Integrated User Data Sets for Multi-Source Performance Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing database reporting tools struggle to efficiently integrate and analyze diverse data types from multiple sources, such as audio/video recordings and digital records, to provide actionable insights for enterprise organizations.

Innovation Solution

A system that utilizes a machine learning algorithm to process stored data, generating performance data sets and integrated data sets for users, and displays relevant information including retention scores, product introductions, and issue lists on a display device, leveraging non-transitory storage and computing systems to facilitate data integration and analysis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional database reporting tools are used to manage and analyze data, then data storage and basic retrieval are achieved, but the ability to efficiently integrate and analyze diverse data types from multiple sources is insufficient

Engineering Contradiction:

Improvedata integration capabilityVSAvoidsystem complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent introduces a machine learning model as an intermediary component between the database and the reporting tools. This model processes raw data from multiple sources (audio/video recordings, digital records, etc.) and transforms it into structured performance datasets that can be easily integrated and analyzed. The intermediary handles the complexity of data integration, allowing the reporting tools to work with pre-processed, standardized data formats.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system segments the data processing workflow into distinct modules: data collection from multiple sources, machine learning-based performance analysis, data integration, and reporting. Each module handles specific data types and processing tasks independently, making the overall system more manageable despite handling diverse data types. The segmentation allows parallel processing of different data streams.

Inventive Principle:

Principle #1Segmentation

2Loss of information

If multiple data sources including audio/video recordings and digital records are integrated, then comprehensive user insights are achieved, but the time and computational resources required for processing increase

Engineering Contradiction:

Improveinformation completenessVSAvoiddata processing time

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

The machine learning model performs preliminary processing of raw data from multiple sources before it reaches the reporting tools. It pre-computes performance metrics, extracts key features from audio/video recordings, and structures digital records in advance. This preliminary action reduces the time required for final analysis and reporting, as the heavy lifting of data processing is already completed.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system transforms raw data into standardized performance datasets by changing parameters and formats. The machine learning model converts unstructured data (audio/video) into structured metrics (performance scores, behavioral patterns), making the data more efficient to process and analyze. This parameter transformation enables faster querying and analysis while preserving comprehensive information.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If machine learning algorithms are used to process stored data and generate performance datasets, then actionable insights and performance metrics are improved, but the computational complexity and processing requirements increase

Engineering Contradiction:

Improveperformance metric accuracyVSAvoidcomputational energy consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The machine learning model extracts only the most relevant features and metrics from the raw data, rather than processing and storing all possible information. It identifies and extracts key performance indicators, behavioral patterns, and critical data points while discarding redundant information. This extraction approach maintains measurement precision for critical metrics while reducing overall computational energy consumption.

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS20260003823A1System for data structure and file management by selecting datatypes and integrating data from stored data

Publication Date: 2026.01.01 TRUIST BANK

AI summary

A system and a method select datatypes and integrate data from data in storage devices connected to a computing system communicating with multiple users. The computing system includes a processor running an application causing the processor to: store, over a predetermined time period, data related to the users, the data being generated by the computing system, by inputs to the computing system from the users and by communications between the users; execute a machine learning algorithm configured to process the stored data and generate a performance data set for each of the users; respond to identifying one of the users by generating an integrated data set based upon a portion of the stored data and the performance data set associated with the one user; and generate on a display device a display of information based upon the integrated data set, the display including links to files in the stored data.