Personalization Module Tuning Generative AI Randomness
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for generating personalized content are impractical due to the need for manual curation, which is not scalable, and lack the ability to leverage the capabilities of generative artificial intelligence (AI).
Innovation Solution
The use of a personalization module that employs generative AI to generate personalized content based on user interactions, attributes, and segment information, with a tuning parameter controlling the randomness of the AI's output.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual curation of personalized content is used, then content quality and personalization accuracy are improved, but scalability and productivity deteriorate
Solution Approach 1:
The system uses generative AI to automatically generate personalized content without human intervention. The AI model receives user attributes, segment information, and tuning parameters, then autonomously produces personalized content responses, eliminating the need for manual curation while maintaining scalability.
Solution Approach 2:
The patent replaces the mechanical process of manual content creation with an automated generative AI system. The AI model substitutes human creators by generating personalized content through algorithmic processing of user data, achieving both high personalization accuracy and unlimited scalability.
2Productivity
If segment-based personalization is used, then scalability is improved, but personalization accuracy deteriorates
Solution Approach 1:
The system enhances segment-based personalization by incorporating individual user attributes alongside segment information. The generative AI model processes both the user's specific characteristics and their segment classification, allowing the system to maintain scalability through segmentation while improving personalization accuracy through individualized attribute processing.
3Adaptability or versatility
If generative AI with high randomness is used, then content creativity and variety are improved, but consistency and reliability deteriorate
Solution Approach 1:
The patent introduces a tuning parameter that controls the randomness of the generative AI model. By adjusting this parameter, the system can balance between content variety (higher randomness) and content consistency (lower randomness), allowing flexible optimization based on specific application requirements while maintaining reliability.
Data Source
AI summary
Techniques for generating personalized content using generative artificial intelligence (AI) are provided. In an example method, a processing device including a personalization module receives an indication that a user interacted with content displayed on a web page. The personalization module receives a set of attributes, comprising information about the user and information about the content, and information about a segment to which the user belongs. The processing module then determines a tuning parameter, wherein the tuning parameter controls the randomness of the output of the generative AI model. The personalization module next inputs to the generative AI model the tuning parameter and a prompt comprising the set of attributes and the information about the segment and subsequently receives personalized content responsive to the tuning parameter and the prompt. The personalization module can then display the personalized content in a dynamic content field associated with the content.