Personalized Search Assistance Using Evolving Memory and ML Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern software programs are complex and often provide generic User Assistance (UA) that does not adapt to individual users' needs over time, failing to provide personalized search assistance effectively.
Innovation Solution
A Machine Learning (ML) model is trained using user feedback to generate a ranked list of query results, with an evolving memory that forgets past actions, ensuring search assistance is tailored to the user's most recent preferences by incorporating scoring functions that consider word frequency and other criteria.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If generic User Assistance applications are used to provide search assistance, then assistance is applicable to all users generally, but the assistance does not adapt to individual user needs or evolve over time
Solution Approach 1:
The system collects feedback from user interactions with search results and uses this feedback to retrain the machine learning model, enabling the assistance to adapt to individual user needs while managing complexity through iterative improvement
Solution Approach 2:
The system transitions from static generic assistance to dynamic personalized assistance by continuously updating the machine learning model with user feedback, allowing the assistance to evolve over time while maintaining manageable complexity through controlled adaptation
2Adaptability or versatility
If all user feedback is retained in the evolving memory, then the ML model has comprehensive training data, but the system cannot adapt to changing user preferences over time
Solution Approach 1:
The system changes the parameter of feedback retention by implementing a time-based filtering mechanism that removes feedback older than a specified threshold, allowing the model to adapt to recent user preferences while selectively preserving relevant historical data
Solution Approach 2:
The evolving memory dynamically adjusts its content by removing outdated feedback and incorporating new feedback, enabling the system to adapt to changing user preferences while maintaining an optimal balance between historical learning and current relevance
Data Source
AI summary
Search assistance personalized to a user, may be afforded by combining the application of scoring functions, with the training a Machine Learning (ML) model based upon feedback from that user. A plurality of scoring functions are applied to query results to calculate a plurality of score vectors. The ML model is then applied to generate a ranked list of vectors. Feedback from the user, is incorporated to develop an evolving memory. The feedback may be explicit, or may be implicit—e.g., based upon user selection of particular score vector(s) from the list or based upon user selection of particular query results corresponding to the score vectors. Embodiments may enhance relevance of search assistance by removing past feedback from the evolving memory that is used to retrain the ML model. Embodiments can provide assistance to search text corpuses utilizing scoring functions considering frequency of occurrence of particular words or terms.