Cracked Conversations: What to Do When Chatbots Aren’t Enough

Enterprise Search to Compliment Your Chatbot ExperienceBy: Robert Smith, Sales Engineer and John Finneran, Product Marketing

Conversational AI, or chatbot, vendors, are everywhere, deafening customers with the promise of AI-Powered solutions for their customer service needs.  According to Capterra, 158 companies currently offer chatbot software.  In Forrester’s evaluation of the emerging market for conversational AI for customer service for Q2 2019, the analyst firm identified the 14 most significant providers in the category – [24]7.ai, Avaamo, Cognigy, eGain, Indenta Technologies, Interactions, IPsoft, Kore.ai, LogMeIn, Nuance Communications, Omilia, Saleforce and Verint.

This makes understanding what works best to improve customer experience hard.

Chatbots work best guiding users along straightforward, well-defined conversational paths.  If a customer asks new, unpredicted questions the typical chatbot gets confused. More complex questions require complementary solutions.  

Sinequa offers one such complementary solution – Enterprise Search that can work with chatbots to help customers and employees find what they need.

We have spoken with a number of companies ranging from those considering the technology, to building prototypes, to deploying chatbots in customer-facing applications.

Several of the concerns about the value produced by chatbot deployments

  • Slow Conversation speeds
  • Conversation path-sets grow larger and longer
  • Low accuracy because the chatbot was unable to answer and was unable to maintain the chat
  • High development effort with too many expert hours spent conceiving, designing, deploying, and maintaining those conversational paths.

Some Reasons Why?

Chatbots work best when guiding a well-defined type of user through a set of preconceived conversational paths.

The typical chatbot’s tooling provides a graphical interface, and some testing capabilities; conceiving, designing, deploying, and maintaining those conversational paths will be up to you.

  • When you consider how many paths a user might take, multiplied by the number of user types, it can grow to an astonishing amount of work.
  • When chatbots have a lot of this work to do, they tend to slow down compromising, the chat experience
  • Most requests for information are ‘ad-hoc’ and therefore not well-suited for a pre-planned and pre-built conversation flow.

When Do Chatbots Make Sense?

An example is a chatbot at your local bank

  • They have a limited set of offerings for users to choose from
    • E.g. checking, savings, mortgages, lines of credit
  • Those offerings have a limited number of actions
    • Checking deposit, transfer, bill pay, balance inquiry
  • The site is often for reference, not as much for execution
    • To actually open up an account type, you typically have to apply in-person

If you can’t narrow the scope to specific user-types and paths like these, then the outcome of multi-step “chats” is by definition, less predictable, leading to a higher failure rate.

This also makes it difficult for some chatbots to get a PTO (Permit to Operate), because companies have not let applications go into production that couldn’t guarantee outcomes.  This is to avoid “Rogue AI” situations, among other things.

Addressing the Challenge

Enterprise Search, like Sinequa’s, leverages natural language processing (NLP) to get users the most relevant content, without the chatbot’s requirement that the conversational path be designed, built and maintained.

Where chatbot interactions are sometimes helpful, that chatbot can connect to enterprise search; when the chatbot gets a user’s request for information, the chatbot can refine and forward the request to the underlying Sinequa search, then channel the results back to the user’s conversation.

In Short

By using chatbots and a powerful enterprise search platform together for the jobs they were designed for, you can deliver profitable and productive solutions that enhance both customer and employee experiences.

+1Share on LinkedInShare on Twitter

Data Doesn’t Drive Finance

Your people need information, not data. On average, they waste a day a week searching across silos, systems, and clouds for information. It’s pre-digital-age work. Learn how AI-Powered Search gives your employees the information and intelligence they need.

View the white paper

em360-11-2019-800

+1Share on LinkedInShare on Twitter

Cognitive Search Brings the Power of AI to Enterprise Search

Forrester, one of the leading analyst firms, defines Cognitive Search in a recent report¹ as: The new generation of enterprise search that employs AI technologies such as natural language processing and machine learning to ingest, understand, organize, and query digital content from multiple data sources. Here is a shorter version, easy to memorize: Cognitive Search = Search + NLP + AI/ML
Of course, “search” in this equation is not the old keyword search but high-performance search integrating different kinds of analytics. Natural Language Processing (NLP) is not just statistical treatment of languages but comprises deep linguistic and semantic analysis. And AI is not just “sprinkled” on an old search framework but part of an integrated, scalable, end-to-end architecture.

AI Needs Data, Lots of Data
For AI and ML algorithms to work well, they need to be fed with as much data you can get at. A cognitive search platform must access the vast majority of data sources of an enterprise: internal and external data of all types, data on premises and in the cloud. Hence the system must be highly scalable.

Continuous Enrichment
Cognitive Search uses NLP and machine learning to accumulate knowledge about structured and unstructured data and about user preferences and behavior. That is how users get ever more relevant information in their work context. To accumulate knowledge, a cognitive search platform needs a repository for this knowledge. We call that a “Logical Data Warehouse” (LDW).

The Strength of Combination
To produce the best possible results, the different analytical methods must be combined, not just executed in isolation of each other. For example, machine learning algorithms deliver much better results much faster if they work on textual data for which linguistic and semantic analyses have already extracted concepts and relationships between concepts.

