Systems and methods for agent interaction with building management system

• US 9,817,383 B1
• Filed: 12/01/2016
• Issued: 11/14/2017
• Est. Priority Date: 07/11/2016
• Status: Active Grant

• Current Assignee: Johnson Controls Technology Company (Johnson Controls International plc)
• Original Assignee: Johnson Controls Technology Company (Johnson Controls International plc)
• Inventors: Sinha, Sudhi, Curtis, Daniel M., Albinger, Donald, Park, Youngchoon, Mueller, Joseph, Reichenberger, Karl
• Primary Examiner(s): Laughlin, Nathan L
• Application Number:
  US15/367,167
• Time in Patent Office: 348 Days
• CPC Class Codes: G05B 13/0205 not using a model or a simulator of the controlled system
• CPC Class Codes: G05B 13/0265 the criterion being a learning criterion
• CPC Class Codes: G05B 13/048 using a predictor
• CPC Class Codes: G05B 15/02 electric
• CPC Class Codes: G05B 2219/2642 Domotique, domestic, home control, automation, smart house
• CPC Class Codes: H04L 12/2814 Exchanging control software or macros for controlling appliance services in a home automation network arrangements for maintenance or administration involving configuration of the network and network elements H04L41/08

Abstract

A building management system (BMS) including a controller having an adaptive interaction manager and an agent manager. The system further includes one or more input-output (I/O) devices, the I/O devices in communication with the adaptive interaction manager. The controller further including a number of BMS field devices. The I/O devices are configured to receive an input from a user, and further configured to communicate the input to the adaptive interaction manager. The agent manager is configured to determine if one or more existing software agents are capable of performing the desired action, and to automatically transmit the existing software agents to one or more of the BMS field devices based on the agent manager determining the existing software agents are capable of performing the desired action. The software agents are configured to automatically be installed in a processing circuit of the BMS field device to perform the required action.

Claims

1. A building management system (BMS), the system comprising:

a controller comprising an adaptive interaction manager and an agent manager, the agent manager comprising an agent scheduler and an agent generator, wherein the agent generator is configured to generate new software agents;

one or more input-output (I/O) devices, the I/O devices in communication with the adaptive interaction manager; and

a plurality of BMS field devices, the BMS field devices in communication with the controller;

wherein the I/O devices are configured to receive an input from a user, the I/O devices configured to communicate the input to the adaptive interaction manager, the adaptive interaction manager is configured to process the received input to determine a required action, and to communicate the required action to the agent manager, the agent scheduler is configured to determine if one or more existing software agents are capable of performing the required action and to automatically transmit the existing software agents to one or more of the BMS field devices based on the agent scheduler determining the existing software agents are capable of performing the desired action;

wherein the existing software agents capable of performing the required actions are configured to automatically be installed in a processing circuit of the BMS field device to perform the required action, wherein the required action is performed by the software agents capable of performing the required action executing an energy optimization function to optimize an energy usage of the one or more of the BMS field devices, the software agents capable of performing the required action are further configured to monitor data from the one or more BMS field devices to determine an effect of the energy optimization function on the BMS, and to automatically adjust the energy optimization function for the one or more BMS field devices based on the determined effect.

2. The BMS of claim 1, wherein the adaptive interaction manager is further configured to instruct the agent generator to generate the new software agents based on the agent manager determining that none of the existing software agents are capable of performing the required action.

3. The BMS of claim 2, wherein the agent generator generates a plurality of agent parameters associated with the new software agent, the agent parameters comprising the information required to generate the agent.

4. The BMS of claim 3, wherein the agent parameters comprise at least one of an installation location, I/O requirements, one or more communication parameters, software agent generation code, and one or more software agent attributes.

5. The BMS of claim 4, wherein the software agent attributes include one or more of building automation system attributes, time series data attributes, command and control engine attributes, energy manager attributes, ontology attributes and constraint attributes.

6. The BMS of claim 3, wherein the adaptive interface manager is further configured to determine one or more of the BMS devices which are capable of performing the required action, and transmit the agent parameters to the determined one or more BMS devices.

7. The BMS of claim 6, wherein the one or more BMS devices install the new software agent in a processing circuit of the one or more BMS devices upon receiving the agent parameters.

8. The BMS of claim 1, further comprising a plurality of cloud-based applications, the cloud-based applications configured to process the input and communicate the processed input to the adaptive interaction manager, wherein the cloud-based applications include a natural language processor for processing the input.

9. The BMS of claim 1, wherein the agent scheduler is configured to evaluate all previously generated software agents in the BMS to determine if any previously generated agents are available to perform the action.

10. The BMS of claim 9, wherein the agent scheduler is configured to communicate with the agent generator, and can instruct the agent generator to generate a new agent based on the agent scheduler determining that no previously generated agents are available to perform the action.

11. The BMS of claim 9, wherein the agent scheduler is configured to communicate with the agent manager to instruct a previously generated agent to perform the action based on the previously generated agent being available to perform the action.

12. The BMS of claim 1, wherein the requested action is a request to schedule a resource associated with a facility.

13. The BMS of claim 1, wherein the requested action is a request to modify the HVAC parameters associated with one or more areas within a building associated with the BMS.

