Preference Graph Ranking for Content Relevance

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional information retrieval systems fail to accurately identify and present relevant information to users due to limitations in specifying and integrating user preferences, leading to user overload and inefficiency in finding desired content.

Innovation Solution

A computer-implemented method and system that calculates a ranking of items based on user preferences using a preference graph, which represents first-order and second-order user preferences, allowing for flexible and precise specification of preferences across multiple attributes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If conventional information retrieval systems present all potentially relevant results to users, then users have access to comprehensive information, but users become overwhelmed and fail to locate desired information efficiently

Engineering Contradiction:

Improvequantity of information presentedVSAvoidease of finding desired information

Core Design Contradiction:

Quantity of substanceVSEase of operation

Solution Approach 1:

The system automatically performs preference analysis and result ranking without requiring manual user intervention. The preference analysis module autonomously processes user profiles, item attributes, and preference expressions to generate optimized search results, eliminating the need for users to manually filter or rank large result sets

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The preference analysis module acts as an intermediary between the user and the information retrieval system. It translates user preferences into weighted criteria that mediate the matching process between search queries and potential results, presenting only the most relevant items rather than all possible matches

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If conventional search systems provide explicit search query interfaces, then users can indicate their information needs, but the indication is insufficient to accurately identify appropriate content from all available content

Engineering Contradiction:

Improveprecision of user preference indicationVSAvoidrelevance of presented content

Core Design Contradiction:

Measurement precisionVSLoss of information

Solution Approach 1:

The system transforms user preferences from simple query keywords into multi-dimensional preference parameters with associated weights. The preference analysis module processes these parameters through mathematical models that consider user profiles, item attributes, and preference expressions, converting qualitative user intentions into quantitative matching criteria for more precise content identification

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The preference analysis module segments the content selection process into distinct analytical components: user profile analysis, item attribute evaluation, preference expression processing, and weighted matching. This segmentation allows each aspect to be analyzed independently and combined to produce accurate content recommendations that fully capture user intent

Inventive Principle:

Principle #1Segmentation

3Ease of operation

If conventional approaches limit the ways users can specify preferences, then the system remains simple to operate, but the utility of preference specification is severely limited

Engineering Contradiction:

Improvesimplicity of preference specificationVSAvoidflexibility of preference specification

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The preference analysis module serves multiple functions through a unified interface: it processes explicit user preferences, infers implicit preferences from user profiles, analyzes item attributes across different domains, and generates weighted matching criteria. This multi-functionality allows diverse preference specifications to be handled through the same operational mechanism, maintaining simplicity while expanding versatility

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS10409880B2Techniques for presenting content to a user based on the user's preferences

Publication Date: 2019.09.10 PRIMAL FUSION INC

AI summary

Techniques for presenting content to users. The techniques include: obtaining user context information including a first keyword; identifying, based on the first keyword, a first attribute and a second attribute among the plurality of attributes, the first attribute being a characteristic of the first keyword and the second attribute being another characteristic of the first keyword; obtaining, based on the user context information, at least one second-order user preference among attributes in the plurality of attributes including a preference between the first attribute and the second attribute; identifying a set of content items among the plurality of content items based on the first attribute and the second attribute; determining a ranking of content items in the set of content items based on the at least one second-order user preference; and presenting content items to the user in accordance with the ranking.