17530149. TECHNIQUES AND SYSTEMS FOR SMART NATURAL LANGUAGE PROCESSING OF SEARCH RESULTS simplified abstract (Capital One Services, LLC)

TECHNIQUES AND SYSTEMS FOR SMART NATURAL LANGUAGE PROCESSING OF SEARCH RESULTS

Organization Name

Capital One Services, LLC

Inventor(s)

Piper Alexandra Coble of Richmond VA (US)

Natalie Kuhn of New York NY (US)

Paul Cho of Boston MA (US)

Ryan M. Parker of Dallas TX (US)

Sergey Petrunin of Cambridge MA (US)

Gary B. Williams of Williamsburg VA (US)

Eric Campbell of Midlothian VA (US)

Lin Ni Lisa Cheng of Fresh Meadows NY (US)

Matthew Kevin Sullivan of Midlothian VA (US)

Chris Demchalk of Frisco TX (US)

TECHNIQUES AND SYSTEMS FOR SMART NATURAL LANGUAGE PROCESSING OF SEARCH RESULTS - A simplified explanation of the abstract

This abstract first appeared for US patent application 17530149 titled 'TECHNIQUES AND SYSTEMS FOR SMART NATURAL LANGUAGE PROCESSING OF SEARCH RESULTS

Simplified Explanation

The patent application describes a system and method for improving search results by analyzing user profiles and search histories. Here are the key points:

• The system receives a search query from a user, which can include a textual phrase, a document, or data with metadata.
• A theme-generating machine learning algorithm is used to generate a theme for the search query.
• Profiles of other users that are similar to the user's profile are identified.
• The system locates the search history of each located user and evaluates it.
• Content in the searchable content that corresponds to the generated theme and the evaluated search history is obtained.
• The obtained content is scored using a scoring algorithm.
• The system outputs a set of scored search results to the user.

Potential applications of this technology:

• Improving search engines: This technology can enhance the relevance and accuracy of search results by considering user profiles and search histories.
• Personalized recommendations: By analyzing user profiles and search histories, the system can provide personalized recommendations for various products or services.
• Content filtering: The system can filter out irrelevant or unwanted content based on user profiles and search histories.

Problems solved by this technology:

• Lack of personalized search results: Traditional search engines may not consider individual user preferences and search histories, leading to less relevant results.
• Information overload: With the vast amount of information available online, it can be challenging for users to find the most relevant content. This technology helps filter and prioritize search results.
• Inefficient search experiences: By analyzing user profiles and search histories, the system can provide more efficient and accurate search results, saving users time and effort.

Benefits of this technology:

• Improved search relevance: By considering user profiles and search histories, the system can deliver more relevant search results tailored to individual preferences.
• Personalized user experience: Users can receive personalized recommendations and content based on their profiles and search histories.
• Time and effort savings: The system provides more efficient search results, helping users find what they need quickly and easily.

Original Abstract Submitted

A system, processes, and a computer-readable storage medium are provided method includes receiving a search query including one or more of a textual phrase, a document, or data including metadata from a user. For example, a processor may execute a theme-generating machine learning algorithm to generate a theme of the search query. Profiles of other users are identified as similar to a profile of the user may be located. A search history of each of the located other users may be located in the collected search history. Content in the searchable content that corresponds to the generated theme of the search query and according to a result of the evaluation of the located search history of each of the other users may be obtained. The obtained content may be scored based on a scoring algorithm and output a set of scored search results to the input/output device.