Mapping Free-Form Tabular Data to Standard Line Items
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current strategic sourcing systems are inflexible and inconvenient for buyers due to their reliance on fixed-field templates and terminology that may not match the buyer's familiar terms, leading to user dissatisfaction and inefficiencies.
Innovation Solution
The system processes free-form tabular data using machine learning models to map column headers and values to standard line item terms, employing context determination and content recognition to identify and infer data types, and allowing for the creation of line items with familiar terminology, enabling flexible input formats and terminology mapping.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If fixed-field templates and standard terminology are used in strategic sourcing systems, then data processing and comparison are standardized, but user convenience and flexibility deteriorate due to mismatch with buyer's familiar terms
Solution Approach 1:
The patent introduces an intermediary layer consisting of machine learning models (context determination model and content recognition model) that mediate between the buyer's familiar terminology and the system's standard line item terms. This intermediary automatically maps and translates user input without requiring the user to learn system-specific terminology, thus maintaining both standardization and user convenience
Solution Approach 2:
The patent replaces the mechanical system of fixed templates and manual term mapping with an intelligent system using machine learning models. Instead of requiring users to manually adapt to fixed-field templates, the system automatically processes free-form tabular data and maps it to standard line item terms through AI-driven context determination and content recognition
2Stability of the object's composition
If fixed-field templates are required for input, then data structure is standardized, but input flexibility and user freedom deteriorate
Solution Approach 1:
The patent makes the data processing system dynamic by using machine learning models that can adapt to various input formats. The system accepts free-form tabular data with flexible structures and dynamically maps them to standardized line item terms, allowing the system to handle diverse input formats while maintaining output consistency
Solution Approach 2:
The patent creates a universal processing capability that handles multiple input formats (different column structures, terminology variations, data layouts) through a single flexible system. The machine learning models are designed to recognize and process various tabular data formats universally, mapping them all to the same standard line item terms
3Measurement precision
If manual mapping of terminology is required, then accuracy of term matching can be ensured, but processing time and operational complexity increase
Solution Approach 1:
The patent implements self-service through automated machine learning models that perform context determination and content recognition without human intervention. The system automatically analyzes column headers and values, determines context, recognizes content, and maps terms to standard line item definitions, eliminating the need for manual term mapping while maintaining high accuracy
Solution Approach 2:
The patent performs preliminary action by pre-training machine learning models with extensive line item term definitions and contexts before deployment. The models are pre-equipped with knowledge of standard terminology and their meanings, enabling them to accurately map user input to correct line item terms automatically without requiring manual intervention during actual processing
Data Source
AI summary
The present disclosure involves systems, software, and computer implemented methods for creating line item information from tabular data. One example method includes receiving event data values at a system. Column headers of columns in the event data values are identified. At least one column header is not included in standard line item terms used by the system. Column values of the columns in the event data values are identified. The identified column headers and the identified column values are processed using one or more models to map each column to a standard line item term used by the system. The processing includes using context determination and content recognition to identify standard line item terms. An event is created in the system, including the creation of line items from the identified column value. Each line item includes standard line item terms mapped to the columns.