Abstract: This disclosure relates to method and system for verifying a positive classification performed by an artificial neural network (ANN) in a given class. The method includes generating a weight matrix comprising a weight of each neural node in a given layer; determining a contribution factor of a given neural node in the given layer with respect to an output of the ANN for the given class based on a known input vector to the given layer and a modified weight matrix; and generating a dominance matrix based on the contribution factor of each neural node in the given layer. The method further includes determining a rank of each neural node based on the corresponding dominance factor; and verifying the positive classification performed by the ANN in the given class for a test input vector based on the rank of each neural node in each layer of the ANN.

Abstract: This disclosure relates to method and system for determining structural blocks of a document. The method may include extracting text lines from the document, generating a feature vector for each text line by determining feature values for a set of features in the each text line, and determining at least one dominant feature from among the set of features and at least one corresponding dominance factor, for each structural class, based on the feature vector for each text line. The method may further include deriving a set of rules for classification of the text lines into respective structural classes and determining a structural block tag for each text line based on the set of rules. Each of the set of rules correspond to one of the structural classes and is based on the at least one dominant feature and the at least one corresponding dominance factor for that class.

Abstract: A method and device for removing noise from an image is disclosed. The method includes creating a single dimensional vector for an image through a multi-layer neural network. The method further includes converting the single dimensional vector into a multi-dimensional matrix based on number of layers in the multi-layer neural network. The method includes generating a feature hierarchy based on the multi-dimensional matrix, such that the feature hierarchy comprises a plurality of levels, and each level in the plurality of levels comprises at least one feature associated with the image. The method further includes creating a plurality of segments for the image based on the feature hierarchy, such that each of the plurality of segments includes a set of features associated with the image. The method includes removing each segment comprising noise from the plurality of segments to generate a de-noised image.

Abstract: This disclosure relates to method and system for improving performance of an artificial neural network (ANN). The method may include generating a weight matrix comprising weights of neural nodes in a given layer for each layer of the ANN, determining a marginal contribution value of a given neural node for each neural node in the given layer with respect to other neural nodes in the given layer, executing an elimination decision for each neural node in each layer based on the corresponding marginal contribution value, determining a distributed surplus value of a given remaining neural node in a given layer based on the marginal contribution values of a coalition of remaining neural nodes in the given layer for each remaining neural node in each layer, and updating the weight matrix based on the distributed surplus value of each remaining neural node in each layer.

Abstract: This disclosure relates generally to document processing, and more particularly to method and system for determining structural blocks of a document. In one embodiment, the method may include extracting text from the document, the text including text lines. The method may further include generating a feature vector for each of the text lines, the feature vector for the text line including a set of feature values for a set of corresponding features in the text line. The method may further include creating an input matrix for each of the text lines, the input matrix for the text line including a set of feature vectors corresponding to a set of neighboring text lines along with the text line. The method may further include determining a structural block tag for each of the text lines based on the corresponding input matrix using a machine learning model.

Abstract: This disclosure relates to method and system for determining structural blocks of a document. The method may include extracting text lines from the document, generating a feature vector for each text line by determining feature values for a set of features in the each text line, and determining at least one dominant feature from among the set of features and at least one corresponding dominance factor, for each structural class, based on the feature vector for each text line. The method may further include deriving a set of rules for classification of the text lines into respective structural classes and determining a structural block tag for each text line based on the set of rules. Each of the set of rules correspond to one of the structural classes and is based on the at least one dominant feature and the at least one corresponding dominance factor for that class.

Abstract: A method and device for removing noise from an image is disclosed. The method includes creating a single dimensional vector for an image through a multi-layer neural network. The method further includes converting the single dimensional vector into a multi-dimensional matrix based on number of layers in the multi-layer neural network. The method includes generating a feature hierarchy based on the multi-dimensional matrix, such that the feature hierarchy comprises a plurality of levels, and each level in the plurality of levels comprises at least one feature associated with the image. The method further includes creating a plurality of segments for the image based on the feature hierarchy, such that each of the plurality of segments includes a set of features associated with the image. The method includes removing each segment comprising noise from the plurality of segments to generate a de-noised image.

Abstract: This disclosure relates generally to document processing, and more particularly to method and system for detecting and extracting tabular data from a document. In one embodiment, the method may include generating a hierarchy of features, for a plurality of features of an image document derived from the document, based on relative spatial properties of the plurality of features. The method may further include segmenting the image document into a plurality of semantic segments based on the hierarchy of features, classifying each of the plurality of semantic segments into at least one of a plurality of tabular structures, and effecting at least one of a detection or an extraction of the tabular data from the image document based on the classification.

Abstract: This disclosure relates to system and method for dynamically creating and building a domain dictionary. In one embodiment, the method comprises computing a syntactic similarity score, a usage similarity score, and a contextual similarity score for an input word with respect to each of a plurality of domain specific words in each of a plurality of existing domains. The method further comprises computing a weighted overall similarity score for the input word with respect to each of the plurality of domain specific words in each of the plurality of existing domains based on the syntactic similarity score, the usage similarity score, and the contextual similarity score. The method further comprises determining belongingness of the input word to each of the plurality of existing domains based on the weighted overall similarity score.

Abstract: This disclosure relates generally to document processing, and more particularly to method and system for determining structural blocks of a document. In one embodiment, the method may include extracting text from the document, the text including text lines. The method may further include generating a feature vector for each of the text lines, the feature vector for the text line including a set of feature values for a set of corresponding features in the text line. The method may further include creating an input matrix for each of the text lines, the input matrix for the text line including a set of feature vectors corresponding to a set of neighboring text lines along with the text line. The method may further include determining a structural block tag for each of the text lines based on the corresponding input matrix using a machine learning model.

