Spoken Announcement Text Conversion for Transit Stations

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Passengers and other individuals in crowded transportation stations often struggle to understand public announcements due to background noise and language barriers, as existing systems fail to effectively translate spoken announcements into text or provide relevant transportation information in a user's preferred language.

Innovation Solution

A method and system that utilize natural language processing to interpret and extract transportation information from spoken announcements, translate this information into text, and deliver it to registered users' mobile devices via SMS or other mobile applications, allowing users to receive announcements in their chosen language.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If public announcements are broadcast through speakers in crowded transportation stations, then information can be transmitted to multiple passengers simultaneously, but passengers cannot understand the content due to background noise, muffled speech, and language barriers

Engineering Contradiction:
Improveannouncement comprehensionVSAvoidbackground noise and language barriers
Core Design Contradiction:
Loss of informationVSObject-affected harmful factors

Solution Approach 1:

The patent introduces an intermediary system consisting of a microphone, natural language processing module, and translation system. The microphone captures the announcement, the NLP module extracts transportation information, and the translation system converts it to the user's preferred language, delivering it via mobile device. This intermediary chain transforms the noisy acoustic environment into clear, personalized text notifications.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the mechanical acoustic transmission system (speakers broadcasting to crowds) with an electronic information processing system. Instead of relying on acoustic waves to convey information through noisy environments, the system uses digital signal processing, natural language understanding, and electronic communication to deliver the same information directly to individual users' mobile devices.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If natural language processing and translation systems are implemented to convert announcements into text messages, then comprehension and accessibility are improved, but system complexity increases

Engineering Contradiction:
Improveannouncement accessibilityVSAvoidprocessing system complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent implements a multi-functional system where a single integrated platform performs multiple tasks: capturing announcements via microphone, transcribing speech to text, extracting transportation information, translating into multiple languages, and delivering notifications. This universal system handles diverse functions through a unified architecture, reducing the need for separate specialized systems.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system automatically captures announcements, processes them through NLP, translates the content, and delivers notifications without requiring user intervention. Users simply register their preferences and receive automated service, eliminating the need for manual transcription or translation efforts.

Inventive Principle:
Principle #25Self-service

3Loss of information

If transportation information is extracted and translated into multiple languages, then user comprehension is enhanced, but processing time and computational resources increase

Engineering Contradiction:
Improveinformation delivery accuracyVSAvoidtranslation and processing time
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The system performs preliminary processing by capturing and transcribing the announcement in real-time, extracting transportation information immediately upon detection. This preliminary action prepares the data for rapid translation and delivery, reducing overall processing time by not waiting for the complete announcement to finish playing before starting information extraction.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system focuses on extracting only the essential transportation information from announcements rather than translating entire texts. By identifying and prioritizing key information elements (such as destination, time, platform), the system rushes through the processing of only the most critical data, reducing translation time while maintaining information accuracy.

Inventive Principle:
Principle #21Skipping (Rushing through)

Data Source

PatentUS20210195385A1Text message delivery based on spoken announcements
Publication Date: 2021.06.24 UNISYS CORP
  • US20210195385A1 patent drawing
  • US20210195385A1 patent drawing
  • US20210195385A1 patent drawing

AI summary

A method and system for delivering announcement broadcasts. The method includes receiving an announcement broadcast from a broadcast system of a transportation station. The method also includes interpreting the received announcement broadcast using natural language processing to extract transportation information. The method also includes the received announcement broadcast and the extracted transportation information in a data storage location. The method also includes translating the stored announcement broadcast into a text message. The method also includes transmitting the text message to at least one mobile device of at least one user registered with the announcement broadcast delivery method, based on the transportation information and the user information stored in the data storage location.