AI Digital Human Consultation for Individualized Digital Addiction Diagnosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing diagnostic criteria for behavioral addiction, derived from substance addiction, are inadequate as they do not account for individual characteristics, leading to unclear conceptualization and ineffective intervention strategies.
Innovation Solution
A method using an AI-based digital human to provide consultation, measure user traits, classify user types, and tailor intervention strategies based on individual characteristics, including disposition, virtue, personality, and personal environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional diagnostic criteria derived from substance addiction are used for behavioral addiction, then diagnostic framework is established, but diagnostic accuracy and intervention effectiveness deteriorate due to lack of consideration for individual characteristics and behavioral addiction-specific factors
Solution Approach 1:
The diagnostic system segments users into distinct types (avoidance type, compromise type, problem-solving type) based on their responses to consultation questions about behavioral addiction. This segmentation allows the system to move from a one-size-fits-all diagnostic approach to targeted, individualized diagnostic criteria that account for different behavioral patterns and psychological characteristics associated with each user type.
Solution Approach 2:
The diagnostic criteria dynamically adapt based on the identified user type. The system adjusts the consultation questions, measurement focus, and diagnostic thresholds according to whether the user exhibits avoidance, compromise, or problem-solving characteristics. This dynamic adaptation enables the diagnostic framework to remain reliable across diverse individual presentations of behavioral addiction.
2Measurement precision
If a single diagnostic approach is used for all users, then implementation simplicity is maintained, but measurement precision and classification accuracy deteriorate due to inability to capture individual differences
Solution Approach 1:
The system changes key parameters including the set of consultation questions presented, the weighting of measurement items, and the classification thresholds based on the identified user type. For example, avoidance-type users receive different question sets and measurement emphasis compared to problem-solving users. These parameter changes enhance measurement precision without requiring entirely separate diagnostic systems for each user type.
Solution Approach 2:
The AI-based digital human serves as an intermediary that manages the complexity of individualized assessment. It automatically adapts the diagnostic protocol, selects appropriate consultation questions, and determines classification thresholds based on real-time analysis of user responses. This intermediary handles the computational complexity, allowing the diagnostic interface to remain simple while maintaining high measurement precision through personalized assessment protocols.
3Productivity
If AI-based personalized consultation is implemented, then individualized diagnostic accuracy improves, but system complexity and computational requirements increase
Solution Approach 1:
The AI-based digital human is designed as a universal system that handles multiple functions: providing consultation questions, analyzing user responses, measuring behavioral addiction characteristics across five dimensions, classifying user types, and generating personalized intervention recommendations. This multi-functionality consolidates what would otherwise require multiple separate systems into a single integrated platform, improving therapeutic efficiency while managing complexity through unified architecture.
Solution Approach 2:
The system employs self-service mechanisms where the AI automatically adjusts consultation protocols, selects measurement items, and determines classification criteria based on user responses without requiring manual configuration for each case. The system serves itself by learning from interaction patterns and automatically optimizing the diagnostic approach, which enhances productivity while containing complexity through automated decision-making algorithms.
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
A method for controlling an electronic device according to an embodiment of the present invention comprises: a consultation step in which the electronic device provides a voice of a digital human(AI agent) including an image in which the digital human is visualized and at least one query, and obtains a user's response to the query; a measurement step in which the electronic device obtains measurement values for five measurement items including the user's disposition, virtue, personality, cognitive faculty, and personal environments according to the response; and a classification step in which the electronic device identifies, on the basis of the obtained measurement values, the user's type associated with tolerance to digital addiction.