17836311. CROSS-APPLICATION COMPONENTIZED DOCUMENT GENERATION simplified abstract (Microsoft Technology Licensing, LLC)

CROSS-APPLICATION COMPONENTIZED DOCUMENT GENERATION

Organization Name

Microsoft Technology Licensing, LLC

Inventor(s)

Sumit Mehra of Bengaluru (IN)

Anish Chandran of Hyderabad (IN)

Mukundan Bhoovaraghavan of Hyderabad (IN)

Neeraj Kumar Verma of Hyderabad (IN)

Srinivasa Chaitanya Kumar Reddy Gopireddy of Hyderabad (IN)

Surabhi Bhatnagar of Greater Noida (IN)

Soumyadeep Dey of Hyderabad (IN)

CROSS-APPLICATION COMPONENTIZED DOCUMENT GENERATION - A simplified explanation of the abstract

This abstract first appeared for US patent application 17836311 titled 'CROSS-APPLICATION COMPONENTIZED DOCUMENT GENERATION

Simplified Explanation

The abstract describes a method for presenting and organizing content of an electronic document on a mobile device using machine learning models. Here is a simplified explanation:

• The method involves displaying the content of an electronic document on a mobile device using a mobile application.
• The content is then classified into different components using machine learning models.
• After classification, the identified components are highlighted within the mobile application.
• The user can select a specific component from the highlighted ones.
• The selected component is then added to a component data store on the mobile device, along with its type determined by the machine learning models.

Potential Applications

This technology can have various applications in the field of mobile computing and document management. Some potential applications include:

• Mobile document organization: The method can help users easily organize and categorize different components of electronic documents on their mobile devices.
• Content extraction: It can be used to extract specific types of content from documents, such as contact information, dates, or addresses, and store them separately for easy access.
• Information retrieval: By classifying and highlighting components, the method can enhance the efficiency of searching and retrieving specific information within documents on mobile devices.

Problems Solved

The method addresses several challenges related to content organization and management on mobile devices:

• Efficient organization: It simplifies the process of organizing and categorizing different components of electronic documents on mobile devices, making it easier for users to find and access specific information.
• Content extraction: By automatically identifying and extracting specific types of content, it eliminates the need for manual extraction, saving time and effort.
• Improved information retrieval: The highlighting of components and the ability to add them to a data store enhances the speed and accuracy of searching and retrieving information within documents on mobile devices.

Benefits

The use of machine learning models in this method offers several benefits:

• Automation: The classification and highlighting of components are automated processes, reducing the need for manual effort and intervention.
• Personalization: The method can adapt to individual user preferences and document types, providing a personalized experience for content organization and retrieval.
• Efficiency: By streamlining the organization and retrieval of document components, the method improves overall efficiency and productivity on mobile devices.

Original Abstract Submitted

A method may include presenting content of an electronic document on a mobile computing device within a mobile version of a computing application; classifying, using a set of machine learning models, by the mobile computing device, the content into a plurality of components; after the classifying, highlighting the plurality of components within the mobile version of the computing application; receiving a user input selecting a component of the plurality of components; and adding, by the mobile computing device, the component to a component data store with a type of the component, the type of the component based on output of the set of machine learning models.