IT Infrastructure Surveying with ML Image Recognition

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Manual recording of IT infrastructure information is time-consuming, costly, and prone to human error, making it inefficient for organizations planning or updating IT projects.

Innovation Solution

A computer-implemented method and system that uses a portable device with a site surveyor to automatically identify the location of IT equipment, capture images, and process them using a machine learning model to update IT records in a geospatial inventory database, simplifying IT infrastructure surveying and inventory management.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If manual recording of IT infrastructure information is used, then detailed inventory data can be collected, but the process is time-consuming and costly

Engineering Contradiction:

ImproveIT equipment inventory dataVSAvoidTime for surveying and recording

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical recording processes with automated image capture and machine learning-based equipment identification. The system uses portable devices to capture images of IT equipment and automatically extracts inventory information through ML models, eliminating the need for manual data entry and significantly reducing surveying time while maintaining data accuracy

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service inventory management by allowing the IT equipment itself to be automatically identified and recorded through image processing. The machine learning model autonomously extracts equipment details from captured images without requiring human intervention, making the inventory process self-executing and highly efficient

Inventive Principle:

Principle #25Self-service

2Reliability

If manual recording methods are used, then inventory data can be obtained, but human error increases

Engineering Contradiction:

ImproveAccuracy of IT equipment dataVSAvoidComplexity of surveying process

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces error-prone manual recording with automated machine learning-based identification. The ML model consistently extracts equipment information from images without human error, improving data reliability. The system validates and standardizes extracted data through automated processes, ensuring high accuracy in inventory records

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system creates accurate digital copies of physical IT equipment through image capture and ML-based information extraction. Each piece of equipment is virtually replicated in the inventory database with precise details extracted from images, maintaining fidelity to the original equipment while eliminating manual transcription errors

Inventive Principle:

Principle #26Copying

3Loss of information

If traditional surveying methods are used, then IT equipment information can be recorded, but costs increase

Engineering Contradiction:

ImproveIT infrastructure detailsVSAvoidEfficiency of inventory management

Core Design Contradiction:

Loss of informationVSProductivity

Solution Approach 1:

The patent creates a multi-functional system where a single portable device performs multiple tasks: capturing images, identifying equipment, extracting information, and updating inventory databases. This universal approach consolidates previously separate functions (surveying, data collection, data entry, validation) into one integrated process, dramatically improving productivity while maintaining comprehensive inventory information

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system automates the entire inventory management process, making it self-service. The machine learning model automatically identifies equipment types, extracts specifications, and populates database records without human intervention. This automation eliminates labor costs associated with manual surveying while ensuring complete and accurate IT infrastructure documentation

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS20240184933A1System and method for information technology (IT) infrastructure surveying and inventory management

Publication Date: 2024.06.06 SAUDI ARABIAN OIL CO

AI summary

An information technology (IT) infrastructure survey and inventory management (SIM) system is described herein. A portable device of the system is configured with a site surveyor that can communicate location information for the device during a site survey of IT equipment of the IT infrastructure to a geospatial inventory database of the system. This database can provide geo-location data for the IT infrastructure and/or site based on the location information to the portable device for rendering therein. The site surveyor can cause a camera of the portable device to capture at least one image of the IT equipment. The system includes an image processing database with a machine learning (ML) model that can output IT equipment data based on the one or more images. The geospatial inventory database can map the IT equipment data to an IT record to update the IT record for the IT infrastructure and/or site.