A Knowledge Graph-Based Method and System for Perceived Quality Analysis of Agricultural Products Sold Online

By constructing a knowledge graph of perceived quality for online sales of agricultural products, and using user historical rating deviation parameters and confidence weights for personalized calibration and fusion calculation, the problem of evaluation distortion caused by differences in user rating habits is solved, and high accuracy and robustness of perceived quality evaluation for online sales of agricultural products are achieved.

CN122115083BActive Publication Date: 2026-07-17HUNAN INST OF INFORMATION TECH
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
HUNAN INST OF INFORMATION TECH
Filing Date
2026-04-30
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing methods for evaluating the perceived quality of agricultural products sold online have failed to effectively eliminate differences in user rating habits, resulting in distorted evaluation results that cannot accurately reflect the true perceived quality of agricultural products.

Method used

A knowledge graph-based approach is adopted to construct a knowledge graph of perceived quality for online sales of agricultural products. The original sentiment scores are personalized by using the historical rating deviation parameters of user entities, and fusion calculation is performed based on confidence weights to eliminate differences in user rating habits and improve the accuracy of evaluation.

Benefits of technology

It achieves highly accurate and robust perceived quality evaluation under scenarios with different user rating habits. By using multi-dimensional bias calibration and information entropy collaborative confidence weighting, it suppresses unreliable historical behavior noise and improves the accuracy and stability of the evaluation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122115083B_ABST
    Figure CN122115083B_ABST
Patent Text Reader

Abstract

This application provides a knowledge graph-based method and system for analyzing the perceived quality of agricultural products sold online. The method includes: performing sentiment analysis on user review texts to obtain raw sentiment scores; constructing a knowledge graph of perceived quality for agricultural products sold online based on a historical review text set; calibrating the raw sentiment scores based on historical rating deviation parameters associated with user entities in the knowledge graph to obtain individual perceived scores; determining the confidence weight of each user review based on the statistical distribution of all individual perceived scores under the same product link; calculating the perceived quality score of the agricultural product under the same product link based on the confidence weight and the individual perceived score; and determining the perceived quality trust score of the agricultural product under each brand based on the perceived quality scores of the agricultural product under each product link and its corresponding brand data. This application can adaptively eliminate differences in user rating habits, thereby improving the accuracy of perceptual quality evaluation for agricultural products sold online.
Need to check novelty before this filing date? Find Prior Art