Cortical.io Case Studies How a Fortune 100 Technology Manufacturer Reduced Support Engineers’ Search Efforts by 70%

Edit This Case Study Record

	How a Fortune 100 Technology Manufacturer Reduced Support Engineers’ Search Efforts by 70% Cortical.io

How a Fortune 100 Technology Manufacturer Reduced Support Engineers’ Search Efforts by 70%

Cortical.io

Technology Category	Analytics & Modeling - Machine Learning
Applicable Industries	Electronics
Services	Data Science Services
Challenge	The support cases handled by the company’s support engineers were difficult and time-consuming to resolve because they referred to complicated technical issues in a complex networking environment. The fact that customers often used different terminology than what is used in the company internal documentation made the task even more difficult. Efficient handling of support cases was predicated on finding a solution from past cases instead of troubleshooting the issue from scratch. Attempts to reduce the time to find meaningful results with other search-based solutions failed, as they were not able to quickly and consistently identify similar support cases and did not improve the support team’s productivity. Read More
About Customer	The customer is a Fortune 100 Technology Manufacturer. They are a large-scale company with a complex networking environment. Their support engineers handle a multitude of support cases that often refer to complicated technical issues. The company's internal documentation uses specific terminology, which often differs from the language used by their customers. This discrepancy in language use further complicates the resolution of support cases. The company had previously attempted to reduce the time to find meaningful results with other search-based solutions, but these attempts failed to improve the support team’s productivity. Read More
Solution	Cortical.io Support Intelligence was rapidly trained in an unsupervised machine-learning approach using support cases. The solution’s patented technology overcame the problems of language ambiguity and vocabulary mismatch by analyzing not just keywords but also the meaning of whole support cases, including customers’ written requests, engineers’ notes, email exchanges, and the meaning of sections of text from support documents, long or short. This allowed the solution to quickly provide the support engineers with the most applicable documents to the support case. As new material became available, it was ingested, indexed and automatically became searchable. Based on support engineer feedback, the system also continuously learned to assess the quality of the applicable documents. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Machine Learning

Applicable Industries

Electronics

Services

Data Science Services

Challenge

The support cases handled by the company’s support engineers were difficult and time-consuming to resolve because they referred to complicated technical issues in a complex networking environment. The fact that customers often used different terminology than what is used in the company internal documentation made the task even more difficult. Efficient handling of support cases was predicated on finding a solution from past cases instead of troubleshooting the issue from scratch. Attempts to reduce the time to find meaningful results with other search-based solutions failed, as they were not able to quickly and consistently identify similar support cases and did not improve the support team’s productivity.

About Customer

The customer is a Fortune 100 Technology Manufacturer. They are a large-scale company with a complex networking environment. Their support engineers handle a multitude of support cases that often refer to complicated technical issues. The company's internal documentation uses specific terminology, which often differs from the language used by their customers. This discrepancy in language use further complicates the resolution of support cases. The company had previously attempted to reduce the time to find meaningful results with other search-based solutions, but these attempts failed to improve the support team’s productivity.

Solution

Cortical.io Support Intelligence was rapidly trained in an unsupervised machine-learning approach using support cases. The solution’s patented technology overcame the problems of language ambiguity and vocabulary mismatch by analyzing not just keywords but also the meaning of whole support cases, including customers’ written requests, engineers’ notes, email exchanges, and the meaning of sections of text from support documents, long or short. This allowed the solution to quickly provide the support engineers with the most applicable documents to the support case. As new material became available, it was ingested, indexed and automatically became searchable. Based on support engineer feedback, the system also continuously learned to assess the quality of the applicable documents.

Impact #1	The company’s support engineers are able to more quickly identify relevant search results compared to previous search methods.
Impact #2	The system continuously learns from user feedback to improve results.
Impact #3	The system seamlessly integrates into the existing support-case software.

Impact #1

The company’s support engineers are able to more quickly identify relevant search results compared to previous search methods.

Impact #2

The system continuously learns from user feedback to improve results.

Impact #3

The system seamlessly integrates into the existing support-case software.

Benefit #1	Reduced by 70% the average search time for relevant solutions that address the support case.

Benefit #1

Reduced by 70% the average search time for relevant solutions that address the support case.

Download PDF Version

Overview

How a Fortune 100 Technology Manufacturer Reduced Support Engineers’ Search Efforts by 70%

Operational Impact

Quantitative Benefit