NLP: Unlock the Hidden Business Value in Voice Communications

By Dr. Jans Aasman, CEO, Franz Inc.

Today organizations capture an enormous amount of information in spoken conversations, from routine customer service calls to sophisticated claims processing interactions in finance and healthcare. But most of this information remains hidden and unused due to the difficulty of turning these conversations into meaningful data that can be effectively analyzed through Natural Language Processing (NLP).

Simply applying speech recognition software to voice conversations often results in unreliable data. State-of-the-art speech recognition systems still have trouble distinguishing between homophones (words with the same pronunciation, but different meanings), as well as the difference between proper names (i.e. people, products) and separate words. In addition, there is also the challenge of identifying domain-specific words accurately. Thus, in most cases, using speech recognition software alone doesn’t produce accurate enough data for reliable NLP.

Domain-specific taxonomies are key to understanding conversations via speech recognition systems. With them, we can feed conversations to knowledge graphs that understand the conversation and make connections in the data. Knowledge graphs provide the ability to extract the correct meaning of text from conversations and connect concepts in order to add business value.

Knowledge graphs fed with NLP provide two prime opportunities for monetization. First, organizations can better understand their customers to improve products and services more to their liking, which in turn boosts marketing, sales and customer retention rates. Secondly, this analysis gives contact center agents real-time support for optimizing customer interactions to produce faster resolutions, better conversion rates, and cross-selling and up-selling opportunities. These approaches enable companies to capitalize on speech recognition knowledge graphs, accelerate their ROI, and expand their bottom lines.

Taxonomy Driven Speech Recognition

The story of taxonomy-driven speech recognition closely relates to knowledge graphs. The first wave of knowledge graphs was built from taking structured data and turning it into semantic graphs that support the linked open data movement. The next wave is all about unstructured data. People started doing Natural Language Processing on documents and textual conversations like emails and chats. Doing so accurately for a given domain requires a taxonomy to understand the words and concepts. Otherwise, downstream processes like entity extraction and event detection won’t work.

Read the full article at DZone.

Text Analytics Forum 2020 – KMWorld Connect

Join us November 17, 2020 – Text Analytics has the ability to add depth, meaning, and intelligence to any organization’s most under-utilized resource – text. Through text analytics, enterprises can unlock a wealth of information that would not otherwise be available. Join us as we explore the power of text analytics to provide relevant, valuable, and actionable data for enterprises of all kinds.

Jans Aasman to present – Analyzing Spoken Conversations for Real-Time Decision Support in Mission-Critical Applications

November 17, 2020 at 2PM Eastern

Knowledge graphs enhance customer experience through speed and accuracy

KMWorld’s recent article covers AllegroGraph and Franz’s customer N3 Solutions.

The Full Article – KMWorld

Knowledge graphs are a way to model enterprise knowledge and represent complex interrelationships in data. Information stored in a graph database can enable rapid retrieval of well-targeted results and provide insights into customers’ interests and needs. Gartner predicts a 100% per-year growth in applications for graph analytics and databases for the next several years. Although knowledge graphs have been deployed by major companies such as Google, Amazon, and LinkedIn due to their ability to incorporate relationships in their analyses as well as their speed, only in the last 5 years has their use become more widespread.

N3 is an outsourced sales company for major organizations that sell complex B2B software, hardware, and tech solutions. It supports businesses in 92 countries, provides services in 25 languages, and holds thousands of hours of conversations every month with customers and prospects. “In today’s world of complex products, it takes a well-educated team to tell the story about how this technology can help a company become more competitive,” said Shannon Copeland, COO of N3. “The sales team needs to be able to instantly access the information they need to do their job.”

Faster insights

The company has been operating for 16 years, and in the last few years began an initiative to manage its knowledge in a more intentional way. “We generate a great deal of data,” noted Copeland, “and we wanted to make more effective use of it to understand our customers. And because of the speed at which business is transacted now, we needed to get insights right away, not a month later in a report.”

N3 built a data model to reflect the essential data elements and the associations among them and decided that a knowledge graph was the best way to represent the information. After looking into partner options, N3 chose to work with Franz, Inc., which provides a semantic graph database called AllegroGraph. “We decided to work with Franz because of its extensive experience and the fact that it had worked with a variety of industries,” Copeland said.

