Centralized Assessment Aggregation with ML Filtering

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Users of electronic markets face challenges in accessing relevant assessments for resources due to the lack of a centralized system for aggregating and presenting user feedback from multiple websites, leading to information overload and scores influenced by irrelevant factors.

Innovation Solution

A centralized system collects and aggregates assessments from multiple websites, using a machine-learning model to assign identifiers to user feedback, allowing users to select relevant information and recalculate scores based on their preferences, providing a unified interface for evaluating resources.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If assessments are collected from multiple websites, then the quantity of assessments increases, but the complexity of managing and presenting these assessments increases

Engineering Contradiction:

Improvequantity of assessmentsVSAvoidcomplexity of assessment management system

Core Design Contradiction:

Quantity of substanceVSDevice complexity

Solution Approach 1:

The patent segments assessments by assigning identifiers to different facets or categories of user experiences. This allows the large volume of assessments to be divided into manageable groups, making it easier to organize, filter, and present them without overwhelming complexity

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces a machine-learning system as an intermediary that automatically processes, categorizes, and tags assessments with identifiers. This intermediary handles the complex work of organizing assessments, reducing the burden on the overall system and enabling efficient management of large quantities of assessments

Inventive Principle:

Principle #24Intermediary (Mediator)

2Loss of information

If all assessments are presented to users, then the completeness of information increases, but the ease of finding relevant information decreases

Engineering Contradiction:

Improvecompleteness of assessment informationVSAvoidease of finding relevant assessments

Core Design Contradiction:

Loss of informationVSEase of operation

Solution Approach 1:

The patent applies local quality by allowing users to selectively view assessments based on specific identifiers or facets relevant to their needs. Instead of presenting all assessments uniformly, the system enables users to focus on particular aspects (e.g., specific features, experiences, or categories), making information retrieval easier while maintaining access to complete information when needed

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The patent implements dynamic filtering and sorting capabilities that allow users to adaptively adjust which assessments are displayed based on their specific needs. The system can dynamically reorganize assessments according to user-selected criteria, making it easy to find relevant information while preserving access to the full set of assessments

Inventive Principle:

Principle #15Dynamics

3Reliability

If aggregate score includes all assessments, then the representativeness of the score increases, but the accuracy for individual user needs decreases

Engineering Contradiction:

Improverepresentativeness of aggregate scoreVSAvoidaccuracy of score for individual user needs

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The patent enables parameter changes by allowing users to modify the composition of the aggregate score based on their specific needs. Users can weight different identifiers or facets differently, or exclude certain aspects from the score calculation. This transforms the aggregate score from a fixed, one-size-fits-all metric into a customizable measurement that maintains representativeness while achieving precision for individual user requirements

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS11550836B1Machine-learning model for resource assessments

Publication Date: 2023.01.10 ORACLE INT CORP

AI summary

A centralized system may collect and aggregate assessments from multiple websites. An aggregate score may be calculated for the resource that cumulatively considers assessments from a plurality of different websites from which assessments are received from users. Text descriptions associated with each of the assessments may be provided to a machine-learning system that uses a trained model to assign identifiers to the assessments as they are received. These identifiers may include common words or text that are descriptive of different facets of user experiences related to receiving and using the resource. After selecting one or more identifiers, assessments associated with that identifier may be included or excluded from the display. Additionally, the overall aggregate score for the resource may be recalculated by removing components of that score that are based on assessments with identifiers that have been selected for exclusion.