Target has patented a method for generating item recommendations using weighted node-based graphs. The system assigns weights based on item images, descriptions, and selection information, then samples nodes to create a graph. Information is aggregated to generate a vector representation, which is used to recommend items from a collection. GlobalData’s report on Target gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on Target, Treatment progress monitoring was a key innovation area identified from patents. Target's grant share as of April 2024 was 86%. Grant share is based on the ratio of number of grants to total number of patents.
Generating item recommendations from retail item collection using weighted graph
A recently granted patent (Publication Number: US11995702B2) outlines a method for generating item recommendations within a retail setting using a computing system with processors. The method involves assigning weights between nodes representing different retail items based on item images, descriptions, and selection information. These weights form a weighted node-based graph that indicates the likelihood of one item being selected alongside another. By sampling from this graph and aggregating information from neighboring nodes using convolutional modules, a vector representation of the sampled graph is generated. This representation is then used to provide recommended items from the collection in response to an item identification, which can be displayed on a retail website through a web server.
Furthermore, the patent details a method for providing item recommendations to customers of a retail enterprise by utilizing a weighted graph-based convolution approach. This involves assigning weights between nodes representing inventory items, generating a weighted node-based graph based on these weights, and determining related inventory items using a sampling degree parameter. The set of related inventory items is then displayed on the retail website server as recommendations for the customer. The system described in the patent includes a computing system with programmable circuits and memory storing instructions for performing the recommendation generation process, including sampling from the weighted node-based graph, aggregating information, applying a loss function, and providing the recommended items to a retail web server for display.
To know more about GlobalData’s detailed insights on Target, 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, 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.
