Interactive Evolutionary Algorithm for Dynamic Product Configuration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conjoint market research studies are tedious and frustrating for respondents due to pre-determined choice sets that are not responsive to their preferences, leading to inaccurate data collection and limited ability to represent complex decision processes.
Innovation Solution
Interactive evolutionary computation methods allow respondents to directly influence the optimization process by providing feedback on attribute variants, enabling them to co-create preferred product forms and overcome the limitations of traditional choice-based conjoint studies by using genetic algorithms that adapt to respondent preferences in real-time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If traditional choice-based conjoint studies are used with pre-determined choice sets, then the research process is standardized and easy to administer, but the respondent experience becomes tedious and frustrating, leading to inaccurate data collection
Solution Approach 1:
The patent implements dynamic adaptation where the choice sets are no longer fixed but evolve based on respondent feedback. The system dynamically adjusts the product profiles presented to respondents based on their attribute-level preferences, transforming the static research protocol into a dynamic interaction that responds to individual respondent needs and preferences in real-time.
Solution Approach 2:
The patent introduces feedback mechanisms where respondents provide attribute-level feedback on product characteristics, and this feedback is used to guide the evolutionary algorithm in generating subsequent choice sets. This closed-loop feedback system ensures that the research process adapts to respondent preferences, improving data accuracy by focusing on attributes that matter most to each respondent.
2Adaptability or versatility
If traditional choice-based conjoint studies present multiple product alternatives at once, then the research covers comprehensive attribute space, but the cognitive load on respondents increases and the task becomes more difficult
Solution Approach 1:
The patent segments the product attributes into distinct components and presents them in a structured manner. Instead of overwhelming respondents with complete product profiles all at once, the system breaks down the evaluation into attribute-level comparisons, allowing respondents to focus on and provide feedback on specific attributes that are most important to them, thereby reducing cognitive load while maintaining comprehensive coverage.
Solution Approach 2:
The system dynamically adjusts the complexity and number of alternatives presented based on respondent performance and preferences. The evolutionary algorithm adapts the choice set composition in real-time, presenting fewer but more relevant alternatives when respondents show expertise or strong preferences, and gradually introducing more complexity as needed, thus balancing coverage with cognitive load management.
3Productivity
If the evolutionary algorithm uses fixed breeding rules, then the optimization process is simple and fast, but it cannot adapt to complex attribute interactions and constraints
Solution Approach 1:
The patent implements dynamic breeding rules that adapt based on the problem domain and respondent feedback patterns. The system learns from the data collection process and adjusts its evolutionary operators (crossover, mutation, selection) in real-time, allowing it to handle complex attribute interactions and constraints more effectively while maintaining computational efficiency through adaptive rather than fixed rules.
Solution Approach 2:
The patent changes key parameters of the evolutionary algorithm dynamically, such as mutation rates, crossover probabilities, and selection pressures, based on the complexity of attribute interactions detected in the data and the specific constraints of the product configuration problem. This allows the algorithm to optimize its behavior for each specific research scenario rather than using a one-size-fits-all fixed parameter set.
Data Source
AI summary
A method comprises displaying visual representations of a plurality of product alternatives each including at least one attribute variant to a respondent, receiving from the respondent an indication of a preferred one of the plurality of product alternatives, transmitting a request to the respondent to identify at least one attribute variant of a non-preferred product alternative that is preferred by the respondent to the corresponding attribute variant of the preferred one of the plurality of product alternatives and receiving a response from the respondent identifying at least one attribute variant of a non-preferred product alternative that is preferred by the respondent to the corresponding attribute variant of the preferred one of the plurality of product alternatives.