18371758. COMPUTERIZED INFORMATION EXTRACTION FROM TABLES simplified abstract (MICROSOFT TECHNOLOGY LICENSING, LLC)
Contents
- 1 COMPUTERIZED INFORMATION EXTRACTION FROM TABLES
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 COMPUTERIZED INFORMATION EXTRACTION FROM TABLES - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Original Abstract Submitted
COMPUTERIZED INFORMATION EXTRACTION FROM TABLES
Organization Name
MICROSOFT TECHNOLOGY LICENSING, LLC
Inventor(s)
Pak On Chan of Redmond WA (US)
Sharada Shirish Acharya of Seattle WA (US)
COMPUTERIZED INFORMATION EXTRACTION FROM TABLES - A simplified explanation of the abstract
This abstract first appeared for US patent application 18371758 titled 'COMPUTERIZED INFORMATION EXTRACTION FROM TABLES
Simplified Explanation
The patent application describes computerized systems for detecting and analyzing tables, extracting information from cells, and generating decision statistics based on the extracted data.
- Tables are detected and analyzed for information extraction and analysis.
- Information is extracted from cells or fields within the table.
- Feature vectors representing cells, rows, and columns are derived and concatenated.
- Contextual values within feature vectors are used as signals for decision statistics.
- Decision statistics, such as classification predictions, are generated for specific cells based on the extracted data.
Potential Applications
The technology could be applied in various fields such as data analysis, financial forecasting, and automated document processing.
Problems Solved
This technology streamlines the process of extracting and analyzing data from tables, reducing manual effort and potential errors in data interpretation.
Benefits
The system enhances efficiency in data processing, improves accuracy in decision-making, and enables faster insights from structured data.
Potential Commercial Applications
One potential commercial application could be in the development of automated data analysis software for businesses looking to streamline their data processing tasks.
Possible Prior Art
One possible prior art could be existing software tools for data extraction and analysis from tables, although the specific features and methods described in this patent application may offer unique advantages.
Unanswered Questions
How does this technology handle tables with complex structures or merged cells?
The patent application does not specify how the system deals with tables that have complex structures or merged cells. This could be a potential limitation if the technology is not able to accurately extract data from such tables.
What are the computational requirements for running this system efficiently?
The patent application does not provide information on the computational resources needed to run the system effectively. Understanding the system's resource demands could be crucial for organizations looking to implement this technology on a large scale.
Original Abstract Submitted
Computerized systems are provided for detecting one or more tables and performing information extraction and analysis on any given table. Information can be extracted from one or more cells or fields of a table and feature vectors representing individual cells, rows, and/or columns of the table can be derived and concatenated together. In this way, embodiments can use some or all of the “context” or values contained in various feature vectors representing some or all of a single table as signals or factors to consider when generating a decision statistic, such as a classification prediction, for a particular cell.
