Personalized Speech Task Selection via Local Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional speech recognition services do not provide tasks that are personalized to individual user preferences, leading to inconvenience as they lack reflection of user-specific preferences when generating tasks.
Innovation Solution
An electronic apparatus that includes a processor and memory to receive user utterances, transmit data to an external server, and perform tasks based on user feedback, using natural language understanding processes to determine rule IDs and confidence levels, and provide personalized tasks by selecting appropriate path rules or sample utterances.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a single server creates tasks for all users, then server resource utilization is efficient, but user preference personalization is lost
Solution Approach 1:
The patent segments the task creation process into two parts: a centralized server that generates basic task templates and a local electronic apparatus that personalizes tasks using stored user feedback data. This segmentation allows task personalization without requiring a completely distributed server architecture.
Solution Approach 2:
The patent implements a feedback mechanism where user interactions with tasks are collected and stored as feedback data in the electronic apparatus. This feedback is used to continuously improve and personalize future task recommendations, creating a closed-loop system that adapts to individual user preferences.
2Ease of operation
If conventional speech recognition provides generic tasks, then implementation is simple, but user satisfaction decreases due to lack of personalization
Solution Approach 1:
The patent performs preliminary actions by collecting and storing user feedback data during normal device usage before it is needed for task personalization. This pre-collection of data allows the system to quickly personalize tasks without adding significant processing delays when tasks are actually needed.
Solution Approach 2:
The electronic apparatus performs self-service by autonomously using its own stored feedback data to personalize tasks without requiring constant external server intervention. This reduces the complexity of server-side personalization while maintaining high task relevance.
3Measurement precision
If user feedback data is collected and processed, then task personalization improves, but data processing complexity increases
Solution Approach 1:
The patent extracts only the essential feedback data elements needed for personalization and stores them locally, rather than processing and storing all possible user interactions. This selective extraction reduces data processing complexity while maintaining sufficient precision for task personalization.
Data Source
AI summary
An electronic apparatus includes a touch screen display, a microphone disposed at least one speaker, a wireless communication circuit, a processor, and a memory. The memory stores instructions that, when executed, cause the processor to receive a first user utterance input, to transmit first data associated with the first user utterance input to an external server, to receive a first response, to provide the first sample utterances, to receive a first user input for selecting one of the first sample utterances, to transmit second data associated with the first user input to the external server, and to perform the second task by causing the electronic apparatus to have a sequence of states. The first user utterance input includes a request for performing a first task. The first response includes first sample utterances indicating a second task.