Dialog Control Device for Personalized Robot Interaction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Entertainment robots face challenges in acquiring and utilizing user-specific information due to limited memory capacity and random topic transitions, leading to unengaging interactions.
Innovation Solution
A dialog control device and method that includes a memory system for storing user information and a conversation generation mechanism to select topics related to previous conversations, generating acquisition or utilization conversations to gather and utilize this information, ensuring personalized and engaging interactions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the robot stores various user-specific information in memory, then the conversation becomes more personalized and engaging, but the memory capacity is limited and cannot store everything that appears in conversations
Solution Approach 1:
The patent extracts only the essential user-specific information (name, birthday, sex, likes, dislikes) from the vast amount of possible conversation data and stores these in a structured memory format. This selective extraction allows the robot to achieve personalization within limited memory capacity by focusing on the most impactful attributes for creating engaging conversations.
Solution Approach 2:
The patent assigns different importance weights to different memory items, with user attributes (name, birthday, sex) having higher priority than other information. This local quality differentiation allows the system to optimize memory usage by storing detailed information for high-priority items while using more compact representations for lower-priority information.
2Productivity
If the robot randomly utilizes acquired memory for speech, then the robot can respond using stored information, but topic transitions occur out of context which embarrasses the user
Solution Approach 1:
The patent implements a feedback mechanism where the robot continuously monitors the current conversation topic and context, then selects memory items for utilization based on their relevance to the ongoing dialogue. The system provides feedback to itself about which memory items have been recently used and adjusts selection to avoid repetitive or contextually inappropriate responses, thereby maintaining natural conversation flow.
Solution Approach 2:
The patent makes the memory utilization process dynamic by adjusting the selection of topics based on the current conversation state. Rather than randomly accessing memory, the system dynamically evaluates which stored information is most relevant to the current context and transitions smoothly between topics by establishing logical connections between them.
3Speed
If the robot acquires and immediately utilizes memorized information, then the robot appears responsive, but the robot may not appear to have a memory device and the action may not appear intellectual
Solution Approach 1:
The patent implements preliminary action by having the robot acquire and store user information during the conversation process rather than waiting until later. The robot proactively asks questions to gather user attributes and stores them in memory for future use, demonstrating both responsiveness and intellectual processing of information over time.
Solution Approach 2:
The patent employs periodic action by alternating between acquiring new information, utilizing stored information, and transitioning between these modes. The robot periodically checks which memory items are available and appropriate to use, creating a rhythm of information acquisition and utilization that demonstrates intelligent memory management rather than immediate robotic response.
Data Source
AI summary
A robot can make a dialog customized for the user by first storing various pieces of information appendant to an object as values of the corresponding items of the object. A topic that is related to the topic used in the immediately preceding conversation is then selected. Then, an acquisition conversation for acquiring the value of the item of the selected topic or a utilization conversation for utilizing the value of the item of the topic that is already stored is generated as the next conversation. The value acquired by the acquisition conversation is stored as the value of the corresponding item.