Entity Page Ranking Algorithm for Dynamic Search Result Placement

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing search engines place entity pages at a fixed position in search results, which can lead to poorly organized results and a diminished user experience, as they do not consider the content or characteristics of the entity page, potentially placing it inappropriately relative to product pages.

Innovation Solution

An entity page ranking algorithm that calculates a relevance value for entity pages based on their characteristics, allowing them to be placed at a dynamic position in search results relative to product pages, using a relevance function optimizer to maximize the objective function and ensure entity pages are interspersed with product pages at desired positions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If entity pages are placed at a fixed position in search results, then the placement is simple and consistent, but the search results become poorly organized and user experience diminishes

Engineering Contradiction:
Improvesimplicity of placementVSAvoidquality of search results
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent transforms the static fixed-position placement into a dynamic ranking system where entity pages are positioned based on calculated relevance scores. The ranking algorithm dynamically adjusts the position of entity pages relative to product pages by evaluating multiple characteristics including content relevance, entity popularity, and query specificity, allowing the search results to adapt to different queries and contexts while maintaining organized presentation

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent changes the placement parameter from a fixed position value to a dynamic relevance score derived from multiple parameters. The ranking system evaluates entity pages using characteristics such as content match quality, entity authority, user engagement metrics, and query relevance, then positions entity pages based on these calculated scores rather than predetermined locations, improving result quality while maintaining systematic organization

Inventive Principle:
Principle #35Parameter changes

2Reliability

If entity pages are ranked based on relevance characteristics, then the search results become better organized and more relevant, but the ranking system becomes more complex

Engineering Contradiction:
Improvequality of search resultsVSAvoidcomplexity of ranking system
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the ranking process into distinct components: a relevance function that calculates scores based on entity page characteristics, an objective function that defines desired ranking positions, and an optimization module that adjusts parameters. This segmentation allows the complex ranking system to be broken down into manageable, independent modules that can be developed, tested, and maintained separately, reducing overall system complexity while maintaining high result quality

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a relevance function as an intermediary between the entity page characteristics and the final ranking position. This intermediary component processes multiple input parameters (content relevance, entity popularity, query match quality) and transforms them into a single relevance score that determines positioning. The intermediary simplifies the ranking logic by providing a clear computational pathway from diverse characteristics to a definitive rank position

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS8666914B1Ranking non-product documents
Publication Date: 2014.03.04 AMAZON TECH INC
  • US8666914B1 patent drawing
  • US8666914B1 patent drawing
  • US8666914B1 patent drawing

AI summary

Systems, methods, and apparatus are provided for determining relevance of documents to queries. An optimized relevance function is configured to determine a relevance value of documents of a first type that are linked to documents of a second type. The relevance function is optimized to satisfy certain criteria. According to one criterion, a relevance value produced by the optimized relevance function, when invoked for documents of the first type, should have a locally maximal degree of fit to the results of the existing relevance function for the sample training documents of the second type. An assessed degree of fit of a document can be increased or decreased to arrive at an optimized relevance function that ranks the documents of the first type in a desired position relative to documents of the second type in search results. The degree of fit can be assessed by a user-provided objective function.