Voice Enabled Bot Platform Adaptation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current chatbot technologies lack support for mixed speech and text inputs and outputs, making them inconvenient for users in various environments and scenarios, as they do not adapt to the user's changing needs for input and output methods.
Innovation Solution
A platform that extends the Microsoft Bot Framework to enable a single bot to handle both speech-enabled and non-speech-enabled clients, allowing for the detection of input types and programmatically generating outputs in suitable formats, including speech and text, based on device capabilities and user preferences.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If speech-to-text conversion is implemented in user-side chat client programs, then users can provide speech input, but the approach increases device complexity and computational load on client devices
Solution Approach 1:
The patent extracts the speech-to-text conversion functionality from the user-side chat client program and relocates it to the server-side bot program. This allows speech input processing to be performed on the server rather than requiring complex speech recognition capabilities on the client device, thereby reducing client device complexity while maintaining speech input capability.
Solution Approach 2:
The patent introduces an intermediary mechanism where the client program captures speech input through a microphone and transmits it to the server, which then performs the conversion to text. This intermediary approach allows speech processing without requiring the client device to have built-in speech-to-text conversion capabilities.
2Adaptability or versatility
If chatbots are designed to support only text input and output, then device compatibility is maintained, but adaptability to different user needs and environments is reduced
Solution Approach 1:
The patent implements a universal bot program architecture that can handle multiple input types (speech and text) and generate multiple output types (speech and text). The server-side bot program detects the client's capabilities and adapts its communication method accordingly, allowing a single bot design to work across speech-enabled and non-speech-enabled platforms without requiring separate bot versions.
Solution Approach 2:
The patent introduces dynamic adaptability where the bot program can change its input and output methods based on the client's capabilities. The system dynamically selects whether to use speech or text for communication based on real-time detection of client device capabilities, making the interaction method flexible rather than fixed.
3Ease of operation
If speech output is implemented on all devices, then user convenience is improved, but devices without speakers or in noisy environments cannot properly receive output
Solution Approach 1:
The patent implements dynamic output method selection where the bot program detects whether the client device has speech output capability (speaker) and whether the environment is suitable for speech (noise levels). Based on these detections, the system dynamically switches between speech output and text output methods, ensuring optimal user experience across different environments and device configurations.
Data Source
AI summary
A server is provided, including a processor configured to execute a bot server program. The bot server program may receive from a computing device an input with an input type that includes one or more of speech and text. The bot server program may programmatically generate an output, wherein the output is generated based on the input. The bot server program may detect one or more output types capable of being output by the computing device and select an output type from a plurality of output types that may include speech and text. The selected output type may be an output type capable of being output by the computing device. The bot server program may modify the programmatically generated output to produce a modified output with the selected output type, and may convey the modified output to the computing device for output on a display and/or speaker.