AI Model for Product Data Quality Score Prediction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The manual and labor-intensive process of reviewing discounts or specialized pricing for orders is time-consuming and inefficient, leading to delays in order approvals and potential loss of business opportunities due to the need for extensive manual audits by special pricing teams.

Innovation Solution

Implementing AI techniques, such as machine learning and statistical methods, to evaluate features and key performance indicators associated with orders and customer accounts to predict a quality score, which can automatically approve, deny, or prioritize orders for further review, thereby streamlining the pricing review process.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual review process is used to evaluate discounts and specialized pricing, then accuracy and control are maintained, but processing time increases significantly and productivity decreases

Engineering Contradiction:

Improvepricing review accuracyVSAvoidorder processing speed

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

An AI model acts as an intermediary between the order submission and final pricing review. The model evaluates product-related data structures and generates quality scores that guide the manual review process, allowing automated pre-screening while preserving human oversight for complex cases.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The pricing review process is segmented into automated evaluation of specific features (account features, product features, order features) and manual review of only those cases requiring human judgment. This segmentation allows parallel processing of routine evaluations while maintaining human control for exceptional cases.

Inventive Principle:

Principle #1Segmentation

2Reliability

If extensive manual audits are performed by special pricing teams, then pricing decisions are controlled and accurate, but resource consumption increases and response time decreases

Engineering Contradiction:

Improvepricing decision controlVSAvoidorder approval time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The AI model performs preliminary evaluation of orders by assessing account features, product features, and order features before manual review. This preliminary action filters out routine cases that can be automatically approved or denied, reserving manual audit resources for complex or high-risk cases.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system enables self-service pricing review for standard cases through automated evaluation. The AI model independently assesses order quality scores and makes pricing recommendations without requiring special pricing team intervention, freeing up human resources for exceptional cases.

Inventive Principle:

Principle #25Self-service

3Productivity

If automated AI evaluation is implemented, then processing speed and productivity improve, but system complexity increases

Engineering Contradiction:

Improvepricing review efficiencyVSAvoidevaluation system complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The manual mechanical review process is replaced with an automated AI-based evaluation system. The model processes product-related data structures using machine learning algorithms to generate quality scores, substituting human manual evaluation with automated computational analysis.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

4Measurement precision

If manual pricing review is used, then detailed analysis of order characteristics can be performed, but the process becomes labor-intensive and time-consuming

Engineering Contradiction:

Improveorder characteristic analysisVSAvoidreview process simplicity

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The AI model serves as an intermediary that performs detailed analysis of order characteristics including account features, product features, and order features. This intermediary handles the complex analysis work, presenting simplified recommendations to reviewers and eliminating the need for manual analysis of routine cases.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS11615366B2Evaluation of product-related data structures using machine-learning techniques

Publication Date: 2023.03.28 EMC IP HLDG CO LLC

AI summary

Artificial intelligence (AI)-based techniques are provided that predict a quality score for a product-related data structure associated with one or more products. One method comprises obtaining data for a given product-related data structure; evaluating a plurality of first features related to a customer account associated with the given product-related data structure using the obtained data; evaluating a plurality of second features related to the given product-related data structure using the obtained data; processing at least some of the first features and the second features using at least one model that provides a predicted quality score for the given product-related data structure; and applying one or more thresholds to the predicted quality score to determine an acceptance status related to the given product-related data structure. A weighting of the first features and the second features can be learned during a training phase.