Online Characteristic Scoring for Partitioned Physical Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting characteristic physical data values, such as those related to text and images, are overly complex and not well adapted to industrial requirements.
Innovation Solution
A computer-implemented method using a trained neural network to extract and score physical data values, partitioning data into respective values, and determining characteristic scores for selection, with optional global scoring and graphical representation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing methods are used for detecting characteristic physical data values, then detection capability is provided, but device complexity and computational burden increase
Solution Approach 1:
The patent segments the physical entity data into multiple respective physical data values before processing. Instead of treating the entire dataset as a single object, the method partitions it into individual elements (e.g., text fields, image fields, audio fields) that can be scored independently. This segmentation reduces the computational burden on the neural network while maintaining detection precision, as each segmented element is processed separately rather than requiring analysis of the complete complex dataset.
2Measurement precision
If existing methods are used for detecting characteristic physical data values, then detection capability is provided, but computational burden increases
Solution Approach 1:
By segmenting the data into respective physical data values, the neural network processes smaller, more manageable units rather than the entire dataset at once. This reduces the computational energy required for each processing step, as the network operates on individual data elements (text, images, audio) separately, thereby lowering overall computational burden while preserving detection accuracy.
Solution Approach 2:
The patent changes the parameter of data representation by converting physical entity data into numerical vectors through the neural network. This parameter transformation allows the system to work with compact numerical representations rather than raw data, reducing computational energy requirements for subsequent scoring and comparison operations while maintaining the ability to detect characteristic values accurately.
3Ease of operation
If physical entity data is treated as a single object, then processing is simplified, but detection precision of characteristic values decreases
Solution Approach 1:
The patent resolves this contradiction by segmenting the physical entity data into respective physical data values. This segmentation provides detection precision by allowing individual characteristics (text, images, audio) to be identified and scored separately, while the overall process remains operationally simple through automated neural network processing. The system maintains ease of operation by handling the segmentation and scoring automatically without requiring complex manual intervention.
Data Source
AI summary
The invention provides, amongst other aspects, a computer-implemented method for detecting characteristic physical data values, the method comprising the steps of: receiving physical entity data; extracting at least two respective physical data values from the physical entity data; determining respective numerical vectors of the respective physical data values by means of a trained neural network; determining respective characteristic scores based on the respective numerical vectors; selecting characteristic physical data values from said respective physical data values, the selection being based on their respective characteristic scores; returning a result comprising said respective characteristic physical data values, preferably along with their respective characteristic scores; wherein said extracting comprises partitioning the physical entity data into the respective physical data values.