Interaction Assistance Device for Speech Example Generation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing interaction services struggle to encourage continuous use of less frequently used functions, as these functions often have low user adoption rates and are not effectively promoted through speech examples.
Innovation Solution
An interaction assistance device that calculates a first use degree for each function based on user interaction history, determines target functions with high re-use potential, generates speech examples for these functions, and presents them to users to encourage continuous use.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If speech examples for less frequently used functions are presented to users, then the chance for executing these functions is increased, but the functions are still not continuously used due to low user adoption rates
Solution Approach 1:
The system performs preliminary actions by presenting speech examples for functions that users are likely to use continuously in the future, based on analysis of interaction histories from multiple users. This allows the system to proactively guide users toward functions that have demonstrated continuous usage patterns in similar user contexts, rather than simply responding to current usage patterns.
Solution Approach 2:
The system incorporates feedback mechanisms by analyzing interaction histories to identify functions that users continuously use, and uses this feedback to determine which speech examples to present. The system continuously monitors usage patterns and adjusts speech example presentations based on observed user behavior, creating a closed-loop system that improves continuous usage over time.
2Adaptability or versatility
If speech examples are generated for all functions, then all functions have equal opportunity to be used, but resources are wasted on functions with low re-use potential
Solution Approach 1:
The system applies local quality by generating speech examples selectively for specific functions based on their re-use potential, rather than uniformly for all functions. Speech examples are concentrated on functions that demonstrate continuous usage patterns in interaction histories, while functions with low re-use potential receive fewer or no speech examples, optimizing resource allocation.
Solution Approach 2:
The system changes parameters by dynamically adjusting the generation of speech examples based on calculated re-use potentials. The re-use potential is determined by analyzing interaction histories and identifying functions with high continuous usage rates, then modifying speech example generation priorities accordingly to match these identified patterns.
3Productivity
If the system presents speech examples based on current usage patterns, then frequently used functions are promoted, but functions with high re-use potential are not effectively identified
Solution Approach 1:
The system performs preliminary analysis of interaction histories to identify functions with high re-use potential before presenting speech examples. By examining patterns across multiple users' interaction histories, the system can predict which functions are likely to be continuously used and prioritize speech example generation for these functions in advance.
Solution Approach 2:
The system uses feedback from aggregated interaction histories to identify re-use potential patterns. By continuously analyzing usage data from multiple users, the system extracts information about which functions tend to be continuously used, and uses this feedback to improve speech example presentations for functions with high re-use potential.
Data Source
AI summary
An interaction assistance device 10 is configured to: calculate a first use degree representing a degree to which a function is used in accordance with the user speech in a first period for each function by referring to an interaction history DB (10a) storing an interaction history for each user including information representing a function corresponding to the user speech input by one or more users and information representing a time point at which the function was executed; determine a target function on the basis of the first use degree for each function; generate speech examples corresponding to the target function; and determine speech examples to be presented to the user from among the speech examples generated by the speech example generating unit (14).