IP Library › Granted Patent US 12,242,232
Granted Patent B2
US 12,242,232 · App. 18/072,094 · Granted Mar 4, 2025

Inference server and environment controller for inferring via a neural network one or more commands for controlling an appliance

Inventors: Francois Gervais (Lachine, CA); Carlo Masciovecchio (St-Isidore-de-Laparairie, CA); Dominique Laplante (St-Dominique, CA)
Assignee: DISTECH CONTROLS INC.
G05B13/0265F24F11/30F24F11/62F24F11/76G05B17/02G06N3/08G06N3/084G06N5/04H04L12/2816H04L12/2823H04L12/2825F24F2110/10F24F2110/20F24F2110/70F24F2120/10
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,242,232
App. No.
18/072,094
Filed
Nov 30, 2022
Granted
Mar 4, 2025
Kind
B2
Art Unit
2117
USPC
700/48
Abstract

Inference server and environment controller for inferring one or more commands for controlling an appliance. The environment controller receives at least one environmental characteristic value (for example, at least one of a current temperature, current humidity level, current carbon dioxide level, and current room occupancy) and at least one set point (for example, at least one of a target temperature, target humidity level, and target carbon dioxide level); and forwards them to the inference server. The inference server executes a neural network inference engine using a predictive model (generated by a neural network training engine) for inferring the one or more commands based on the received at least one environmental characteristic value and the received at least one set point; and transmits the one or more commands to the environment controller. The environment controller forwards the one or more commands to the controlled appliance.

Claims (42)

1. An environment controller, comprising:

a communication interface; and

a processing unit for:

receiving a current room occupancy of a room via the communication interface;

receiving a target temperature for the room via one of the communication interface and a user interface of the environment controller;

transmitting the current room occupancy and the target temperature to an inference server executing a neural network inference engine via the communication interface;

receiving one or more command for controlling an appliance inferred by the neural network inference engine executed by the inference server via the communication interface, the one or more command for controlling the appliance being inferred by the neural network inference engine based on the current room occupancy and the target temperature; and

transmitting the one or more command to the controlled appliance via the communication interface.

2. The environment controller of claim 1 , wherein the processing unit further receives via the communication interface at least one additional environmental characteristic value and transmits the at least one additional environmental characteristic value to the inference server via the communication interface.

3. The environment controller of claim 2 , wherein the at least one additional environmental characteristic value comprises at least one of the following: a current temperature, a current humidity level, and a current carbon dioxide (CO2) level.

4. The environment controller of claim 1 , wherein the current room occupancy consists of a determination whether the room is occupied or not, or the current room occupancy consists of a number of persons present in the room.

5. The environment controller of claim 1 , wherein the processing unit further receives via one of the communication interface and the user interface at least one additional set point and transmits the at least one additional set point to the inference server via the communication interface.

6. The environment controller of claim 5 , wherein the at least one additional set point comprises at least one of the following: a target humidity level and a target CO2 level.

7. The environment controller of claim 1 , wherein the controlled appliance consists of a heating, ventilation, and air-conditioning (HVAC) appliance.

8. The environment controller of claim 1 , wherein the one or more command for controlling the appliance includes at least one of the following: a command for controlling a speed of a fan, a command for controlling a pressure generated by a compressor, and a command for controlling a rate of an airflow through a valve.

9. A method for inferring via a neural network one or more command for controlling an appliance, the method comprising:

receiving by a processing unit of the environment controller a current room occupancy of a room via a communication interface of the environment controller;

receiving by the processing unit a target temperature for the room via one of the communication interface and a user interface of the environment controller;

transmitting by the processing unit the current room occupancy and the target temperature to an inference server executing a neural network inference engine via the communication interface;

receiving by the processing unit the one or more command for controlling the appliance inferred by the neural network inference engine executed by the inference server via the communication interface, the one or more command for controlling the appliance being inferred by the neural network inference engine based on the current room occupancy and the target temperature; and

transmitting by the processing unit the one or more command to the controlled appliance via the communication interface.

10. The method of claim 9 , further comprising receiving by the processing unit via the communication interface at least one additional environmental characteristic value and transmitting the at least one additional environmental characteristic value to the inference server via the communication interface.

