Drink Blend Planning Using Consumer-Liking and Raw Material Constraints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Business unit managers face challenges in developing consistent production plans for fruit-based drinks due to variable fruit quantities, costs, and qualities, relying heavily on intuition and losing institutional knowledge when personnel change, leading to inconsistent results across regions.
Innovation Solution
A system and method for optimizing drink blends using a blend plan optimization system that interacts with suppliers, inventory, production resources, and consumers to predict demand, manage inventory, and control production, incorporating a blending model that analyzes data to form optimal blend plans considering multiple attributes and constraints.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If business unit managers rely on intuition to develop production plans, then they can make decisions based on personal experience, but the results become inconsistent over time and across regions
Solution Approach 1:
The patent replaces the manual, intuition-based decision-making process with an automated computer-based optimization system. The system uses software to analyze fruit availability data, consumer demand data, and production constraints, then automatically generates optimized production plans. This substitution eliminates human subjectivity and ensures consistent, data-driven decisions across all regions and time periods.
Solution Approach 2:
The optimization system captures and stores production plan data, consumer demand data, and fruit availability data in databases. When managers leave or positions change, the system retains institutional knowledge automatically. The system serves itself by continuously learning from historical data and improving its optimization algorithms without requiring human intervention to preserve knowledge.
2Adaptability or versatility
If business unit managers use intuitive approaches to balance limited sweet fruit with consumer demand, then they can respond to market conditions, but institutional knowledge is lost when personnel change
Solution Approach 1:
The system creates digital copies of institutional knowledge by storing production plans, consumer preferences, and fruit availability patterns in databases. These digital records preserve the expertise that would otherwise be held only in managers' minds. The system can replicate successful production strategies across different regions and maintain them over time, preventing knowledge loss when personnel change.
Solution Approach 2:
The optimization system serves multiple functions: it analyzes current market conditions, optimizes production plans, stores institutional knowledge, and provides a common communication platform for cross-functional coordination. This universal system handles both adaptive market response and knowledge preservation simultaneously, eliminating the need for human managers to manually transfer knowledge when transitioning positions.
3Reliability
If the system analyzes multiple scenarios and varies demand and raw material attributes, then it can evaluate trade-offs effectively, but the device complexity increases
Solution Approach 1:
The patent divides the complex optimization problem into manageable segments: fruit availability analysis, consumer demand analysis, production constraint analysis, and optimization calculation. Each segment is handled by specific software modules that process particular types of data. This segmentation allows the system to analyze multiple scenarios without becoming unmanageably complex, as each module focuses on a specific aspect of the overall optimization problem.
Solution Approach 2:
The system uses databases as intermediaries to store and manage the complex data required for multi-scenario analysis. Rather than requiring direct complex interactions between all system components, the databases serve as centralized repositories that organize fruit availability data, consumer demand data, and production constraint data. This intermediary structure simplifies the overall system architecture while enabling comprehensive analysis.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A system for optimizing blending. The system can include a processor configured to aggregate material information, aggregate production information, model consumer liking of the at least one product, and provide plan information for controlling production resources based on the material information, the production information, and the consumer liking. The material information can be associated with a product input of the at least one product. The production information can be associated with the production resources of the at least one product.