Dialogue Manager for Multi-Modal Language Independent Interaction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing user-machine interaction systems are language, input/output modality, and backend system dependent, leading to functional limitations, increased implementation complexity, and high costs due to their inability to support multiple input/output modalities and flexible dialogue interactions.

Innovation Solution

A language-independent user-machine interaction platform that supports multiple input/output modalities and interacts with backend systems regardless of data format, using a dialogue manager to transform user-input data into generic semantic representations, determining request types, and sending multi-facet output data for appropriate actions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a user-machine interaction system is designed to support multiple input/output modalities and languages, then the adaptability and versatility of the system is improved, but the device complexity and implementation costs increase

Engineering Contradiction:

Improvesupport for multiple input/output modalitiesVSAvoidimplementation complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system is divided into distinct functional modules: a dialogue manager that handles high-level conversation flow, a natural language processing module that processes language-specific inputs, and a semantic interpretation module that extracts meaning. This segmentation allows each module to specialize in specific tasks, making the overall system more manageable and reusable across different languages and modalities without proportionally increasing complexity.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The dialogue manager and semantic interpretation components are designed as universal modules that can handle multiple languages and input modalities (speech, text, keyboard) through a common architecture. By creating a language-independent dialogue management layer, the system achieves multi-functionality where the same core components serve diverse linguistic and modal requirements, reducing overall implementation complexity.

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Adaptability or versatility

Engineering Contradiction:

Improvesupport for multiple languagesVSAvoidimplementation costs

Core Design Contradiction:

Adaptability or versatilityVSEase of manufacture

Solution Approach 1:

The system employs a universal dialogue manager and semantic interpretation engine that work across multiple languages and modalities. This multi-functional architecture avoids the need to build separate systems for each language or modality, significantly reducing development, deployment, and maintenance costs while maintaining full multilingual and multi-modal capability.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system uses parameter-driven language adaptation where the same core processing pipeline handles different languages by adjusting linguistic parameters and vocabularies. This approach allows the system to support multiple languages without duplicating the entire processing infrastructure, thereby reducing implementation costs while maintaining versatility.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If a user-machine interaction system uses language-specific and modality-specific processing, then the measurement precision and dialogue accuracy are improved, but the adaptability and reusability of the system deteriorate

Engineering Contradiction:

Improvedialogue accuracyVSAvoidsystem reusability

Core Design Contradiction:

Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The system separates language-specific processing (vocabulary, grammar, semantics) from modality-specific processing (speech recognition, text parsing) and delivers both to a universal dialogue manager. This segmentation enables accurate, specialized processing for each language and modality while maintaining a reusable core dialogue management system that can be applied across different linguistic and modal contexts.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system introduces an intermediary semantic representation layer that translates language-specific and modality-specific inputs into a unified, language-independent format. This intermediary layer preserves the precision of specialized processing while enabling the universal dialogue manager to handle diverse inputs consistently, thereby maintaining both accuracy and reusability.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS9330089B2Method and apparatus for a multi I/O modality language independent user-interaction platform

Publication Date: 2016.05.03 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

Automated user-machine interaction is gaining attraction in many applications and services. However, implementing and offering smart automated user-machine interaction services still present technical challenges. According to at least one example embodiment, a dialogue manager is configured to handle multiple dialogue applications independent of the language, the input modalities, or output modalities used. The dialogue manager employs generic semantic representation of user-input data. At a step of a dialogue, the dialogue manager determines whether the user-input data is indicative of a new request or a refinement request based on the generic semantic representation and at least one of a maintained state of the dialogue, general knowledge data representing one or more concepts, and data representing history of the dialogue. The dialogue manager then responds to determined user-request with multi-facet output data to a client dialogue application indicating action(s) to be performed.