Guide Robot Content Recommendation by Position and User Traits
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Guide robots face challenges in efficiently providing users with relevant content due to the exposure of unnecessary functions and decreased availability, as they often include multiple functions that may not be used by all users.
Innovation Solution
A guide robot system that includes a position recognition device, an image recognition device, a behavior controller, a content recommendation device, and a data management device, which work together to provide a target contents list based on the robot's position and user characteristics, thereby optimizing content delivery and reducing unnecessary function exposure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple functions are added to the guide robot to expand service capabilities, then the robot's versatility is improved, but the device complexity increases and availability decreases due to unnecessary functions being exposed
Solution Approach 1:
The system performs preliminary actions by collecting user characteristic data and mapping the service area before the user actually requests content. The content recommendation device pre-processes and stores recommended content based on user characteristics, so that when a user calls the guide robot, the content is already prepared and can be quickly delivered without exposing unnecessary functions.
2Adaptability or versatility
If comprehensive content is provided to all users, then the robot's adaptability is improved, but the loss of information increases due to unnecessary content being exposed to specific users
Solution Approach 1:
The system applies local quality by providing different content recommendations to different users based on their specific characteristics. The content recommendation device generates customized content lists tailored to each user's preferences, behavior patterns, and characteristics, so that each user receives only the relevant content they need rather than comprehensive content for all possible users.
Solution Approach 2:
The system performs preliminary content filtering and recommendation generation based on user characteristics before the user actually interacts with the guide robot. The content recommendation device pre-processes content data and creates personalized recommendations, so that when content is delivered, it is already optimized for the specific user, preventing unnecessary content exposure.
3Ease of operation
If content recommendation is based on real-time user interaction only, then the ease of operation is improved, but the productivity decreases due to lack of pre-processed content data
Solution Approach 1:
The system performs preliminary content processing and recommendation generation before user interaction occurs. The content recommendation device pre-processes content data, user characteristic data, and service area information to create ready-to-deliver content recommendations. This preliminary action maintains ease of operation during user interaction while significantly improving productivity by avoiding real-time processing delays.
Data Source
AI summary
A guide robot can include a position recognition device configured to recognize a position, an image recognition device configured to recognize a user from a target image, a behavior controller configured to transmit to a content recommendation device a request for generating a target contents list in which a position of the guide robot and a characteristic of the user are reflected, and outputs the target contents list through an output device of the guide robot, and the content recommendation device is configured to combine the position with map information to generate first feature data, generate second feature data about the characteristic of the user from the target image, and transmit to the behavior controller the target contents list obtained by applying each of the first feature data and the second feature data to a content recommendation model.