The system built by N3 allows sales teams to organize signals from the market in a way that allows them to better explain the products to prospective buyers. “We build relationships with tech buyers on behalf of our clients,” continued Copeland. “Our employees are typically college graduates who would like to begin their careers in sales and marketing in tech solutions. They take ownership of their territory and we help them be as sophisticated as a future CMO would be.” The resources supplied by the knowledge graph provide the support the sales team needs to tailor information to each prospective customer.

The specific expertise required by the team varies depending on the products being sold, the geographic region, and other factors, and the knowledge graph supports these needs. For example, if a team in southern Portugal needs to know the preferences of that market, the associations built into the graph database can provide the information that is essential for them. “The information we can access helps customers understand the answers to their questions very quickly,” Copeland commented. “We believe the experience that the customers have helps them scope out what they need and what the road map might be.”

The strength of graph databases

A graph databases is a type of NoSQL database that stores data according to associations among data elements rather than in the rows and columns of a relational database. Because graph databases use a dynamic schema rather than a fixed, table-based one, adding new data types and categories is much easier. And because they are semantics-based, graph databases have strengths in inferring intent, producing answers to questions, and making recommendations. They can also make inferences about possible associations from existing associations.

A graph database also provides much more context than a relational database and therefore can return more relevant results when a user is searching; they also integrate data from multiple sources. “At one telecom company we worked with, customer service reps might have [had] to open 15 databases to find out what went wrong and what the solution was,” said Jans Aasman, CEO of Franz. “We took their core customer data, billing information, every CRM call, and every action and put them into AllegroGraph, and the customer service reps were finally able to respond in a meaningful way, whether that was to make an offer to the customer or provide appropriate technical support.” The capability of graph databases to overcome silos and provide an integrated view of the customer is one of its strengths.

In order to create the graph database on which the knowledge graph is built, the relationships among entities need to be mapped. In the case of a hospital patient, the patient is the core entity, and the events are medical encounters or lab results, which may come out of different databases or a data warehouse. “The mapping is a major project, but it only needs to be done once,” Aasman pointed out. “After that, the relationships do not need to be regenerated during the search because they are indexed in AllegroGraph, which makes retrieval very rapid.”

Graphorum – Dr. Aasman Presenting

Graph-Driven Event Processing for Intelligent Customer Operations

Wednesday, October 16, 2019
10:15 AM – 11:15 AM
Level: Case Study

In the typical organization, the contents of the actual chat or voice conversation between agent and customer is a black hole. In the modern Intelligent Customer Operations center, the interactions between agent and customer are a source of rich information that helps agents to improve the quality of the interaction in real time, creates more sales, and provides far better analytics for management. The Intelligent Customer Operations center is enabled by a taxonomy of the products and services sold, speech recognition to turn conversations into text, a taxonomy-driven entity extractor to take the important concepts out of conversations, and machine learning to classify chats in various ways. All of this is stored in a real-time Knowledge Graph that also knows (and stores) everything about customers and agents and provides the raw data for machine learning to improve the agent/customer interaction.

In this presentation, we describe a real-world Intelligent Customer Organization that uses graph-based technology for taxonomy-driven entity extraction, speech recognition, machine learning, and predictive analytics to improve quality of conversations, increase sales, and improve business visibility.



Turn Customer Service Calls into Enterprise Knowledge Graphs

Franz’s CEO, Jans Aasman’s recent Destination CRM article:

The need for text analytics and speech recognition has broadened over the years, becoming more prevalent and essential in the sales, marketing, and customer service departments of various types of businesses and industries. The goal is simple for these contact center use cases: provide real-time assistance to human agents interacting with potential customers to close sales, initiate them, and increase customer satisfaction.

Until fairly recently, the rich array of unstructured data encompassing client texts, chats, and phone calls was obscured from contact centers and organizations due to the sheer arduousness of speech recognition and text analytics. When readily integrated into knowledge graphs, however, these same sources become some of the most credible for improving agent interactions and achieving business objectives.

Powered by the shrewd usage of organizational taxonomies, machine learning, natural language processing (NLP), and semantic search, knowledge graphs make speech recognition and text analytics immediately accessible, enabling real-time customer interactions that can maximize business objectives—and revenues.


Taxonomies are the foundation of the knowledge graph approach to rapidly conveying results of speech recognition and text analytics for timely customer interactions. Agents need three types of information to optimize customer interactions: their personas (such as an executive or a purchase department representative, for example), their reasons for contacting them, and their industries. Taxonomies are instrumental to performing these functions because they provide a hierarchy of relevant terms to organizations.

Read the full article at Destination CRM