Digital Assistant Command Mapping Across Languages and Dialects
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional digital assistants are limited by the need for users to structure their spoken commands in a specific language and dialect, often misinterpret commands, and fail to execute actions within applications already installed on mobile devices, leading to frustration and inefficiency.
Innovation Solution
A digital assistant system that generates and distributes crowd-sourced action datasets, allowing users to invoke actions in their natural language, with a central server translating and mapping commands across multiple languages and dialects, enabling seamless execution of actions on various applications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a digital assistant uses speech recognition and natural language processing to interpret commands, then command interpretation accuracy is improved, but the system becomes more complex and requires more computational resources
Solution Approach 1:
The system segments the command interpretation process into multiple stages: speech recognition, natural language processing, action dataset matching, and action execution. Each stage handles a specific aspect of command processing, allowing the system to manage complexity through modular functional decomposition while maintaining high accuracy through specialized processing at each stage.
Solution Approach 2:
The patent introduces an intermediary action dataset structure that mediates between the user's natural language command and the target application's required input format. This intermediary layer translates and adapts commands, reducing the complexity of direct interface requirements while improving interpretation accuracy by providing structured context for disambiguation.
2Ease of operation
If a digital assistant is designed to work with applications already installed on mobile devices, then user convenience is improved, but the assistant's ability to execute actions is limited by device-specific constraints
Solution Approach 1:
The system achieves universality by creating a language-agnostic action dataset framework that can interface with multiple application types across different mobile devices. The action datasets are designed to be platform-independent, allowing the same conceptual action to be executed across different applications and devices through standardized interfaces and protocols.
Solution Approach 2:
The system adapts to device-specific constraints by parameterizing action datasets with configurable parameters that can be adjusted for different platforms and applications. This allows the universal action framework to modify its behavior based on detected device capabilities while maintaining consistent user interaction through natural language commands.
3Adaptability or versatility
If a digital assistant supports multiple languages and dialects, then adaptability is improved, but the storage requirements and processing resources increase
Solution Approach 1:
Instead of storing complete language-specific action datasets for every language and dialect, the system creates a single language-agnostic action dataset structure and generates language-specific versions by copying and adapting the core framework. This allows efficient language support through selective instantiation rather than storing all possible language variations as separate complete systems.
Solution Approach 2:
The action dataset is designed as a universal, language-independent core structure that can be instantiated for multiple languages. This universal framework handles the common functionality across all languages, while language-specific variations are handled through configurable parameters and translation layers, reducing overall storage requirements compared to maintaining separate complete systems for each language.
4Adaptability or versatility
If a digital assistant uses crowd-sourced action datasets, then the variety of available actions is improved, but the system requires complex data distribution and synchronization mechanisms
Solution Approach 1:
The system merges multiple action datasets from different users and sources into a unified, standardized action dataset structure. This consolidation process integrates crowd-sourced actions while maintaining consistency through standardized formats and protocols, reducing the complexity of managing distributed data by transforming it into a cohesive system.
Solution Approach 2:
The system performs preliminary processing and validation of crowd-sourced action datasets before incorporating them into the main system. This preliminary action includes verifying action feasibility, standardizing formats, and pre-filtering for quality, which reduces the complexity of subsequent data distribution and synchronization by ensuring only prepared and validated actions are integrated.
Data Source
AI summary
Systems, methods, and non-transitory computer-readable storage media are provided for crowdsourcing actions and commands of a digital assistant application, irrespective of the languages spoken by users of the digital assistant application. Techniques described herein enable the on-boarding of actions datasets, which include defined commands and actions that result therefrom, from client devices to a remote server device. More specifically, the described techniques facilitate the proper on-boarding, distribution, and retrieval of action datasets regardless of the command language employed by users of the digital assistant application to invoke a properly-determined corresponding action.