11. The method of claim 10 , wherein the at least one additional environmental characteristic value comprises at least one of the following: a current temperature, a current humidity level, and a current carbon dioxide (CO2) level.

12. The method of claim 9 , wherein the current room occupancy consists of a determination whether the room is occupied or not, or the current room occupancy consists of a number of persons present in the room.

13. The method of claim 9 , further comprising receiving by the processing unit via one of the communication interface and the user interface at least one additional set point and transmitting the at least one additional set point to the inference server via the communication interface.

14. The method of claim 13 , wherein the at least one additional set point comprises at least one of the following: a target humidity level and a target CO2 level.

15. The method of claim 9 , wherein the controlled appliance consists of a heating, ventilation, and air-conditioning (HVAC) appliance.

16. The method of claim 9 , wherein the one or more command for controlling the appliance includes at least one of the following: a command for controlling a speed of a fan, a command for controlling a pressure generated by a compressor, and a command for controlling a rate of an airflow through a valve.

17. An inference server, comprising:

a communication interface;

memory for storing a predictive model generated by a neural network training engine, the predictive model comprising weights of a neural network determined by the neural network training engine; and

a processing unit for:

receiving from an environment controller via the communication interface a current room occupancy of a room and a target temperature for the room;

executing a neural network inference engine, the neural network inference engine implementing a neural network using the predictive model for inferring one or more command for controlling an appliance based on the current room occupancy and the target temperature; and

transmitting to the environment controller via the communication interface the one or more command inferred by the neural network inference engine, the one or more command being used by the environment controller for controlling the appliance.

18. The inference of claim 17 , wherein the processing unit further receives from the environment controller via the communication interface at least one additional environmental characteristic value; and wherein the inputs of the neural network inference engine further comprise the at least one additional environmental characteristic value.

19. The inference server of claim 18 , wherein the at least one additional environmental characteristic value comprises at least one of the following: a current temperature, a current humidity level, and a current carbon dioxide (CO2) level.

20. The inference server of claim 17 , wherein the current room occupancy consists of a determination whether the room is occupied or not, or the current room occupancy consists of a number of persons present in the room.

21. The inference server of claim 17 , wherein the processing unit further receives via one of the communication interface and the user interface at least one additional set point; and wherein the inputs of the neural network inference engine further comprise the at least one additional set point.

22. The inference server of claim 21 , wherein the at least one additional set point comprises at least one of the following: a target humidity level and a target CO2 level.

23. The inference server of claim 17 , wherein the controlled appliance consists of a heating, ventilation, and air-conditioning (HVAC) appliance.

