Image Item Identification Using Location-Based Filtering

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing systems lack efficiency in identifying and providing information about items depicted in images, particularly in a location-based context, often requiring excessive computational resources and failing to offer timely and accurate navigation guidance.

Innovation Solution

A method that utilizes location data to identify items in images by determining nearby locations with associated item information, providing instructions on the item and locations where it can be retrieved, and ranking these locations based on predicted retrieval time, thereby optimizing resource usage and user experience.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If existing systems analyze images to identify objects without using location data, then they can identify any object in the image, but they require excessive computational resources and time

Engineering Contradiction:
Improvecomputational efficiencyVSAvoidlocation context information
Core Design Contradiction:
ProductivityVSLoss of information

Solution Approach 1:

The system performs preliminary filtering by determining a set of candidate locations based on device location data before conducting image analysis. This preliminary action narrows down the search space, allowing the system to focus computational resources on identifying items at these specific locations rather than analyzing all possible objects in the image, thereby improving computational efficiency while maintaining accuracy

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

Location data serves as an intermediary that connects the device to relevant item information. By using location data to identify candidate locations and then accessing item information associated with those locations, the system efficiently bridges the gap between image analysis and object identification without requiring exhaustive computational analysis of the entire image

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If existing systems provide item identification without location-based filtering, then they can identify all items in the image, but they fail to provide timely and accurate navigation guidance

Engineering Contradiction:
Improveitem identification accuracyVSAvoidnavigation guidance time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system applies local quality by focusing item identification on specific locations relevant to the device's position. Instead of treating the entire image uniformly, the system determines candidate locations based on location data and accesses item information specifically for those locations, providing both accurate identification and timely navigation guidance by concentrating resources on locally relevant items

Inventive Principle:
Principle #3Local quality

3Reliability

If systems access item information for all locations without filtering, then they ensure complete item coverage, but they consume excessive memory and processing power

Engineering Contradiction:
Improveitem identification reliabilityVSAvoidcomputational resource consumption
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system segments the problem by dividing the search space into relevant and irrelevant portions based on location data. It determines a specific set of candidate locations that are geographically relevant to the device, then accesses item information only for those segmented locations. This segmentation maintains reliability by ensuring all relevant items are considered while dramatically reducing computational resource consumption by excluding irrelevant locations

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS11200614B2Identifying items in images
Publication Date: 2021.12.14 ACCENTURE GLOBAL SOLUTIONS LTD
  • US11200614B2 patent drawing
  • US11200614B2 patent drawing
  • US11200614B2 patent drawing

AI summary

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using location data to identify and provide services in association with items appearing in captured images. One of the methods includes receiving, from a device, an image and location data representing the device's physical location, determining, based on the location data, that a particular set of one or more locations are within a threshold distance of the device's physical location, accessing, for each of the one or more locations in the particular set, item information that indicates one or more items that are associated with the location, determining, based on the accessed item information, that the image likely shows a particular item that is associated with one or more locations in the particular set, and providing, to the device, instructions for presentation of information about (i) the particular item and (ii) one or more locations in the particular set that are associated with the particular item.