Geometric NLP for Faster Customer Support Procedure Matching

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current mechanisms for handling customer support requests are inefficient and costly, often requiring substantial human intervention, time, and resources, and existing operating procedures may become obsolete, leading to extended downtime and decreased customer satisfaction.

Innovation Solution

A system utilizing geometric progressing natural language processing (NLP) algorithms to encode and compare customer support requests with operating procedures, automatically identifying or generating procedures for resolving issues, minimizing manual intervention and updating models dynamically.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual intervention is used to analyze customer support requests and identify operating procedures, then accuracy in identifying appropriate procedures can be maintained, but productivity and resolution speed decrease significantly

Engineering Contradiction:
Improveaccuracy in identifying operating proceduresVSAvoidresolution speed
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent replaces the mechanical system of manual analysis with an automated NLP-based system. The geometric progressing NLP algorithm processes customer support requests and compares them against the operating procedure library automatically, eliminating the need for manual intervention while maintaining identification accuracy through sophisticated text encoding and matching mechanisms.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by allowing the automated NLP system to independently analyze requests, encode text representations, compare against stored procedures, and identify appropriate operating procedures without human assistance. The system serves itself by maintaining and updating the operating procedure library automatically.

Inventive Principle:
Principle #25Self-service

2Reliability

If extensive human resources are deployed to handle customer support requests, then comprehensive analysis can be performed, but cost and resource consumption increase

Engineering Contradiction:
Improvecomprehensive analysis qualityVSAvoidhuman resources required
Core Design Contradiction:
ReliabilityVSQuantity of substance

Solution Approach 1:

The patent substitutes human analysts with an automated NLP system that performs comprehensive text analysis. The geometric progressing algorithm encodes customer requests and operating procedures into comparable representations, enabling the system to analyze requests thoroughly without requiring human resources.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The automated system performs multiple functions that previously required different human roles: analyzing customer requests, searching the operating procedure library, comparing text representations, identifying appropriate procedures, and even generating new procedures when needed. This multi-functional system eliminates the need for multiple specialized human workers.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Productivity

If a traditional operating procedure library is maintained, then existing procedures can be reused, but the library becomes obsolete quickly requiring continuous manual updates

Engineering Contradiction:
Improvereuse of existing proceduresVSAvoidcurrency of operating procedures
Core Design Contradiction:
ProductivityVSAdaptability or versatility

Solution Approach 1:

The system implements feedback mechanisms where the NLP algorithm continuously learns from new customer support requests and identified procedures. The geometric progressing NLP model updates its text encoding representations based on new data, ensuring the operating procedure library remains current and adaptive to changing conditions while maintaining reuse of proven procedures.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The operating procedure library transitions from a static collection to a dynamic system that automatically adapts. The NLP system continuously processes new requests, encodes them, compares against existing procedures, and updates the library with newly identified or generated procedures, ensuring ongoing relevance without manual intervention.

Inventive Principle:
Principle #15Dynamics

4Productivity

If automated systems are implemented to process customer support requests, then productivity and resolution speed improve, but complexity of the system increases

Engineering Contradiction:
Improverequest processing speedVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent segments the automated system into distinct functional modules: the geometric progressing NLP algorithm for text encoding, the comparison engine for matching requests against procedures, and the library management system for storing and retrieving operating procedures. This segmentation manages complexity by organizing functions into separate, manageable components that can operate independently.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS12373845B2Method and system of intelligently managing customer support requests
Publication Date: 2025.07.29 MICROSOFT TECHNOLOGY LICENSING LLC
  • US12373845B2 patent drawing
  • US12373845B2 patent drawing
  • US12373845B2 patent drawing

AI summary

A system and method for automatically identifying an operating procedure for resolving a customer support request includes receiving a customer support request for resolving an issue, encoding the issue into one or more text encoding representations, providing the one or more text encoding representations as a first input to a matching and selection unit, providing operating procedure encodings for a plurality of operating procedures as a second input to the matching and selection unit, comparing, by the matching and selection unit, the one or more text encoding representations to the operating procedure encodings to identify one or more operating procedures for resolving the issue, and providing the one or more operating procedures as recommendations for resolving the issue, wherein at least one of the one or more text encoding representations and the operating procedure encodings are generated by utilizing a geometric progressing natural language processing (NLP) algorithm.