All Posts

How to Train Your Robot

What do curated content, personalization and machine learning have in common? 

Personalization is all about giving people appropriate information when they need it and anticipating what they need next so they can solve their problems and satisfy their needs more quickly and easily.  No one wants to waste time on useless tasks, and certainly slogging through endless links on a poorly organized set of web search results is a useless task if it does not lead me to what I want.  Consider also the transformations in processes and technologies that this requires.  We need to know what the customer wants and needs in many different contexts and have to have the data and content models to support pulling the correct products and related information in those contexts.  We need a mechanism to segment audiences and we have to recombine content through a rules engine or machine learning algorithm that optimizes offers, content and product information.  

Doing this requires rethinking multiple processes, including understanding how customers behave and when and why they need products and services under a variety of circumstances.  This problem is difficult to solve but there are several ways to approach it.  The image below illustrates that the personalized and contextualized user experience is the result of many upstream processes, and reflects organizational maturity across a number of different areas. 

Starting with product

Without good product data, users cannot find what they need, and the content management machinery behind ecommerce and user experience cannot assemble the necessary components (images and related content) with products. Search engines will not have the correct facets to index, and product details will be invisible.  Therefore good product data is a must-have.

Understanding the user    

Knowing the characteristics and needs of your target customers is the next most important piece of the puzzle.  What product combinations will make the most sense for users?  Under what circumstances?  How can customers’ past behaviors provide clues about how to sell to them successfully?  What products can be correlated with their current browse paths in order to increase the likelihood that they will convert?  Information about user needs and interests can be mined from their behaviors and the content they consume.  We can also ask questions about problems, needs, interests and in the case of B2B applications, the industry and type of job. 

Mining data sources 

Product combinations can be derived through shopping basket analysis, but that is not enough to determine the most important product combinations.  We also need to understand the inherent product relationships at the level of specific solutions.  These can be captured in a product and solution ontology.  Other data sources include the knowledge of merchandizers and subject matter experts, mining of solution content from reference manuals and troubleshooting guides, speech to text translation of YouTube videos, and other knowledge base content.

What’s this got to do with robots?

Funny you should ask that.  Here is the big secret of all of the AI, intelligent assistant and user support bots – they all need content for training.  And the big aha:  The same content that is needed to train humans is needed to train robots. 

Training robots with curated, structured content

The content for personalization tuning is the same content that robots need in order to answer questions and support users.  The two are really the same thing, though with varying use cases and varying specificity of results.   A more defined process might have only one answer for a next step, whereas a more ambiguous use case might require more detail or present a larger result set that users can then filter on.

Chat bots are trying to help the user by providing an answer or, more frequently, walking users down a path so they can get to their answer or make a selection.  The task may be complex, there may be multiple steps or the users may not know what they want until the do some exploration.   In order to retrieve content for a user, the bot needs to access it in the correct context.  Context is facilitated by metadata and tagging.  Even if the content is not explicitly tagged, the AI system ingests and indexes the content and enriches it with derived meaning and characteristics.  That can done simply through knowledge about relationships with other content, or it can be achieved through automated extraction of characteristics, clustering, or some other type of text analytics. 

Search operates on the same paradigm.  A user provides signals by entering a search term. The signal can be enhanced by looking at previous searches the user has conducted before (if the user is authenticated) or by looking at what was previously purchased, or by looking at what others with the same behavioral or interest characteristics purchased.

Rather than using the search term as the sole signal, the term is one of many that the search engine uses to make recommendations in addition to the result set that is returned through full text search or searching on metadata fields (facets) that use product data and attributes.

Taking a step toward AI

Curating and structuring knowledge bases and product information is important not only because it helps to short-term findability problems, but also because it is a stepping stone and foundational component of more automated approaches.  In fact, many search algorithms, including those developed by EIS, use AI and machine learning without calling it AI.  A chat bot is simply a front end to content.  It is how you create and structure that content where the greatest value is created. From that perspective it is a good first step toward AI.

For a look into how we use information architecture as the foundation for digital transformation read our whitepaper: "Knowledge is Power: Context-Driven Digital Transformation

Seth Earley
Seth Earley
Seth Earley is the Founder & CEO of Earley Information Science and the author of the award winning book The AI-Powered Enterprise: Harness the Power of Ontologies to Make Your Business Smarter, Faster, and More Profitable. An expert with 20+ years experience in Knowledge Strategy, Data and Information Architecture, Search-based Applications and Information Findability solutions. He has worked with a diverse roster of Fortune 1000 companies helping them to achieve higher levels of operating performance.

Recent Posts

Conversation with ChatGPT on Enterprise Knowledge Management

In another article, I discussed my research into ChatGPT and the interesting results that it produced depending on the order in which I entered queries. In some cases, the technology seemed to learn from a prior query, in others it did not. In many cases, the results were not factually correct.

The Future of Bots and Digital Transformation – Is ChatGPT a Game Changer?

Digital assistants are taking a larger role in digital transformations. They can improve customer service, providing more convenient and efficient ways for customers to interact with the organization. They can also free up human customer service agents by providing quick and accurate responses to customer inquiries and automating routine tasks, which reduces call center volume. They are available 24/7 and can personalize recommendations and content by taking into consideration role, preferences, interests and behaviors. All of these contribute to improved productivity and efficiency. Right now, bots are only valuable in very narrow use cases and are unable to handle complex tasks. However, the field is rapidly changing and advances in algorithms are having a very significant impact.

[February 15] Demystifying Knowledge Graphs – Applications in Discovery, Compliance and Governance

A knowledge graph is a type of data representation that utilizes a network of interconnected nodes to represent real-world entities and the relationships between them. This makes it an ideal tool for data discovery, compliance, and governance tasks, as it allows users to easily navigate and understand complex data sets. In this webinar, we will demystify knowledge graphs and explore their various applications in data discovery, compliance, and governance. We will begin by discussing the basics of knowledge graphs and how they differ from other data representation methods. Next, we will delve into specific use cases for knowledge graphs in data discovery, such as for exploring and understanding large and complex datasets or for identifying hidden patterns and relationships in data. We will also discuss how knowledge graphs can be used in compliance and governance tasks, such as for tracking changes to data over time or for auditing data to ensure compliance with regulations. Throughout the webinar, we will provide practical examples and case studies to illustrate the benefits of using knowledge graphs in these contexts. Finally, we will cover best practices for implementing and maintaining a knowledge graph, including tips for choosing the right technology and data sources, and strategies for ensuring the accuracy and reliability of the data within the graph. Overall, this webinar will provide an executive level overview of knowledge graphs and their applications in data discovery, compliance, and governance, and will equip attendees with the tools and knowledge they need to successfully implement and utilize knowledge graphs in their own organizations. *Thanks to ChatGPT for help writing this abstract.