Emoji Event Sequences for Machine Learning on Unstructured Process Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Unstructured data in process mining is challenging to analyze using statistical and machine learning techniques due to the lack of a predefined data model, leading to information loss and difficulty in applying analytical methods effectively.
Innovation Solution
Convert unstructured data into sequences of electronic characters, such as emojis, to create a structured format that can be analyzed using machine learning techniques, enabling pattern recognition and visualization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If unstructured data is used in process mining, then data flexibility and adaptability are improved, but the ability to apply statistical and machine learning techniques deteriorates
Solution Approach 1:
The patent introduces an intermediary transformation layer that converts unstructured event data into a structured format suitable for machine learning. The system captures event content, extracts features, and transforms them into a structured representation that can be processed by statistical and machine learning techniques, thus serving as a bridge between unstructured data and analytical methods.
Solution Approach 2:
The patent changes the parameters of the data representation by transforming unstructured event descriptions into structured feature vectors with specific attributes (time, event type, outcome). This parameter transformation enables the data to be compatible with machine learning algorithms while preserving the essential information from the original unstructured format.
2Adaptability or versatility
If unstructured data is used in process mining, then data flexibility is improved, but information loss increases
Solution Approach 1:
The patent performs preliminary actions by capturing and storing the complete event content before transformation. The system records all relevant information about events (descriptions, timestamps, outcomes) and maintains this information throughout the processing pipeline, ensuring that no information is lost during the conversion to structured format.
Solution Approach 2:
The patent creates a structured copy of the unstructured data that preserves all essential information. The transformation process generates a structured representation that is information-equivalent to the original unstructured data, allowing the structured copy to be used for analysis while the original unstructured data remains available for reference.
3Difficulty of detecting and measuring
If unstructured data is transformed into structured format, then machine learning analysis capability is improved, but processing complexity increases
Solution Approach 1:
The patent segments the transformation process into distinct modular steps: event capture, feature extraction, and structured format conversion. Each step is independently implemented and can be processed separately, reducing the overall complexity by breaking down the transformation into manageable segments rather than requiring a single complex operation.
Data Source
AI summary
Systems and methods are described for preparing unstructured data for machine learning analysis. An example method may include: receiving data representing a plurality of processes; analyzing the data to identify, for each process of the plurality of processes, a time-ordered sequence of events that occurred during the process; generating a plurality of emoji sequences by, for each process of the plurality of processes, generating an emoji sequence, each emoji in the emoji sequence representing an event of the events that occurred during the process, and the emoji sequence ordered in accordance with the time-ordered sequence; generating a plurality of feature vectors corresponding to the respective plurality of emoji sequences; and applying a machine learning technique to the plurality of feature vectors.