Enterprise Search Development: Start With the User Interface

This article was originally published on CMSWire.

Enterprise Search Development: Start With the User Interface 

By Martin White | Mar 10, 2020

sinequa-screenshot-enterprise-search

Start with the user interface (UI) and work backwards. That was the advice I shared with search managers developing their existing application or planning a new application during an enterprise search workshop at the recent IntraTeam event in Copenhagen, Denmark. Sinequa recently sent me some examples of user interfaces from its customers (thank you Laurent Fanichet), which showed the variety and inevitable complexity of enterprise search UIs. Too often businesses make a deliberate choice on the technology and give little thought to the UI (so much for the ethos of user-centric delivery!).

The topics outlined below cannot be left to the implementation stage. Most search applications (with the obvious exception of Office 365) are UI neutral and can support almost any UI development language. Early work around these topics is essential, even at the specification stage, to ensure the investment is fit for purpose, not just to specification.

Metadata

Enterprise information collections are much larger than might be imagined and inevitably contain many near-identical documents. HR and related corporate policies are just one example of this. So delivering the “most relevant” document in response to a query is limited at best.

The rhetoric of personalization through AI usually fails to deliver for two reasons: First, it assumes the user is seeking the information for themselves. Second, AI works on the basis of prior searches, but many of the searches will be by people who are new to an organization or role.

sinequa-screenshot-patent-miningProvide users with filters and facets so they can refine a set of results. But keep in mind, providing filtering just by file format and last revised date is a waste of screen space. Ask people how they might want to filter (e.g. country, date of publication, department, language). With that valuable information in hand, work out how the metadata to drive these filters is going to be derived — either from the text of the document, through tags or a combination.

Snippet Options

Quite a lot of work has been undertaken into the format of snippets. One size does not fit all. This is especially the case in enterprise search where the primary assessment of results is through information foraging. The format of the result and what ancillary information can be switched on or off by the user is important to consider. For some searches an expanded snippet with highlighted query terms might be invaluable, but this will limit the number of results displayed per page.

Usability

Designing search pages that scroll is a seriously bad idea. Even if the results are scrolled, the ancillary filters and facets will remain stationery, and in any case people will want to see the results in the context of a page of results. When usability testing happens later in the project, it will start with a discussion about which elements of the UI have been the subject of continuing discussion without a clear resolution and need real-life testing.

Accessibility

In the digital workplace, accessibility is very important as there will be few workarounds. At the outset you should be working with accessibility consultants to consider how voice browsers will work with the proposed UI and what the implications are for staff on the dyslexia spectrum.

Federated Search/Multilingual Search

The current interest in presenting the results from multiple repositories seems to ignore the challenges in how to present the final results. When there are only two applications (or languages) then two windows might be the best option, but as the number increases so does the complexity of the user interface. This becomes even more acute when results from text searches need to be interleaved with results from enterprise databases.

Training and Support

No matter how well you design a user interface, enterprise search is never going to be intuitive. This is due to the variable quality of the content and the metadata and the wide range of queries. Any discussion about a search UI has to take into account the extent to which training might be required for one or more aspects which will be a challenge to use.

To read the full article please visit https://www.cmswire.com/information-management/enterprise-search-development-start-with-the-user-interface/

+1Share on LinkedInShare on Twitter

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

Becoming Information-Driven Begins with Pragmatic AI

d_schubmehl_m
Written by guest blogger, David Schubmehl, IDC Research Director, Cognitive/Artificial

Intelligence Systems.  Sponsored by Sinequa.

Over the last several years, I’ve spoken to many organizations that have all asked the same question: How can we most effectively make use of all of the research, documents, email, customer records and other information that our employees have collected over the years, especially those that are now retiring? In the past, organizations had corporate libraries and corporate librarians whose job it was to help collect, organize, and disseminate information to employees and staff when and where they needed it. That department and positions are long gone from most organizations today. Why have they gone? The rate of data and documents (including research papers, contracts, and even emails) has exploded, making this task impossible. But let’s be honest: even before today’s information explosion, no classification system could ever keep up with the fast pace of change in the economy. No one could have foreseen today’s most important questions, in content categories that did not exist until today. And with the baby boomers retiring at an ever-increasing rate, an urgent question must be asked: How do organizations get the most value from the vast amounts of information and knowledge that they’ve accumulated over decades?

IDC has identified the characteristics of organizations that are able to extract more value out of the information and the data available to them. Leader organizations make use of information access and analysis technologies to facilitate information access, retrieval, location, discovery, and sharing among their employees and other stakeholders. These insight leaders are characterized by:

  • Strategic use of information extracted from both content and data assets
  • Efficient access to unified and efficient access to information
  • Effective query capabilities (including dashboards)
  • Effective sharing and reuse of information among employees and other stakeholders
  • Access to subject matter experts and to the accumulated expertise of the organization
  • Effective leverage of relationships between information from different content and data sources

So how can artificial intelligence (AI) and machine learning affect information access and retrieval? The types of questions that are best answered by AI-enabled information access and retrieval tools are those that require input from many different data sources and often aren’t simple yes/no answers. In many cases, these types of questions rely on semantic reasoning where AI makes connections across an aggregated corpus of data and uses reasoning strategies to surface insights about entities and relationships. This is often done by building a broad-based searchable information index covering structured, unstructured, and semi-structured data across a range of topics (commonly called a knowledge base) and then using a knowledge graph that supports the AI based reasoning.

