17542412. RANKING ENTITY SEARCH RESULTS BASED ON INFORMATION DENSITY simplified abstract (INTERNATIONAL BUSINESS MACHINES CORPORATION)

RANKING ENTITY SEARCH RESULTS BASED ON INFORMATION DENSITY

Organization Name

INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor(s)

Christopher F. Ackermann of Fairfax VA (US)

Charles E. Beller of Baltimore MD (US)

Michael Drzewucki of Woodbridge VA (US)

RANKING ENTITY SEARCH RESULTS BASED ON INFORMATION DENSITY - A simplified explanation of the abstract

This abstract first appeared for US patent application 17542412 titled 'RANKING ENTITY SEARCH RESULTS BASED ON INFORMATION DENSITY

Simplified Explanation

The patent application describes a method for organizing and ranking documents based on their relevance to a target entity mentioned in a search query. Here are the key points:

• The method involves receiving a collection of documents that mention a specific target entity.
• The mentions of the target entity in each document are identified, and the surrounding content is extracted to form sections.
• Metrics are calculated to determine the relevance and irrelevance of each section to the target entity.
• A density score is generated for each section, indicating the concentration of relevant information.
• Based on the density scores of the sections, a relevancy score is assigned to each document.
• The documents are then ranked and presented in an order based on their relevancy score.

Potential applications of this technology:

• Search engines can use this method to improve the ranking and presentation of search results, providing more relevant information to users.
• Content recommendation systems can utilize this method to suggest relevant documents or articles to users based on their interests or search queries.

Problems solved by this technology:

• The method addresses the challenge of organizing and ranking a large number of documents based on their relevance to a specific entity, improving the efficiency and accuracy of information retrieval.
• It helps overcome the issue of irrelevant or low-quality information cluttering search results, ensuring that users are presented with the most relevant and useful documents.

Benefits of this technology:

• Users can save time and effort by quickly accessing the most relevant documents related to their search query or topic of interest.
• Search engines and recommendation systems can provide more accurate and personalized results, enhancing user satisfaction.
• Organizations can improve their information management and retrieval processes by efficiently organizing and prioritizing documents based on their relevance to specific entities.

Original Abstract Submitted

The method provides for receiving a plurality of documents including mentions of a target entity from a search query about the entity. The mentions of the target entity are identified in respective documents of the plurality of documents. Content surrounding the one or more mentions of the target entity are extracted with the mentions within the respective documents and form section. A respective document includes a plurality of sections. Metrics of relevance and irrelevance to the target entity are determined within the plurality of sections of the respective documents. A density score is generated for the plurality of sections of the respective documents. A relevancy score is assigned to respective documents of the plurality of documents, based on the density scores of the sections of the respective documents. The documents are ranked based on the relevancy score and presented in an order based on the ranking.