Detecting and displaying exceptions in tabular data
AssigneeMicrosoft Corporation
InventorsRaman S. Iyer, C. James MacLennan, Ioan Bogdan Crivat
Life of this patent
Estimating the term…
Abstract
Data expressed as tabular data having columns and rows can be analyzed and data determined to be an exception can be flagged. In addition, reasons for flagging such data as exceptions can be presented to a user to facilitate further analysis and action on the data. A predictive analysis component can utilize a clustering algorithm with predictive capabilities to autonomously analyze the data. Periodic re-analysis of the data can be performed to determine if exceptions have changed based on new or modified data.
Claims20
A system that facilitates automatic detection of exceptions in tabular data, comprising:
- an application that contains tabular data expressed as a plurality of rows that include a plurality of columns;
- and
- a predictive analysis component that receives the tabular data and predicts exceptions in the table data utilizing a clustering algorithm with predictive capabilities.
A method for exception detection, comprising:
- building a predictive clustering model on tabular data;
- comparing each row contained in the tabular data to the clustering model;
- ascertaining one or more row that is an exception;
- and
- presenting the exception to a user.
A computer executable system that provides autonomous analysis of tabular data, comprising:
- means for building a model for tabular data;
- means for comparing each row contained in the tabular data against the model;
- means for detecting a row as an outlier;
- means for identifying at least one column in the row detected an outlier that caused the row to be the outlier.
Dependencies are inferred from the claim text.