Computing device and method for providing conversation with target character generated using artificial neural network
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing chatbot services that simulate direct conversations lack personalization and realism, particularly when interacting with deceased individuals, leading to high maintenance costs and resource wastage.
Innovation Solution
A computing device uses a generative artificial neural network to generate a target character based on pre-acquired information and fine-tuned by user input, incorporating a character generator, storage for basic commands, and a communicator to interact with user terminals, reducing resource waste and enhancing personalization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a chatbot service simulates direct conversation with a person, then conversation capability is improved, but personalization and realism are insufficient
Solution Approach 1:
The system pre-generates basic character data including appearance, personality traits, and background information before actual conversation occurs. This preliminary character generation enables the chatbot to simulate more realistic and personalized conversations from the outset, rather than relying on generic responses
Solution Approach 2:
The system creates a virtual copy of the deceased person by generating a target character that replicates their appearance, personality, and conversational patterns. This digital twin approach allows users to have realistic conversations with someone who closely resembles the actual person in terms of character and demeanor
2Adaptability or versatility
If a chatbot service simulates direct conversation with a person, then conversation capability is improved, but maintenance costs increase
Solution Approach 1:
The system performs character generation once in advance and stores the generated character data for reuse. This eliminates the need to continuously train or generate characters during each conversation session, significantly reducing computational resources and maintenance costs while maintaining conversation quality
Solution Approach 2:
The generated target character can serve multiple users and handle various conversation scenarios simultaneously. One pre-generated character instance can be reused across different interactions, making the system more cost-effective compared to creating dedicated chatbots for each user or conversation type
Data Source
AI summary
A computing device and method are disclosed for providing conversation with a target character generated using an artificial neural network. The computing device stores a basic command that generates a basic character related to a deceased individual based on pre-obtained information. This information is mapped to a pre-designated information code for efficient access. The device further includes a communicator that receives a first request message from a user terminal, identifying the target character through scanning an information code, and transmits a second request message to fine-tune the basic character according to user-specific preferences. In response to the received request messages, the device employs a generative artificial neural network to customize and generate the target character for conversational interaction. This approach minimizes computing resource usage by selectively generating and customizing characters only when necessary, improving efficiency and reducing costs associated with storing and maintaining multiple characters.