Data Handling Method Recommendation via Time-Weighted Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data handling methods often recommend the most historically used method, which may not be the most suitable for a pending task, leading to inefficiencies, especially in applications like payment processing where users must manually switch methods, reducing overall efficiency.
Innovation Solution
A method that identifies attribute information of a pending data handling process, weights historical processes based on recency, and recommends the method with the highest recommended weight, aligning with user preferences by sorting historical data handling methods based on time and method usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If the data handling method with the highest historical usage rate is recommended first, then the recommendation is simple to implement, but it may not be the most suitable method for the pending data handling process, leading to reduced data handling efficiency
Solution Approach 1:
The patent changes the parameter for recommendation from simple historical usage rate to a time-weighted score that incorporates both usage frequency and recency. This allows the system to dynamically adjust recommendations based on temporal patterns, improving data handling efficiency while maintaining implementation feasibility through standardized scoring mechanisms.
Solution Approach 2:
The system performs preliminary analysis of historical data handling processes, calculating time-weighted scores in advance. By pre-processing historical usage patterns and establishing scoring criteria before the pending task occurs, the system can provide suitable recommendations without adding complexity during the actual data handling process.
2Ease of operation
If users manually switch and select alternative payment methods when the recommended method is not ideal, then users can choose their preferred method, but additional time is consumed and overall data handling efficiency is reduced
Solution Approach 1:
The system incorporates feedback from historical user behavior patterns to continuously improve recommendations. By analyzing which methods users actually choose and when they switch methods, the system adjusts time-weighted scores to better predict user preferences, reducing the need for manual switching while preserving user choice flexibility.
Solution Approach 2:
The recommendation system is dynamic rather than static, adjusting weights and priorities based on recency and changing usage patterns. This allows the system to adapt to evolving user preferences and task contexts, providing increasingly accurate recommendations that reduce manual intervention while maintaining user autonomy.
Data Source
AI summary
Attribute information of a pending data handling process to be performed is identified. Historical data handling processes for a same application scenario as the pending data handling process are identified based on the attribute information. A time that each identified historical data handling process is performed and methods used to perform the identified historical data handling processes are also identified. A weighting coefficient for each identified historical data handling process is determined. Weighted identified historical data handling processes are calculated by applying the weight coefficient to each identified historical data handling process. A recommended weight for each method used to perform the identified historical data handling processes is determined by combining weighted identified historical data handling processes that use the same method. A method that has the highest recommended weight to perform the pending data handling process is recommended.