24. The inference server of claim 17 , wherein the one or more command for controlling the appliance includes at least one of the following: a command for controlling a speed of a fan, a command for controlling a pressure generated by a compressor, and a command for controlling a rate of an airflow through a valve.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 1, 2022
From: GERVAIS, FRANCOIS; MASCIOVECCHIO, CARLO; LAPLANTE, DOMINIQUE
To: DISTECH CONTROLS INC.
Reel/Frame 061943/0105 →
Continuity (3)
Continuation 17067060 · Oct 9, 2020
Continuation 15839055 · Dec 12, 2017
Related Publication 20230259074A1 · Aug 17, 2023
References Cited (99)
US 5257735A · Takahashi et al. · 1993 [cited by applicant]
US 7156316B2 · Kates · 2007 [cited by applicant]
US 7206670B2 · Pimputkar et al. · 2007 [cited by applicant]
US 7839275B2 · Spalink et al. · 2010 [cited by applicant]
US 7840310B2 · Orfield · 2010 [cited by applicant]
US 7904209B2 · Podgorny et al. · 2011 [cited by applicant]
US 8010237B2 · Cheung et al. · 2011 [cited by applicant]
US 8412654B2 · Montalvo · 2013 [cited by applicant]
US 8457796B2 · Thind · 2013 [cited by applicant]
US 8925358B2 · Kasper · 2015 [cited by applicant]
US 9002761B2 · Montalvo · 2015 [cited by applicant]
US 9046896B1 · Brunelle · 2015 [cited by applicant]
US 9285134B2 · Bray et al. · 2016 [cited by applicant]
US 9477239B2 · Bergman et al. · 2016 [cited by applicant]
US 9594384B2 · Bergman et al. · 2017 [cited by applicant]
US 9905122B2 · Sloo et al. · 2018 [cited by applicant]
US 10094586B2 · Pavlovski et al. · 2018 [cited by applicant]
US 10107511B2 · Boulbes et al. · 2018 [cited by applicant]
US 10616121B2 · Gervais · 2020 [cited by applicant]
US 10838375B2 · Gervais et al. · 2020 [cited by applicant]
US 10845768B2 · Gervais et al. · 2020 [cited by applicant]
US 10895853B2 · Gervais · 2021 [cited by applicant]
US 10897374B2 · Choi et al. · 2021 [cited by applicant]
US 10908561B2 · Gervais · 2021 [cited by applicant]
US 11371739B2 · Wenzel · 2022 [cited by examiner]
US 11526138B2 · Gervais · 2022 [cited by examiner]
US 11543786B2 · Gervais · 2023 [cited by examiner]
US 11675322B2 · Du · 2023 [cited by examiner]
US 11747771B2 · Gervais · 2023 [cited by examiner]
US 11754983B2 · Gervais · 2023 [cited by examiner]
US 20020144537A1 · Sharp et al. · 2002 [cited by applicant]
US 20030160103A1 · Guo · 2003 [cited by applicant]
US 20070119958A1 · Kates · 2007 [cited by applicant]
US 20080001712A1 · Agarwal et al. · 2008 [cited by applicant]
US 20080281472A1 · Podgorny et al. · 2008 [cited by applicant]
US 20100088261A1 · Montalvo · 2010 [cited by applicant]
US 20110113360A1 · Johnson et al. · 2011 [cited by applicant]
US 20110166712A1 · Kramer et al. · 2011 [cited by applicant]
US 20110295430A1 · Kouninski · 2011 [cited by applicant]
US 20120144057A1 · Meredith et al. · 2012 [cited by applicant]
US 20120245740A1 · Raestik et al. · 2012 [cited by applicant]
US 20140277757A1 · Wang et al. · 2014 [cited by applicant]
US 20140321839A1 · Armstrong · 2014 [cited by applicant]
US 20150248118A1 · Li et al. · 2015 [cited by applicant]
US 20150276253A1 · Montalvo · 2015 [cited by applicant]
US 20150276508A1 · Smullin · 2015 [cited by applicant]
US 20150293504A1 · Blum et al. · 2015 [cited by applicant]
US 20150296594A1 · Blum et al. · 2015 [cited by applicant]
US 20150330923A1 · Smullin · 2015 [cited by applicant]
US 20160223218A1 · Barrett · 2016 [cited by applicant]
US 20170108236A1 · Guan et al. · 2017 [cited by applicant]
US 20170227950A1 · Kinoshita et al. · 2017 [cited by applicant]
US 20170364829A1 · Fyffe · 2017 [cited by applicant]
US 20180017947A1 · Kupa et al. · 2018 [cited by applicant]
US 20180100662A1 · Farahmand et al. · 2018 [cited by applicant]
US 20180195911A1 · Kakade et al. · 2018 [cited by applicant]
US 20180268220A1 · Lee et al. · 2018 [cited by applicant]
US 20180299153A1 · Ajax et al. · 2018 [cited by applicant]
US 20180306459A1 · Turney · 2018 [cited by applicant]
US 20180363933A1 · Ross · 2018 [cited by applicant]
US 20180364654A1 · Locke et al. · 2018 [cited by applicant]
