Method and system of controlling a cohort of ozone gas generating devices

1 . A method, performed in one or more processors of a computing device, of controlling a plurality of ozone gas generating devices, the method comprising:

detecting, via at least one remote ozone gas sensor device in communication with the one or more processors, a concentration of ozone gas constituent of ambient air within a spatial area, the plurality of ozone gas generating devices generating ozone gas at a first rate of ozone gas generation, the at least one remote ozone gas sensor device being located in the spatial area; and

responsive to detecting the concentration of the ozone gas constituent as being one of above and below a predetermined threshold concentration, performing, by the plurality of ozone gas generating devices in conjunction with the one or more processors of the computing device, one of increasing and decreasing the first rate of ozone gas generation to a second rate of ozone gas generation.

2 . The method of claim 1 wherein the at least one remote ozone gas sensor device comprises a plurality of remote ozone gas sensor devices located within the spatial area associated with the plurality of ozone gas generating devices, and further comprising detecting the concentration of ozone gas constituent of ambient air at least partly using a trained machine learning model in conjunction with the plurality of remote ozone gas sensor devices.

3 . The method of claim 2 further comprising producing the trained machine learning model via a training process comprising:

receiving a plurality of input datasets at respective ones of a plurality of input layers of a neural network, the neural network being instantiated in the one or more processors and having an output layer interconnected to the plurality of input layers via a set of intermediate layers, each of the plurality of input datasets comprising an input attribute associated with ones of a plurality of ozone gas generating devices, ones of the set of intermediate layers being configured in accordance with an initial matrix of weights; and

training the neural network in accordance with the respective ones of the plurality of input layers based at least in part upon recursively adjusting the initial matrix of weights by back propagation in generating, at the output layer, an output attribute in accordance with diminishment of an error matrix computed at the output layer of the neural network.

4 . The method of claim 3 wherein the plurality of input datasets comprise one or more of: ozone gas generation capacity in regular mode of operation, ozone gas generation capacity in higher order mode of operation, location coordinates defining external boundaries or perimeter of a given spatial area, coordinate location of ozone gas generating device within the spatial area, model identification of ozone gas generating device, device operational reliability metrics, device wireless communication reliability metrics and device historical, cumulative ozone gas generating metrics.

5 . The method of claim 3 wherein the output attribute comprises a desired concentration of ozone gas as constituted in ambient air of the spatial area.

6 . The method of claim 2 wherein the trained machine learning model comprises one of a trained convolutional neural network and a trained recurrent neural network.

7 . The method of claim 1 wherein, responsive to the instructing, at least one ozone gas generating device of the plurality of ozone gas generating devices increases the rate of ozone gas generation associated therewith in accordance with switching from a first mode to a second mode of ozone gas generation, the second mode of ozone gas generation being associated with a higher rate of generation of ozone gas than the first mode.

8 . The method of claim 7 wherein the at least ozone generating device includes an optical lamp module comprised of a plurality of optical lamps, and the second mode of ozone gas generation comprises activating at least one additional optical lamp of the plurality of optical lamps.

9 . The method of claim 7 wherein, responsive to the instructing, the at least one ozone gas generating device of the plurality of ozone gas generating devices decreases the rate of ozone gas generation associated therewith in accordance with one of (i) switching from the second mode to the first mode of ozone gas generation, and (ii) switching from an operational state to a non-operational state.

10 . The method of claim 9 wherein the at least ozone generating device includes an optical lamp module comprised of a plurality of optical lamps, and the first mode of ozone gas generation comprises de-activating at least one optical lamp of the plurality of optical lamps.

11 . A computing device comprising:

one or more processors; and

a non-transitory memory including instructions, the instructions when executed by the one or more processors causing the one or more processors to perform operations comprising:

detecting, via at least one remote ozone gas sensor device in communication with the one or more processors, a concentration of ozone gas constituent of ambient air within a spatial area, the plurality of ozone gas generating devices generating ozone gas at a first rate of ozone gas generation, the at least one remote ozone gas sensor device being located in the spatial area; and

responsive to detecting the concentration of the ozone gas constituent as being one of above and below a predetermined threshold concentration, performing, by the plurality of ozone gas generating devices in conjunction with the one or more processors of the computing device, one of increasing and decreasing the first rate of ozone gas generation to a second rate of ozone gas generation.

12 . The computing device of claim 11 wherein the at least one remote ozone gas sensor device comprises a plurality of remote ozone gas sensor devices located within the spatial area associated with the plurality of ozone gas generating devices, and further comprising detecting the concentration of ozone gas constituent of ambient air at least partly using a trained machine learning model in conjunction with the plurality of remote ozone gas sensor devices.

13 . The computing device of claim 12 further comprising instructions executable in the processor to produce the trained machine learning model via a training process comprising:

receiving a plurality of input datasets at respective ones of a plurality of input layers of a neural network, the neural network being instantiated in the one or more processors and having an output layer interconnected to the plurality of input layers via a set of intermediate layers, each of the plurality of input datasets comprising an input attribute associated with ones of a plurality of ozone gas generating devices, ones of the set of intermediate layers being configured in accordance with an initial matrix of weights; and

training the neural network in accordance with the respective ones of the plurality of input layers based at least in part upon recursively adjusting the initial matrix of weights by back propagation in generating, at the output layer, an output attribute in accordance with diminishment of an error matrix computed at the output layer of the neural network.

14 . The computing device of claim 13 wherein the plurality of input datasets comprise one or more of: ozone gas generation capacity in regular mode of operation, ozone gas generation capacity in higher order mode of operation, location coordinates defining external boundaries or perimeter of a given spatial area, coordinate location of ozone gas generating device within the spatial area, model identification of ozone gas generating device, device operational reliability metrics, device wireless communication reliability metrics and device historical, cumulative ozone gas generating metrics.

15 . The computing device of claim 13 wherein the output attribute comprises a desired concentration of ozone gas as constituted in ambient air of the spatial area.

16 . The computing device of claim 12 wherein the trained machine learning model comprises one of a trained convolutional neural network and a trained recurrent neural network.

17 . The computing device of claim 11 wherein, responsive to the instructing, at least one ozone gas generating device of the plurality of ozone gas generating devices increases the rate of ozone gas generation associated therewith in accordance with switching from a first mode to a second mode of ozone gas generation, the second mode of ozone gas generation being associated with a higher rate of generation of ozone gas than the first mode.

18 . The computing device of claim 17 wherein the at least ozone generating device includes an optical lamp module comprised of a plurality of optical lamps, and the second mode of ozone gas generation comprises activating at least one additional optical lamp of the plurality of optical lamps.

19 . The computing device of claim 17 wherein, responsive to the instructing, the at least one ozone gas generating device of the plurality of ozone gas generating devices decreases the rate of ozone gas generation associated therewith in accordance with one of (i) switching from the second mode to the first mode of ozone gas generation, and (ii) switching from an operational state to a non-operational state.

20 . The computing device of claim 19 wherein the at least ozone generating device includes an optical lamp module comprised of a plurality of optical lamps, and the first mode of ozone gas generation comprises de-activating at least one optical lamp of the plurality of optical lamps.