Automated Issue Identification in Customer Transcripts

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Manual processes for identifying customer issues in call centers are inefficient and time-consuming, making it difficult for companies to keep up with changing customer grievances across various demographics, leading to potential missed issues and increased costs.

Innovation Solution

A system and method that automatically identify issues in customer-agent interactions using digital media, text mining, and information retrieval, which includes collecting and normalizing text-based data, clustering historical issues, and generating legitimacy scores to rank issues based on relevance, allowing for quick and effective solution design.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual processes are used to identify customer issues in call centers, then agents can characterize and tag grievances using existing CRM tools, but the process becomes time-consuming and inefficient

Engineering Contradiction:

Improveissue identification accuracyVSAvoidtime to identify issues

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces the manual mechanical process of reading transcripts and tagging issues with an automated text mining system that uses natural language processing to extract and classify customer issues, thereby eliminating time consumption while maintaining identification accuracy

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by automatically analyzing call transcripts and identifying issues without requiring agent intervention, allowing the system to serve itself in the issue identification task that previously required manual human effort

Inventive Principle:

Principle #25Self-service

2Reliability

If agents manually maintain a comprehensive list of customer issues, then all grievances can be tracked, but the process is not scalable and becomes unsustainable

Engineering Contradiction:

Improvecomprehensiveness of issue listVSAvoidscalability of issue maintenance

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The system automatically maintains and updates the issue list through self-service mechanisms, continuously mining new issues from incoming transcripts without requiring manual intervention, thereby achieving both comprehensiveness and scalability

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary action by proactively identifying and adding new issues to the database before they accumulate, maintaining an up-to-date comprehensive list automatically rather than requiring periodic manual updates

Inventive Principle:

Principle #10Preliminary action

3Reliability

If companies conduct customer surveys to maintain an issue list, then comprehensive coverage can be achieved, but the cost to the company increases

Engineering Contradiction:

Improvecompleteness of issue coverageVSAvoidcost of issue identification

Core Design Contradiction:

ReliabilityVSLoss of energy

Solution Approach 1:

Instead of conducting expensive customer surveys, the system creates a digital copy of customer feedback by automatically analyzing existing call transcripts, thereby achieving comprehensive issue coverage at minimal cost

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent replaces the expensive mechanical process of conducting surveys with an automated text mining system that extracts issues from existing communication data, eliminating survey costs while maintaining comprehensive coverage

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

4Loss of information

If manual interpretation of call transcripts is performed, then useful information can be extracted, but the process is inefficient and cannot keep up with changing customer issues

Engineering Contradiction:

Improvebusiness-actionable information extractionVSAvoidspeed of information extraction

Core Design Contradiction:

Loss of informationVSProductivity

Solution Approach 1:

The system replaces manual interpretation with automated text mining technology that uses natural language processing to extract business-actionable information from transcripts, achieving both complete information extraction and high processing speed

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system is dynamic and adaptive, automatically adjusting to changing customer issues by continuously learning from new transcripts, thereby maintaining information extraction quality while keeping up with evolving customer grievances

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS10922734B2Automatic identification of issues in text-based transcripts

Publication Date: 2021.02.16 FMR CORP

AI summary

A computerized method is provided for automatically identifying a set of historical issues derived from historical customer interactions with an enterprise. The method includes collecting text-based data corresponding to the historical customer interactions, extracting customer queries from the text-based data, and normalizing and filtering the customer queries to generate the set of historical issues of the customer queries. The method also includes assigning the historical issues to one or more clusters that capture variances among the historical issues. The method further includes generating a legitimacy score for each historical issue and ranking the set of historical issues in accordance with their corresponding legitimacy scores. The method can further include identifying one or more issues in a transcript of unstructured text using the set of historical issues.