Cognitive Proximate Recommendation for Return Items
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional cognitive models for search and recommendation do not intelligently determine the best alternative when a match does not exist and fail to consider user preferences in weighing feature values to provide better alternatives.
Innovation Solution
A cognitive proximate recommendation method that extracts features and values from user requests, calculates the proximal distance between alternative items, and uses user preferences to rank and return the closest alternatives, enhancing the efficiency of search results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional search techniques rank results based on category data and quality matrix, then search results can be displayed, but the system cannot intelligently determine the best alternative when a match does not exist
Solution Approach 1:
The patent segments the search problem into distinct components: feature extraction from user requests, feature extraction from alternative items, value comparison, and proximal distance calculation. This segmentation allows the system to handle complex cognitive analysis through modular, manageable steps rather than requiring a monolithic complex system.
Solution Approach 2:
The patent performs preliminary actions by pre-extracting and storing features and values for alternative items in the database before user queries are processed. When a user request is received, the system compares against pre-processed data, enabling intelligent alternative determination without real-time complex analysis of all item attributes.
2Measurement precision
If conventional techniques do not consider user preferences in weighing feature values, then the system is simpler to operate, but the quality of recommendations deteriorates
Solution Approach 1:
The patent introduces user preferences as adjustable parameters that weight the importance of different features during comparison. The system allows dynamic adjustment of feature weights based on user preferences, enabling precise measurement of how well alternative items match user needs while maintaining ease of operation through automated parameter application.
Solution Approach 2:
The system performs self-service by automatically applying user preferences to weight feature values during comparison without requiring manual intervention. The cognitive analysis system autonomously determines the proximal distance between alternative items and user requests, providing precise recommendations while keeping the interface simple for users.
3Productivity
If the system extracts and compares multiple features and values of alternative items, then the quality of search results improves, but the computational complexity increases
Solution Approach 1:
The patent extracts only the relevant features and values needed for comparison from alternative items, storing them in a structured format. This extraction approach allows the system to work with essential data elements rather than complete item descriptions, improving productivity while managing computational complexity through selective data processing.
Solution Approach 2:
The system performs preliminary extraction and organization of features and values for alternative items before they are needed for comparison. This pre-processing enables efficient runtime queries by comparing against pre-structured data, enhancing productivity without requiring complex real-time analysis.
Data Source
AI summary
A cognitive proximate recommendation method, system, and non-transitory computer readable medium, include first extracting a requested feature and a requested value of the requested feature for a requested item and returning a return item from a plurality of return items stored in the database and returning a ranked list of the plurality of return items, where the ranked list further includes inter-relationships that are defined by defining a primary value of each of the requested items and the return feature corresponding to the requested feature or anchor value for each of the requested items and the return feature corresponding to the requested feature.