Dynamic Character Generation for Digital Interactive Platforms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing digital interactive platforms in the sports and iGaming industry limit user experience by restricting avatars to predefined activities, failing to provide dynamic and personalized interactions.
Innovation Solution
A computer-implemented system that generates characters with face expressions based on user inputs and actions, using diffusion models, GAN models, and pix2pix models, to optimize user experience in digital interactive platforms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If avatars are restricted to predefined activities, then system complexity is reduced and ease of manufacture is improved, but user experience and adaptability deteriorate
Solution Approach 1:
The system transitions from static predefined avatar activities to dynamic generated activities. The generation subsystem creates activities in real-time based on user inputs and platform context, allowing avatars to perform diverse actions beyond fixed templates while maintaining system manageability through algorithmic generation rather than manual configuration of each possibility.
Solution Approach 2:
The system enables avatars to generate their own activities autonomously through the generation subsystem. Instead of requiring pre-programming of all possible avatar actions, the system allows avatars to self-generate appropriate activities based on user inputs, platform state, and historical data, reducing the burden of manual system configuration.
2Adaptability or versatility
If AI and machine learning models are implemented for character generation, then adaptability and user experience are improved, but device complexity and manufacturing difficulty increase
Solution Approach 1:
The system is divided into distinct functional subsystems: creation subsystem for generating character data, generation subsystem for creating activities, and selection subsystem for choosing appropriate activities. This segmentation allows each AI/ML model to be independently developed, trained, and optimized, reducing overall system complexity while maintaining high adaptability through specialized models for each function.
Solution Approach 2:
The creation subsystem pre-generates character data including visual appearances, personality traits, and background information before characters are needed in the platform. This preliminary generation allows the runtime system to focus on activity generation and selection using simpler models that leverage pre-computed character data, reducing the complexity of real-time processing.
3Productivity
If dynamic character generation is implemented, then user engagement and experience are improved, but computational resources and energy consumption increase
Solution Approach 1:
The system applies different levels of generation complexity to different characters and contexts. The selection subsystem chooses activities based on character type, user preferences, and platform context, allowing computationally intensive generation only when necessary while using simpler selection from pre-generated options in other cases, optimizing energy usage while maintaining engagement.
Solution Approach 2:
The creation subsystem generates character data periodically or in batches rather than continuously in real-time. Characters are pre-generated with their visual appearances, personalities, and potential activities, then stored for efficient retrieval. This periodic batch processing reduces peak computational energy consumption compared to continuous real-time generation for every user interaction.
Data Source
AI summary
A computer-implemented system for generating characters associated with digital interactive platforms to optimize user experience, is disclosed. The computer-implemented system is configured to: pre-create characters for users based on first inputs from user devices of users, by diffusion models, cycle (GAN) model, and pix2pix model; select at least one character with face expressions during playing of video contents associated with digital interactive platforms based on historical data and first inputs; obtain second inputs from the user devices of users upon actions performed by the users during digital interactive platforms, and current state of digital interactive platforms; and determine corresponding characters providing the face expressions to be played as animated media contents with the video contents, based on second inputs from the user devices of the users, to optimize the user experience in digital interactive platforms, by a machine learning model.