Snowflake inc. (20240330412). COLUMN CLASSIFICATION MODEL simplified abstract
Contents
COLUMN CLASSIFICATION MODEL
Organization Name
Inventor(s)
Zachary Charles Frazier of Seattle WA (US)
Stephen Joe Jonany of Seattle WA (US)
Nabajyoti Patowary of Seattle WA (US)
Yunqiao Zhang of Bellevue WA (US)
COLUMN CLASSIFICATION MODEL - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240330412 titled 'COLUMN CLASSIFICATION MODEL
The abstract describes systems and methods for classifying columns using a model. These systems and methods access a table associated with a column of features and retrieve a list of categories, each with a different scoring model. For each category in the list, a scoring model is applied to the features of the column to generate confidence values indicating the likelihood that the column belongs to that category. The systems and methods then process these confidence values to select a target category and associate it with the column.
- Systems and methods for classifying columns based on features using scoring models
- Accessing a table to retrieve categories and scoring models
- Applying scoring models to features to generate confidence values
- Selecting a target category based on confidence values
- Associating the target category with the column
Potential Applications: - Automated data classification in databases - Content categorization in information retrieval systems - Product categorization in e-commerce platforms
Problems Solved: - Streamlining the process of classifying columns based on features - Improving accuracy in assigning categories to columns - Enhancing efficiency in data organization and retrieval
Benefits: - Increased automation and efficiency in data classification - Improved accuracy and consistency in categorization - Enhanced organization and retrieval of information
Commercial Applications: Title: Automated Column Classification System This technology could be utilized in various industries such as: - Data management companies - E-commerce platforms - Information retrieval systems
Questions about the technology: 1. How does this system compare to traditional manual column classification methods? 2. What are the potential limitations of using scoring models for column classification?
Original Abstract Submitted
systems and methods for classifying columns using a model are provided. the systems and methods access a table associated with a column of features and retrieve a list of categories each associated with a different scoring model. the systems and methods, for each category in the list of categories, apply a respective scoring model to the features of the column to generate a respective set of confidence values indicating a likelihood that the column belongs to a respective one of the categories. the systems and methods process the respective sets of confidence values to select a target category from the list of categories and associate the selected target category with the column.