18527104. INTERACTIVE CONCEPT EDITING IN COMPUTER-HUMAN INTERACTIVE LEARNING simplified abstract (Microsoft Technology Licensing, LLC)
Contents
- 1 INTERACTIVE CONCEPT EDITING IN COMPUTER-HUMAN INTERACTIVE LEARNING
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 INTERACTIVE CONCEPT EDITING IN COMPUTER-HUMAN INTERACTIVE LEARNING - 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
INTERACTIVE CONCEPT EDITING IN COMPUTER-HUMAN INTERACTIVE LEARNING
Organization Name
Microsoft Technology Licensing, LLC
Inventor(s)
Patrice Y. Simard of Bellevue WA (US)
David G. Grangier of Kirkland WA (US)
Leon Bottou of Kirkland WA (US)
Saleema A. Amershi of Seattle WA (US)
INTERACTIVE CONCEPT EDITING IN COMPUTER-HUMAN INTERACTIVE LEARNING - A simplified explanation of the abstract
This abstract first appeared for US patent application 18527104 titled 'INTERACTIVE CONCEPT EDITING IN COMPUTER-HUMAN INTERACTIVE LEARNING
Simplified Explanation
The abstract describes a patent application for a system that automatically classifies queries and web pages into useful categories to improve relevance. This system involves building a large number of classifiers and schematizers to categorize different types of information, activities, and products. The classifiers and schematizers are then applied to large data sets to add valuable meta-data and improve search and analysis capabilities.
- The patent application focuses on automatically classifying queries and web pages into useful categories to improve relevance.
- The system involves building a large number of classifiers and schematizers to categorize different types of information, activities, and products.
- The classifiers and schematizers are applied to large data sets to add valuable meta-data and improve search and analysis capabilities.
Potential Applications
The technology described in this patent application could be applied in various fields such as e-commerce, information retrieval, data analysis, and content recommendation systems.
Problems Solved
This technology addresses the challenge of searching and analyzing extremely large data sets by automatically classifying queries and web pages into relevant categories, thus improving the overall relevance of search results.
Benefits
The benefits of this technology include improved search and analysis capabilities, enhanced relevance of search results, and the ability to extract valuable meta-data from large data sets.
Potential Commercial Applications
The technology could be used in search engines, e-commerce platforms, data analysis tools, and content recommendation systems to enhance user experience and improve the efficiency of information retrieval processes.
Possible Prior Art
One possible prior art for this technology could be the use of machine learning algorithms for data classification and categorization in various applications such as search engines and recommendation systems.
Unanswered Questions
How does the system handle real-time data processing?
The article does not mention how the system deals with real-time data processing and whether it can classify queries and web pages in real-time.
What are the potential limitations of the system in terms of scalability?
The article does not discuss the potential limitations of the system in terms of scalability and whether it can handle extremely large data sets efficiently.
Original Abstract Submitted
A collection of data that is extremely large can be difficult to search and/or analyze. Relevance may be dramatically improved by automatically classifying queries and web pages in useful categories, and using these classification scores as relevance features. A thorough approach may require building a large number of classifiers, corresponding to the various types of information, activities, and products. Creation of classifiers and schematizers is provided on large data sets. Exercising the classifiers and schematizers on hundreds of millions of items may expose value that is inherent to the data by adding usable meta-data. Some aspects include active labeling exploration, automatic regularization and cold start, scaling with the number of items and the number of classifiers, active featuring, and segmentation and schematization.
