Meet Siri’s Little Sister, Lola. She’s Training for a Bank Job.
Whatever you want Lola to get, Lola will get it for you. As long as it has something to do with your bank account.
Lola is a new virtual personal assistant that BBVA Compass, the North American subisidiary of Spanish banking giant Banco Bilbao Viczaya Argentaria, started testing on its website Tuesday. She’s the co-creation of BBVA and SRI International, the same Menlo Park, CA-based contract R&D institute that developed Siri, the virtual personal assistant now built into Apple’s iPhone 4S.
Lola’s purpose in life is to make self-service experiences more gratifying for BBVA customers, says Beatriz Lara Bartolomé, BBVA’s chief innovation officer. “I’m responsible for designing the bank of the future, the next banking model based on technology,” Bartolomé explains. “The Lola project is a key component of our customer-centric orientation—our new relationship with customers.”
Both Lola and Siri are offspring of CALO project, a five-year defense project at SRI to build a personalized assistant that could help military leaders manage information in command-and-control environments. But while they share a common genetic heritage, their personalities are nothing alike. Siri is like a polymath with a touch of memory loss. She can show you a traffic map, or send a text message, or tell you whether it’s raining in Sacramento, but she has no real picture of you and your needs; every time you talk to her, it’s like she’s meeting you for the first time. Lola, by contrast, has deep knowledge of you and your history, remembers the theme of a conversation, and can figure out what you’re aiming at even if you don’t say it. But she only understands one subject: banking and finance.
I drove down to Menlo Park Tuesday to see one of the first live demonstrations of Lola offered to anyone outside SRI or BBVA. As I watched, SRI computer scientist Michael Wolverton asked Lola standard banking questions such as when his next loan payment was coming up, how much was left in his checking account, and whether he could set up a regular monthly mortgage payment. Lola answered with aplomb, asked for clarification when necessary, and carried out instructions. The whole conversation took place in spoken English, though Lola also understands typed commands.
Basically, Lola is the first virtual personal assistant tailored for a specific area of commerce. Bill Mark, SRI’s vice president of information and computer sciences, calls Lola the “next generation of virtual personal assistant technology”—the first generation being Siri—and says the high-level goal of the project with BBVA was to create a program that could understand a user’s intent and reason about the best course of action. “We felt we had to go beyond Siri because here we want a system that can really be an assistant, meaning software that knows us, knows what to do, knows how to do it, and then does it,” Mark says.
SRI supplied the core artificial-intelligence engine behind Lola, while BBVA helped to prime her with specific knowledge about the kinds of tasks banking customers need to accomplish. In the field trials that started yesterday and will continue for several months, BBVA Compass is rounding out Lola’s training through live encounters with bank employees and their families.
The bank hopes to open up the service to general customers “as soon as possible,” according to Bartolomé. Only BBVA Compass account holders will be able to try out the technology, at least at first—“For the moment, it is our baby,” Bartolomé says. But there’s a possibility that BBVA would eventually license the technology to other banks as a standard conversational interface.
Bartolomé says BBVA first approached SRI about building Lola back in 2006, after field research showed that customers want more “simplicity and human reassurance” when they bank. “Our vision is that we should include human-like interactions at all of our touch points,” whether that means a website, an ATM, or a mobile app, she says.
“BBVA came to us with this vision of a virtual personal assistant for online banking, and we talked it over for a period of time, and said ‘Yes, we can build this,’” says SRI’s Mark.
But that was easier said than done. “We wanted a system that can take speech, typing, and other user interface gestures and understand the user’s intent, then reason about the best course of action to pursue, and then output it. But in order to do what BBVA wanted to do, it also had to be deeply integrated into banking.” And a key aspect of banking or any other business field is that when people are trying to do something complicated, they find themselves in conversation. “We kind of have to figure it out as we are talking to the person on the other side,” says Mark. “So you had to have a system that could actually have a conversation with the user in order to get something done.”
That’s where a lot of the heavy lifting in the Lola project occurred, according to Mark and Bartolomé. Researchers at SRI had to come up with a way to quickly diagnose a user’s intent and remember that intent through multiple conversational exchanges, while remaining ready to detect a different intent and switch to it at any moment. Here’s the example Wolverton played out for me in a live demo:
Wolverton: “What is the next payment amount on my loan?”
Lola: “Please tell me the account.”
Wolverton: “My loan.”
Lola: “The next payment amount for your installment loan is $436.”
Wolverton: “Sorry, my mortgage.”
Lola: “The next payment amount for your mortgage is $1,982.28.”
Wolverton: “And what is the payment due date?”
Lola: “The payment due date for your mortgage account is July 25, 2012.”
Notice the trick here: Wolverton switches intents halfway through the conversation, asking about his mortgage rather than his installment loan. When he asks a followup question, Lola hasn’t forgotten the change in context, and she very reasonably assumes that the question is about his mortgage loan rather than his installment loan, so she gives him the correct due date.
“This happens so naturally in human dialogue that we don’t even think about it,” says Mark. But making it work in software is tricky, and requires a thorough understanding in advance of all the directions in which a banking conversation might flow, and what actions to trigger in each case.
“The speech recognition and natural language is still a pretty hard thing to get good at, and it’s something we’re still working on,” Mark says. “But the ability to follow dialogue and keep the context straight is another hard thing. And then to actually get the work flows right is a third hard thing.”
Work flows are a big deal at BBVA: as Bartolomé noted, the bank has built its whole brand around providing a personalized human touch in all interactions with customers, even automated ones. Bartolomé says BBVA spends more on technology than any other European bank, which makes it more efficient, but that more than half of its technology investment goes to improving customer relationships. “What we have discovered is that as important as the functional needs of our customers is satisfying their emotional needs,” she says. “If you are not happy with our customer service, you are not happy trusting your money to us.”
The more tasks banks can offload to virtual assistants, certainly, the more money they’ll be able to save on human staff. But that’s not the only benefit of virtual personal assistant technology. If Lola were to catch on the way Siri did, it could help boost BBVA’s brand as an innovator. Eventually, BBVA says, Lola could even grow beyond her role as a kind of glorified bank teller and evolve into a financial advisor, giving customers personalized answers to questions about which savings or investment options are best for them. (Don’t expect that from Siri anytime soon.)
BBVA is the second largest bank in Spain and one of the 15 largest banks in the world. It entered the U.S. market in the mid-2000s by buying a series of banks in Texas, Alabama, and other Sun Belt states, forming BBVA Compass, which is based in Birmingham, AL.