Automated Brand Theft Detection on E-Commerce Platforms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting brand theft on e-commerce platforms are time-consuming and costly, and are limited by the sophistication of brand theft techniques, making it difficult to efficiently monitor and manage brand theft.
Innovation Solution
A method and electronic device for detecting brand theft by acquiring protected object data related to a brand, crawling e-commerce web pages, parsing the data to extract relevant information, analyzing the data to detect the presence of protected brand elements, and monitoring e-commerce websites based on the detection results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual detection and supervision methods are used to handle brand theft, then brand theft cases can be detected and managed, but the process becomes time-consuming and costly
Solution Approach 1:
The patent replaces manual mechanical detection methods with an automated computer-based system that uses crawlers to scrape e-commerce data, NLP models to analyze text content, and image recognition models to detect brand logos and trademarks. This substitution of mechanical human labor with automated computational systems resolves the contradiction by maintaining detection accuracy while dramatically reducing the time required for brand theft surveillance.
Solution Approach 2:
The system enables self-service detection by automatically crawling e-commerce platforms, parsing product information, analyzing images and text for brand infringement, and generating detection reports without requiring continuous manual intervention. The automated pipeline performs detection, analysis, and reporting functions independently, resolving the time loss issue while preserving detection capability.
2Reliability
If manual detection methods are used to supervise brand theft products, then brand theft can be detected, but the cost of manual supervision increases
Solution Approach 1:
The patent replaces costly manual supervision with automated computational resources. The system uses computer-based crawlers, NLP models for text analysis, and image recognition models to reliably detect brand theft products across e-commerce platforms without incurring ongoing manual labor costs, thus maintaining reliability while reducing energy loss in the form of supervision costs.
Solution Approach 2:
The system creates digital copies of brand assets (logos, trademarks, product images) and compares them against e-commerce listings through automated image recognition and text analysis. This copying and comparison approach enables reliable detection of brand theft products at minimal cost by using computational algorithms rather than manual review processes.
3Productivity
If conventional brand theft detection methods are used, then some brand theft cases can be identified, but sophisticated brand theft techniques evade detection
Solution Approach 1:
The patent implements a multi-functional detection system that simultaneously analyzes multiple data types including product titles, descriptions, images, and seller information using different specialized models (NLP for text, image recognition for visuals). This universal approach capable of handling various brand theft techniques maintains both high productivity and accuracy by adapting different analysis methods to different infringement patterns.
Solution Approach 2:
The system combines multiple detection technologies (crawling, NLP, image recognition, data analysis) into a composite detection framework. This composite approach integrates different analytical capabilities to detect sophisticated brand theft techniques that single-method systems would miss, thereby maintaining both efficiency and accuracy simultaneously.
Data Source
AI summary
A method of detecting a brand theft according to an embodiment of the present disclosure includes: acquiring protected object data related to a brand to be protected, the protected object data including brand character data and brand logo image data related to a brand, and CDN keyword data indicating a source in which the brand logo image data is stored; acquiring crawled data by crawling an e-commerce web page; parsing the crawled data to acquire first data corresponding to a title or content of the web page, second data corresponding to an image, and third data related to a source of the image; analyzing each of the first data, the second data, and the third data to detect whether the protected object data is included in the crawled data for the web page; and monitoring e-commerce websites based on the detection result.


