Natural Language Parameter Retrieval for Voice Assistant Commands
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
AI engines in electronic devices, such as voice assistants or chatbots, often lack necessary parameters to understand and process user commands, leading to repetitive queries that can fatigue users and negatively impact their experience.
Innovation Solution
An electronic device with a touchscreen, microphone, and processor that can obtain user inputs through touch or voice, identify intent, and retrieve additional required parameters from stored applications without further user queries.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If speech-to-text conversion is performed in real-time during a call, then communication convenience is improved, but power consumption increases
Solution Approach 1:
The system performs speech-to-text conversion on recorded call logs after the call ends, rather than in real-time during the call. This preliminary action allows the conversion to occur when power consumption is less critical, providing the convenience of text conversion without the continuous power drain of real-time processing.
Solution Approach 2:
The speech-to-text conversion is performed periodically on recorded call logs at scheduled intervals rather than continuously. This periodic processing reduces overall power consumption while still providing updated text conversions for call logs, balancing convenience with energy efficiency.
2Loss of information
If speech-to-text conversion is performed on all call logs, then information completeness is improved, but processing time increases
Solution Approach 1:
The system selectively converts speech-to-text for only certain call logs based on predefined criteria (e.g., important calls, calls from specific contacts, or calls exceeding a certain duration) rather than converting all call logs. This partial action reduces processing time while still providing complete information for the most relevant calls.
Solution Approach 2:
The system applies different conversion strategies to different call logs based on their characteristics. For example, high-priority calls may be converted in full, while less important calls may use summary conversion or be excluded entirely. This localized quality approach optimizes the balance between information completeness and processing efficiency.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An electronic device is provided. The electronic device includes a display including a touchscreen, a microphone configured to receive a voice input from a user, a memory, and at least one processor configured to be operatively connected to the display, the microphone, and the memory, wherein the at least one processor may be configured to obtain an instruction based on text that is input through a touch input on the display or a voice input that is input through the microphone, obtain intent corresponding to the instruction, identify at least one parameter additionally required to perform an operation corresponding to the obtained intent, and obtain the at least one additionally required parameter from at least one application stored in the memory.