Interactive Intervention Platform State Transition Optimization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing technologies fail to effectively guide users into preferred, low-probability or unknown states based on their current conditions, limiting the ability to provide proactive and personalized interactions in various environments.

Innovation Solution

A platform that processes multi-modal inputs from sensors to determine a user's current state and select a target state, using machine learning models to initiate actions that guide the user through a sequence of states, even if the target state is not initially in their state space, by determining probabilities and optimizing action sequences.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If the system selects target states with low transition probability, then the user can be guided to preferred states that provide new experiences or information, but the computational complexity increases and system performance deteriorates

Engineering Contradiction:

Improveability to guide user to preferred statesVSAvoidcomputational complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system pre-computes and stores transition probabilities between states in a probability matrix during system initialization or offline processing. This preliminary action allows the online decision-making process to simply query pre-computed values rather than performing complex calculations in real-time, thereby reducing computational complexity while maintaining the ability to guide users to preferred states

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The state space is segmented into discrete states with defined transition probabilities. By breaking down the complex state transition problem into manageable segments (individual states and transitions), the system can efficiently compute and store probability values for each segment, making the overall system more tractable and performant

Inventive Principle:

Principle #1Segmentation

2Productivity

If the system determines transition probabilities for multiple candidate states, then it can select optimal action sequences, but the computational resources required increase

Engineering Contradiction:

Improveaction selection optimizationVSAvoidcomputational resources

Core Design Contradiction:

ProductivityVSUse of energy by moving object

Solution Approach 1:

Instead of computing transition probabilities for all possible candidate states, the system computes probabilities only for a subset of relevant or high-priority candidate states. This partial action approach reduces computational resource consumption while still enabling effective action sequence selection by focusing computational effort on the most promising transitions

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS20220207395A1Interactive intervention platform

Publication Date: 2022.06.30 ACCENTURE GLOBAL SOLUTIONS LTD

AI summary

This document describes a platform that processes multi-modal inputs received from multiple sensors and initiates actions that cause the user to transition to a target state. In one aspect, a method includes detecting, based on data received from sensors, a current state of a user. A set of candidate states to which the user can transition from the current state is identified based on the current state. A target state for the user is selected based on the data received from the sensors and/or the current state of the user. For each of multiple candidate states, a probability at which the user will transition from the current state to the target state through the candidate state is determined. A next state for the user is selected based on the probabilities. One or more actions are determined and initiated to transition the user from the current state to the next state.