Generic Framework Data Mapping for ML Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing process execution systems lack efficient and scalable methods for predicting outcomes using machine learning, requiring significant manual intervention and configuration for each use case, limiting their applicability to specific implementations.
Innovation Solution
A method involving mapping customer-specific data with a generic framework, performing data adjustment and enhancement, and implementing machine learning algorithms to generate predictive results, which can be seamlessly integrated across different process scenarios.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machine learning algorithms are implemented for predicting process execution outcomes, then prediction accuracy is improved, but system complexity increases due to data mapping, adjustment, and enhancement requirements
Solution Approach 1:
The patent introduces an intermediary data processing layer between raw customer-specific data and machine learning algorithms. This layer includes data mapping components that translate customer data into generic framework data, and data adjustment components that enhance and clean the data. This intermediary structure enables accurate predictions while managing system complexity by modularizing the data preparation process.
Solution Approach 2:
The system segments the data processing pipeline into distinct functional modules: data mapping (customer-specific to generic framework), data adjustment (cleaning and enhancement), and machine learning prediction. This segmentation allows each component to be independently optimized and maintained, reducing overall system complexity while maintaining prediction accuracy.
2Adaptability or versatility
If a generic framework is created to support multiple process scenarios, then adaptability is improved, but data processing complexity increases due to mapping and joining operations
Solution Approach 1:
The patent creates a universal generic framework that can accommodate multiple customer-specific data formats and process scenarios. The framework defines standard data structures and schemas that can represent diverse process types (insurance claims, loan applications, etc.). This universality enables the system to adapt to different scenarios while maintaining consistent data processing procedures, thereby managing complexity.
Solution Approach 2:
The generic framework acts as an intermediary layer between diverse customer-specific data sources and the machine learning algorithms. By translating various data formats into a standardized generic framework, the system achieves high adaptability while simplifying downstream processing operations.
3Measurement precision
If manual data configuration is performed for each use case, then prediction precision is maintained, but productivity decreases due to significant manual intervention requirements
Solution Approach 1:
The system implements automated data mapping and adjustment processes that operate without significant manual intervention. The data mapping component automatically translates customer-specific data into the generic framework based on predefined rules. The data adjustment component automatically cleans and enhances data using configured algorithms. This self-service capability maintains prediction precision while dramatically improving productivity by eliminating repetitive manual configuration tasks.
4Productivity
If data adjustment and enhancement are performed automatically, then productivity is improved, but data processing complexity increases
Solution Approach 1:
The patent implements preliminary data adjustment and enhancement operations as automated preprocessing steps before machine learning prediction. Data cleaning, normalization, and enhancement are performed automatically based on predefined rules and algorithms. This preliminary automation improves productivity by eliminating manual data preparation tasks while managing complexity through rule-based approaches that can be configured once and reused across multiple scenarios.
Data Source
Figure 1
Figure 2
Figure 3A
AI summary
The present disclosure relates to computer-implemented methods, software, and systems for utilizing tools and techniques for providing data that can be used for prediction and automation of process execution. One example method includes that customer-specific data is joined with generic framework data based on identification of work item to create initial data. The generic framework data is for a generic workflow associated with multiple process scenarios. The initial data set is provided for predicting variable of a process scenario of the generic workflow. Machine learning prediction is performed for a instant process scenario execution at a customer environment. The initial data is adjusted based on provided data enhancement rules to generate an output data set. The output data set is provided for evaluation by an implementation of the machine learning algorithm to provide a prediction result for the process scenario execution.