weekday. Your routine varies only on weekends, holidays, vacation, or when you’re sick. And those events can all be predicted.”
Ed nodded and saw some other heads nodding as well.
“So let’s say that I have a workday routine. It’s one of my standard templates of routines. If you think about it, from the time you wake up to the time you go to bed, there are a million things you do the same each day. You shut off the alarm, turn on the lights, brush your teeth, shave, shower, eat breakfast. If we put each of these events in a database, you could easily determine the next probable activity. Some of these tasks require interacting with an electronic device. Some of these tasks use up consumables. Some tasks might be optimized with feedback from other variables.”
“Example?” Dale asked.
“If you’re going to run a marathon tomorrow, you might want to alter your typical menu choices to include more carbohydrates. If you’re going to take a long trip you might want to fill up the car on the way home even though the tank is only half-empty.”
Dale nodded.
“We already have sensors or inputs for most of these events—you have your calendar online, your phone’s GPS can track your travel, you purchase some of your consumables online. What we don’t have is one big relational database to store and collate all this information. What I’ve been working on is a database that will filter and connect all this data. On top of that database, I’ve built a layer to recognize patterns and devise optimizations. When I get to my house and pull into my parking spot, the system can turn on the lights on my walkway through my home automation system.
“Regardless if I get home on time, the system is recording the news from TV and has it paused and ready to watch. If I’ve had a lucrative month financially and I don’t have any major bills coming up, the system can move a percentage of my cash into my investment portfolio.”
Ed looked over at Lister. This must have been the thing that Lister had him set up with his broker account.
“But how many useful things could the system do?” Kevin asked.
“It depends on how well your devices are connected. I’ve got my lights and appliances connected to my home automation. I’ve also got my car starter, DVR, and heat connected to my server. My banking and all my nutrition and workout information is available online. The more connected you are, the more the system can do. One of the biggest input devices for the system is the cell phone. It has cameras and a microphone as well as accelerometers and GPS. Your phone knows more about you than any other device. Once you add all the inputs from your cell phone, the database becomes incredibly rich.”
“How do you predict the patterns?” Lister asked.
“I’ve come up with a technique to extrapolate clusters of nodes. I’ll explain it more in a minute, and I’ve written a document that describes it. I’ll email everyone document. Events are classified as they’re entered into the database. If an event can be influenced by the control system, that record is marked. When the system reaches a certain confidence, it will influence the event.”
Jim was interrupted by the sounds of cellphones. Most people had their phones muted, but they still vibrated on the tables. Ed looked at his as the other people picked up their phones to see the alert. It was an email from Jim. The subject was “Description of node cluster extrapolation technique.” The email contained an attachment which was a document about the technique.
“So you scheduled this email to be sent during your presentation?” Kevin asked.
“No,” Jim said. “Fyre sent it.”
“Who is Flier?” Dale asked.
“It’s Fyre,” Jim said, “F-Y-R-E. That’s the name I’ve given to the system. It’s monitoring my phone. It runs speech recognition on the microphone. It’s not a hundred percent, but it often picks up tasks that I voice and executes them
Ed nodded and saw some other heads nodding as well.
“So let’s say that I have a workday routine. It’s one of my standard templates of routines. If you think about it, from the time you wake up to the time you go to bed, there are a million things you do the same each day. You shut off the alarm, turn on the lights, brush your teeth, shave, shower, eat breakfast. If we put each of these events in a database, you could easily determine the next probable activity. Some of these tasks require interacting with an electronic device. Some of these tasks use up consumables. Some tasks might be optimized with feedback from other variables.”
“Example?” Dale asked.
“If you’re going to run a marathon tomorrow, you might want to alter your typical menu choices to include more carbohydrates. If you’re going to take a long trip you might want to fill up the car on the way home even though the tank is only half-empty.”
Dale nodded.
“We already have sensors or inputs for most of these events—you have your calendar online, your phone’s GPS can track your travel, you purchase some of your consumables online. What we don’t have is one big relational database to store and collate all this information. What I’ve been working on is a database that will filter and connect all this data. On top of that database, I’ve built a layer to recognize patterns and devise optimizations. When I get to my house and pull into my parking spot, the system can turn on the lights on my walkway through my home automation system.
“Regardless if I get home on time, the system is recording the news from TV and has it paused and ready to watch. If I’ve had a lucrative month financially and I don’t have any major bills coming up, the system can move a percentage of my cash into my investment portfolio.”
Ed looked over at Lister. This must have been the thing that Lister had him set up with his broker account.
“But how many useful things could the system do?” Kevin asked.
“It depends on how well your devices are connected. I’ve got my lights and appliances connected to my home automation. I’ve also got my car starter, DVR, and heat connected to my server. My banking and all my nutrition and workout information is available online. The more connected you are, the more the system can do. One of the biggest input devices for the system is the cell phone. It has cameras and a microphone as well as accelerometers and GPS. Your phone knows more about you than any other device. Once you add all the inputs from your cell phone, the database becomes incredibly rich.”
“How do you predict the patterns?” Lister asked.
“I’ve come up with a technique to extrapolate clusters of nodes. I’ll explain it more in a minute, and I’ve written a document that describes it. I’ll email everyone document. Events are classified as they’re entered into the database. If an event can be influenced by the control system, that record is marked. When the system reaches a certain confidence, it will influence the event.”
Jim was interrupted by the sounds of cellphones. Most people had their phones muted, but they still vibrated on the tables. Ed looked at his as the other people picked up their phones to see the alert. It was an email from Jim. The subject was “Description of node cluster extrapolation technique.” The email contained an attachment which was a document about the technique.
“So you scheduled this email to be sent during your presentation?” Kevin asked.
“No,” Jim said. “Fyre sent it.”
“Who is Flier?” Dale asked.
“It’s Fyre,” Jim said, “F-Y-R-E. That’s the name I’ve given to the system. It’s monitoring my phone. It runs speech recognition on the microphone. It’s not a hundred percent, but it often picks up tasks that I voice and executes them
Similar Books
