|
Automatic Schedule Detection
|
Signal Handler & Voice UI
|
Favorite POI Detection
|
Reasoning Automation For Vehicles And Not Only
Figuring out what the user likes or dislikes and acting upon it
The today's sophisticated hardware is more and more in need of automated control. While the plugs for this type of control are available for decades already, programming behaviour itself is - generally speaking - not a trivial task.
Therefore, there is a great need for machines which are able to make inferences and make intelligent choices in an autonomous manner. Imagine for instance that the user wakes up at 7 AM, has breakfast and at about 8:20 heads towards work using their car. He/she does this every day from Monday to Friday except for vacation days and maybe public holidays.
Glas.AI (R) is able to track the user’s behaviour, make a statistic of the daily predicted morning departure time and output this time to 3'rd party users. It can also process this information internally and use it for instance for preheating the car 20 minutes before the statistical daily departure time, given the proper vehicle integration.
It can also cool down the car if the platform is given access to the vehicle's inside temperature and understands that the weather is very hot outside.
This is just one use case that can be built using Glas.AI (R), the possibilities are endless.
The GLAS.AI (R) platform is fully data driven and uses a very intuitive API for any data I/O. Moreover, internally, as a framework, developers can further develop strategies of Reasoning through the data and finally conclude possible actions to be taken. This is done by means of an intuitive scripting language.
Therefore, there is a great need for machines which are able to make inferences and make intelligent choices in an autonomous manner. Imagine for instance that the user wakes up at 7 AM, has breakfast and at about 8:20 heads towards work using their car. He/she does this every day from Monday to Friday except for vacation days and maybe public holidays.
Glas.AI (R) is able to track the user’s behaviour, make a statistic of the daily predicted morning departure time and output this time to 3'rd party users. It can also process this information internally and use it for instance for preheating the car 20 minutes before the statistical daily departure time, given the proper vehicle integration.
It can also cool down the car if the platform is given access to the vehicle's inside temperature and understands that the weather is very hot outside.
This is just one use case that can be built using Glas.AI (R), the possibilities are endless.
The GLAS.AI (R) platform is fully data driven and uses a very intuitive API for any data I/O. Moreover, internally, as a framework, developers can further develop strategies of Reasoning through the data and finally conclude possible actions to be taken. This is done by means of an intuitive scripting language.
Predictive User Behavior Analysis
Predicting what the user is gonna do next
Understanding user preferences is key in the upcoming autonomous driving era and beyond. Knowing the users' preferences in-depth is crucial for the safe, reliable and comfortable operation of autonomous vehicles.
Our platform contains a set of plug-ins specialised on tracking and detecting user preferences.
For instance we can automatically detect the user's home and work position in just 3 days of usage* and can use these geographic positions for predicting the movement habits and patterns in the users' daily life.
Some good examples of such patterns are the morning departure times, morning commute times or the favourite commute routes.
The system is able to detect the users' favourite gas station / supermarket brands, favourite roads and shortcuts. This information is very important when trying to route the user to a refuelling point or shop.
All the processing is done while respecting the users' privacy by employing the today's smartphones' massive processing power.
* the detection is accurate for users with a stable home and work geographic location.
Our platform contains a set of plug-ins specialised on tracking and detecting user preferences.
For instance we can automatically detect the user's home and work position in just 3 days of usage* and can use these geographic positions for predicting the movement habits and patterns in the users' daily life.
Some good examples of such patterns are the morning departure times, morning commute times or the favourite commute routes.
The system is able to detect the users' favourite gas station / supermarket brands, favourite roads and shortcuts. This information is very important when trying to route the user to a refuelling point or shop.
All the processing is done while respecting the users' privacy by employing the today's smartphones' massive processing power.
* the detection is accurate for users with a stable home and work geographic location.
Automatic Speech Understanding
Towards a natural human-machine interface
Since speech is the most common way of interacting with humans, it came as a natural step to support speech understanding as a method of interacting with Glas.AI (R).
Our Speech Understanding plug-in converts the meaning of the sentences uttered by the user into Thoughts and Concepts understood and stored by the framework.
The Speech Understanding problem is - however - not a simple one.
Everyone of us attended at least once in our lives a cocktail party. At such parties, it’s impractical for all guests to join a single conversation. So instead, we break into groups of twos, threes and fours to discuss whatever it is we end up discussing.
The result is dozens of simultaneous conversations– and a great deal of background noise. And yet, just about every guest will effortlessly tune out every single conversation bar the one they’re actually involved in. It’s a phenomenon known, tellingly, as the cocktail party effect.
The situation occurs oftenly also inside vehicleswhen mutiple passengers engage into conversations while the driver is supposed to issue voice commandsthat are supposed to be understood by the vehicle.
The Glas.AI (R) VoiceTuner (R) library employs a set of deep neural networks which de-noise a multiple-voice signal then split each voice on a separate audio channel.
Only the channel which contains a voice speaking the predefined trigger word is passed through and outputted outputted for the ASR step.
Available on Android and QNX. Other operating system builds can be provided upon request.
Our Speech Understanding plug-in converts the meaning of the sentences uttered by the user into Thoughts and Concepts understood and stored by the framework.
The Speech Understanding problem is - however - not a simple one.
Everyone of us attended at least once in our lives a cocktail party. At such parties, it’s impractical for all guests to join a single conversation. So instead, we break into groups of twos, threes and fours to discuss whatever it is we end up discussing.
The result is dozens of simultaneous conversations– and a great deal of background noise. And yet, just about every guest will effortlessly tune out every single conversation bar the one they’re actually involved in. It’s a phenomenon known, tellingly, as the cocktail party effect.
The situation occurs oftenly also inside vehicleswhen mutiple passengers engage into conversations while the driver is supposed to issue voice commandsthat are supposed to be understood by the vehicle.
The Glas.AI (R) VoiceTuner (R) library employs a set of deep neural networks which de-noise a multiple-voice signal then split each voice on a separate audio channel.
Only the channel which contains a voice speaking the predefined trigger word is passed through and outputted outputted for the ASR step.
Available on Android and QNX. Other operating system builds can be provided upon request.
