Event Forecasting With Reduced Category-Sequence Modeling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies fail to adequately account for lengthy histories and resource optimization in fault prediction and user interaction forecasting, leading to inefficient intervention and resource distribution in environments with limited resources.
Innovation Solution
A computer-implemented method that determines a model category subset and a target category subset based on event history, incorporating time spans for initial occurrence, to enhance forecasting accuracy and optimize resource allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the entire event history is taken into account for forecasting, then the forecasting accuracy is improved, but the computational complexity and time required increases
Solution Approach 1:
The patent divides the entire event history into a base portion and a tail category, processing them separately. The base is processed to extract relevant patterns while the tail is evaluated against these patterns, reducing the computational burden of analyzing the complete history while maintaining forecasting accuracy.
Solution Approach 2:
The patent extracts only the necessary portions of event history that are relevant to predicting the tail category. By identifying and extracting relevant base events from the full history, the system avoids processing irrelevant data, thus reducing computational complexity while preserving forecasting precision.
2Reliability
If all information is treated on an equal footing, then comprehensive analysis is achieved, but resource optimization and timely intervention are hindered
Solution Approach 1:
The patent applies different processing qualities to different parts of the event history. The base events are processed to identify patterns, while the tail events are evaluated against these patterns with different weighting. This local differentiation allows comprehensive analysis while optimizing resource allocation by focusing computational effort where it matters most.
Solution Approach 2:
The patent changes the parameters of event processing by introducing time spans for initial occurrence and differential weighting of base versus tail events. This allows the system to prioritize certain events over others, enabling resource optimization and timely intervention while maintaining comprehensive analysis through the structured approach.
3Loss of time
If detailed time information is included in sequences, then intervention timing is improved, but the complexity of sequence processing increases
Solution Approach 1:
The patent performs preliminary processing of time information by extracting time spans for initial occurrence of events during the pattern mining phase. This preliminary action prepares the time data in advance, allowing efficient intervention timing decisions without adding complexity to the real-time sequence processing.
Data Source
AI summary
A computer-implemented method, a computer system and a computer program product for event forecasting and information provision are disclosed. For each entity of a group of entities one or more events are obtained, wherein each event is associated with a category of a set of categories. A model category subset of the set of categories, and a target category subset based on the model category subset, are determined. For entities for which for each category of the target category subset an event has been obtained, a sequence of categories of the model category subset is determined, and corresponding probabilities are calculated. For a target entity, a target sequence of categories of the model category subset is determined based on the events obtained for the target entity. A target category is determined based on the target sequence and the calculated probabilities. Information is provided based on the target entity and the determined target category.