Dynamic Facet Ranking via Supervised Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current facet generation and ranking technologies are inefficient and prone to human error, as they rely on manual, unsupervised processes for generating and ranking facets, leading to increased time and error in information retrieval.
Innovation Solution
The implementation of a supervised machine learning algorithm to dynamically generate and rank facets based on a performed query, using a search engine algorithm to identify indicative markers, select relevant facets, and assign weighted values for prioritization, thereby reducing human error and improving efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual facet generation and ranking processes are used, then human oversight and customization are possible, but time consumption and human errors increase
Solution Approach 1:
The patent replaces manual mechanical facet generation and ranking processes with an automated machine learning system. The ML algorithm automatically generates facets from query data and ranks them based on learned patterns, eliminating human manual intervention while maintaining or improving accuracy through supervised learning and quantitative similarity measurements.
Solution Approach 2:
The system enables self-service facet generation where the machine learning model autonomously processes queries, identifies indicative markers, generates relevant facets, and ranks them without human intervention. The system serves itself by automatically training on data and improving its facet generation capabilities over time through the supervised learning process.
2Productivity
If manual facet ranking is performed, then human judgment can be applied, but productivity and efficiency decrease
Solution Approach 1:
The patent transforms the complex qualitative judgment of manual facet ranking into quantitative parameter-based ranking. The system calculates quantitative similarity values between facets and indicative markers, assigns numerical weights to facets based on their relevance, and ranks them using calculated overall scores. This parameter transformation simplifies the ranking process while maintaining sophistication through mathematical measurements.
Solution Approach 2:
The machine learning algorithm acts as an intermediary between the raw query data and the final facet presentation to users. The ML model processes the complex task of facet generation and ranking, translating unstructured query information into organized, ranked facets. This intermediary handles the complexity internally while presenting simplified results to users.
3Reliability
If unsupervised facet generation is used, then automation is achieved, but errors and inaccuracies increase
Solution Approach 1:
The patent implements supervised machine learning where the system learns from labeled training data that provides feedback on correct facet generation and ranking. The model adjusts its parameters based on feedback from training examples, improving its accuracy over time. This feedback mechanism ensures high reliability while maintaining full automation in production.
Solution Approach 2:
The system performs preliminary training action before actual facet generation, where the machine learning model is trained on labeled datasets to learn correct facet ranking patterns. This preliminary supervised learning phase prepares the model to automatically generate accurate facets without human intervention during actual use, combining the benefits of supervision and automation.
Data Source
AI summary
Embodiments of the present invention provide a computer system, a computer program product, and a method that comprises analyzing a performed query by identifying a plurality of indicative markers based on a pre-stored classification database associated with the performed query; generating a plurality of facets based on the analysis of the performed query; selecting at least two facets within the generated plurality of facets by determining a quantitative similarity value between each respective facet and the plurality of identified indicative markers associated with the performed query; dynamically ranking the selected facets by prioritizing the selected facets based on a calculated overall score associated with assigned weighted values for each selected facet in the generated plurality of facets using a supervised machine learning algorithm; and displaying the dynamically ranked facets within a user interface of a computing device associated with a user.