Obsolescence Prediction Using Nested Graph Embeddings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing obsolescence prediction techniques are unreliable in rapidly changing markets, particularly those relying on Enterprise Resource Planning (ERP) systems, as they fail to accurately forecast product obsolescence due to fluctuating market demands.
Innovation Solution
A system and method utilizing generative artificial intelligence (Gen AI), machine learning (ML), and deep learning (DL) techniques to analyze multi-dimensional product data, create nested graphs, and generate graph embeddings to predict obsolescence by identifying customer patterns and market demands, enabling real-time predictions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional ERP systems and future forecasts are used to predict obsolescence, then the prediction process is simple and straightforward, but the accuracy of obsolescence predictions is unreliable
Solution Approach 1:
The patent transitions from traditional single-dimensional forecast data to multi-dimensional nested graph representations that incorporate product attributes, customer demographics, purchase patterns, and market trends across multiple layers, enabling more accurate obsolescence predictions through enhanced data dimensionality
Solution Approach 2:
The patent introduces graph embedding techniques and machine learning models as intermediary components that transform raw multi-dimensional data into meaningful patterns and insights, bridging the gap between complex data sources and accurate obsolescence predictions
2Measurement precision
If multi-dimensional data and nested graphs are used to improve prediction accuracy, then the accuracy of obsolescence predictions is improved, but the computational complexity increases
Solution Approach 1:
The patent segments the multi-dimensional data into hierarchical nested graphs where product data, customer data, and market data are organized into separate but interconnected layers, allowing computational processing to be distributed and managed more efficiently
Solution Approach 2:
The patent performs preliminary data processing, graph construction, and embedding generation before the actual obsolescence prediction, pre-organizing complex multi-dimensional data into structured nested graphs that reduce computational burden during prediction execution
Data Source
AI summary
The present disclosure discloses systems and methods to predict obsolescence. A method includes obtaining multi-dimensional data corresponding to a product from a plurality of data sources and identifying properties associated with the product. Further, relationships between each of the identified properties is determined. A multi-dimensional nested graph for the product based on the identified properties and the determined relationships is created followed by generation of a nested relationship models from the created multi-dimensional nested graph. Additionally, a transactional data node indicating a relationship between the product and the current sales data is created. Furthermore, a graph embedding values based on the created transactional data node and the nested relationships is created. Consequently, an obsolescence data for the product based on the created graph embedding values, the customer purchase patterns, a product inventory forecast data and a sales data is predicted and sends to the user device.