Building automation system with NLP service abstraction
A building automation system (BAS) is configured to support a variety of different natural language processing (NLP) service providers with minimal or no redesign effort. The BAS includes an event handler configured to receive an external request from a service provider. The external request is associated with a voice input uttered by a user. The BAS further includes an abstraction layer configured to receive the external request from the event handler and generate an internal request based on the external request. The BAS further includes an intent processor configured to receive the internal request from the abstraction layer and an intent handler in communication with the intent processor and configured to perform an action in accordance with the internal request.
1. A building automation system (BAS) comprising:
an event handler configured to receive an external request from a natural language processing (NLP) service provider, the external request providing a NLP service provider conversion specific to the NLP service provider of a voice input uttered by a user;
an abstraction layer configured to receive the external request from the event handler and convert the external request into an internal request in a common format different from a format of the external request, wherein the abstraction layer is configured to convert a plurality of different formats of a plurality of different NLP service providers into the common format;
an intent processor configured to receive the internal request from the abstraction layer; and
an intent handler in communication with the intent processor and configured to perform an action in accordance with the internal request.
2. The system of claim 1 , wherein the internal request comprises an intent associated with the voice input and one or more entities associated with the voice input.
3. The system of claim 2 , wherein the intent processor is further configured to select the intent handler from one of a plurality of intent handlers associated with the BAS in accordance with the intent.
4. The system of claim 1 , wherein the internal request comprises an intent to change a temperature setpoint of a building space, and wherein the action comprises changing the temperature setpoint of the building space.
5. The system of claim 1 , wherein the voice input is related to heating, cooling, lighting, air quality, or security in a building.
6. The system of claim 1 , wherein the action performed by the intent handler is related to heating, cooling, lighting, air quality, or security in a building.
7. The system of claim 1 , wherein the intent handler is further configured to generate a response to provide to the user based on the action performed.
8. The system of claim 1 , wherein the NLP service provider is separate from the BAS.
9. A method of user interaction with a building automation system (BAS), the method comprising:
receiving an external request from a natural language processing (NLP) service provider, the external request providing a NLP service provider conversion specific to the NLP service provider of a voice input uttered by a user;
converting the external request into an internal request in a common format different from a format of the external request, wherein the abstraction layer is configured to convert a plurality of different formats of a plurality of different NLP service providers into the common format;
selecting one of a plurality of intent handlers to service the internal request; and
performing an action in accordance with the internal request.
10. The method of claim 9 , wherein the voice input uttered by the user comprises an intent to change a temperature setpoint of a building space.
11. The method of claim 10 , wherein performing the action in accordance with the internal request comprises changing the temperature setpoint of the building space.
12. The method of claim 9 , further comprising providing a response to the user based on the action performed.
13. The method of claim 9 , wherein the service provider is a natural language processing (NLP) service provider separate from the BAS.
14. The method of claim 9 , wherein the voice input uttered by the user comprises an intent to adjust lighting in a building space.
15. The method of claim 14 , wherein performing the action in accordance with the internal request comprises adjusting the lighting in the building space.
16. The method of claim 9 , wherein the internal request comprises an intent associated with the voice input and one or more entities associated with the voice input.
17. A method of user interaction with a building automation system (BAS), the method comprising:
receiving a voice input uttered by a user at a user interface;
providing the voice input to a natural language processing (NLP) service provider separate from the BAS, the external request providing a NLP service provider conversion specific to the NLP service provider of the voice input;
receiving the external request from the NLP service provider at the BAS;
converting the external request into an internal request in a common format different from a format of the external request, the method further comprising converting a plurality of different formats of a plurality of different NLP service providers into the common format;
selecting one of a plurality of intent handlers to service the internal request; and
performing an action in accordance with the internal request.
18. The method of claim 17 , further comprising providing a response to the user based on the action performed.
19. The method of claim 17 , wherein the internal request comprises an intent associated with the voice input and one or more entities associated with the voice input.
20. The method of claim 17 , wherein the voice input uttered by the user comprises an intent to change a temperature setpoint of a building space, and wherein performing the action comprises changing the temperature setpoint of the building space.