Whitepaper-kmworld-07-2017Get your copy of the full paper here and learn more about current use cases of cognitive search and AI at large information-driven companies.

(1) Forrester Wave: Cognitive Search & Knowledge Discovery Solutions, Q2 2017
Read the full report on https://www.sinequa.com/forrester-wave-2017/

+1Share on LinkedInShare on Twitter

Digital Workplace: Digitized Chaos or Information at your Fingertips?

Digital Workplace

You have a digital Workplace, of course. Does it fulfil all the expectations you had when you went “all digital”? Or is getting at the right information still too complex, too cumbersome and time-consuming? Companies often need specialists to extract information for each specific work context. That is not agileand it’s in total contradiction with the modern digital workplace principles promising “information self-services”.

In decent Digital Workplaces, you find information, not data! And this information must be comprehensive and relevant, and delivered instantly, since in the era of digital business models, there is no time to sift through tons of data when you need information. At best, information is delivered proactively, in order to gain time, increase productivity and improve decision making.

Now, many of you may be wondering: “how to create value from data in increasingly digitalized businesses?”; “how to extract relevant information from big and diverse data and then, deliver precise and relevant information to each and every person at the right time?” This might seem like an elusive goal as we create more data than ever in digitalized workplaces, potentially increasing chaos every day.

To overcome these challenges, we need to simplify the digital workplace for users. This requires high performance systems of data retrieval, analytics and information delivery.

In the past, organizations have installed data warehouses and search engines to help people find relevant data. Many of these never delivered on the expectations – and the needs – of users and organizations. They were lacking in analytical power and in performance when faced with large and growing amounts of heterogeneous data and with the need to combine analysis of structured and unstructured data, including most prominently natural language processing (NLP) for a while range of languages.

The new generation of enterprise search platforms have evolved into whatGartner calls “Insight Engines”.

According to this leading analyst firm, 25% of large organizations will have an explicit strategy to make their corporate computing environment similar to a consumer computing experience by 2018; 46% have a digital workplace initiative underway and 4% have appointed a Digital Workplace leader.

As usual, the bright new digital future cannot be “bought” with a new piece of technology. It requires a change of mind-set and a change in corporate culture.  Nevertheless, be aware that the digital workplace technology you select can either facilitate or impede adoption and change of culture.

Gartner specifies these Digital Workplace Principles : Contribution/ Enthusiasm; Digital Dexterity; Autonomy

#1 Contribution/ Enthusiasm: By promoting employee engagement, digital workplaces create a workforce that makes discretionary contributions to business effectiveness

#2 Digital Dexterity: Creating a “consumer-like computing experience” to enable teams to be more effective

#3 Autonomy:  Exploiting emerging smart technologies and people-centric design to support dynamic non-routine work

To step into the era of the reimagined Digital workplace you need the “Insight Engine” to increase your employees’ effectiveness and productivity, to help them better serve their customers while enjoying their work environment.

Sinequa has been mentioned next to Apple, IBM and the likes in the latest Gartner’s Hype Cycle Content Management/Digital Workplace 2015 Reports – for proactive search capabilities that are mandatory for a transition to Digital Workplaces.

Take a look at our presentation in the Gartner Digital Workplace Summit last September in London:

 “The Re-Imagined Digital Workplace: Where is the Beef?

+1Share on LinkedInShare on Twitter

3 Key Drivers for a Performant Enterprise Big Data Search and Analytics Platform

If you are aiming at deploying a performant Enterprise Search platform you would do well to consider these 3 key criteria:

Strong Content Analytics

In order to be extremely effective and efficient, an Enterprise Big Data Search and Analytics platform should offer strong Content Analytics that combines indexing of both structured and unstructured data. Indeed, it’s the combination of both types of analysis that delivers more relevant results and insights to users.

In addition, a performant Enterprise Big Data Search and Analytics platform should also “put powerful NLP to work in surprising scenarios” according to Forrester Research. The semantic analysis (named entities extraction, text mining agents, etc.) coupled with the statistical analysis and machine learning algorithms enables data-driven businesses getting more relevant and contextual information from search results.


Big Data Search and Analytics  PlatformHigh Connectivity

A Big Data Search & Analytics platform only deserves its name if it connects easily to virtually all data sources of an organization. If you need access to a new data source, you want to have it now, not in 3 months.

Multiple connectors to structured and unstructured data sources (internal and external to an enterprise) will help you cope with “data variety” and ensure that projects can start delivering value to users in a matter of weeks rather than months.

Extreme Scalability

Your platform architecture should offer the necessary scalability to deal with your large and diverse amounts of Big Data. It should be scalable enough to combine statistical analysis of structured and unstructured data with linguistic and semantic analysis of texts in several major languages (NLP – Natural Language processing). Moreover, an out-of-the box Grid Architecture that allows you to flexibly adapt resources will help you gain agility and get faster response times.

So, is your Enterprise Big Data Search & Analytics platform as performant as you thought?

If not, request a demo here and see how you can get value from your big data easily and rapidly!

+1Share on LinkedInShare on Twitter