AI-enabled search systems facilitate the discovery, use, and informed collaboration during analysis and decision making. These technologies use information curation, machine learning, information retrieval, knowledge graphs, relevancy training, anomaly detection, and numerous other components to help workers answer questions, predict future events, surface unseen relationships and trends, provide recommendations, and take actions to fix issues.

Content analytics, natural language processing, and entity and relationship extraction are key components in dealing with enterprise information. According to IDC’s Global DataSphere model developed in 2018, of the 29 ZB of data creation, 88% is unstructured content that needs the aforementioned technologies to understand and extract the value from it. In addition, most of this content is stored in dozens, if not hundreds of individual silos, so repository connectors and content aggregation capabilities are also highly desired.

AI and machine learning provide actionable insights and can enable intelligent automation and decision making. Key technology and process considerations include:

  • Gleaning insights from unstructured data and helping to “connect the dots” between previously unrelated data points
  • Presenting actionable information in context to surface insights, inform decisions, and elevate productivity with an easy-to-use application
  • Utilizing information handling technologies that can be used in large scale deployments in complex, heterogeneous, and data-sensitive environments
  • Enriching content automatically and at scale
  • Improving relevancy continuously over time, based on user actions driven by machine learning
  • Improving understanding by intelligently analyzing unstructured content

IDC believes that the future for AI-based information access and retrieval systems is very bright, because the use of AI and machine learning coupled with next-generation content analysis technologies enable search systems to empower knowledge workers with the right information at the right time.

The bottom line is this: enabled by machine learning–based automation, there will be a massive change in the way data and content is managed and analyzed to provide advisory services and support or automate decision making across the enterprise. Using information-driven technologies and processes, the scope of knowledge work, advisory services, and decisions that will benefit from automation will expand exponentially based on intelligent AI-driven systems like those that Sinequa is offering.

For more information on using AI to be an information leader, I invite you to read the IDC Infographic, Become Information Driven, sponsored by Sinequa at https://www.sinequa.com/become-information-driven-sinequa/

+1Share on LinkedInShare on Twitter

Big Projects on Track: Achieving the Goals of Long, Complex Projects

big-track-manufacturing-06-2019-1024Big projects, well executed, are the lifeblood of large, distributed manufacturing organizations.

Such projects solve existing and future problems that enable the organization and its stakeholders (and sometimes all of society) to move forward economically. These projects are naturally chaotic and require significant organization and planning to manage the chaos. Successfully executing these projects also means bringing together the right people and making it easy for them to collaborate, share ideas and provide inspiration.Today’s large, distributed manufacturing organizations cannot successfully plan and execute big projects without intelligent automation to help connect project stakeholders to relevant information and to each other.

Download the Big Projects On Track solution white paper to learn how one of the largest rolling stock manufacturers in the world addressed this challenge.

+1Share on LinkedInShare on Twitter

Accelerating GDPR Compliance with an Information-Driven Approach

With GDPR in full effect, Ovum has published a new white paper featuring Sinequa and outlining how cognitive search can be a compliance accelerator.  The full white paper can be found at http://go.sinequa.com/white-paper-gdpr-ovum-2018.html.

ovum-gdprThe white paper, written by Ovum senior analyst Paige Bartley, outlines the challenges of aligning existing business objectives with GDPR compliance and how companies can accelerate GDPR compliance with an information-driven approach.

There is a new precedent with GDPR for enterprise control of data of all kinds, both structured and unstructured. Gaining better control of data is a deceptively simple concept, but requires numerous capabilities, such as the ability to search for data across silos and granularly manage who has access to what. Sophisticated search and analytics capabilities, spanning organizational silos, are key to both facilitating compliance and driving informational value.

According to the white paper: “GDPR compliance requirements should not be thought of as an antithetical force against enterprise initiatives to leverage and analyze data. The more the enterprise can align its compliance obligations with existing business objectives – such as the demand to provide excellent customer service via a 360° understanding of customer desires – the more it can benefit from the perceived ‘burden’ of GDPR compliance. Enterprise-wide search is central to these capabilities and will help the enterprise gain a centralized view of subjects and topics in the increasingly distributed IT ecosystem.”

As an example of this concept, the white paper highlights Sinequa’s platform deployment at Stibbe, a global, full-service law firm with an internationally oriented commercial practice. Stibbe implemented Sinequa’s Cognitive Search & Analytics Platform to provide secure, unified access to millions of documents and legal matters. The result was a holistic view of the firm’s informational landscape, with the ability to quickly retrieve all material related to individual topics, cases or clients.

This Ovum white paper gets at the heart of Sinequa’s approach to GDPR and data analytics. By taking control of data and unleashing it as a strategic tool, organizations can become information-driven in a way that meets compliance requirements while accelerating innovation and creating a key competitive advantage.

The full white paper can be found at http://go.sinequa.com/white-paper-gdpr-ovum-2018.html

 

+1Share on LinkedInShare on Twitter