Evaluation Information Identifying Device for Biased Review Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing electronic commerce systems face challenges in identifying and filtering out biased reviews posted by interested parties, which can undermine the reliability of evaluation information for users.

Innovation Solution

An evaluation information identifying device and method that determine correlations between suppliers and evaluators based on the proportion of positive evaluations, allowing for the extraction and processing of specific evaluation information to distinguish and manage reviews from interested parties.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If all evaluation information is displayed to users, then the quantity of information is increased, but the reliability of the information deteriorates due to inclusion of biased reviews from interested parties

Engineering Contradiction:

Improvequantity of evaluation informationVSAvoidreliability of evaluation information

Core Design Contradiction:

Quantity of substanceVSReliability

Solution Approach 1:

The patent extracts and identifies evaluation information from interested parties using correlation analysis between suppliers and evaluators. By calculating correlation based on evaluation patterns, the system separates biased reviews from genuine user feedback, removing harmful elements while preserving useful evaluation data.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent introduces an intermediary correlation determination mechanism that analyzes the relationship between suppliers and evaluators. This intermediary system calculates correlation values based on evaluation patterns and uses these to identify biased reviews, acting as a mediator between raw evaluation data and final displayed information.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If correlation analysis is performed to identify biased reviews, then the reliability of evaluation information is improved, but the device complexity increases

Engineering Contradiction:

Improvereliability of evaluation informationVSAvoidcomplexity of evaluation processing system

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system performs self-service by automatically analyzing evaluation patterns and identifying biased reviews without requiring manual intervention. The correlation determination mechanism autonomously calculates relationships between suppliers and evaluators, and the extraction mechanism automatically identifies and separates biased information, reducing operational complexity.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent changes the parameter of evaluation information by introducing correlation values as a new dimension for analysis. By calculating correlation between suppliers and evaluators based on evaluation patterns, the system transforms raw evaluation data into correlated information that can be systematically filtered, simplifying the identification of biased reviews.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If correlation determination conditions are set to identify interested parties, then the precision of identifying biased reviews is improved, but the difficulty of detecting and measuring increases

Engineering Contradiction:

Improveprecision of identifying biased reviewsVSAvoiddifficulty of detecting correlation between supplier and evaluator

Core Design Contradiction:

Measurement precisionVSDifficulty of detecting and measuring

Solution Approach 1:

The system uses feedback from evaluation patterns to continuously refine correlation determination. By analyzing the relationship between suppliers and evaluators across multiple evaluations, the system accumulates data that improves the precision of identifying biased reviews. The feedback loop allows the system to learn from past evaluation patterns and enhance detection accuracy over time.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent performs preliminary correlation analysis before displaying evaluation information to users. By pre-calculating correlation values between suppliers and evaluators and identifying biased reviews in advance, the system reduces the complexity of real-time detection. The preliminary identification of interested parties allows for streamlined processing when presenting evaluation information.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS9576304B2Evaluation information identifying device, evaluation information identifying method, evaluation information identifying program, and computer readable recording medium for recording the program

Publication Date: 2017.02.21 RAKUTEN GROUP INC

AI summary

An evaluation information identifying device includes an extracting unit that, when, as a result of determining the presence or absence of a correlation between a supplier of an evaluation target and an evaluator having made a positive evaluation on the evaluation target, it is determined that there is a correlation, extracts evaluation information posted by the evaluator on the evaluation target provided by the supplier as specific evaluation information, and an outputting unit that performs specified processing based on the extracted specific evaluation information. It is thereby determined whether the possibility that the evaluator is an interested party to the supplier is high or low, and the evaluation information by an interested party to the evaluation target or the like is identified. It is thereby possible to provide useful evaluation information.