Digital Companion System for Adaptive Therapy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current digital companions lack the ability to develop long-term relationships with users that can lead to significant changes in psychological states or behaviors, particularly in therapeutic contexts such as affinity therapy for autistic individuals, due to limitations in intelligent interaction and adaptation.
Innovation Solution
A digital companion system that utilizes an intelligent agent, combining human and automated processes, to engage in successive conversations and interactions, adapting character and behavior over time, and using real-time user input to tailor responses and evolve the companion's role from friend to therapist, incorporating natural language processing and voice morphing to provide consistent and personalized therapy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If an automated intelligent agent is used to provide therapy, then productivity and scalability are improved, but the ability to develop genuine long-term relationships and adapt to individual user needs deteriorates
Solution Approach 1:
The patent merges automated intelligent agent capabilities with human therapist involvement in a hybrid system. The automated agent handles routine interactions and data processing, while human therapists provide periodic guidance and complex decision-making, combining the scalability of automation with the relational expertise of humans.
Solution Approach 2:
The system introduces a knowledge graph as an intermediary structure that mediates between user inputs and therapeutic responses. This knowledge graph accumulates and structures relationship data over time, enabling the automated agent to adapt responses based on accumulated understanding while maintaining consistency in the therapeutic relationship.
2Reliability
If successive conversations are facilitated over a long time period to develop relationships, then therapeutic effectiveness is improved, but the complexity of tracking and managing user state changes deteriorates
Solution Approach 1:
The system transforms the complex, unstructured data from successive conversations into structured parameters within a knowledge graph. By converting qualitative relationship developments into quantifiable state parameters, the system can track changes over time without proportionally increasing complexity.
Solution Approach 2:
The therapeutic process is segmented into discrete conversational interactions, each contributing to incremental state changes. The knowledge graph divides the overall relationship development into manageable state transitions, allowing the system to process long-term therapy as a sequence of discrete, trackable events.
3Adaptability or versatility
If the intelligent agent learns from scratch rather than being pre-trained, then adaptability to individual users is improved, but the time required to reach effective therapeutic interaction deteriorates
Solution Approach 1:
The system performs preliminary actions by establishing a structured knowledge graph framework and initial interaction protocols before actual therapy begins. This pre-established structure allows the agent to start learning from scratch with a head start, reducing the effective learning period while maintaining high adaptability.
Data Source
AI summary
A succession of conversations are facilitated between a user of a device and a non-human companion portrayed on the device, to develop a relationship between the user and the non-human companion over a time period that spans the successive conversations. The relationship is developed between the user and the non-human companion to cause a change in a state of the user over the time period. A conversation is facilitated by presenting a segment of speech of the non-human companion to the user and detecting a segment of speech of the user, the segments including a portion of the conversation. At the device, information is received from an intelligent agent about a next segment of speech to be presented to the user, as determined by the intelligent agent based on intelligent processes applied to the segment of speech of the user and to the change in state to be caused.