Generative AI Recommendation Reasoning for Large Option Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data management platforms (DMPs) struggle with managing large pools of options or audience segments, making it difficult for users to quickly and effectively navigate, analyze, and understand their relevance, viability, or preferability, leading to inefficiencies in selection processes.
Innovation Solution
Utilizing generative artificial intelligence (AI) models, such as large language models (LLMs), to generate natural-language textual justifications for selecting options or audience segments, reducing the complexity by providing clear reasoning behind the choices and optimizing computational resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If users manually navigate and analyze large pools of options in existing DMPs, then they can understand the relevance and viability of options, but the process becomes time-consuming and inefficient
Solution Approach 1:
The patent introduces an AI model as an intermediary between the user and the large pool of options. The AI model automatically analyzes the options, evaluates their relevance and viability, and presents recommendations to the user, eliminating the need for users to manually navigate and analyze each option, thus resolving the contradiction between thorough analysis and time efficiency
Solution Approach 2:
The patent replaces the manual mechanical process of user navigation and analysis with an automated AI-based system. The AI model performs the cognitive tasks of evaluating and ranking options, substituting the mechanical interaction of users scrolling and analyzing with an automated intelligent system that processes options efficiently
2Measurement precision
If comprehensive context data is provided to AI models for analysis, then recommendation precision improves, but computational costs and memory usage increase
Solution Approach 1:
The patent extracts only the most relevant features and context data needed for making recommendations, rather than processing all available data. The system identifies and extracts key attributes that matter for the specific recommendation task, reducing the volume of data processed while maintaining recommendation precision and lowering computational costs
Solution Approach 2:
The patent applies different levels of data processing and analysis to different parts of the context data based on their relevance. High-priority features receive more detailed analysis while less critical data is processed more efficiently or skipped, optimizing the balance between precision and computational resource usage
Data Source
AI summary
Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for recommendation from among a plurality of options with reasoning using generative artificial intelligence (AI). An example embodiment operates by receiving a natural-language textual request for a recommendation from among a plurality of options based on one or more criteria. A natural-language textual prompt is generated based on the request. The prompt references context data comprising the options. The prompt and context data is provided to a generative AI model, which provides an output that includes a textual description uniquely specifying a chosen one of the plurality of options, a numeric value scoring the chosen one of the plurality of options, and a natural-language textual justification for choosing the chosen one of the plurality of options. The textual justification generated by the generative AI model is based on the textual prompt and the context data.