User Feature Identification via Reliability Weighted Mean
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining user features in service interactions are inaccurate due to malicious or unobjective evaluations, which can lead to false identification of service providers and receivers, affecting trust and fairness in online transactions.
Innovation Solution
A method and apparatus that calculate a reliability weighted mean value of evaluations based on their frequency weights, distinguishing between incremental and decremental relationships, to accurately determine user features by comparing this value to a preset threshold, thereby reducing the impact of malicious evaluations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If user features are determined based on the number or ratio of negative evaluations, then the identification process is simple and fast, but the accuracy is low due to malicious or unobjective evaluations
Solution Approach 1:
The patent segments the evaluation data analysis into multiple dimensions: reliability determination (assessing whether evaluations are malicious), frequency weight calculation (analyzing evaluation patterns), and reliability weighted mean value computation (integrating both reliability and frequency). This segmentation allows each aspect to be handled separately with appropriate algorithms, improving overall accuracy while maintaining manageable system complexity
Solution Approach 2:
The patent introduces new parameters to transform the evaluation analysis: reliability values (indicating whether an evaluation is malicious), frequency weights (reflecting evaluation patterns), and reliability weighted mean values (comprehensive assessment metric). By changing from simple counting to multi-parameter analysis, the system achieves higher accuracy in identifying user features
2Reliability
If all evaluations are treated equally in determination, then the calculation is straightforward, but malicious evaluations unfairly affect the results
Solution Approach 1:
The patent applies local quality by assigning different weights to different evaluations based on their specific characteristics. Each evaluation receives a reliability value and frequency weight tailored to its pattern and context, rather than treating all evaluations uniformly. This allows the system to differentiate between malicious and legitimate evaluations, improving fairness while the automated calculation maintains efficiency
3Measurement precision
If the system only counts negative evaluations, then the implementation is simple, but it cannot distinguish between genuine negative feedback and malicious attacks
Solution Approach 1:
The patent introduces reliability values and frequency weights as intermediary metrics between raw evaluation data and final user feature determination. These intermediaries capture nuanced information about evaluation authenticity and patterns, enabling the system to distinguish genuine feedback from malicious attacks without requiring complex direct analysis of evaluation content
Data Source
AI summary
A method and an apparatus of identifying a user feature include: in response to receiving a designated evaluation of an interacting party in a service interaction, determining a reliability value of the designated evaluation of the interacting party based on a feature value of the service interaction; based on reliability values of multiple designated evaluations of the interacting party in multiple service interactions including the designated evaluation, determining a reliability mean value of the multiple designated evaluations; determining a reliability weighted mean value of the multiple designated evaluations based on a frequency weight corresponding to the multiple designated evaluations and the reliability mean value, wherein a number of the multiple designated evaluations is in a monotonically incremental or decremental relationship with the corresponding frequency weight; determining a user feature of the interacting party based on a size relationship between the reliability weighted mean value and a preset reliability threshold. Using the solution provided in the embodiment of the present disclosure can improve the accuracy of determining a user feature of an interacting party in a service interaction.