Outcome Creation Engine Inversion for Active Influence
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Machine learning techniques are passive and unable to create desired outcomes, as they primarily focus on predicting future events based on past data, lacking the capability to actively influence or achieve specific results.
Innovation Solution
A method and device that input a desired outcome into a machine learning server, parse rules to determine necessary past attributes, filter through synthetic features to identify required contributors, and output these contributors to create the desired outcome, allowing for active influence on future events.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machine learning models are used to predict future events based on past data, then prediction accuracy is improved, but the system remains passive and cannot create or influence desired outcomes
Solution Approach 1:
The patent inverts the traditional machine learning approach by working backwards from a desired future outcome to identify the necessary past conditions. Instead of predicting future events from past data, the system takes a target outcome and determines what attributes and events must have occurred to create it, enabling active creation of desired outcomes rather than passive prediction.
2Loss of information
If traditional machine learning algorithms analyze historical data to identify patterns, then pattern recognition is improved, but the system cannot generate actions to achieve specific results
Solution Approach 1:
The patent applies preliminary action by identifying and establishing the necessary past attributes and synthetic contributors before the desired outcome occurs. The system determines what conditions must be created in advance to ensure the target outcome is achieved, transforming the system from merely analyzing patterns to actively creating the conditions for desired results.
3Reliability
If machine learning models are trained on existing data sets, then model reliability is improved, but the system cannot determine how to create new desired outcomes
Solution Approach 1:
The patent introduces synthetic contributors as an intermediary between the trained machine learning model and the desired outcome. These synthetic entities represent the necessary past conditions and attributes that bridge the gap between historical data patterns and future desired outcomes, enabling the system to create new outcomes while maintaining reliability through the underlying trained model.
Data Source
AI summary
A method of exercising effective influence over future occurrences using knowledge synthesis is described. Techniques include influencing methods that yield actions, once a proposed outcome has been assumed. This is different from methods, typically referred to as “predictive” or “prescriptive” that use analytics to model future results based upon existing data and predict most likely outcome. One or more methods of analysis of historical data, in a hierarchical manner, determine events which led to an observed outcome. The outcome-based algorithms use, as input, a future event or state and generate attributes that are necessary precursors. By creating these attributes, the future can be affected. Where necessary, synthetic contributors of such attributes are also created and made to act in ways consistent with generating the assumed outcome. These contributors might be called upon respectively, to post favorable opinions, to report balmy weather, or to describe sales to a certain population demographic.