Predictive Model Stream Prioritization for IoT Data Overload
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The proliferation of data from IoT sensors and wearable technologies overwhelms the ability to transmit and process data effectively in value chain networks, leading to complexity and missed opportunities for insight and timely decision-making.
Innovation Solution
A method for transmitting predictive model parameters between devices and prioritizing data streams using predictive models to forecast future data values, enabling actions such as avoiding stock shortages and maintaining equipment, and refining models with additional data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If data collection from IoT sensors and wearable technologies is expanded, then the amount of available data increases, but the complexity and volume of data management increases, overwhelming users and causing missed opportunities for insight
Solution Approach 1:
The patent segments data streams into multiple channels with different priorities, dividing the overwhelming data volume into manageable portions. High-priority streams are processed first, while lower-priority streams are handled subsequently or filtered out, making data management tractable despite increased data quantity
Solution Approach 2:
The system dynamically changes the parameter of data stream priority assignment based on current operational context and predictive model outputs. By adjusting priority parameters in real-time, the system adapts to varying conditions and prevents information overload by focusing attention on the most relevant data streams
2Loss of information
If all data streams are transmitted and processed, then complete information is available, but transmission and processing capacity is overwhelmed, leading to delays in decision-making
Solution Approach 1:
The system performs preliminary actions by generating predictive models from historical data and pre-establishing priority assignments for different data streams. This advance preparation enables rapid response to new data without requiring complex real-time analysis of all streams, reducing decision-making time while maintaining information quality
Solution Approach 2:
The system applies partial action by selectively processing only the most high-priority data streams in real-time, while lower-priority streams are processed asynchronously or filtered. This approach prevents system overload and reduces processing time for critical decisions, accepting that not all data is processed with equal immediacy
3Productivity
If predictive model parameters are transmitted between devices, then operational efficiency is improved through actionable insights, but data transmission volume and network load increase
Solution Approach 1:
The system extracts only the essential predictive model parameters and high-priority data stream information for transmission between devices, rather than transmitting complete datasets. This selective extraction maintains operational efficiency by sharing only the most relevant insights while minimizing network load and energy consumption
Data Source
AI summary
A method for prioritizing predictive model data streams includes receiving, by a first device, a plurality of predictive model data streams. Each predictive model data stream includes a set of model parameters for a corresponding predictive model. Each predictive model is trained to predict future data values of a data source. The method includes prioritizing, by the first device, priorities to each of the plurality of predictive model data streams. The method includes selecting at least one of the predictive model data streams based on a corresponding priority. The method includes parameterizing, by the first device, a predictive model using the set of model parameters included in the selected predictive model data stream. The method includes predicting, by the first device, future data values of the data source using the parameterized predictive model.