Visual Search Digital Supplement Retrieval via Neural Network Metadata

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current technologies lack an efficient method for identifying and presenting digital supplements based on visual content, such as images captured by mobile devices, which limits the ability to provide relevant augmented reality experiences and information in real-time.

Innovation Solution

A system and method that involves a client computing device capturing images, transmitting visual-content queries to a server, and retrieving digital supplements associated with identified entities or objects, using neural networks for image analysis and metadata indexing to provide relevant digital content.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If a visual-content query system is implemented to identify digital supplements based on images, then relevant augmented reality content and information can be provided in real-time, but the system complexity and computational requirements increase

Engineering Contradiction:
Improvereal-time identification and presentation of digital supplementsVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system is divided into distinct functional modules: image capture component, neural network analysis component, metadata indexing component, and digital supplement presentation component. This segmentation allows each module to specialize in specific tasks, improving overall efficiency while managing complexity through modular design.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Metadata serves as an intermediary layer between the visual content and digital supplements. The system extracts metadata from images (such as entity identifiers, object types, or scene descriptors) and uses this structured data to efficiently retrieve relevant digital supplements, reducing direct computational complexity between image analysis and content delivery.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If neural networks are used for image analysis to identify entities and objects, then accurate digital supplement retrieval is enabled, but processing time and computational resources increase

Engineering Contradiction:
Improveimage analysis accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-processing images to extract metadata (such as entity identifiers, object types, or scene descriptors) before the actual digital supplement retrieval. This preliminary metadata extraction creates a simplified representation that accelerates subsequent processing while maintaining analysis accuracy.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system dynamically adjusts processing depth based on requirements: for simple queries, it uses lightweight metadata comparison; for complex queries requiring higher precision, it engages full neural network analysis. This dynamic approach optimizes processing time while maintaining necessary accuracy levels.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS11023106B2Digital supplement association and retrieval for visual search
Publication Date: 2021.06.01 GOOGLE LLC
  • US11023106B2 patent drawing
  • US11023106B2 patent drawing
  • US11023106B2 patent drawing

AI summary

Systems and methods for identification and retrieval of content for visual search are provided. An example method includes transmitting a visual-content query to a server computing device and receiving a response to the visual-content query that identifies a digital supplement. The example method also includes causing a user interface to be displayed that includes information associated with the digital supplement. The visual-content query may be based on an image. The digital supplement may include information about the content of the image.