Virtual Recommendation Engine Using Contact Interaction Weighting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional online rating and review systems are unreliable due to their discrete and uncontrolled nature, allowing for manipulated and outdated opinions, lack of integration, and failure to consider non-user input behavioral ratings, leading to inaccurate product or service recommendations.
Innovation Solution
A computer program product that aggregates user contacts' recorded online consumer events to generate a virtual recommendation based on weighted consumer interactions, providing a reliable and integrated view of product or service experiences from trusted sources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional discrete rating systems are used, then users can provide feedback through multiple channels (reviews, ratings, thumbs up), but the system becomes unreliable due to uncontrolled sources and manipulation
Solution Approach 1:
The patent merges multiple discrete feedback channels (reviews, ratings, thumbs up) into a single integrated feedback model. The system combines these separate evaluation methods into one unified approach that processes all feedback types together, eliminating the reliability issues associated with uncontrolled discrete sources while preserving the versatility of multiple feedback channels.
Solution Approach 2:
The patent introduces a feedback model as an intermediary layer between users and the rating system. This model acts as a mediator that processes, validates, and integrates feedback from multiple sources, filtering out manipulation and uncontrolled inputs while preserving genuine user opinions across different feedback channels.
2Productivity
If uncontrolled sources are allowed to submit reviews and ratings, then user participation increases, but reliability decreases due to purchased reviews and bot manipulation
Solution Approach 1:
The patent implements feedback mechanisms that allow the system to learn from and adjust to user behavior patterns. The feedback model continuously refines its understanding of authentic vs. manipulative patterns, enabling the system to maintain high user participation while filtering out purchased reviews and bot manipulation through adaptive detection algorithms.
Solution Approach 2:
The system performs self-validation and self-filtering of feedback inputs. The feedback model automatically detects and excludes manipulative patterns (such as purchased reviews or bot behavior) without requiring external intervention, maintaining reliability while preserving user participation through autonomous quality control.
3Device complexity
If static review systems are used, then implementation is simple, but the system becomes outdated and unreliable as user experiences change over time
Solution Approach 1:
The patent transforms the static review system into a dynamic feedback model that continuously adapts to changing user experiences over time. The model processes feedback in real-time and updates its recommendations dynamically, maintaining high reliability and accuracy while managing complexity through intelligent algorithms that learn from evolving user behavior patterns.
4Quantity of substance
If multiple discrete feedback sources are aggregated, then comprehensive coverage is achieved, but the system becomes complex and difficult to manage
Solution Approach 1:
The patent creates a universal feedback model that handles multiple feedback types (reviews, ratings, thumbs up) through a single integrated framework. This multi-functional approach allows the system to process diverse feedback sources comprehensively while maintaining manageable complexity through unified processing logic and consistent evaluation criteria.
Data Source
AI summary
A system and process provides consumers with product or services virtual recommendations from a list of contacts. In response to the consumer searching for or browsing a product or service, the system searches through stored contacts that have also interacted with the searched/browsed product or service. A virtual recommendation may be provided to the consumer based on the contacts' interaction with the product or service. In some embodiments, the virtual recommendation is displayed as a list of the contacts that had a previous consumer interaction with the product or service.


