-
公开(公告)号：US20220318545A1
公开(公告)日：2022-10-06
申请号：US17222412
申请日：2021-04-05
Applicant: AT&T Intellectual Property I, L.P.
Inventor： Tyler Poff , Vijayan Nagarajan , Abhay Dabholkar , Abhishek Mishra
Abstract: Techniques for processing of electronic documents comprising tables to desirably extract and/or recreate tables, including information in the tables, are presented. A document processing management component (DPMC) can perform a multi-stage process to extract a table from a document and recreate the table, including the table structure and information, in an editable form. During first stage, DPMC can identify candidate cells of the table based on analysis of the document, including identifying border lines that can represent cell borders, identifying any free floating candidate cells, and identifying characters of the candidate cells. During second stage, DPMC can determine structural relationships between respective candidate cells and respective neighbor candidate cells in all directions, based on applicable rules, and record the respective associations between those candidate cells. During third stage, DPMC can determine row/column placement and scaling of the candidate cells based on the respective associations and applicable rules.
-
公开(公告)号：US10805901B1
公开(公告)日：2020-10-13
申请号：US16799253
申请日：2020-02-24
Applicant: AT&T Intellectual Property I, L.P.
Inventor： Rudolph Mappus , Vijayan Nagarajan , Abhishek Mishra
Abstract: A processing system collects data points, wherein each data point indicates a location of user equipment in a telecommunication service provider network at a point in time, generates, for a first data point, a set of features over a plurality of time windows, wherein the set includes time series features, estimates an importance of each feature, wherein the importance indicates an accuracy with which the feature allows for estimation of an unseen location of the user equipment, wherein the unseen location is a location that is not identified in the plurality of data points, selects a threshold number of features from the set, wherein the threshold number of features have a greatest importance relative to all features in the set, generates a plurality of predictions of the unseen location, using the threshold number of features, aggregates the plurality of predictions, and estimates the unseen location based on the aggregating.
-
公开(公告)号：US10575276B1
公开(公告)日：2020-02-25
申请号：US16418034
申请日：2019-05-21
Applicant: AT&T Intellectual Property I, L.P.
Inventor： Rudolph Mappus , Vijayan Nagarajan , Abhishek Mishra
Abstract: A processing system collects data points, wherein each data point indicates a location of user equipment in a telecommunication service provider network at a point in time, generates, for a first data point, a set of features over a plurality of time windows, wherein the set includes time series features, estimates an importance of each feature, wherein the importance indicates an accuracy with which the feature allows for estimation of an unseen location of the user equipment, wherein the unseen location is a location that is not identified in the plurality of data points, selects a threshold number of features from the set, wherein the threshold number of features have a greatest importance relative to all features in the set, generates a plurality of predictions of the unseen location, using the threshold number of features, aggregates the plurality of predictions, and estimates the unseen location based on the aggregating.
-
-
Search Results
3
records
(took 0.017 seconds)
