Intelligent Customer Service Using Knowledge Graphs

Presented by Joe Pindell, Managing Director on the Global Solution Management team at Pitney Bowes.
sps.columbia.edu/executive-edu...
Consistently providing excellent customer service is a challenge for even the friendliest organizations. Customer service representatives (CSRs) use rigid decision-tree scripts, customer complaints match against available CSRs using a first available strategy rather than their expertise or knowledge of an issue, and organizations don’t automatically learn from their most effective complaint resolutions.
Our Intelligent Customer Handling solution (ICH) uses a knowledge graph (KG) to understand the Customer 360 space from analyzing call transcripts using natural language processing, incorporating expert feedback, and recommendation discovery for optimal resolutions. Our knowledge graph solution addresses the key challenges of customer turnover and churn through a better understanding of a customer complaint and can dynamically learn when to retrain a new knowledge graph from expert-driven feedback.
This session presents how our novel solution improves the customer experience, how a knowledge graph can model complaints and provide context for customer relationships, merges distinct domain schemas, and scales with its architecture in both design and engineering.
- - -
Offered on Columbia University’s Morningside campus in New York City, the Knowledge Graph Conference (KGC) is a world-class curated program that brings experienced practitioners, technology leaders, cutting-edge researchers, academics and vendors together for two days of presentations, discussions and networking on the topic of knowledge graphs.
While the underlying technologies to store, retrieve, publish and model knowledge graphs have been around for a while, it is only in recent years that widespread adoption has started to take hold.
As knowledge is an essential component of intelligence, knowledge graphs are an essential component of AI. They form an organized and curated set of facts that provide support for models to understand the world. Today, they power tasks like natural language understanding, search and recommendation, and logical reasoning. Tomorrow they will ubiquitously be used to store and retrieve facts learned by intelligent agents.
In the enterprise, knowledge graphs are the ultimate dataset. Integrating and organizing together internal and external data sources. Knowledge graphs integrate with the larger information system: master data management, data governance, data quality. Their flexibility and powerful representation capabilities allow data scientists to tap them to build powerful models.
The Knowledge Graph Conference is coordinated by Columbia University School of Professional Studies' Executive Education program. Visit: sps.columbia.edu/executive-edu... for more information.
--
SPS advances knowledge with purpose to move careers, communities, and markets forward. Our mission is to provide a rigorous education, informed by rapidly evolving global market needs, that supports the academic and professional aspirations of our student community. Our vision is to become the premier destination for professional education by generating interdisciplinary thought leadership, developing innovative pedagogy, and advancing globally competitive academic solutions for ambitious agents of change and impact. Through specialized programs taught by leading educators and leading-edge practitioners, SPS students gain the skills and support they need to move their careers, communities and industries forward.
sps.columbia.edu