Rakuten Group. has been granted a patent for an information processing system designed for electronic commerce. The system utilizes machine learning to analyze descriptive text and images of items, generating correspondence information by identifying and detecting objects, and ensuring consistency in referring parts related to those objects. GlobalData’s report on Rakuten Group gives a 360-degree view of the company including its patenting strategy. Buy the report here.

Smarter leaders trust GlobalData

Report-cover

Data Insights Rakuten - Company Profile

Buy the Report

Data Insights

The gold standard of business intelligence.

Find out more

According to GlobalData’s company profile on Rakuten Group, Dynamic premium pricing was a key innovation area identified from patents. Rakuten Group's grant share as of June 2024 was 62%. Grant share is based on the ratio of number of grants to total number of patents.

Electronic commerce platform with object recognition and correspondence

Source: United States Patent and Trademark Office (USPTO). Credit: Rakuten Group Inc

The patent US12046065B2 describes an advanced information processing system designed to enhance electronic commerce platforms. This system utilizes at least one processor and memory to execute a series of instructions that facilitate the acquisition of descriptive text and images related to items. The system employs two machine learning models: the first model detects objects in images using a region proposal method, while the second model identifies object words from the descriptive text through natural language processing. The system generates correspondence information that links detected objects to their respective object words, allowing for improved consistency in referring parts of the objects. Additionally, it can identify objects without corresponding images and prompt users to add missing images.

Further functionalities of the system include estimating the orientation of detected objects using a specialized orientation recognition model. This model utilizes three-dimensional object data to derive rotation parameters, which are then mapped to predetermined orientation options. The system also generates correspondence information that highlights any referring portions of objects that lack corresponding photographed portions. By integrating these capabilities, the system not only enhances the user experience by displaying relevant information but also ensures that users are notified when additional images are needed, thereby improving the overall quality and accuracy of the electronic commerce platform.

To know more about GlobalData’s detailed insights on Rakuten Group, buy the report here.

Data Insights

From

The gold standard of business intelligence.

Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.

GlobalData

GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.

GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.