Computer Vision Item Identification via Knowledge Graph Confirmation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional textual search methods for items in inventories often result in inaccuracies and inefficiencies due to incomplete or ambiguous user descriptions, leading to increased burdens on users and resource utilization in image search systems.
Innovation Solution
A computer vision system that receives images from client devices, determines a set of predicted characteristics matching the object, and uses a knowledge graph to confirm these characteristics, thereby reducing the need for textual searches and minimizing computing resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional textual search methods are used to search for items in inventory, then users can query items using text descriptions, but the search accuracy decreases and user burden increases due to incomplete or ambiguous descriptions
Solution Approach 1:
The patent replaces the mechanical textual search system with an image-based computer vision system. Instead of requiring users to type text descriptions and process textual data, the system captures images of items and uses image recognition algorithms to identify and retrieve items from inventory, thereby improving accuracy while reducing user burden
Solution Approach 2:
The patent introduces image recognition technology as an intermediary between the user and the item inventory system. The image serves as a mediator that automatically extracts item characteristics and matches them with inventory data, eliminating the need for users to manually describe items and reducing search inaccuracies
2Productivity
If conventional textual search methods are used, then users can perform item searches, but computational and network resources are unnecessarily consumed
Solution Approach 1:
The patent performs preliminary image-based item identification before initiating a full textual search process. By first recognizing the item from its image and extracting key characteristics, the system can perform more targeted and efficient searches, reducing unnecessary computational steps and network resource consumption
Solution Approach 2:
The patent extracts essential item characteristics directly from images using computer vision technology, separating the identification function from the full textual search process. This extraction of key features enables more efficient searching by focusing only on relevant item attributes rather than processing complete textual descriptions
Data Source
AI summary
In various example embodiments, a system and method for determining an item that has confirmed characteristics are described herein. An image that depicts an object is received from a client device. Structured data that corresponds to characteristics of one or more items are retrieved. A set of characteristics is determined, the set of characteristics being predicted to match with the object. An interface that includes a request for confirmation of the set of characteristics is generated. The interface is displayed on the client device. Confirmation that at least one characteristic from the set of characteristics matches with the object depicted in the image is received from the client device.