Sign Information Capture Using Machine Learning Extraction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems are inadequate for efficiently capturing and distributing information from ephemeral signs, such as signboards and posters, which often lack complete event details and require manual user searches, posing safety risks and limiting awareness of local events.

Innovation Solution

A system comprising a motor vehicle equipped with an imaging system and positioning system that captures images of signs, uses machine learning to extract event information, and an event aggregation server that processes and distributes this information to users based on their interests and location, creating event profiles and geofences to ensure timely and relevant notifications.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If manual searching through web pages and listings is used to find event details, then complete event information can be obtained, but user safety is compromised and time is lost

Engineering Contradiction:

Improveevent information completenessVSAvoiduser safety

Core Design Contradiction:

Loss of informationVSObject-affected harmful factors

Solution Approach 1:

The system performs preliminary actions by capturing images of signs and extracting event information in advance, storing it in a database before users need it. This allows users to receive pre-processes information without having to manually search, thus preventing safety issues while ensuring information completeness.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system introduces an intermediary component (event information extraction system using image recognition and OCR) that automatically retrieves event details from sign images. This intermediary handles the information search task, eliminating the need for users to manually search through multiple web pages while ensuring complete event information is obtained.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Loss of information

If manual searching through multiple sources is performed to obtain complete event details, then information accuracy improves, but time consumption increases

Engineering Contradiction:

Improveevent information completenessVSAvoidsearch time

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system replaces the mechanical manual searching process with an automated image recognition and OCR system. The machine learning models automatically extract event information from sign images, substituting the time-consuming manual search through multiple web pages and listings with rapid automated processing.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If only physical proximity to signs is required for event awareness, then system complexity remains low, but event awareness coverage is limited

Engineering Contradiction:

Improveevent awareness coverageVSAvoidsystem complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system creates digital copies of sign information by capturing images and extracting text data through OCR. These digital copies are stored and distributed to users, allowing event information to be accessed remotely without requiring physical proximity to the original signs, thus expanding event awareness coverage.

Inventive Principle:

Principle #26Copying

4Adaptability or versatility

If sign information is distributed in real-time to all users, then event awareness is maximized, but information relevance to individual users decreases

Engineering Contradiction:

Improveevent distribution reachVSAvoidinformation relevance

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system applies local quality by customizing event information distribution according to individual user characteristics, locations, and preferences. Instead of uniform distribution, the system tailors the type, timing, and content of event notifications to match each user's specific context, thereby maintaining high relevance while achieving broad distribution reach.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system changes parameters such as notification timing, information detail level, and distribution channels based on user preferences and contextual factors. This dynamic parameter adjustment allows the system to maximize event distribution reach while maintaining high information relevance for each user by adapting to their specific needs and behaviors.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS11308719B2System and method for capture and distribution of information collected from signs

Publication Date: 2022.04.19 QUALCOMM INC

AI summary

Disclosed is a method and apparatus for capturing, collecting, and distributing event information displayed on signs. The method may include capturing, by a mobile device, an image of a sign that displays information for an event. The method may also include extracting information for the event from the captured image of the sign, and determining a location of the mobile device when the image of the sign was captured. Furthermore, the method may include uploading, to a server, a time when the image was captured, the information for the event extracted from the captured image, a location of the event determined from extracted event information, a location of the sign, or a combination thereof.