AI Transaction Contextualization with Fuzzy Logic for Efficient Analytics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Unstructured data is not suitable for use as a grouping variable in data analytics systems, leading to increased computing resource requirements and reduced predictive value of AI/ML models, and existing AI/ML models struggle to process unstructured data effectively.
Innovation Solution
A data analytics and contextualization platform that uses fuzzy logic to extract contextual items from unstructured data, generating synthetic features that enhance the input dataset, enabling efficient processing and analysis by AI/ML models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If unstructured data is fed directly to AI/ML models without pre-processing, then the models can process the raw data, but operating time increases, predictive value decreases, and computing resource requirements increase
Solution Approach 1:
The patent applies preliminary action by performing pre-processing of unstructured data before feeding it to AI/ML models. The system extracts contextual information, generates synthetic features, and structures the data in advance, which reduces operating time and improves predictive value during model execution.
Solution Approach 2:
The patent introduces an intermediary processing layer between raw unstructured data and AI/ML models. This intermediary system performs contextualization, feature extraction, and data structuring, acting as a mediator that transforms unstructured data into a format suitable for efficient model processing.
2Reliability
If unstructured data is fed directly to AI/ML models without pre-processing, then the models can process the raw data, but computing resource requirements such as memory and disk space increase
Solution Approach 1:
The patent applies the extraction principle by removing unnecessary components from unstructured data and retaining only the relevant contextual information. The system extracts meaningful features and discards redundant data, reducing memory and disk space requirements while maintaining predictive value.
Solution Approach 2:
The patent changes the parameters of the data by transforming unstructured data into structured formats with optimized features. This parameter transformation reduces the volume of data that needs to be stored and processed, thereby reducing computing resource requirements.
3Adaptability or versatility
If unstructured data is used as a grouping variable for data grouping operations, then the data can be analyzed, but the operations become inefficient and resource-intensive
Solution Approach 1:
The patent applies preliminary action by pre-processing unstructured data to extract contextual features that can serve as effective grouping variables. This preliminary extraction enables efficient data grouping operations by transforming unstructured data into structured grouping keys in advance.
Data Source
AI summary
A data analytics and contextualization platform instance acquires an input dataset. Using fuzzy logic, the platform generates a set of contextual items based on the unstructured textual data. Items in the input dataset are labeled using contextual items. Using a labeled particular item, a set of entity behavior maps can be generated to include one or more features selected based on a first particular label of the particular item. One or more AI/ML modeling operations can be selected based on a type of the entity behavior map and performed for items in the entity behavior map. A particular first subset of AI/ML modeling operations can be performed, using a particular contextual item as a trigger, in parallel relative to a particular second subset of AI/ML modeling operations. The entity behavior map, which can be populated using outputs of the AI/ML operations, can be transmitted to a target computing system.