Abstract: A method and device for automatic data correction using context and semantic aware learning techniques is disclosed. The method includes extracting data within a document as machine readable text in a predefined format. The method further includes encoding each word of each line in the machine readable text to a multi-dimension word vector. The method includes generating a context word vector for each word in each line based on multi-dimension vectors associated with words succeeding and preceding the word in a line comprising the word. The method further includes decoding the context word vector associated with each word in each line to generate a corrected context word vector for each word. The method includes validating the corrected context word vector associated with each word in each line.

Abstract: Disclosed herein is a method and system for dynamically integrating a plurality of BOTs. The method comprises creating the plurality of BOTs offering one or more automated services, wherein each of the plurality of BOTs has a common BOT structure comprising one or more field parameters. One or more predefined functions are assigned to each of the plurality of BOTs, wherein at least one of the one or more predefined functions comprises a function value. A maturity score for each of the plurality of BOTs is determined based on the one or more field parameters and the function value upon assigning the one or more predefined functions to each of the plurality of BOTs. Finally, the plurality of BOTs are integrated by synchronizing data amongst the plurality of BOTs based on the maturity score.

Abstract: This disclosure relates to providing information access in an enterprise network. The method includes creating automatically an ontology by analyzing at least one document comprising semantic information for roles, responsibilities, authority, and restrictions associated with a plurality of users; extracting based on the ontology a plurality of contextual terms associated with at least one of roles, responsibilities, authority, or restrictions; assigning a plurality of annotation tags to each sentence in at least one enterprise policy document based on the plurality of contextual terms; generating a plurality of information access rules based on the plurality of contextual terms and assigned plurality of annotation tags to each sentence in the at least one enterprise policy document; and creating a context similarity tree based on the assigned plurality of annotation tags and the plurality of information access rules.

Abstract: This disclosure relates generally to image processing, and more particularly to system and method for detecting and annotating bold text in an image document. In one embodiment, a method is provided for annotating bold text in an image document. The method comprises receiving the image document, processing the image document to derive a digitized textual image, detecting one or more regions of bold text within the digitized textual image using an adaptive edge rounding filter, and annotating the one or more regions of bold text within the image document.

Abstract: Methods, devices, and non-transitory computer readable storage media for extracting text from documents are disclosed. The method includes performing layout analysis on the document to identify a plurality of regions within a plurality of pages in the document. The method further includes identifying a table region from within the plurality of regions based on homogeneity between a plurality of textual lines in a page from the plurality of pages. The method includes identifying at least two rows and at least two columns within the table region. The method further includes identifying a plurality of cells within the table region based on the at least two rows and the at least two columns. The method includes extracting text from each of the plurality of cells.

Abstract: In one embodiment, a system, comprising a processor and a memory, for alerting a user, is disclosed. The processor receives one or more sensor data. The processor further determines one or more environmental factors, a current activity of the user, one or more motion data and one or more objects in proximity to the user based on the one or more sensor data. The processor further generates an initial degree of safety for each of the one or more environmental factors, the current activity of the user, the one or more motion data of the electronic device and the one or more objects in proximity to the user based on dynamically adaptive thresholds. The processor further generates an aggregate degree of safety based on the initial degree of safety and one or more pre-defined rules. The processor further alerts the user based on the aggregate degree of safety.

Abstract: Methods, devices, and non-transitory computer readable storage media for extracting text from documents are disclosed. The method includes performing layout analysis on the document to identify a plurality of regions within a plurality of pages in the document. The method further includes identifying a table region from within the plurality of regions based on homogeneity between a plurality of textual lines in a page from the plurality of pages. The method includes identifying at least two rows and at least two columns within the table region. The method further includes identifying a plurality of cells within the table region based on the at least two rows and the at least two columns. The method includes extracting text from each of the plurality of cells.

Abstract: This disclosure relates generally to data processing, and more particularly, to methods and systems for determining an equipment operation based on historical data. In one embodiment, a hardware processor-implemented method for facilitating an operation of a device is provided. The method comprises: receiving an indication of an operation problem for a first device; acquiring historical operation data of a plurality of devices including the first device, the historical operation data including structured data and unstructured data; determining at least a list of first entities and a list of second entities based on the structured data; determining a set of entity associations, each entity association including at least one of the first entities and at least one of the second entities; determining one or more relationships between each of the entity associations; and determining, based on the one or more determined relationships, an operation solution to solve the operation problem.

Abstract: This disclosure relates generally to image processing, and more particularly to system and method for detecting and annotating bold text in an image document. In one embodiment, a method is provided for annotating bold text in an image document. The method comprises receiving the image document, processing the image document to derive a digitized textual image, detecting one or more regions of bold text within the digitized textual image using an adaptive edge rounding filter, and annotating the one or more regions of bold text within the image document.

Abstract: A method and a system are provided for facilitating operation of an electronic device. The method comprises receiving a semi-structured dataset comprising one or more entities, wherein the semi-structured dataset corresponds to at least an indication of an operation problem associated with an electronic device. The method comprises extracting one or more unique classes associated with one or more entities from the semi-structured dataset. The method comprises creating one or more n-grams representative of a relationship between the one or more entities and the one or more unique classes. The method comprises generating a hypothesis associated with the one or more entities based on a first set of entities from the one or more entities using one or more n-grams, wherein the generated hypothesis corresponds to an operation solution to solve the operation problem associated with the electronic device.