Generative Scheduling Method for Structured Music
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing generative music software either produces random outputs lacking structure or relies on machine-learning to imitate specific music styles, failing to create coherent and varied musical sequences.
Innovation Solution
A method combining a random number generator with algorithmic processes and probability arrays to generate coherent sequences of data objects, ensuring structured music by applying rules and constraints to random outputs in real-time or batch processing, allowing for the creation of musically coherent and varied compositions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If random number generation is used without rules and constraints, then the output is varied and unpredictable, but the music lacks structure and coherence
Solution Approach 1:
The patent segments the music generation process into distinct components: a random number generator for variation, probability arrays for stylistic constraints, and rule-based filtering for structural coherence. This segmentation allows each component to address specific aspects of music generation independently, resolving the contradiction between variation and structure.
Solution Approach 2:
The patent uses probability arrays that can be dynamically adjusted to change the constraints on random number generation. By modifying the probability distributions in these arrays, the system can adapt between highly structured and highly varied outputs, resolving the contradiction through parameter adjustment rather than fixed architecture.
2Stability of the object's composition
If machine-learning is used to imitate music styles, then structured music can be generated, but the output lacks genuine creativity and variety
Solution Approach 1:
The patent replaces machine-learning algorithms with a rule-based system using probability arrays and deterministic filtering. This substitution eliminates the need for training data and complex neural networks, while achieving similar structural coherence through explicit mathematical constraints and probability distributions that can be manually designed and adjusted.
Solution Approach 2:
The system generates its own structural constraints through probability arrays that are updated based on the generated music itself. The random number generator operates independently without external training data, creating self-contained music generation that maintains coherence through internal probability rules rather than imitating learned patterns.
3Stability of the object's composition
If rules and constraints are applied to random output in real-time, then coherent music is generated, but the processing complexity increases
Solution Approach 1:
The patent pre-calculates probability arrays and rules before music generation begins. These probability arrays contain pre-computed constraints and stylistic guidelines that can be directly applied during generation without requiring complex real-time computation. This preliminary preparation reduces the computational burden during actual music generation while maintaining coherence.
Solution Approach 2:
The system applies constraints selectively through probability arrays rather than enforcing strict deterministic rules. By using partial constraints (probability distributions rather than fixed values), the system achieves sufficient musical coherence without the full complexity of exhaustive rule enforcement, balancing quality and processing requirements.
Data Source
AI summary
A method for providing one or more outputs at one or more respective time instants is provided. The method comprises generating a data object executable to provide an output, placing the object in a position in a sequence, and executing the object at said position in said sequence to provide said output. Each position in the sequence represents a time instant.