If it happens to be an API call / data retrieval, then the control flow handle will remain within the ‘dialogue management’ component that will further use/persist this information to predict the next_action, once again. The dialogue manager will update its current state based on this action and the retrieved results to make the next prediction. Once the next_action corresponds to responding to the user, then the ‘message generator’ component takes over.
One key reason: The technology that powers bots, artificial intelligence software, is improving dramatically, thanks to heightened interest from key Silicon Valley powers like Facebook and Google. That AI enables computers to process language — and actually converse with humans — in ways they never could before. It came about from unprecedented advancements in software (Google’s Go-beating program, for example) and hardware capabilities.
H&M’s consistent increased sales over the past year and its August announcement to launch an eCommerce presence in Canada and South Korea during the fall of 2016, along with 11 new H&M online markets (for a total of 35 markets by the end of the year), appear to signify positive results for its chatbot implementation (though direct correlations are unavailable on its website).
Even if it sounds crazy, chatbots might even challenge apps and websites! An app requires space, it has to be downloaded. Websites take time to load and most of them are pretty slow. A bot works instantly. You type something, it replies. Another great thing about them is that they bypass user interface and completely change how customers interact with your business. People will navigate your content by using their natural language.
Of course, each messaging app has its own fine print for bots. For example, on Messenger a brand can send a message only if the user prompted the conversation, and if the user doesn't find value and opt to receive future notifications within those first 24 hours, there's no future communication. But to be honest, that's not enough to eradicate the threat of bad bots.
Conversational bots “live” online and give customers a familiar experience, similar to engaging an employee or a live agent, and they can offer that experience in higher volumes. Conversational bots offer scaling—or the capability to perform equally well under an expanding workload—in ways that human can’t, assisting businesses to reach customers in a way they couldn’t before. For one, businesses have created 24/7/365 online presence through conversational bots.
These are hardly ideas of Hollywood’s science fiction. Even when the Starbucks bot can sound like Scarlett Johansson’s Samantha, the public will be unimpressed — we would prefer a real human interaction. Yet the public won’t have a choice; efficient task-oriented dialog agents will be the automatic vending machines and airport check-in kiosks of the near future.
In 1950, Alan Turing's famous article "Computing Machinery and Intelligence" was published, which proposed what is now called the Turing test as a criterion of intelligence. This criterion depends on the ability of a computer program to impersonate a human in a real-time written conversation with a human judge, sufficiently well that the judge is unable to distinguish reliably—on the basis of the conversational content alone—between the program and a real human. The notoriety of Turing's proposed test stimulated great interest in Joseph Weizenbaum's program ELIZA, published in 1966, which seemed to be able to fool users into believing that they were conversing with a real human. However Weizenbaum himself did not claim that ELIZA was genuinely intelligent, and the introduction to his paper presented it more as a debunking exercise: