Back to results
US 2026/0228195 A1Published application
Range error detection and correction in table data
AssigneeInternational Business Machines Corporation
InventorsMinhao YAN, Bing ZHANG, Pawan Raghunath CHOWDHARY, Taiga NAKAMURA
Life of this patent
Estimating the term…
Abstract
Method and apparatus for using similarity analysis, and a plurality of different machine learning algorithms to detect parsing errors or missing data in data tables. The AI system can then generate a new data table with the errors corrected. The corrected data table can include predicted values of what the original data table was missing. The AI system offers an improvement for generating data tables with range values where such data tables are normally produced with errors and missing information. The AI system provides an automatic way of correcting errors, via the generation of a new data table.
Claims20
A method comprising:
- evaluating, using an artificial intelligence (AI) system, a first data table to detect missing and error data and automatically correct data of the first data table, wherein the missing data comprises null cell content and the error data further comprises inconsistent and anomalous cell content, and wherein evaluating the first data table comprises:
- performing a first similarity analysis of cell content of a plurality of neighboring cells of the first data table to identify data patterns, relationships, and anomalies that indicate one or more cells containing the missing and error data, wherein performing the first similarity analysis comprises:
- interpreting a meaning of the extracted data from the plurality of neighboring cells, header cells;
- of the first data table, and corresponding numerical data of cells under the header cells to detect the missing and error data based on the interpreted meaning of the extracted data;
- evaluating the plurality of neighboring cells of the first data table to identify a type of range data present in the one or more cells containing the missing and error data in the first data table;
- predicting corrected values of the one or more cells containing the missing and error data of the first data table by performing a second similarity analysis based on the one or more cells containing the missing and error data, the plurality of neighboring cells, and the identified type of range data present in the first data table;
- and
- generating, based on the predicted corrected values, a second data table containing the predicted corrected values in the one or more cells containing the missing and error data, wherein the second data table is a completed version of the first data table.
5 more elements
A computer program product for generating a data table, the computer program product comprising:
- a computer-readable storage medium having computer-readable program code embodied therewith, the computer-readable program code executable by one or more computer processors configured to perform operations comprising:
- evaluating, using an artificial intelligence (AI) system, a first data table to detect missing and error data and automatically correct data of the first data table, wherein the missing data comprises null cell content and the error data further comprises inconsistent and anomalous cell content, and wherein evaluating the first data table comprises:
- performing a first similarity analysis of cell content of a plurality of neighboring cells of the first data table to identify data patterns, relationships, and anomalies that indicate one or more cells containing the missing and error data, wherein performing the first similarity analysis comprises:
- interpreting a meaning of the extracted data from the plurality of neighboring cells, header cells;
- of the first data table, and corresponding numerical data of cells under the header cells to detect the missing and error data based on the interpreted meaning of the extracted data;
- evaluating the plurality of neighboring cells of the first data table to identify a type of range data present in the one or more cells containing the missing and error data in the first data table;
- predicting corrected values of the one or more cells containing the missing and error data of the first data table by performing a second similarity analysis based on the one or more cells containing the missing and error data, the plurality of neighboring cells, and the identified type of range data present in the first data table;
- and
- generating, based on the predicted corrected values, a second data table containing the predicted corrected values in the one or more cells containing the missing and error data, wherein the second data table is a completed version of the first data table.
6 more elements
A computer system for generating a data table, the computer system comprising:
- one or more computer processors;
- one or more computer readable storage media;
- and
- program instructions stored on the computer readable storage media for execution by at least one of the one or more processors, the program instructions comprising:
- evaluating, using an artificial intelligence (AI) system, a first data table to detect missing and error data and automatically correct data of the first data table, wherein the missing data comprises null cell content and the error data further comprises inconsistent and anomalous cell content, and wherein evaluating the first data table comprises:
- performing a first similarity analysis of cell content of a plurality of neighboring cells of the first data table to identify data patterns, relationships, and anomalies that indicate one or more cells containing the missing and error data. wherein performing the first similarity analysis comprises:
- interpreting a meaning of extracted data from the plurality of neighboring cells, header cells;
- of the first data table, and corresponding numerical data of cells under the header cells to detect the missing and error data based on the interpreted meaning of the extracted data;
- evaluating the plurality of neighboring cells of the first data table to identify a type of range data present in the one or more cells containing the missing and error data in the first data table;
- predicting corrected values of the one or more cells containing the missing and error data of the first data table by performing a second similarity analysis based on the one or more cells containing the missing and error data, the plurality of neighboring cells, and the identified type of range data present in the first data table;
- and
- generating, based on the predicted corrected values, a second data table containing the predicted corrected values in the one or more cells containing the missing and error data, wherein the second data table is a completed version of the first data table.
9 more elements
Dependencies are inferred from the claim text.