Service Request Processing Using Modified Device Images

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing device management systems face challenges in efficiently processing service requests due to variability in image quality caused by differences in object positioning, orientation, and capture angle, leading to reduced accuracy in qualitative assessment and increased costs from hardware upgrades and process adjustments.

Innovation Solution

A deep learning-based approach that uses object detection and trapezoidal augmentation to automatically crop and standardize device images, removing background noise and adjusting for image inconsistencies, enabling accurate qualitative assessment without requiring optimal image capture conditions or additional hardware.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional image processing methods are used to assess device conditions, then the system can process service requests, but image quality variability due to positioning, orientation, and capture angle differences reduces assessment accuracy

Engineering Contradiction:

Improvequalitative assessment accuracyVSAvoidimage capture condition flexibility

Core Design Contradiction:

Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent creates a standardized virtual copy of the device from the captured image through 3D reconstruction and rendering. This virtual model replicates the device's appearance and characteristics, allowing assessment to be performed on the standardized virtual copy rather than the variable original image, thus resolving the contradiction between maintaining accuracy and accepting varied capture conditions

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The system transforms images captured under varying parameters (positioning, orientation, angle, lighting) into a standardized representation by extracting geometric features and reconstructing a canonical 3D model. This parameter transformation allows the assessment to be performed on normalized data, eliminating the negative effects of parameter variability while maintaining the flexibility of diverse capture conditions

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If hardware upgrades and process adjustments are implemented to improve image quality, then assessment accuracy may improve, but system costs increase

Engineering Contradiction:

Improveimage quality consistencyVSAvoidhardware and process investment

Core Design Contradiction:

Measurement precisionVSQuantity of substance

Solution Approach 1:

The patent replaces the mechanical approach of controlling physical image capture conditions (requiring fixed cameras, controlled lighting, standardized positioning fixtures) with a computational approach. Image processing algorithms, 3D reconstruction, and rendering techniques substitute for expensive hardware upgrades, achieving image quality standardization through software rather than additional physical infrastructure

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system changes the approach from modifying physical capture parameters (hardware-based) to transforming digital image parameters (software-based). By performing geometric correction, normalization, and 3D reconstruction on the captured images, the system achieves consistent assessment quality without investing in expensive hardware upgrades or process reengineering

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If strict image capture conditions are enforced to ensure quality, then assessment accuracy is maintained, but operational flexibility and ease of use decrease

Engineering Contradiction:

Improveimage quality controlVSAvoidimage capture flexibility

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The system creates a standardized virtual representation that serves as a universal interface for assessment. Instead of requiring users to capture images under strict conditions, they can capture from any position or angle, and the system will generate the standardized virtual model, thereby maintaining precision while dramatically improving ease of operation

Inventive Principle:

Principle #26Copying

Solution Approach 2:

Rather than requiring the capture process to produce a perfect image, the patent inverts the approach: it accepts any image and uses computational methods to generate the perfect standardized representation. This inversion of the quality assurance mechanism from capture-time to processing-time resolves the contradiction between quality control and operational flexibility

Inventive Principle:

Principle #13The other way round (Inversion)

Data Source

PatentUS11830105B2Service request processing utilizing modified versions of images of computing devices

Publication Date: 2023.11.28 DELL PROD LP

AI summary

An apparatus comprises a processing device configured to obtain a first image, to detect one or more designated types of objects in the first image, at least a given one of the designated types of objects comprising at least a given portion of a computing device associated with a service request and, responsive to detecting the given one of the designated types of objects, to identify features of the given portion of the computing device in the first image. The processing device is also configured to perform an augmentation of the identified features of the given portion of the computing device to generate a second image, the second image comprising a modified version of the first image that contains the given portion of the computing device and excludes one or more other portions of the first image, and to process the service request utilizing the second image.