Multi-lingual Communication Service Using Dynamic Key Routing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current technologies lack an effective solution for organizing and facilitating real-time multi-lingual conversations across different languages, especially in large populations, due to limitations in direct client-server communication through firewalls and the absence of dynamic language and domain selection in existing speech and language technologies.

Innovation Solution

A system and method utilizing public and private key combinations to create dynamic communication links over a network, enabling multi-lingual real-time communications by employing a web service for translation, which supports speech-to-speech, text-to-text, and text-to-speech translations, and uses Distributed Speech Recognition to extract and transmit speech features, allowing flexible language and domain selection.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If direct client-server communication is used on the internet, then communication simplicity is improved, but communication reliability deteriorates due to firewalls and proxy servers blocking direct links

Engineering Contradiction:
Improvecommunication simplicityVSAvoidcommunication reliability
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent introduces a server as an intermediary that relays communications between clients. Instead of direct peer-to-peer connections, the server acts as a mediator that receives messages from one client and forwards them to the intended recipient, thereby bypassing firewall and proxy server restrictions while maintaining communication reliability.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Productivity

If data streaming based Distributed Speech Recognition is used, then real-time speech processing capability is improved, but system flexibility deteriorates due to lack of control channel for dynamic language or domain selection

Engineering Contradiction:
Improvereal-time speech processing capabilityVSAvoidsystem flexibility
Core Design Contradiction:
ProductivityVSAdaptability or versatility

Solution Approach 1:

The patent segments the speech recognition system into separate functional modules: data streaming speech recognition for real-time processing, and a control channel for dynamic configuration. This allows the speech processing to operate in real-time while the control channel independently manages language and domain selections, thereby maintaining both productivity and adaptability.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a control channel as an intermediary between the user and the speech recognition system. This control channel enables dynamic selection of languages and domains without interrupting the real-time speech processing stream, thus preserving system flexibility while maintaining real-time processing capability.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Adaptability or versatility

If speech and language technologies are used for cross-lingual conversation, then translation capability is improved, but system organization capability deteriorates due to lack of open structure for large populations

Engineering Contradiction:
Improvetranslation capabilityVSAvoidsystem organization capability
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements a universal server architecture that handles multiple functions: message relay, control signal processing, language translation coordination, and domain management. This single multi-functional system can organize conversations among large populations across multiple languages and domains, improving system organization capability while maintaining translation capability through its universal design.

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

Data Source

PatentEP2274870B1Open architecture based domain dependent real time multi-lingual communication service
Publication Date: 2016.09.07 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • EP2274870B1 patent drawingFigure 1
  • EP2274870B1 patent drawingFigure 2
  • EP2274870B1 patent drawingFigure 3

AI summary

A system and method for real-time network communications provides a session identifier (Session ID) as a public key for group communication (20, 22) between clients, and provides a channel identifier (Channel ID) representing a private key for each of a plurality of clients (12). The channel identifier includes client-specific attributes, which function to indicate grouping criteria for the group communication. A dynamic communication link is created over a network between a client (12) and a service (14) based upon the public and private key combination such that group communication is enabled based upon the attributes of the private key and the public key. Communications are translated using a translation service (16) which employs the attributes associated with the private key and the public key combination to provide response information in a designated language to enable multi- lingual real-time communications.