14. A method of dynamically configuring one or more software agents within a building management system (BMS), comprising:

receiving a user input via an input module of the BMS;

processing the user input using an interaction manager to determine an output associated with the user input;

evaluating, by an agent manager, a capability matrix to determine the capability of one or more existing software agents associated with the BMS to provide the determined output;

configuring an existing software agent to perform an action required to provide the determined output based on the agent manager determining that the existing software agent is capable of providing the determined output;

dispatching the configured existing software agent to a BMS device to perform the required action, wherein the required action is performed by the configured software agent executing an energy optimization function to optimize an energy usage of one or more BMS field device, the configured software agents are further configured to monitor data from the one or more BMS field devices to determine an effect of the energy optimization function on the BMS, and to automatically adjust the energy optimization function for the one or more BMS field devices based on the determined effect; and

instructing an agent generator to generate a new software agent based on the agent manager determining that no existing software agents associated with the BMS are capable of providing the determined output, wherein the new software agent is configured to monitor data from the one or more BMS field devices to determine an effect of the energy optimization function on the BMS, and to automatically adjust the energy optimization function for the one or more BMS field devices based on the determined effect.

15. The method of claim 14, further comprising:

dispatching the new software agent to one or more BMS devices to perform the required action.

16. The method of claim 15, wherein the agent generator generates a plurality of agent parameters associated with the new software agent, the agent parameters comprising one or more of an installation location, I/O requirements, one or more communication parameters, software agent generation code, and one or more software agent attributes.

17. The method of claim 15, further comprising:

querying an agent scheduler within the agent manager to determine if the existing software agent is available to provide the determined output; and

generating a new software agent based on the agent scheduler determining that the existing software agent is not available to provide the determined output.

18. The method of claim 15, wherein the capability matrix comprises a list of all previously generated software agents and a functionality associated with each previously generated software agent.

19. The method of claim 14, further comprising:

receiving the user input at a cloud based service;

interpreting the user input using the cloud-based service; and

transmitting the interpreted user input to the interaction manager for processing.

20. A method of dynamically processing a user input using one or more software agents within a building management system (BMS), comprising:

receiving the user input via an input module of the BMS;

transmitting the user input to one or more cloud-based services, the cloud-based services configured to interpret the user input;

receiving the interpreted user input from the one or more cloud-based services;

processing the interpreted user input to determine an output associated with the user input using an interaction manager;

evaluating, by an agent manager, a capability matrix to determine the capability of one or more existing software agents associated with the BMS to provide the determined output;

configuring an existing software agent to perform an action required to provide the determined output based on the agent manager determining that the existing software agent is capable of providing the determined output, and dispatching the existing software agent to one or more BMS devices to perform the required action;

generating a new software agent based on the agent manager determining that none of the existing software agents associated with the BMS are capable of providing the determined output, and dispatching the new software agent to one or more BMS devices to perform the required action;

wherein the required action is performed by one of the configured software agent and the new software agent executing an energy optimization function to optimize an energy usage of the one or more of the BMS field devices, the one of the configured software agent and the new software agent are further configured to monitor data from the one or more BMS field devices to determine an effect of the energy optimization function on the BMS, and to automatically adjust the energy optimization function for the one or more BMS field devices based on the determined effect.

21. The method of claim 20, wherein the user input is a voice input.

22. The method of claim 20, further comprising:

determining an availability of the existing software agent to provide the determined output;

generating a new software agent based on determining that the existing software agent is unavailable; and

dispatching the available software to one or more BMS devices to perform the required action.

23. The method of claim 22, wherein the availability is determined by an agent scheduler.

24. The method of claim 22, wherein the new software agent is generated using an agent generator associated with the agent manager.

25. The method of claim 24, wherein the agent generator is configured to generate the new software agent as a plurality of agent parameters associated with the new software agent, the agent parameters comprising at least one of an installation location, I/O requirements, one or more communication parameters, software agent generation code, and one or more software agent attributes.

26. The method of claim 25, wherein the software agent attributes include one or more of building automation system attributes, time series data attributes, command and control engine attributes, energy manager attributes, ontology attributes and constraint attributes.

27. A building management system (BMS), the system comprising:

a controller comprising an adaptive interaction manager and an agent manager comprising;

an agent generator configured to generate new software agents; and

an agent scheduler configured to evaluate previously generated software agents in the BMS and determine their current availability;

one or more input-output (I/O) devices, the I/O devices in communication with the adaptive interaction manager; and

a plurality of BMS field devices, the BMS field devices in communication with the controller;

wherein the I/O devices are configured to receive an input from a user, the I/O devices configured to communicate the input to the adaptive interaction manager, the adaptive interaction manager is configured to process the received input to determine a required action, and to communicate the required action to the agent manager, the agent manager is configured to determine if the one or more existing software agents are capable of performing the required action, and based on the agent manager determining that one or more existing software agents are capable of performing the desired action, the agent scheduler configured to determine if the one or more determined existing software agents are available to perform the required actions, the agent manager further configured to automatically transmit the existing software agents to one or more of the BMS field devices based on the agent manager determining the existing software agents are capable of performing the required action;

wherein the adaptive interaction manager is further configured to instruct the agent generator to generate the new software agents based on the agent manager determining that none of the existing software agents are capable of performing the required action; and

wherein the one of the capable software agents and the new software agents are configured to automatically be installed in a processing circuit of the BMS field device to perform the required action, wherein the required action is performed by one of the capable software agents and the new software agents executing an energy optimization function to optimize an energy usage of the one or more of the BMS field devices, the one of the capable software agent and the new software agent are further configured to monitor data from the one or more BMS field devices to determine an effect of the energy optimization function on the BMS, and to automatically adjust the energy optimization function for the one or more BMS field devices based on the determined effect.

28. The BMS of claim 27, wherein the adaptive interaction manager further comprises a capability matrix comprising a list of all previously generated software agents and one or more functions associated with each previously generated software agent, the capability matrix configured to determine the capability of the one or more existing software agents, and to evaluate the ability of the existing software agents to perform the required action.