US 20180367320A1 · Montalvo · 2018 [cited by applicant]
US 20180367483A1 · Rodriguez et al. · 2018 [cited by applicant]
US 20180375444A1 · Gamroth · 2018 [cited by applicant]
US 20190017719A1 · Sinha et al. · 2019 [cited by applicant]
US 20190126472A1 · Tunyasuvunakool et al. · 2019 [cited by applicant]
US 20190179269A1 · Gervais et al. · 2019 [cited by applicant]
US 20190179270A1 · Gervais · 2019 [cited by applicant]
US 20190182069A1 · Gervais · 2019 [cited by applicant]
US 20190309978A1 · Song · 2019 [cited by applicant]
US 20190316802A1 · Alanquar et al. · 2019 [cited by applicant]
US 20200025401A1 · Cheon et al. · 2020 [cited by applicant]
US 20200050178A1 · Gao et al. · 2020 [cited by applicant]
US 20210088987A1 · Gervais · 2021 [cited by applicant]
US 20210096519A1 · Gervais · 2021 [cited by applicant]
US 20240069502A1 · Gervais · 2024 [cited by examiner]
CN 114811833A · 2022 [cited by applicant]
WO 2017076433A1 · 2017 [cited by applicant]
WO 2018200225A1 · 2018 [cited by applicant]
Barrett, E. and Linder, S., 2015. Autonomous hvac control, a reinforcement learning approach. In Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2015, Porto, Portugal, Sep. 7-11, 20… [cited by applicant]
Final Office Action for U.S. Appl. No. 15/914,610, dated Jun. 9, 2023, 35 pages. [cited by applicant]
Chen, Y., Shi, Y. and Zhang, B., Oct. 2017, Modeling and optimization of complex building energy systems with deep neural networks. In 2017 51st Asilomar Conference on Signals, Systems, and Computers (pp. 1368-1373) IEE… [cited by applicant]
Final Office Action for U.S. Appl. No. 15/914,610, mailed Apr. 6, 2022, 24 pages. [cited by applicant]
Hafner et al., “Reinforcement Learning in Feedback Control Challenges and Benchmarks from Technical Process Control” Mach. Learn., 2011, vol. 84, pp. 137-169. [cited by applicant]
Kalogirou, S.A., 2000. Applications of artificial neural-networks for energy systems. Applied Energy 67(1-2), pp. 17-35 (Year:2000). [cited by applicant]
Non Final Office Action for U.S. Appl. No. 15/914,610, mailed Dec. 13, 2021, 28 pages. [cited by applicant]
Non Final Office Action for U.S. Appl. No. 17/067,060, mailed Mar. 30, 2022, 17 pages. [cited by applicant]
Non Final Office Action for U.S. Appl. No. 17/116,514, mailed Oct. 13, 2022, 30 pages. [cited by applicant]
Non Final Office Action for U.S. Appl. No. 17/117,928, mailed Jun. 24, 2022, 21 pages. [cited by applicant]
Non Final Office Action for U.S. Appl. No. 17/117,928, mailed Oct. 13, 2020, 16 pages. [cited by applicant]
Notice of Allowance for U.S. Appl. No. 17/069,233, mailed Aug. 18, 2022, 17 pages. [cited by applicant]
Ryu et al., “Development of an Occupancy Prediction Model Using Indoor Environmental Data Based on Machine Learning Techniques”, Building and Environment, 2016, vol. 197, pp. 1-9. [cited by applicant]
Wang, Y., Velswamy, K. and Huang, B., “A long-short term memory recurrent neural network based reinforcement learning controller for office heating ventilation and air conditioning systems”, Processes, 5(3), p. 46 (Year… [cited by applicant]
Wei, T., Wang, Y. and Zhu, Q., Jun. 2017, Deep reinforcement learning for building HVAC control. In Proceedings of the 54th annual design automation conference 2017 (pp. 1-6). (Year: 2017). [cited by applicant]
Entire patent prosecution history of U.S. Appl. No. 15/839,055, filed Dec. 12, 2017, entitled, “Inference Server and Environment Controller for Inferring via a Neural Network One or More Commands for Controlling an Appl… [cited by applicant]
Entire patent prosecution history of U.S. Appl. No. 17/067,060, filed Oct. 9, 2020, entitled, “Inference Server and Environment Controller for Inferring via a Neural Network One or More Commands for Controlling an Appli… [cited by applicant]
Notice of Allowance for U.S. Appl. No. 17/116,514, mailed Apr. 19, 2023, 13 pages. [cited by applicant]
Notice of Allowance for U.S. Appl. No. 17/117,928, mailed May 3, 2023, 17 pages. [cited by applicant]
Non Final Office Action for U.S. Appl. No. 15/914,610, mailed Nov. 9, 2023, 27 pages. [cited by applicant]