Voice Bundle Download for Conversation Assistant Adaptability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current electronic conversation assistants on smartphones are limited to performing basic tasks and lack the capability to handle complex, multi-step interactions, restricting user engagement and functionality beyond basic operations.
Innovation Solution
The development of a conversation assistant application that utilizes voice bundles, which are software packages containing call flow instructions, media, and parameters, allowing users to interact with electronic devices through voice, video, or text, enabling execution of specialized tasks by accessing a cloud-based repository of voice bundles that can perform various functions, such as social networking or troubleshooting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a limited number of basic tasks are integrated into the speech assistant, then the device complexity is reduced and ease of operation is improved, but the adaptability and versatility are worsened
Solution Approach 1:
The speech assistant is designed to perform multiple functions beyond basic tasks by integrating access to a cloud-based repository of voice bundles. The system can dynamically load and execute specialized voice bundles for social networking, troubleshooting, shopping, and other domain-specific tasks, making the assistant universal rather than limited to predetermined functions.
Solution Approach 2:
The speech assistant transitions from a static system with fixed basic tasks to a dynamic system that can adapt its capabilities. Voice bundles are downloaded and loaded on-demand from the cloud repository, allowing the assistant to dynamically expand its functionality based on user needs and available tasks, rather than being constrained to a fixed set of operations.
2Adaptability or versatility
If the speech assistant is configured to perform a wide variety of tasks, then the adaptability is improved, but the device complexity increases
Solution Approach 1:
A cloud-based repository and delivery system serves as an intermediary between the speech assistant and the extensive collection of voice bundles. Instead of storing all possible voice bundles locally on the device, the system downloads only the needed bundles from the cloud, reducing local device complexity while maintaining access to a wide variety of tasks through the intermediary cloud infrastructure.
Solution Approach 2:
The functionality of the speech assistant is segmented into a core platform and modular voice bundles. The core assistant handles basic operations and coordinates task execution, while specialized functions are divided into separate voice bundles that can be independently downloaded, loaded, and executed. This segmentation allows the device to maintain low complexity while accessing diverse capabilities.
3Adaptability or versatility
If voice bundles are downloaded from a cloud-based repository, then the adaptability and task variety are improved, but the loss of time for downloading and installation increases
Solution Approach 1:
Voice bundles are pre-configured and stored in a cloud-based repository, allowing users to search for and download needed functionality in advance. The system can also pre-load frequently used voice bundles or those relevant to the user's profile, so that when a task is needed, it is already available or can be quickly retrieved, reducing the time loss associated with downloading and installation.
Data Source
AI summary
A graphical user interface (GUI) on a display of an electronic device visually presents to a user a group of voice bundles that are available for use on the electronic device. Each voice bundle includes a software application for performing a call flow that includes a sequence of prompt instructions and grammar instructions executable to result in a simulated multi-step spoken interaction between the electronic device and the user. An input is received from the user entered through the GUI indicating a selection of a voice bundle from the group of voice bundles. In response to the input, a remote server is identified that stores the selected voice bundle. Network communications is established between the electronic device and the remote server. The selected voice bundle is located on the remote server. A copy of the selected voice bundle is downloaded from the remote server onto the electronic device.


