Recurrent Neural Network Data Format Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional methods for determining data formats are inflexible, labor-intensive, and require significant computing resources, especially when dealing with data of unknown formats or complex relationships between data values.

Innovation Solution

The use of conditional probabilities in data value sequences, combined with machine learning models such as recurrent neural networks, to determine data formats and reformat data efficiently, reducing the need for human intervention and computational resources.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If rule-based algorithms are used to determine data formats, then the approach is straightforward to implement, but it fails to recognize unknown formats and requires additional human input and complex algorithms

Engineering Contradiction:

Improveease of implementationVSAvoidability to recognize unknown formats

Core Design Contradiction:

Ease of manufactureVSAdaptability or versatility

Solution Approach 1:

The system uses machine learning models to automatically determine data formats without requiring human intervention or pre-programmed rules. The model learns patterns from training data and autonomously identifies formats of unknown data, making the system self-sufficient in handling diverse data formats.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent transitions from fixed rule-based parameters to dynamic machine learning models that can adapt their parameters based on learned patterns. This allows the system to change its behavior dynamically to recognize various data formats including unknown ones, resolving the contradiction between implementation simplicity and format recognition capability.

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If complex algorithms are used to classify data formats, then recognition accuracy may improve, but computing resources and time requirements increase significantly

Engineering Contradiction:

Improvedata format recognition accuracyVSAvoiddata processing speed

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The system performs preliminary training of machine learning models using labeled data before actual data format determination. This pre-computation of knowledge allows the model to quickly and accurately classify data formats during runtime without requiring complex real-time computations, thus maintaining both high accuracy and processing speed.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent uses machine learning models that learn and copy patterns from training data rather than implementing complex classification algorithms for each new data format. The model generalizes from examples, enabling fast and accurate recognition without replicating complex rule-based logic for every possible format.

Inventive Principle:

Principle #26Copying

3Adaptability or versatility

If human input is required to adjust rule-based approaches, then flexibility may improve, but labor intensity and time consumption increase

Engineering Contradiction:

Improveflexibility in handling various formatsVSAvoidtime for human intervention

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The machine learning model automatically adapts to different data formats through training and inference without requiring human adjustment or intervention. The system serves itself by learning from data and applying learned patterns to determine formats of new data, eliminating the need for human time while maintaining flexibility.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system uses feedback from training data to continuously improve its format recognition capability. During training, the model receives feedback on its predictions and adjusts its parameters accordingly, enabling it to become increasingly accurate and flexible without human intervention in the operational phase.

Inventive Principle:

Principle #23Feedback

4Productivity

If large amounts of computing resources are allocated to process data formats, then processing capability improves, but resource efficiency decreases

Engineering Contradiction:

Improvedata processing capabilityVSAvoidcomputing resource consumption

Core Design Contradiction:

ProductivityVSLoss of energy

Solution Approach 1:

The system performs computationally intensive model training in advance during a preliminary phase. Once trained, the model can quickly process data format determination with minimal computing resources during operational use. This shifts the resource burden to a one-time preliminary action rather than continuous resource consumption.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20250045295A1Systems and methods for formatting data using a recurrent neural network

Publication Date: 2025.02.06 CAPITAL ONE SERVICES LLC

AI summary

Systems and methods for formatting data are disclosed. For example, a system may include at least one memory storing instructions and one or more processors configured to execute the instructions to perform operations. The operations may include receiving data comprising a plurality of sequences of data values and training a recurrent neural network model to output conditional probabilities of subsequent data values based on preceding data values in the data value sequences. The operations may include generating conditional probabilities using the trained recurrent neural network model and the received data. The operations may include determining a data format of a subset of the data value sequences, based on the generated conditional probabilities, and reformatting at least one of the data value sequences according to the determined data format.