the cheque image are identified based on the one or more access privileges assigned to the user and a comparison with the selected cheque template. One or more characters are extracted from the one or more zones of sensitive information. The extracted one or more characters are aliased based on an aliasing rule. Another cheque image is generated by overlaying the one or more zones of sensitive information with the aliased one or more characters.

Abstract: Systems and methods for improved management of sentiments over conventional approaches are disclosed. Supervised approach is used to augment the rule-based approach for classification. Initially, sentiment evaluation is performed by the system using a rule based approach and an interface is provided to the user to give feedback on the correctness of evaluated sentiment. This feedback is used by the sentiment evaluation system to update the set of rule-based and also apply the supervised approach to train the classifier for evaluating complex posts.

Abstract: Embodiments of the present invention relate to an inventory management method and system. The present invention addresses the foregoing need of an inventory management system through which all size and shape of components can tracked before and after an assembly process in a manufacturing facility. The invention address the challenges faced by store keeping clerks in locating the position of excess components returned from assembly floor, which are taken in excess but not being utilized during assembly process. Since basic spare parts which are smaller in size but taken in large quantity from store room due to their frequent usage, excess components needs to be kept back in store keeping units for effective inventory management.

Abstract: Embodiments of the present invention relate to a system for data integration and information retrieval by bringing semantically related data together for a given context. As described, the integration of data may include the building of an ontology, the mapping of one or more processes, semantic maps and concept dictionaries in the ontology to one or more data sources, tagging the data sources in accordance with the ontology, providing a query interface for accepting an input query from a user, the mapping of the input query to one or more concepts in the ontology, and deriving one or more subqueries thereby, and the querying of data sources in accordance with the composed one or more subqueries, wherein the data sources queried are tagged with one or more concepts from the ontology. Additionally, the tracking of data across data sources in accordance with a defined data value chain is disclosed.

Abstract: A method and a system for registering multi-modal brain images includes registering two or more full volumes of brain images based on a projection based reference image. The registration is based on sharing of mass in a predetermined direction such as axial, sagittal and coronal direction. After the registration of two or more brain images, a two or more partial volumes in a region of interest is registered through a modified mutual information. The modified mutual information may be a factor of an overlap rate and a weight assigned to it.

Abstract: A method, non-transitory computer readable medium, and apparatus for receiving data from a cloud database. One or more queries requesting data from the cloud database are received. The one or more queries are converted from a row-store database query into a column-store database query. An optimal join plan is identified for the one or more queries using a cost based optimizer based on metadata for one or more relations in the cloud database. The optimal join plan is executed using a cloud application programming interface.