Voice Response Display Using Utterance History for Ambiguous Inputs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional interactive systems struggle to comprehend user intentions accurately, particularly with ambiguous uttered voices, limiting the system's ability to perform operations or provide information accordingly.
Innovation Solution
An interactive server that includes a communicator, storage device, extractor, and controller to process and generate response information based on utterance history and extracted elements, allowing it to handle various user utterances by combining stored execution languages and commands or estimating them from history.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the external server parses uttered voices to comprehend user intentions, then clear uttered voices can be correctly understood and responded to, but ambiguous uttered voices cannot be properly comprehended, limiting the system's ability to handle various user utterances
Solution Approach 1:
The system performs preliminary actions by storing execution languages and commands corresponding to uttered elements in advance. When a user utterance is received, the system extracts uttered elements and checks whether corresponding execution languages and commands are stored. This preliminary preparation enables the system to quickly determine whether it can respond to various types of utterances, including ambiguous ones, by matching extracted elements against pre-stored associations.
Solution Approach 2:
The system introduces an intermediary mechanism of uttered elements as mediators between user utterances and system responses. By extracting uttered elements from user speech and matching them against stored execution languages and commands, the system creates an intermediate layer that bridges the gap between ambiguous user input and precise system interpretation, enabling accurate comprehension even when the original utterance is unclear.
2Ease of operation
If the system only performs operations for predefined uttered voices, then parsing accuracy is maintained, but user interaction is restricted and flexibility is reduced
Solution Approach 1:
The system implements universality by storing multiple execution languages and commands corresponding to different uttered elements in a unified structure. This allows the system to handle various types of user utterances through a common processing framework, where the same extraction and matching mechanism works for both clear and ambiguous utterances, enhancing user interaction flexibility while maintaining reliable parsing through consistent application of the universal matching rules.
Data Source
AI summary
An electronic apparatus, method, and computer readable medium are provided. The electronic apparatus includes a communicator, and a controller. The controller, based on a first voice input being received, controls the communicator to receive data including first response information corresponding to the first voice input from a server, and outputs the first response information on a display, and based on a second voice input being received, controls the communicator to receive data including second response information corresponding to the second voice input from the server, and outputs the second response information on the display. Based on whether the second voice input is received within a predetermined time from a time corresponding to the output of the first response information, whether a use of utterance history information is identified, and the second response information is displayed differently based on whether the second voice input is received within the predetermined time.