Firms specializing artificial intelligence (AI) that generates written text are developing tools that will allow you to have sophisticated conversations with common business databases like Microsoft Excel, Microsoft Power BI, Microstrategy, Qlik, Spotfire, SAP, and Tableau. Instead of typing at your computer to gain insights, you'll be able voice-chat with your computer about sales forecasts, investment options, and five-year plans.
"It is totally possible," says Robert Weissgraeber, chief technology officer at AX Semantics, a firm specializing in natural language generation (NLG). Weissgraeber says getting to the point where you can easily converse with your database is mainly a problem of collecting and unifying the data into a source that can be connected to the right tools.
"The big thing that has changed in the past two years is that, thanks to commoditization of natural language generation tools, a conversational business database is not a special project with a million-dollar price tag anymore. It can be set up for a far lower price point, allowing even smaller businesses to implement and benefit from it."
Many consumers have used basic conversational databases without even realizing it. When you ask Alexa or asks a question like "What happened today in history?" or "How does the intercom work?" or "How many ounces are in a pound?" you're using a conversational database.
Natural language generation firms like AX Semantics and Arria NLG to take this technology and apply it to a business database, so businesses can verbally ask questions of their databases, like:
Software from NLG companies can respond to such questions by relying on pre-programmed code templates that are activated by the questions, which instruct it how to obtain the information in a company's database, then report its findings verbally.
The level of detail such software is able to produce is limited by the number of questions companies want answered. Some companies may be satisfied if the software can produce verbal answers to 10 crucial questions, while others may want their managers' top 100 questions answered.
Many NLG can create custom conversational databases because they already have tools that can query databases via a text prompt and respond with a short text paragraph. Migrating to verbal questions with verbal responses from a computer is an enhancement of what they already are doing.
Narrative Science, for example, currently offers an artificial intelligence (AI) tool that, on receipt of a user request for a chart, graph, or other visualization in Microsoft Excel, will respond with a text explanation of the chart, graph, or visualization. This graphics-to-text explanation tech—which is a precursor to a verbal explanation of the chart, and what Narrative Science refers to as 'data storytelling'—has been a welcome relief for many business users, according to Anna Schena, the company's director of growth marketing. Schena says many business users find charts, graphics and other business illustrations difficult to understand and easy to misinterpret.
Says Schena, "Instead of forcing people to learn how to analyze spreadsheets or explore dashboards, data storytelling uses simple, easy-to-understand language and one-click collaboration features to ensure that everyone in your company actually understands data, all the time. With data storytelling, your team can read a personalized story that tells them what they need to know about their business, tailored specifically to their needs, automatically."
Schena says data storytelling technology is "intelligent," in that "it naturally articulates the most important and interesting information to each employee, every day, and it allows them to share that information with each other, too."
Adds Sharon Daniels, CEO of Arria NLG, which offers technology for data analytics and information delivery, "With the addition of natural language generation, business intelligence dashboards are transformed. The ability to access key information in near-real time, communicated as if written by the company's top analyst, without bias, at natural language generation writing-speed, is truly astonishing."
Other vendors offering similar graphics-to-text solutions include Automated Insights, SAP, Salesforce, and Yesop. Each offer custom programming that adds text explanations to proprietary business intelligence software built around graphics. Many also offer off-the-shelf graphics-to-text plug-ins for commonly used business intelligence packages like Microsoft Excel, Microsoft Power BI, Microstrategy, Qlik, Spotfire SAP, and Tableau.
So far, only a handful of first-generation conversational business interfaces have emerged on the market from familiar tech players, including Alexa Business, Google Assistant, Salesforce Einstein and Oracle Digital Assistant. These off-the-shelf apps have only taken initial steps toward the ultimate vision of providing in-depth interaction with a business database via voice queries and commands.
The dream of having a sophisticated conversation with a business database is still only a speck on the horizon, according to Christopher Pal, Google Scholar and professor at Polytechnique Montreal who specializes in artificial intelligence. The ability to obtain high-level business analysis from software is already available, Pal says, but no commercially available interface currently exists to access sophisticated information via verbal command.
Developers need to come up with natural language processing that will be able to anticipate all the different ways someone might ask a business question, as well as all the different types of business questions someone might ask, according to Pal.
Recent research by customer relationship management (CRM) vendor Salesforce could bring the company's conversational computing much closer to sophisticated interaction with business databases, according to Lav R. Varshney, principal research scientist at Salesforce Research.
The company, along with academic partners at Yale and Cornell universities and the University of Michigan, has developed a method for using conversational text for making SQL queries. Explains Varshney, "Recall that SQL queries are a sophisticated way of obtaining, potentially, complex information from databases. The algorithms that are emerging from this work are aiming to converse with human users along the lines of an SQL expert retrieving answers with SQL: clarifying ambiguous questions, and otherwise informing of unanswerable questions.
"Given the state of the art is already so advanced, I think we are fairly close to having technology that can provide conversational insight about the state of a given business, and even provide actionable directives to executives."
Weissgraeber agrees. "In the future, specific generated text/voice will give out more information than just a graph or table could ever provide."
In the meantime, businesses can still look for somewhat more sophisticated interaction with their databases by turning to custom natural language processing programming for those solutions, according to Weissgraeber. With custom programming, he says, business users can go beyond simple 'change my calendar' requests and begin having basic conversations with their computers about sales forecasts, rundowns on goods and services, and details of investments.
Joe Dysart is an Internet speaker and business consultant based in Manhattan, NY, USA.
No entries found