Adp, Inc.

Akshay Chopra

Kenneth G Kingery

Anuradha Verma

Ajit Sri Kumar

Michael Oliver Plonski

Nagamalleswara Bodeddula

Arjun Hegde

Hongguo An

Harsh Sharma

Paren Desai

Vijaya Mahesh Sayi

Ram Sama

Margaret Aronson-Olague

Madhusudhan Kakurala

Maria Rios

Srikanth Chintamaneni

Jie Huang

Christine Wymore

Deepak Gupta

Ravi Lankalapalli

Gopal Prasad

Pablo Budke

A method, computer system, and computer program product are provided for processing an output of batch processed information. A document storage system receives the output of batch processed information from a number of company portals, websites, and online systems of organization. The document storage system separates the output into individual documents and individual forms. The document storage system indexes the individual documents and forms according to metadata. The metadata includes structural attributes extracted from the individual documents and forms, and company relevant parameters identified from business intelligence for the organization. The document storage system stores the individual documents and forms in association with the metadata. Responsive to storing the individual documents and forms, the document storage system generates an event message. The event message comprises information about the storing of the individual documents and forms. The document storage system publishes the event message to a message pipeline. The document storage system notifies a subscribed client device about the event message, including a notification of availability of the individual documents and individual forms separated from the output.

Method and system for interactive search indexing

An illustrative embodiment provides a computer implemented method for extracting named entity information from full text includes obtaining text data from a document. The method also includes tokenizing the text data as numbers to produce a tokenized layer. The method also includes creating an embedded layer from the tokenized layer by encoding the text data by indices. The method also includes creating a one-dimensional Xception layer from the embedded layer according to a one-dimensional convolution. The method also includes determining a sequence of classification for the text data according to the one-dimensional Xception layer. The method also includes determining a named entity value from the text data according to the sequence of classification, wherein each sequence of classification predicts one character of the named entity value.

Named-entity recognition through sequence of classification using a deep learning neural network

Growing community of inventors

Pasadena, CA, United States of America

Akshay Chopra